Compare commits
4 Commits
mb/update-
...
khk-greedy
| Author | SHA1 | Date | |
|---|---|---|---|
|
45a7e0a797 | ||
|
|
e96141b291 | ||
|
|
a8faaca1c9 | ||
|
|
f985ab7f1b |
87
.github/ISSUE_TEMPLATE/1-bug_report.yml
vendored
87
.github/ISSUE_TEMPLATE/1-bug_report.yml
vendored
@@ -1,87 +0,0 @@
|
||||
name: Bug report
|
||||
description: Report a bug or unexpected behavior
|
||||
type: Bug
|
||||
body:
|
||||
- type: markdown
|
||||
attributes:
|
||||
value: |
|
||||
## Bug Report
|
||||
|
||||
Thank you for taking the time to fill out this bug report.
|
||||
|
||||
- type: markdown
|
||||
attributes:
|
||||
value: |
|
||||
### Environment
|
||||
|
||||
- type: input
|
||||
id: pipecat-version
|
||||
attributes:
|
||||
label: pipecat version
|
||||
description: Which version are you using?
|
||||
placeholder: e.g., 0.0.63
|
||||
validations:
|
||||
required: true
|
||||
|
||||
- type: input
|
||||
id: python-version
|
||||
attributes:
|
||||
label: Python version
|
||||
description: Which Python version are you using?
|
||||
placeholder: e.g., 3.12.8
|
||||
validations:
|
||||
required: true
|
||||
|
||||
- type: input
|
||||
id: os
|
||||
attributes:
|
||||
label: Operating System
|
||||
description: Which OS are you using?
|
||||
placeholder: e.g., Ubuntu 24.04, Windows 11, macOS 12.5
|
||||
validations:
|
||||
required: true
|
||||
|
||||
- type: textarea
|
||||
id: description
|
||||
attributes:
|
||||
label: Issue description
|
||||
description: Provide a clear description of the issue.
|
||||
validations:
|
||||
required: true
|
||||
|
||||
- type: textarea
|
||||
id: repro
|
||||
attributes:
|
||||
label: Reproduction steps
|
||||
description: List the steps to reproduce the issue.
|
||||
placeholder: |
|
||||
1. Do this...
|
||||
2. Then do that...
|
||||
3. Observe the error...
|
||||
validations:
|
||||
required: true
|
||||
|
||||
- type: textarea
|
||||
id: expected
|
||||
attributes:
|
||||
label: Expected behavior
|
||||
description: What did you expect to happen?
|
||||
validations:
|
||||
required: true
|
||||
|
||||
- type: textarea
|
||||
id: actual
|
||||
attributes:
|
||||
label: Actual behavior
|
||||
description: What actually happened?
|
||||
validations:
|
||||
required: true
|
||||
|
||||
- type: textarea
|
||||
id: logs
|
||||
attributes:
|
||||
label: Logs
|
||||
description: If applicable, include any relevant logs or error messages
|
||||
render: shell
|
||||
validations:
|
||||
required: false
|
||||
67
.github/ISSUE_TEMPLATE/2-question.yml
vendored
67
.github/ISSUE_TEMPLATE/2-question.yml
vendored
@@ -1,67 +0,0 @@
|
||||
name: Question
|
||||
description: Ask a question or get help
|
||||
type: Question
|
||||
body:
|
||||
- type: markdown
|
||||
attributes:
|
||||
value: |
|
||||
## Question
|
||||
|
||||
Use this form to ask a question about pipecat.
|
||||
|
||||
- type: markdown
|
||||
attributes:
|
||||
value: |
|
||||
### Environment (if applicable)
|
||||
|
||||
- type: input
|
||||
id: pipecat-version
|
||||
attributes:
|
||||
label: pipecat version
|
||||
description: Which version are you using? (if applicable)
|
||||
placeholder: e.g., 0.0.63
|
||||
validations:
|
||||
required: false
|
||||
|
||||
- type: input
|
||||
id: python-version
|
||||
attributes:
|
||||
label: Python version
|
||||
description: Which Python version are you using? (if applicable)
|
||||
placeholder: e.g., 3.12.8
|
||||
validations:
|
||||
required: false
|
||||
|
||||
- type: input
|
||||
id: os
|
||||
attributes:
|
||||
label: Operating System
|
||||
description: Which OS are you using? (if applicable)
|
||||
placeholder: e.g., Ubuntu 24.04, Windows 11, macOS 12.5
|
||||
validations:
|
||||
required: false
|
||||
|
||||
- type: textarea
|
||||
id: question
|
||||
attributes:
|
||||
label: Question
|
||||
description: Provide your question in detail here.
|
||||
validations:
|
||||
required: true
|
||||
|
||||
- type: textarea
|
||||
id: tried
|
||||
attributes:
|
||||
label: What I've tried
|
||||
description: Describe what you've already tried or research you've done.
|
||||
placeholder: I've looked at the documentation and tried...
|
||||
validations:
|
||||
required: false
|
||||
|
||||
- type: textarea
|
||||
id: context
|
||||
attributes:
|
||||
label: Context
|
||||
description: Any additional context or information that might help others understand your question better.
|
||||
validations:
|
||||
required: false
|
||||
52
.github/ISSUE_TEMPLATE/3-feature_request.yml
vendored
52
.github/ISSUE_TEMPLATE/3-feature_request.yml
vendored
@@ -1,52 +0,0 @@
|
||||
name: Feature request
|
||||
description: Suggest an enhancement or new feature
|
||||
type: Enhancement
|
||||
body:
|
||||
- type: markdown
|
||||
attributes:
|
||||
value: |
|
||||
## Feature Request
|
||||
|
||||
Thank you for suggesting an enhancement to pipecat.
|
||||
|
||||
- type: textarea
|
||||
id: problem
|
||||
attributes:
|
||||
label: Problem Statement
|
||||
description: A clear description of the problem this feature would solve.
|
||||
placeholder: I'm always frustrated when...
|
||||
validations:
|
||||
required: true
|
||||
|
||||
- type: textarea
|
||||
id: solution
|
||||
attributes:
|
||||
label: Proposed Solution
|
||||
description: A clear and concise description of what you want to happen.
|
||||
validations:
|
||||
required: true
|
||||
|
||||
- type: textarea
|
||||
id: alternatives
|
||||
attributes:
|
||||
label: Alternative Solutions
|
||||
description: Any alternative solutions or features you've considered.
|
||||
validations:
|
||||
required: false
|
||||
|
||||
- type: textarea
|
||||
id: context
|
||||
attributes:
|
||||
label: Additional Context
|
||||
description: Add any other context, mockups, or screenshots about the feature request here.
|
||||
placeholder: You can drag and drop images here to include them.
|
||||
validations:
|
||||
required: false
|
||||
|
||||
- type: checkboxes
|
||||
id: contribution
|
||||
attributes:
|
||||
label: Would you be willing to help implement this feature?
|
||||
options:
|
||||
- label: Yes, I'd like to contribute
|
||||
- label: No, I'm just suggesting
|
||||
82
.github/ISSUE_TEMPLATE/4-service-issue.yml
vendored
82
.github/ISSUE_TEMPLATE/4-service-issue.yml
vendored
@@ -1,82 +0,0 @@
|
||||
name: Service Issue
|
||||
description: An issue with a third-party service
|
||||
type: Service Issue
|
||||
body:
|
||||
- type: markdown
|
||||
attributes:
|
||||
value: |
|
||||
## Service Issue
|
||||
|
||||
Use this form to report an issue with a third-party service integration.
|
||||
|
||||
- type: input
|
||||
id: pipecat-version
|
||||
attributes:
|
||||
label: pipecat version
|
||||
description: Which version are you using?
|
||||
placeholder: e.g., 0.0.63
|
||||
validations:
|
||||
required: true
|
||||
|
||||
- type: input
|
||||
id: service-name
|
||||
attributes:
|
||||
label: Service Name
|
||||
description: Which third-party service is having issues?
|
||||
placeholder: e.g., OpenAI, ElevenLabs, Anthropic
|
||||
validations:
|
||||
required: true
|
||||
|
||||
- type: input
|
||||
id: service-version
|
||||
attributes:
|
||||
label: Service or model version
|
||||
description: Which version of the service API or model are you using?
|
||||
placeholder: e.g., v1, gpt-4.1
|
||||
validations:
|
||||
required: false
|
||||
|
||||
- type: textarea
|
||||
id: description
|
||||
attributes:
|
||||
label: Issue Description
|
||||
description: Provide a clear description of the service issue.
|
||||
validations:
|
||||
required: true
|
||||
|
||||
- type: textarea
|
||||
id: reproduction
|
||||
attributes:
|
||||
label: Reproduction Steps
|
||||
description: Provide steps to reproduce the issue.
|
||||
placeholder: |
|
||||
1. Configure service X
|
||||
2. Call method Y
|
||||
3. See error Z
|
||||
validations:
|
||||
required: true
|
||||
|
||||
- type: textarea
|
||||
id: expected
|
||||
attributes:
|
||||
label: Expected Behavior
|
||||
description: What did you expect to happen?
|
||||
validations:
|
||||
required: true
|
||||
|
||||
- type: textarea
|
||||
id: actual
|
||||
attributes:
|
||||
label: Actual Behavior
|
||||
description: What actually happened?
|
||||
validations:
|
||||
required: true
|
||||
|
||||
- type: textarea
|
||||
id: logs
|
||||
attributes:
|
||||
label: Error Logs
|
||||
description: If available, include any error messages or logs.
|
||||
render: shell
|
||||
validations:
|
||||
required: false
|
||||
56
.github/ISSUE_TEMPLATE/5-new-service.yml
vendored
56
.github/ISSUE_TEMPLATE/5-new-service.yml
vendored
@@ -1,56 +0,0 @@
|
||||
name: New Service
|
||||
description: Request to support a new third-party service
|
||||
type: New Service
|
||||
body:
|
||||
- type: markdown
|
||||
attributes:
|
||||
value: |
|
||||
## New Service Request
|
||||
|
||||
Use this form to request support for a new third-party service in pipecat.
|
||||
|
||||
- type: input
|
||||
id: service-name
|
||||
attributes:
|
||||
label: Service Name
|
||||
description: What is the name of the third-party service?
|
||||
placeholder: e.g., NewAPI, SomeService
|
||||
validations:
|
||||
required: true
|
||||
|
||||
- type: input
|
||||
id: service-website
|
||||
attributes:
|
||||
label: Service Website
|
||||
description: Link to the service's website or documentation
|
||||
placeholder: e.g., https://newapi.com
|
||||
validations:
|
||||
required: true
|
||||
|
||||
- type: textarea
|
||||
id: service-description
|
||||
attributes:
|
||||
label: Service Description
|
||||
description: Briefly describe what this service does and how it works.
|
||||
validations:
|
||||
required: true
|
||||
|
||||
- type: textarea
|
||||
id: api-info
|
||||
attributes:
|
||||
label: API Information
|
||||
description: If available, provide details about the service's API.
|
||||
placeholder: |
|
||||
- API documentation link
|
||||
- Authentication method
|
||||
- Key endpoints you'd like supported
|
||||
validations:
|
||||
required: false
|
||||
|
||||
- type: checkboxes
|
||||
id: contribution
|
||||
attributes:
|
||||
label: Would you be willing to help implement this service?
|
||||
options:
|
||||
- label: Yes, I'd like to contribute
|
||||
- label: No, I'm just suggesting
|
||||
74
.github/ISSUE_TEMPLATE/6-dependency.yml
vendored
74
.github/ISSUE_TEMPLATE/6-dependency.yml
vendored
@@ -1,74 +0,0 @@
|
||||
name: Dependency Issue
|
||||
description: An issue with a Pipecat dependency (not a third-party service)
|
||||
type: Dependency Issue
|
||||
body:
|
||||
- type: markdown
|
||||
attributes:
|
||||
value: |
|
||||
## Dependency Issue
|
||||
|
||||
Use this form to report an issue with a Pipecat dependency.
|
||||
|
||||
- type: input
|
||||
id: pipecat-version
|
||||
attributes:
|
||||
label: pipecat version
|
||||
description: Which version are you using?
|
||||
placeholder: e.g., 0.0.63
|
||||
validations:
|
||||
required: true
|
||||
|
||||
- type: input
|
||||
id: dependency-name
|
||||
attributes:
|
||||
label: Dependency Name
|
||||
description: Which Pipecat dependency is causing the issue?
|
||||
placeholder: e.g., openai, anthropic, fastapi
|
||||
validations:
|
||||
required: true
|
||||
|
||||
- type: input
|
||||
id: dependency-version
|
||||
attributes:
|
||||
label: Dependency Version
|
||||
description: Which version of the dependency are you using?
|
||||
placeholder: e.g., 1.2.3
|
||||
validations:
|
||||
required: true
|
||||
|
||||
- type: textarea
|
||||
id: description
|
||||
attributes:
|
||||
label: Issue Description
|
||||
description: Provide a clear description of the dependency issue.
|
||||
validations:
|
||||
required: true
|
||||
|
||||
- type: textarea
|
||||
id: impact
|
||||
attributes:
|
||||
label: Impact
|
||||
description: How is this dependency issue affecting your usage of pipecat?
|
||||
validations:
|
||||
required: true
|
||||
|
||||
- type: textarea
|
||||
id: reproduction
|
||||
attributes:
|
||||
label: Reproduction Steps
|
||||
description: If applicable, provide steps to reproduce the issue.
|
||||
placeholder: |
|
||||
1. Install dependency X
|
||||
2. Run command Y
|
||||
3. See error Z
|
||||
validations:
|
||||
required: false
|
||||
|
||||
- type: textarea
|
||||
id: logs
|
||||
attributes:
|
||||
label: Error Logs
|
||||
description: If applicable, include any relevant error messages or logs.
|
||||
render: shell
|
||||
validations:
|
||||
required: false
|
||||
70
.github/ISSUE_TEMPLATE/7-troubleshooting.yml
vendored
70
.github/ISSUE_TEMPLATE/7-troubleshooting.yml
vendored
@@ -1,70 +0,0 @@
|
||||
name: Troubleshooting
|
||||
description: Help with a specific use case
|
||||
type: Troubleshooting
|
||||
body:
|
||||
- type: markdown
|
||||
attributes:
|
||||
value: |
|
||||
## Troubleshooting Request
|
||||
|
||||
Use this form to get help with a specific use case or implementation.
|
||||
|
||||
- type: input
|
||||
id: pipecat-version
|
||||
attributes:
|
||||
label: pipecat version
|
||||
description: Which version are you using?
|
||||
placeholder: e.g., 0.0.63
|
||||
validations:
|
||||
required: true
|
||||
|
||||
- type: input
|
||||
id: python-version
|
||||
attributes:
|
||||
label: Python version
|
||||
description: Which version of Python are you using?
|
||||
placeholder: e.g., 3.12.8
|
||||
validations:
|
||||
required: true
|
||||
|
||||
- type: input
|
||||
id: os
|
||||
attributes:
|
||||
label: Operating System
|
||||
description: Which OS are you using?
|
||||
placeholder: e.g., Ubuntu 24.04, Windows 11, macOS 12.5
|
||||
validations:
|
||||
required: true
|
||||
|
||||
- type: textarea
|
||||
id: use-case
|
||||
attributes:
|
||||
label: Use Case Description
|
||||
description: Describe what you're trying to accomplish with pipecat.
|
||||
validations:
|
||||
required: true
|
||||
|
||||
- type: textarea
|
||||
id: current-approach
|
||||
attributes:
|
||||
label: Current Approach
|
||||
description: What have you tried so far? Include code snippets if relevant.
|
||||
render: python
|
||||
validations:
|
||||
required: true
|
||||
|
||||
- type: textarea
|
||||
id: errors
|
||||
attributes:
|
||||
label: Errors or Unexpected Behavior
|
||||
description: Describe any errors or unexpected behavior you're encountering.
|
||||
validations:
|
||||
required: true
|
||||
|
||||
- type: textarea
|
||||
id: additional-context
|
||||
attributes:
|
||||
label: Additional Context
|
||||
description: Any other information that might help us understand your situation.
|
||||
validations:
|
||||
required: false
|
||||
1
.github/ISSUE_TEMPLATE/config.yml
vendored
1
.github/ISSUE_TEMPLATE/config.yml
vendored
@@ -1 +0,0 @@
|
||||
blank_issues_enabled: false
|
||||
1
.github/PULL_REQUEST_TEMPLATE.md
vendored
1
.github/PULL_REQUEST_TEMPLATE.md
vendored
@@ -1 +0,0 @@
|
||||
#### Please describe the changes in your PR. If it is addressing an issue, please reference that as well.
|
||||
34
.github/workflows/build.yaml
vendored
34
.github/workflows/build.yaml
vendored
@@ -21,20 +21,24 @@ jobs:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v3
|
||||
with:
|
||||
version: "latest"
|
||||
|
||||
- name: Set up Python
|
||||
run: uv python install 3.10
|
||||
|
||||
- name: Install development dependencies
|
||||
run: uv sync --group dev
|
||||
|
||||
id: setup_python
|
||||
uses: actions/setup-python@v4
|
||||
with:
|
||||
python-version: '3.10'
|
||||
- name: Setup virtual environment
|
||||
run: |
|
||||
python -m venv .venv
|
||||
- name: Install basic Python dependencies
|
||||
run: |
|
||||
source .venv/bin/activate
|
||||
python -m pip install --upgrade pip
|
||||
pip install -r dev-requirements.txt
|
||||
- name: Build project
|
||||
run: uv build
|
||||
|
||||
- name: Install project in editable mode
|
||||
run: uv pip install --editable .
|
||||
run: |
|
||||
source .venv/bin/activate
|
||||
python -m build
|
||||
- name: Install project and other Python dependencies
|
||||
run: |
|
||||
source .venv/bin/activate
|
||||
pip install --editable .
|
||||
|
||||
47
.github/workflows/coverage.yaml
vendored
47
.github/workflows/coverage.yaml
vendored
@@ -1,47 +0,0 @@
|
||||
name: coverage
|
||||
|
||||
on:
|
||||
workflow_dispatch:
|
||||
push:
|
||||
branches:
|
||||
- main
|
||||
pull_request:
|
||||
branches:
|
||||
- "**"
|
||||
paths-ignore:
|
||||
- "docs/**"
|
||||
|
||||
jobs:
|
||||
coverage:
|
||||
name: "Coverage"
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout repo
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v3
|
||||
with:
|
||||
version: "latest"
|
||||
|
||||
- name: Set up Python
|
||||
run: uv python install 3.10
|
||||
|
||||
- name: Install system packages
|
||||
run: |
|
||||
sudo apt-get install -y portaudio19-dev
|
||||
|
||||
- name: Install dependencies
|
||||
run: |
|
||||
uv sync --group dev --extra anthropic --extra aws --extra google --extra langchain
|
||||
|
||||
- name: Run tests with coverage
|
||||
run: |
|
||||
uv run coverage run
|
||||
uv run coverage xml
|
||||
|
||||
- name: Upload coverage to Codecov
|
||||
uses: codecov/codecov-action@v5
|
||||
with:
|
||||
token: ${{ secrets.CODECOV_TOKEN }}
|
||||
slug: pipecat-ai/pipecat
|
||||
43
.github/workflows/format.yaml
vendored
43
.github/workflows/format.yaml
vendored
@@ -1,43 +0,0 @@
|
||||
name: format
|
||||
|
||||
on:
|
||||
workflow_dispatch:
|
||||
push:
|
||||
branches:
|
||||
- main
|
||||
pull_request:
|
||||
branches:
|
||||
- "**"
|
||||
paths-ignore:
|
||||
- "docs/**"
|
||||
|
||||
concurrency:
|
||||
group: build-format-${{ github.event.pull_request.number || github.ref }}
|
||||
cancel-in-progress: true
|
||||
|
||||
jobs:
|
||||
ruff-format:
|
||||
name: "Code quality checks"
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout repo
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v3
|
||||
with:
|
||||
version: "latest"
|
||||
|
||||
- name: Set up Python
|
||||
run: uv python install 3.10
|
||||
|
||||
- name: Install development dependencies
|
||||
run: uv sync --group dev
|
||||
|
||||
- name: Ruff formatter
|
||||
id: ruff-format
|
||||
run: uv run ruff format --diff
|
||||
|
||||
- name: Ruff linter (all rules)
|
||||
id: ruff-check
|
||||
run: uv run ruff check
|
||||
44
.github/workflows/lint.yaml
vendored
Normal file
44
.github/workflows/lint.yaml
vendored
Normal file
@@ -0,0 +1,44 @@
|
||||
name: lint
|
||||
|
||||
on:
|
||||
workflow_dispatch:
|
||||
push:
|
||||
branches:
|
||||
- main
|
||||
pull_request:
|
||||
branches:
|
||||
- "**"
|
||||
paths-ignore:
|
||||
- "docs/**"
|
||||
|
||||
concurrency:
|
||||
group: build-lint-${{ github.event.pull_request.number || github.ref }}
|
||||
cancel-in-progress: true
|
||||
|
||||
jobs:
|
||||
autopep8:
|
||||
name: "Formatting lints"
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout repo
|
||||
uses: actions/checkout@v4
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v4
|
||||
with:
|
||||
python-version: '3.10'
|
||||
- name: Setup virtual environment
|
||||
run: |
|
||||
python -m venv .venv
|
||||
- name: Install development Python dependencies
|
||||
run: |
|
||||
source .venv/bin/activate
|
||||
python -m pip install --upgrade pip
|
||||
pip install -r dev-requirements.txt
|
||||
- name: autopep8
|
||||
id: autopep8
|
||||
run: |
|
||||
source .venv/bin/activate
|
||||
autopep8 --max-line-length 100 --exit-code -r -d --exclude "*_pb2.py" -a -a src/
|
||||
- name: Fail if autopep8 requires changes
|
||||
if: steps.autopep8.outputs.exit-code == 2
|
||||
run: exit 1
|
||||
26
.github/workflows/publish.yaml
vendored
26
.github/workflows/publish.yaml
vendored
@@ -5,7 +5,7 @@ on:
|
||||
inputs:
|
||||
gitref:
|
||||
type: string
|
||||
description: "what git tag to build (e.g. v0.0.74)"
|
||||
description: "what git ref to build"
|
||||
required: true
|
||||
|
||||
jobs:
|
||||
@@ -17,17 +17,23 @@ jobs:
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
ref: ${{ github.event.inputs.gitref }}
|
||||
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v3
|
||||
with:
|
||||
version: "latest"
|
||||
- name: Set up Python
|
||||
run: uv python install 3.10
|
||||
- name: Install development dependencies
|
||||
run: uv sync --group dev
|
||||
id: setup_python
|
||||
uses: actions/setup-python@v4
|
||||
with:
|
||||
python-version: '3.10'
|
||||
- name: Setup virtual environment
|
||||
run: |
|
||||
python -m venv .venv
|
||||
- name: Install basic Python dependencies
|
||||
run: |
|
||||
source .venv/bin/activate
|
||||
python -m pip install --upgrade pip
|
||||
pip install -r dev-requirements.txt
|
||||
- name: Build project
|
||||
run: uv build
|
||||
run: |
|
||||
source .venv/bin/activate
|
||||
python -m build
|
||||
- name: Upload wheels
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
|
||||
32
.github/workflows/publish_test.yaml
vendored
32
.github/workflows/publish_test.yaml
vendored
@@ -1,6 +1,10 @@
|
||||
name: publish-test
|
||||
|
||||
on: workflow_dispatch
|
||||
on:
|
||||
workflow_dispatch:
|
||||
push:
|
||||
branches:
|
||||
- main
|
||||
|
||||
jobs:
|
||||
build:
|
||||
@@ -10,18 +14,26 @@ jobs:
|
||||
- name: Checkout repo
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
ref: ${{ github.event.inputs.gitref }}
|
||||
fetch-tags: true
|
||||
fetch-depth: 100
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v3
|
||||
with:
|
||||
version: "latest"
|
||||
- name: Set up Python
|
||||
run: uv python install 3.10
|
||||
- name: Install development dependencies
|
||||
run: uv sync --group dev
|
||||
id: setup_python
|
||||
uses: actions/setup-python@v4
|
||||
with:
|
||||
python-version: '3.10'
|
||||
- name: Setup virtual environment
|
||||
run: |
|
||||
python -m venv .venv
|
||||
- name: Install basic Python dependencies
|
||||
run: |
|
||||
source .venv/bin/activate
|
||||
python -m pip install --upgrade pip
|
||||
pip install -r dev-requirements.txt
|
||||
- name: Build project
|
||||
run: uv build
|
||||
run: |
|
||||
source .venv/bin/activate
|
||||
python -m build
|
||||
- name: Upload wheels
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
@@ -31,7 +43,7 @@ jobs:
|
||||
publish-to-test-pypi:
|
||||
name: "Publish to Test PyPI"
|
||||
runs-on: ubuntu-latest
|
||||
needs: [build]
|
||||
needs: [ build ]
|
||||
environment:
|
||||
name: testpypi
|
||||
url: https://pypi.org/p/pipecat-ai
|
||||
|
||||
123
.github/workflows/python-compatibility.yaml
vendored
123
.github/workflows/python-compatibility.yaml
vendored
@@ -1,123 +0,0 @@
|
||||
name: Python Compatibility Test
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [main, develop]
|
||||
paths: ['pyproject.toml']
|
||||
pull_request:
|
||||
branches: [main, develop]
|
||||
paths: ['pyproject.toml']
|
||||
|
||||
jobs:
|
||||
test-dev-environment:
|
||||
runs-on: ubuntu-latest
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
python-version: ['3.10.18', '3.11.13', '3.12.11', '3.13.5']
|
||||
|
||||
name: Dev Environment - Python ${{ matrix.python-version }}
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Install system dependencies
|
||||
run: |
|
||||
sudo apt-get update
|
||||
sudo apt-get install -y \
|
||||
portaudio19-dev \
|
||||
libcairo2-dev \
|
||||
libgirepository1.0-dev \
|
||||
pkg-config
|
||||
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v4
|
||||
with:
|
||||
version: 'latest'
|
||||
|
||||
- name: Set up Python ${{ matrix.python-version }}
|
||||
run: |
|
||||
uv python install ${{ matrix.python-version }}
|
||||
uv python pin ${{ matrix.python-version }}
|
||||
|
||||
- name: Test uv sync with all extras (Python < 3.13)
|
||||
if: "!startsWith(matrix.python-version, '3.13.')"
|
||||
run: |
|
||||
uv sync --group dev --all-extras --no-extra krisp
|
||||
|
||||
- name: Test uv sync without PyTorch extras (Python 3.13+)
|
||||
if: startsWith(matrix.python-version, '3.13.')
|
||||
run: |
|
||||
uv sync --group dev --all-extras \
|
||||
--no-extra krisp \
|
||||
--no-extra ultravox \
|
||||
--no-extra local-smart-turn \
|
||||
--no-extra moondream \
|
||||
--no-extra mlx-whisper
|
||||
|
||||
- name: Verify dev installation
|
||||
run: |
|
||||
uv run python --version
|
||||
uv run python -c "import pipecat; print('✅ Dev environment - Pipecat imports successfully')"
|
||||
|
||||
test-user-experience:
|
||||
runs-on: ubuntu-latest
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
python-version: ['3.10.18', '3.11.13', '3.12.11', '3.13.5']
|
||||
|
||||
name: User Experience - Python ${{ matrix.python-version }}
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Install system dependencies
|
||||
run: |
|
||||
sudo apt-get update
|
||||
sudo apt-get install -y \
|
||||
portaudio19-dev \
|
||||
libcairo2-dev \
|
||||
libgirepository1.0-dev \
|
||||
pkg-config
|
||||
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v4
|
||||
with:
|
||||
version: 'latest'
|
||||
|
||||
- name: Set up Python ${{ matrix.python-version }}
|
||||
run: |
|
||||
uv python install ${{ matrix.python-version }}
|
||||
|
||||
- name: Build local package
|
||||
run: |
|
||||
uv build
|
||||
|
||||
- name: Create test project
|
||||
run: |
|
||||
mkdir test-project
|
||||
cd test-project
|
||||
uv init --python ${{ matrix.python-version }}
|
||||
|
||||
- name: Test comprehensive extras with uv add (Python 3.10-3.12)
|
||||
if: "!startsWith(matrix.python-version, '3.13.')"
|
||||
run: |
|
||||
cd test-project
|
||||
# Use uv add with built wheel to leverage dependency management
|
||||
uv add "../dist/pipecat_ai-"*".whl[anthropic,assemblyai,asyncai,aws,aws-nova-sonic,azure,cartesia,cerebras,deepseek,daily,deepgram,elevenlabs,fal,fireworks,fish,gladia,google,grok,groq,gstreamer,heygen,inworld,koala,langchain,livekit,lmnt,local,mcp,mem0,mlx-whisper,moondream,nim,neuphonic,noisereduce,openai,openpipe,openrouter,perplexity,playht,qwen,rime,riva,runner,sambanova,sentry,local-smart-turn,remote-smart-turn,silero,simli,soniox,soundfile,speechmatics,tavus,together,tracing,ultravox,webrtc,websocket,whisper]"
|
||||
|
||||
- name: Test Python 3.13 compatible extras with uv add
|
||||
if: startsWith(matrix.python-version, '3.13.')
|
||||
run: |
|
||||
cd test-project
|
||||
# Use uv add with built wheel and Python 3.13 compatible extras
|
||||
uv add "../dist/pipecat_ai-"*".whl[anthropic,assemblyai,asyncai,aws,aws-nova-sonic,azure,cartesia,cerebras,deepseek,daily,deepgram,elevenlabs,fal,fireworks,fish,gladia,google,grok,groq,gstreamer,heygen,inworld,koala,langchain,livekit,lmnt,local,mcp,mem0,nim,neuphonic,noisereduce,openai,openpipe,openrouter,perplexity,playht,qwen,rime,riva,runner,sambanova,sentry,remote-smart-turn,silero,simli,soniox,soundfile,speechmatics,tavus,together,tracing,webrtc,websocket,whisper]"
|
||||
|
||||
- name: Verify user installation
|
||||
run: |
|
||||
cd test-project
|
||||
uv run python --version
|
||||
uv run python -c "import pipecat; print('✅ User experience - Pipecat imports successfully')"
|
||||
# Test that basic functionality works
|
||||
uv run python -c "from pipecat.pipeline.pipeline import Pipeline; print('✅ Pipeline import works')"
|
||||
56
.github/workflows/sync-quickstart.yaml
vendored
56
.github/workflows/sync-quickstart.yaml
vendored
@@ -1,56 +0,0 @@
|
||||
name: Sync Quickstart to pipecat-quickstart repo
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [main]
|
||||
paths:
|
||||
- 'examples/quickstart/**'
|
||||
workflow_dispatch: # Manual trigger
|
||||
|
||||
jobs:
|
||||
sync-quickstart:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout main repo
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 0
|
||||
|
||||
- name: Checkout quickstart repo
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
repository: pipecat-ai/pipecat-quickstart
|
||||
token: ${{ secrets.QUICKSTART_SYNC_TOKEN }}
|
||||
path: quickstart-repo
|
||||
|
||||
- name: Sync files (excluding READMEs)
|
||||
run: |
|
||||
# Copy code files only, skip READMEs
|
||||
cp examples/quickstart/bot.py quickstart-repo/
|
||||
cp examples/quickstart/requirements.txt quickstart-repo/
|
||||
cp examples/quickstart/env.example quickstart-repo/
|
||||
|
||||
# Copy any other files that aren't README.md
|
||||
find examples/quickstart -type f \
|
||||
-not -name "README.md" \
|
||||
-not -name "*.md" \
|
||||
-exec cp {} quickstart-repo/ \;
|
||||
|
||||
- name: Commit and push changes
|
||||
run: |
|
||||
cd quickstart-repo
|
||||
git config user.name "GitHub Action"
|
||||
git config user.email "action@github.com"
|
||||
git add .
|
||||
|
||||
# Only commit if there are changes
|
||||
if ! git diff --staged --quiet; then
|
||||
git commit -m "Sync from pipecat main repo
|
||||
|
||||
Updated files from examples/quickstart/
|
||||
Commit: ${{ github.sha }}
|
||||
"
|
||||
git push
|
||||
else
|
||||
echo "No changes to sync"
|
||||
fi
|
||||
39
.github/workflows/tests.yaml
vendored
39
.github/workflows/tests.yaml
vendored
@@ -1,4 +1,4 @@
|
||||
name: tests
|
||||
name: test
|
||||
|
||||
on:
|
||||
workflow_dispatch:
|
||||
@@ -20,25 +20,30 @@ jobs:
|
||||
name: "Unit and Integration Tests"
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout repo
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v3
|
||||
with:
|
||||
version: "latest"
|
||||
|
||||
- uses: actions/checkout@v4
|
||||
- name: Set up Python
|
||||
run: uv python install 3.10
|
||||
|
||||
id: setup_python
|
||||
uses: actions/setup-python@v4
|
||||
with:
|
||||
python-version: '3.10'
|
||||
- name: Cache virtual environment
|
||||
uses: actions/cache@v3
|
||||
with:
|
||||
# We are hashing requirements-dev.txt and requirements-extra.txt which
|
||||
# contain all dependencies needed to run the tests and examples.
|
||||
key: venv-${{ runner.os }}-${{ steps.setup_python.outputs.python-version}}-${{ hashFiles('linux-py3.10-requirements.txt') }}-${{ hashFiles('dev-requirements.txt') }}
|
||||
path: .venv
|
||||
- name: Install system packages
|
||||
run: sudo apt-get install -y portaudio19-dev
|
||||
- name: Setup virtual environment
|
||||
run: |
|
||||
sudo apt-get install -y portaudio19-dev
|
||||
|
||||
- name: Install dependencies
|
||||
python -m venv .venv
|
||||
- name: Install basic Python dependencies
|
||||
run: |
|
||||
uv sync --group dev --extra anthropic --extra aws --extra google --extra langchain
|
||||
|
||||
source .venv/bin/activate
|
||||
python -m pip install --upgrade pip
|
||||
pip install -r linux-py3.10-requirements.txt -r dev-requirements.txt
|
||||
- name: Test with pytest
|
||||
run: |
|
||||
uv run pytest
|
||||
source .venv/bin/activate
|
||||
pytest --doctest-modules --ignore-glob="*to_be_updated*" src tests
|
||||
|
||||
42
.github/workflows/update-lockfile.yaml
vendored
42
.github/workflows/update-lockfile.yaml
vendored
@@ -1,42 +0,0 @@
|
||||
name: Update lockfile
|
||||
|
||||
on:
|
||||
push:
|
||||
paths:
|
||||
- 'pyproject.toml'
|
||||
branches:
|
||||
- main
|
||||
workflow_dispatch: # Allows manual triggering from GitHub UI
|
||||
|
||||
jobs:
|
||||
update-lockfile:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
with:
|
||||
# This gives the workflow permission to push back to the repo
|
||||
token: ${{ secrets.GITHUB_TOKEN }}
|
||||
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v1
|
||||
|
||||
- name: Update lockfile
|
||||
run: uv lock
|
||||
|
||||
- name: Check for changes
|
||||
id: verify-changed-files
|
||||
run: |
|
||||
if [ -n "$(git status --porcelain)" ]; then
|
||||
echo "changed=true" >> $GITHUB_OUTPUT
|
||||
else
|
||||
echo "changed=false" >> $GITHUB_OUTPUT
|
||||
fi
|
||||
|
||||
- name: Commit lockfile
|
||||
if: steps.verify-changed-files.outputs.changed == 'true'
|
||||
run: |
|
||||
git config --local user.email "action@github.com"
|
||||
git config --local user.name "GitHub Action"
|
||||
git add uv.lock
|
||||
git commit -m "chore: update uv.lock after dependency changes"
|
||||
git push
|
||||
28
.gitignore
vendored
28
.gitignore
vendored
@@ -4,10 +4,9 @@ __pycache__/
|
||||
*~
|
||||
venv
|
||||
.venv
|
||||
/.idea
|
||||
#*#
|
||||
|
||||
# Distribution / Packaging
|
||||
# Distribution / packaging
|
||||
.Python
|
||||
build/
|
||||
develop-eggs/
|
||||
@@ -28,27 +27,4 @@ share/python-wheels/
|
||||
MANIFEST
|
||||
.DS_Store
|
||||
.env
|
||||
fly.toml
|
||||
|
||||
# Examples
|
||||
examples/**/node_modules/
|
||||
examples/**/.expo/
|
||||
examples/**/dist/
|
||||
examples/**/npm-debug.*
|
||||
examples/**/*.jks
|
||||
examples/**/*.p8
|
||||
examples/**/*.p12
|
||||
examples/**/*.key
|
||||
examples/**/*.mobileprovision
|
||||
examples/**/*.orig.*
|
||||
examples/**/web-build/
|
||||
|
||||
# macOS
|
||||
.DS_Store
|
||||
|
||||
# Documentation
|
||||
docs/api/_build/
|
||||
docs/api/api
|
||||
|
||||
# uv
|
||||
.python-version
|
||||
fly.toml
|
||||
@@ -1,8 +0,0 @@
|
||||
repos:
|
||||
- repo: https://github.com/astral-sh/ruff-pre-commit
|
||||
rev: v0.12.1
|
||||
hooks:
|
||||
- id: ruff
|
||||
language_version: python3
|
||||
args: [--fix]
|
||||
- id: ruff-format
|
||||
@@ -1,28 +0,0 @@
|
||||
version: 2
|
||||
|
||||
build:
|
||||
os: ubuntu-22.04
|
||||
tools:
|
||||
python: '3.12'
|
||||
apt_packages:
|
||||
- portaudio19-dev
|
||||
- python3-dev
|
||||
- libasound2-dev
|
||||
jobs:
|
||||
post_install:
|
||||
- pip install uv
|
||||
- UV_PROJECT_ENVIRONMENT=$READTHEDOCS_VIRTUALENV_PATH uv sync --group docs --all-extras --no-extra krisp --no-extra gstreamer --no-extra ultravox --no-extra local_smart_turn --no-extra moondream --no-extra riva --no-extra mlx-whisper
|
||||
|
||||
sphinx:
|
||||
configuration: docs/api/conf.py
|
||||
fail_on_warning: false
|
||||
|
||||
search:
|
||||
ranking:
|
||||
api/*: 5
|
||||
getting-started/*: 4
|
||||
guides/*: 3
|
||||
|
||||
submodules:
|
||||
include: all
|
||||
recursive: true
|
||||
3617
CHANGELOG.md
3617
CHANGELOG.md
File diff suppressed because it is too large
Load Diff
320
CONTRIBUTING.md
320
CONTRIBUTING.md
@@ -1,320 +0,0 @@
|
||||
## Contributing to Pipecat
|
||||
|
||||
We welcome contributions of all kinds! Your help is appreciated. Follow these steps to get involved:
|
||||
|
||||
1. **Fork this repository**: Start by forking the Pipecat Documentation repository to your GitHub account.
|
||||
|
||||
2. **Clone the repository**: Clone your forked repository to your local machine.
|
||||
```bash
|
||||
git clone https://github.com/your-username/pipecat
|
||||
```
|
||||
3. **Create a branch**: For your contribution, create a new branch.
|
||||
```bash
|
||||
git checkout -b your-branch-name
|
||||
```
|
||||
4. **Make your changes**: Edit or add files as necessary.
|
||||
5. **Test your changes**: Ensure that your changes look correct and follow the style set in the codebase.
|
||||
6. **Commit your changes**: Once you're satisfied with your changes, commit them with a meaningful message.
|
||||
|
||||
```bash
|
||||
git commit -m "Description of your changes"
|
||||
```
|
||||
|
||||
7. **Push your changes**: Push your branch to your forked repository.
|
||||
|
||||
```bash
|
||||
git push origin your-branch-name
|
||||
```
|
||||
|
||||
8. **Submit a Pull Request (PR)**: Open a PR from your forked repository to the main branch of this repo.
|
||||
> Important: Describe the changes you've made clearly!
|
||||
|
||||
Our maintainers will review your PR, and once everything is good, your contributions will be merged!
|
||||
|
||||
## Code Style and Documentation
|
||||
|
||||
### Python Code Style
|
||||
|
||||
We use Ruff for code linting and formatting. Please ensure your code passes all linting checks before submitting a PR.
|
||||
|
||||
### Docstring Conventions
|
||||
|
||||
We follow Google-style docstrings with these specific conventions:
|
||||
|
||||
**Regular Classes:**
|
||||
|
||||
- Class docstring describes the class purpose and key functionality
|
||||
- `__init__` method has its own docstring with complete `Args:` section documenting all parameters
|
||||
- All public methods must have docstrings with `Args:` and `Returns:` sections as appropriate
|
||||
|
||||
**Dataclasses:**
|
||||
|
||||
- Class docstring describes the purpose and documents all fields in a `Parameters:` section
|
||||
- No `__init__` docstring (auto-generated)
|
||||
|
||||
**Properties:**
|
||||
|
||||
- Must have docstrings with `Returns:` section
|
||||
|
||||
**Abstract Methods:**
|
||||
|
||||
- Must have docstrings explaining what subclasses should implement
|
||||
|
||||
**`__init__.py` Files:**
|
||||
|
||||
- **Skip docstrings** for pure import/re-export modules
|
||||
- **Add brief docstrings** for top-level packages or those with initialization logic
|
||||
|
||||
**Enums:**
|
||||
|
||||
- Class docstring describes the enumeration purpose
|
||||
- Use `Parameters:` section to document each enum value and its meaning
|
||||
- No `__init__` docstring (Enums don't have custom constructors)
|
||||
|
||||
**Code Examples in Docstrings:**
|
||||
|
||||
- Use `Examples:` as a section header for multiple examples
|
||||
- Use descriptive text followed by double colons (`::`) for each example
|
||||
- **Always include a blank line after the `::"`**
|
||||
- Indent all code consistently within each block
|
||||
- Separate multiple examples with blank lines for readability
|
||||
|
||||
**Lists and Bullets in Docstrings:**
|
||||
|
||||
- Use dashes (`-`) for bullet points, not asterisks (`*`)
|
||||
- **Add a blank line before bullet lists** when they follow a colon
|
||||
- Use section headers like "Supported features:" or "Behavior:" before lists
|
||||
- For complex nested information, consider using paragraph format instead
|
||||
|
||||
**Deprecations:**
|
||||
|
||||
- Use `warnings.warn()` in code for runtime deprecation warnings
|
||||
- Add `.. deprecated::` directive in docstrings for documentation visibility
|
||||
- Include version information and describe current status
|
||||
- Describe parameters in present tense, use directive to indicate deprecation status
|
||||
|
||||
#### Examples:
|
||||
|
||||
```python
|
||||
# Regular class
|
||||
class MyService(BaseService):
|
||||
"""Description of what the service does.
|
||||
|
||||
Provides detailed explanation of the service's functionality,
|
||||
key features, and usage patterns.
|
||||
|
||||
Supported features:
|
||||
|
||||
- Feature one with detailed explanation
|
||||
- Feature two with additional context
|
||||
- Feature three for advanced use cases
|
||||
"""
|
||||
|
||||
def __init__(self, param1: str, old_param: str = None, **kwargs):
|
||||
"""Initialize the service.
|
||||
|
||||
Args:
|
||||
param1: Description of param1.
|
||||
old_param: Controls legacy behavior.
|
||||
|
||||
.. deprecated:: 1.2.0
|
||||
This parameter no longer has any effect and will be removed in version 2.0.
|
||||
|
||||
**kwargs: Additional arguments passed to parent.
|
||||
"""
|
||||
if old_param is not None:
|
||||
import warnings
|
||||
warnings.warn(
|
||||
"Parameter 'old_param' is deprecated and will be removed in version 2.0.",
|
||||
DeprecationWarning,
|
||||
)
|
||||
super().__init__(**kwargs)
|
||||
|
||||
@property
|
||||
def sample_rate(self) -> int:
|
||||
"""Get the current sample rate.
|
||||
|
||||
Returns:
|
||||
The sample rate in Hz.
|
||||
"""
|
||||
return self._sample_rate
|
||||
|
||||
async def process_data(self, data: str) -> bool:
|
||||
"""Process the provided data.
|
||||
|
||||
Args:
|
||||
data: The data to process.
|
||||
|
||||
Returns:
|
||||
True if processing succeeded.
|
||||
"""
|
||||
pass
|
||||
|
||||
# Dataclass with code examples
|
||||
@dataclass
|
||||
class MessageFrame:
|
||||
"""Frame containing messages in OpenAI format.
|
||||
|
||||
Supports both simple and content list message formats.
|
||||
|
||||
Example::
|
||||
|
||||
[
|
||||
{"role": "user", "content": "Hello"},
|
||||
{"role": "assistant", "content": "Hi there!"}
|
||||
]
|
||||
|
||||
Parameters:
|
||||
messages: List of messages in OpenAI format.
|
||||
"""
|
||||
|
||||
messages: List[dict]
|
||||
|
||||
# Enum class
|
||||
class Status(Enum):
|
||||
"""Status codes for processing operations.
|
||||
|
||||
Parameters:
|
||||
PENDING: Operation is queued but not started.
|
||||
RUNNING: Operation is currently in progress.
|
||||
COMPLETED: Operation finished successfully.
|
||||
FAILED: Operation encountered an error.
|
||||
"""
|
||||
|
||||
PENDING = "pending"
|
||||
RUNNING = "running"
|
||||
COMPLETED = "completed"
|
||||
FAILED = "failed"
|
||||
```
|
||||
|
||||
# Contributor Covenant Code of Conduct
|
||||
|
||||
## Our Pledge
|
||||
|
||||
We as members, contributors, and leaders pledge to make participation in our
|
||||
community a harassment-free experience for everyone, regardless of age, body
|
||||
size, visible or invisible disability, ethnicity, sex characteristics, gender
|
||||
identity and expression, level of experience, education, socio-economic status,
|
||||
nationality, personal appearance, race, caste, color, religion, or sexual
|
||||
identity and orientation.
|
||||
|
||||
We pledge to act and interact in ways that contribute to an open, welcoming,
|
||||
diverse, inclusive, and healthy community.
|
||||
|
||||
## Our Standards
|
||||
|
||||
Examples of behavior that contributes to a positive environment for our
|
||||
community include:
|
||||
|
||||
- Demonstrating empathy and kindness toward other people
|
||||
- Being respectful of differing opinions, viewpoints, and experiences
|
||||
- Giving and gracefully accepting constructive feedback
|
||||
- Accepting responsibility and apologizing to those affected by our mistakes,
|
||||
and learning from the experience
|
||||
- Focusing on what is best not just for us as individuals, but for the overall
|
||||
community
|
||||
|
||||
Examples of unacceptable behavior include:
|
||||
|
||||
- The use of sexualized language or imagery, and sexual attention or advances of
|
||||
any kind
|
||||
- Trolling, insulting or derogatory comments, and personal or political attacks
|
||||
- Public or private harassment
|
||||
- Publishing others' private information, such as a physical or email address,
|
||||
without their explicit permission
|
||||
- Other conduct which could reasonably be considered inappropriate in a
|
||||
professional setting
|
||||
|
||||
## Enforcement Responsibilities
|
||||
|
||||
Community leaders are responsible for clarifying and enforcing our standards of
|
||||
acceptable behavior and will take appropriate and fair corrective action in
|
||||
response to any behavior that they deem inappropriate, threatening, offensive,
|
||||
or harmful.
|
||||
|
||||
Community leaders have the right and responsibility to remove, edit, or reject
|
||||
comments, commits, code, wiki edits, issues, and other contributions that are
|
||||
not aligned to this Code of Conduct, and will communicate reasons for moderation
|
||||
decisions when appropriate.
|
||||
|
||||
## Scope
|
||||
|
||||
This Code of Conduct applies within all community spaces, and also applies when
|
||||
an individual is officially representing the community in public spaces.
|
||||
Examples of representing our community include using an official email address,
|
||||
posting via an official social media account, or acting as an appointed
|
||||
representative at an online or offline event.
|
||||
|
||||
## Enforcement
|
||||
|
||||
Instances of abusive, harassing, or otherwise unacceptable behavior may be
|
||||
reported to the community leaders responsible for enforcement at pipecat-ai@daily.co.
|
||||
All complaints will be reviewed and investigated promptly and fairly.
|
||||
|
||||
All community leaders are obligated to respect the privacy and security of the
|
||||
reporter of any incident.
|
||||
|
||||
## Enforcement Guidelines
|
||||
|
||||
Community leaders will follow these Community Impact Guidelines in determining
|
||||
the consequences for any action they deem in violation of this Code of Conduct:
|
||||
|
||||
### 1. Correction
|
||||
|
||||
**Community Impact**: Use of inappropriate language or other behavior deemed
|
||||
unprofessional or unwelcome in the community.
|
||||
|
||||
**Consequence**: A private, written warning from community leaders, providing
|
||||
clarity around the nature of the violation and an explanation of why the
|
||||
behavior was inappropriate. A public apology may be requested.
|
||||
|
||||
### 2. Warning
|
||||
|
||||
**Community Impact**: A violation through a single incident or series of
|
||||
actions.
|
||||
|
||||
**Consequence**: A warning with consequences for continued behavior. No
|
||||
interaction with the people involved, including unsolicited interaction with
|
||||
those enforcing the Code of Conduct, for a specified period of time. This
|
||||
includes avoiding interactions in community spaces as well as external channels
|
||||
like social media. Violating these terms may lead to a temporary or permanent
|
||||
ban.
|
||||
|
||||
### 3. Temporary Ban
|
||||
|
||||
**Community Impact**: A serious violation of community standards, including
|
||||
sustained inappropriate behavior.
|
||||
|
||||
**Consequence**: A temporary ban from any sort of interaction or public
|
||||
communication with the community for a specified period of time. No public or
|
||||
private interaction with the people involved, including unsolicited interaction
|
||||
with those enforcing the Code of Conduct, is allowed during this period.
|
||||
Violating these terms may lead to a permanent ban.
|
||||
|
||||
### 4. Permanent Ban
|
||||
|
||||
**Community Impact**: Demonstrating a pattern of violation of community
|
||||
standards, including sustained inappropriate behavior, harassment of an
|
||||
individual, or aggression toward or disparagement of classes of individuals.
|
||||
|
||||
**Consequence**: A permanent ban from any sort of public interaction within the
|
||||
community.
|
||||
|
||||
## Attribution
|
||||
|
||||
This Code of Conduct is adapted from the [Contributor Covenant][homepage],
|
||||
version 2.1, available at
|
||||
[https://www.contributor-covenant.org/version/2/1/code_of_conduct.html][v2.1].
|
||||
|
||||
Community Impact Guidelines were inspired by
|
||||
[Mozilla's code of conduct enforcement ladder][Mozilla CoC].
|
||||
|
||||
For answers to common questions about this code of conduct, see the FAQ at
|
||||
[https://www.contributor-covenant.org/faq][FAQ]. Translations are available at
|
||||
[https://www.contributor-covenant.org/translations][translations].
|
||||
|
||||
[homepage]: https://www.contributor-covenant.org
|
||||
[v2.1]: https://www.contributor-covenant.org/version/2/1/code_of_conduct.html
|
||||
[Mozilla CoC]: https://github.com/mozilla/diversity
|
||||
[FAQ]: https://www.contributor-covenant.org/faq
|
||||
[translations]: https://www.contributor-covenant.org/translations
|
||||
40
Dockerfile
Normal file
40
Dockerfile
Normal file
@@ -0,0 +1,40 @@
|
||||
# setup
|
||||
FROM python:3.11.5
|
||||
|
||||
WORKDIR /app
|
||||
COPY requirements.txt /app
|
||||
COPY *.py /app
|
||||
COPY pyproject.toml /app
|
||||
|
||||
COPY src/ /app/src/
|
||||
COPY examples/ /app/examples/
|
||||
|
||||
WORKDIR /app
|
||||
RUN ls --recursive /app/
|
||||
RUN pip3 install --upgrade -r requirements.txt
|
||||
RUN python -m build .
|
||||
RUN pip3 install .
|
||||
RUN pip3 install gunicorn
|
||||
# If running on Ubuntu, Azure TTS requires some extra config
|
||||
# https://learn.microsoft.com/en-us/azure/ai-services/speech-service/quickstarts/setup-platform?pivots=programming-language-python&tabs=linux%2Cubuntu%2Cdotnetcli%2Cdotnet%2Cjre%2Cmaven%2Cnodejs%2Cmac%2Cpypi
|
||||
|
||||
RUN wget -O - https://www.openssl.org/source/openssl-1.1.1w.tar.gz | tar zxf -
|
||||
WORKDIR openssl-1.1.1w
|
||||
RUN ./config --prefix=/usr/local
|
||||
RUN make -j $(nproc)
|
||||
RUN make install_sw install_ssldirs
|
||||
RUN ldconfig -v
|
||||
ENV SSL_CERT_DIR=/etc/ssl/certs
|
||||
|
||||
#ENV LD_LIBRARY_PATH=/usr/local/lib:$LD_LIBRARY_PATH
|
||||
RUN apt clean
|
||||
RUN apt-get update
|
||||
RUN apt-get -y install build-essential libssl-dev ca-certificates libasound2 wget
|
||||
|
||||
ENV PYTHONUNBUFFERED=1
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
EXPOSE 8000
|
||||
# run
|
||||
CMD ["gunicorn", "--workers=2", "--log-level", "debug", "--chdir", "examples/server", "--capture-output", "daily-bot-manager:app", "--bind=0.0.0.0:8000"]
|
||||
2
LICENSE
2
LICENSE
@@ -1,6 +1,6 @@
|
||||
BSD 2-Clause License
|
||||
|
||||
Copyright (c) 2024–2025, Daily
|
||||
Copyright (c) 2024, Daily
|
||||
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are met:
|
||||
|
||||
@@ -1,4 +0,0 @@
|
||||
prune docs
|
||||
prune examples
|
||||
prune scripts
|
||||
prune tests
|
||||
361
README.md
361
README.md
@@ -1,240 +1,221 @@
|
||||
<h1><div align="center">
|
||||
<img alt="pipecat" width="300px" height="auto" src="https://raw.githubusercontent.com/pipecat-ai/pipecat/main/pipecat.png">
|
||||
</div></h1>
|
||||
<div align="center">
|
||||
<img alt="pipecat" width="300px" height="auto" src="https://raw.githubusercontent.com/pipecat-ai/pipecat/main/pipecat.png">
|
||||
</div>
|
||||
|
||||
[](https://pypi.org/project/pipecat-ai)  [](https://codecov.io/gh/pipecat-ai/pipecat) [](https://docs.pipecat.ai) [](https://discord.gg/pipecat)
|
||||
# Pipecat
|
||||
|
||||
# 🎙️ Pipecat: Real-Time Voice & Multimodal AI Agents
|
||||
[](https://pypi.org/project/pipecat-ai) [](https://discord.gg/pipecat)
|
||||
|
||||
**Pipecat** is an open-source Python framework for building real-time voice and multimodal conversational agents. Orchestrate audio and video, AI services, different transports, and conversation pipelines effortlessly—so you can focus on what makes your agent unique.
|
||||
`pipecat` is a framework for building voice (and multimodal) conversational agents. Things like personal coaches, meeting assistants, [story-telling toys for kids](https://storytelling-chatbot.fly.dev/), customer support bots, [intake flows](https://www.youtube.com/watch?v=lDevgsp9vn0), and snarky social companions.
|
||||
|
||||
> Want to dive right in? Try the [quickstart](https://docs.pipecat.ai/getting-started/quickstart).
|
||||
|
||||
## 🚀 What You Can Build
|
||||
|
||||
- **Voice Assistants** – natural, streaming conversations with AI
|
||||
- **AI Companions** – coaches, meeting assistants, characters
|
||||
- **Multimodal Interfaces** – voice, video, images, and more
|
||||
- **Interactive Storytelling** – creative tools with generative media
|
||||
- **Business Agents** – customer intake, support bots, guided flows
|
||||
- **Complex Dialog Systems** – design logic with structured conversations
|
||||
|
||||
🧭 Looking to build structured conversations? Check out [Pipecat Flows](https://github.com/pipecat-ai/pipecat-flows) for managing complex conversational states and transitions.
|
||||
|
||||
## 🧠 Why Pipecat?
|
||||
|
||||
- **Voice-first**: Integrates speech recognition, text-to-speech, and conversation handling
|
||||
- **Pluggable**: Supports many AI services and tools
|
||||
- **Composable Pipelines**: Build complex behavior from modular components
|
||||
- **Real-Time**: Ultra-low latency interaction with different transports (e.g. WebSockets or WebRTC)
|
||||
|
||||
## 🎬 See it in action
|
||||
Take a look at some example apps:
|
||||
|
||||
<p float="left">
|
||||
<a href="https://github.com/pipecat-ai/pipecat-examples/tree/main/simple-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat-examples/main/simple-chatbot/image.png" width="400" /></a>
|
||||
<a href="https://github.com/pipecat-ai/pipecat-examples/tree/main/storytelling-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat-examples/main/storytelling-chatbot/image.png" width="400" /></a>
|
||||
<a href="https://github.com/pipecat-ai/pipecat/tree/main/examples/simple-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat/main/examples/simple-chatbot/image.png" width="280" /></a>
|
||||
<a href="https://github.com/pipecat-ai/pipecat/tree/main/examples/storytelling-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat/main/examples/storytelling-chatbot/image.png" width="280" /></a>
|
||||
<br/>
|
||||
<a href="https://github.com/pipecat-ai/pipecat-examples/tree/main/translation-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat-examples/main/translation-chatbot/image.png" width="400" /></a>
|
||||
<a href="https://github.com/pipecat-ai/pipecat-examples/tree/main/moondream-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat-examples/main/moondream-chatbot/image.png" width="400" /></a>
|
||||
<a href="https://github.com/pipecat-ai/pipecat/tree/main/examples/translation-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat/main/examples/translation-chatbot/image.png" width="280" /></a>
|
||||
<a href="https://github.com/pipecat-ai/pipecat/tree/main/examples/moondream-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat/main/examples/moondream-chatbot/image.png" width="280" /></a>
|
||||
</p>
|
||||
|
||||
## 📱 Client SDKs
|
||||
## Getting started with voice agents
|
||||
|
||||
You can connect to Pipecat from any platform using our official SDKs:
|
||||
You can get started with Pipecat running on your local machine, then move your agent processes to the cloud when you’re ready. You can also add a 📞 telephone number, 🖼️ image output, 📺 video input, use different LLMs, and more.
|
||||
|
||||
| Platform | SDK Repo | Description |
|
||||
| -------- | ------------------------------------------------------------------------------ | -------------------------------- |
|
||||
| Web | [pipecat-client-web](https://github.com/pipecat-ai/pipecat-client-web) | JavaScript and React client SDKs |
|
||||
| iOS | [pipecat-client-ios](https://github.com/pipecat-ai/pipecat-client-ios) | Swift SDK for iOS |
|
||||
| Android | [pipecat-client-android](https://github.com/pipecat-ai/pipecat-client-android) | Kotlin SDK for Android |
|
||||
| C++ | [pipecat-client-cxx](https://github.com/pipecat-ai/pipecat-client-cxx) | C++ client SDK |
|
||||
```shell
|
||||
# install the module
|
||||
pip install pipecat-ai
|
||||
|
||||
## 🧩 Available services
|
||||
|
||||
| Category | Services |
|
||||
| ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| Speech-to-Text | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [AWS](https://docs.pipecat.ai/server/services/stt/aws), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Cartesia](https://docs.pipecat.ai/server/services/stt/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [Fal Wizper](https://docs.pipecat.ai/server/services/stt/fal), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [NVIDIA Riva](https://docs.pipecat.ai/server/services/stt/riva), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [SambaNova (Whisper)](https://docs.pipecat.ai/server/services/stt/sambanova), [Soniox](https://docs.pipecat.ai/server/services/stt/soniox), [Speechmatics](https://docs.pipecat.ai/server/services/stt/speechmatics), [Ultravox](https://docs.pipecat.ai/server/services/stt/ultravox), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper) |
|
||||
| LLMs | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [AWS](https://docs.pipecat.ai/server/services/llm/aws), [Azure](https://docs.pipecat.ai/server/services/llm/azure), [Cerebras](https://docs.pipecat.ai/server/services/llm/cerebras), [DeepSeek](https://docs.pipecat.ai/server/services/llm/deepseek), [Fireworks AI](https://docs.pipecat.ai/server/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/server/services/llm/gemini), [Grok](https://docs.pipecat.ai/server/services/llm/grok), [Groq](https://docs.pipecat.ai/server/services/llm/groq), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nim), [Ollama](https://docs.pipecat.ai/server/services/llm/ollama), [OpenAI](https://docs.pipecat.ai/server/services/llm/openai), [OpenRouter](https://docs.pipecat.ai/server/services/llm/openrouter), [Perplexity](https://docs.pipecat.ai/server/services/llm/perplexity), [Qwen](https://docs.pipecat.ai/server/services/llm/qwen), [SambaNova](https://docs.pipecat.ai/server/services/llm/sambanova) [Together AI](https://docs.pipecat.ai/server/services/llm/together) |
|
||||
| Text-to-Speech | [Async](https://docs.pipecat.ai/server/services/tts/asyncai), [AWS](https://docs.pipecat.ai/server/services/tts/aws), [Azure](https://docs.pipecat.ai/server/services/tts/azure), [Cartesia](https://docs.pipecat.ai/server/services/tts/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/tts/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/tts/elevenlabs), [Fish](https://docs.pipecat.ai/server/services/tts/fish), [Google](https://docs.pipecat.ai/server/services/tts/google), [Groq](https://docs.pipecat.ai/server/services/tts/groq), [Inworld](https://docs.pipecat.ai/server/services/tts/inworld), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [MiniMax](https://docs.pipecat.ai/server/services/tts/minimax), [Neuphonic](https://docs.pipecat.ai/server/services/tts/neuphonic), [NVIDIA Riva](https://docs.pipecat.ai/server/services/tts/riva), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [Piper](https://docs.pipecat.ai/server/services/tts/piper), [PlayHT](https://docs.pipecat.ai/server/services/tts/playht), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [Sarvam](https://docs.pipecat.ai/server/services/tts/sarvam), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts) |
|
||||
| Speech-to-Speech | [AWS Nova Sonic](https://docs.pipecat.ai/server/services/s2s/aws), [Gemini Multimodal Live](https://docs.pipecat.ai/server/services/s2s/gemini), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai) |
|
||||
| Transport | [Daily (WebRTC)](https://docs.pipecat.ai/server/services/transport/daily), [FastAPI Websocket](https://docs.pipecat.ai/server/services/transport/fastapi-websocket), [SmallWebRTCTransport](https://docs.pipecat.ai/server/services/transport/small-webrtc), [WebSocket Server](https://docs.pipecat.ai/server/services/transport/websocket-server), Local |
|
||||
| Serializers | [Plivo](https://docs.pipecat.ai/server/utilities/serializers/plivo), [Twilio](https://docs.pipecat.ai/server/utilities/serializers/twilio), [Telnyx](https://docs.pipecat.ai/server/utilities/serializers/telnyx) |
|
||||
| Video | [HeyGen](https://docs.pipecat.ai/server/services/video/heygen), [Tavus](https://docs.pipecat.ai/server/services/video/tavus), [Simli](https://docs.pipecat.ai/server/services/video/simli) |
|
||||
| Memory | [mem0](https://docs.pipecat.ai/server/services/memory/mem0) |
|
||||
| Vision & Image | [fal](https://docs.pipecat.ai/server/services/image-generation/fal), [Google Imagen](https://docs.pipecat.ai/server/services/image-generation/fal), [Moondream](https://docs.pipecat.ai/server/services/vision/moondream) |
|
||||
| Audio Processing | [Silero VAD](https://docs.pipecat.ai/server/utilities/audio/silero-vad-analyzer), [Krisp](https://docs.pipecat.ai/server/utilities/audio/krisp-filter), [Koala](https://docs.pipecat.ai/server/utilities/audio/koala-filter), [Noisereduce](https://docs.pipecat.ai/server/utilities/audio/noisereduce-filter) |
|
||||
| Analytics & Metrics | [OpenTelemetry](https://docs.pipecat.ai/server/utilities/opentelemetry), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry) |
|
||||
|
||||
📚 [View full services documentation →](https://docs.pipecat.ai/server/services/supported-services)
|
||||
|
||||
## ⚡ Getting started
|
||||
|
||||
You can get started with Pipecat running on your local machine, then move your agent processes to the cloud when you're ready.
|
||||
|
||||
1. Install uv
|
||||
|
||||
```bash
|
||||
curl -LsSf https://astral.sh/uv/install.sh | sh
|
||||
```
|
||||
|
||||
> **Need help?** Refer to the [uv install documentation](https://docs.astral.sh/uv/getting-started/installation/).
|
||||
|
||||
2. Install the module
|
||||
|
||||
```bash
|
||||
# For new projects
|
||||
uv init my-pipecat-app
|
||||
cd my-pipecat-app
|
||||
uv add pipecat-ai
|
||||
|
||||
# Or for existing projects
|
||||
uv add pipecat-ai
|
||||
```
|
||||
|
||||
3. Set up your environment
|
||||
|
||||
```bash
|
||||
cp env.example .env
|
||||
```
|
||||
|
||||
4. To keep things lightweight, only the core framework is included by default. If you need support for third-party AI services, you can add the necessary dependencies with:
|
||||
|
||||
```bash
|
||||
uv add "pipecat-ai[option,...]"
|
||||
```
|
||||
|
||||
> **Using pip?** You can still use `pip install pipecat-ai` and `pip install "pipecat-ai[option,...]"` to get set up.
|
||||
|
||||
## 🧪 Code examples
|
||||
|
||||
- [Foundational](https://github.com/pipecat-ai/pipecat/tree/main/examples/foundational) — small snippets that build on each other, introducing one or two concepts at a time
|
||||
- [Example apps](https://github.com/pipecat-ai/pipecat-examples) — complete applications that you can use as starting points for development
|
||||
|
||||
## 🛠️ Contributing to the framework
|
||||
|
||||
### Prerequisites
|
||||
|
||||
**Python Version:** 3.10+
|
||||
|
||||
### Setup Steps
|
||||
|
||||
1. Clone the repository and navigate to it:
|
||||
|
||||
```bash
|
||||
git clone https://github.com/pipecat-ai/pipecat.git
|
||||
cd pipecat
|
||||
```
|
||||
|
||||
2. Install development and testing dependencies:
|
||||
|
||||
```bash
|
||||
uv sync --group dev --all-extras --no-extra gstreamer --no-extra krisp --no-extra local
|
||||
```
|
||||
|
||||
3. Install the git pre-commit hooks:
|
||||
|
||||
```bash
|
||||
uv run pre-commit install
|
||||
```
|
||||
|
||||
### Python 3.13+ Compatibility
|
||||
|
||||
Some features require PyTorch, which doesn't yet support Python 3.13+. Install using:
|
||||
|
||||
```bash
|
||||
uv sync --group dev --all-extras \
|
||||
--no-extra gstreamer \
|
||||
--no-extra krisp \
|
||||
--no-extra local \
|
||||
--no-extra local-smart-turn \
|
||||
--no-extra mlx-whisper \
|
||||
--no-extra moondream \
|
||||
--no-extra ultravox
|
||||
# set up an .env file with API keys
|
||||
cp dot-env.template .env
|
||||
```
|
||||
|
||||
> **Tip:** For full compatibility, use Python 3.12: `uv python pin 3.12`
|
||||
By default, in order to minimize dependencies, only the basic framework functionality is available. Some third-party AI services require additional dependencies that you can install with:
|
||||
|
||||
> **Note**: Some extras (local, gstreamer) require system dependencies. See documentation if you encounter build errors.
|
||||
```shell
|
||||
pip install "pipecat-ai[option,...]"
|
||||
```
|
||||
|
||||
Your project may or may not need these, so they're made available as optional requirements. Here is a list:
|
||||
|
||||
- **AI services**: `anthropic`, `azure`, `deepgram`, `google`, `fal`, `moondream`, `openai`, `openpipe`, `playht`, `silero`, `whisper`
|
||||
- **Transports**: `local`, `websocket`, `daily`
|
||||
|
||||
## Code examples
|
||||
|
||||
- [foundational](https://github.com/pipecat-ai/pipecat/tree/main/examples/foundational) — small snippets that build on each other, introducing one or two concepts at a time
|
||||
- [example apps](https://github.com/pipecat-ai/pipecat/tree/main/examples/) — complete applications that you can use as starting points for development
|
||||
|
||||
## A simple voice agent running locally
|
||||
|
||||
Here is a very basic Pipecat bot that greets a user when they join a real-time session. We'll use [Daily](https://daily.co) for real-time media transport, and [ElevenLabs](https://elevenlabs.io/) for text-to-speech.
|
||||
|
||||
```python
|
||||
#app.py
|
||||
|
||||
import asyncio
|
||||
import aiohttp
|
||||
|
||||
from pipecat.frames.frames import EndFrame, TextFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.services.elevenlabs import ElevenLabsTTSService
|
||||
from pipecat.transports.services.daily import DailyParams, DailyTransport
|
||||
|
||||
async def main():
|
||||
async with aiohttp.ClientSession() as session:
|
||||
# Use Daily as a real-time media transport (WebRTC)
|
||||
transport = DailyTransport(
|
||||
room_url=...,
|
||||
token=...,
|
||||
"Bot Name",
|
||||
DailyParams(audio_out_enabled=True))
|
||||
|
||||
# Use Eleven Labs for Text-to-Speech
|
||||
tts = ElevenLabsTTSService(
|
||||
aiohttp_session=session,
|
||||
api_key=...,
|
||||
voice_id=...,
|
||||
)
|
||||
|
||||
# Simple pipeline that will process text to speech and output the result
|
||||
pipeline = Pipeline([tts, transport.output()])
|
||||
|
||||
# Create Pipecat processor that can run one or more pipelines tasks
|
||||
runner = PipelineRunner()
|
||||
|
||||
# Assign the task callable to run the pipeline
|
||||
task = PipelineTask(pipeline)
|
||||
|
||||
# Register an event handler to play audio when a
|
||||
# participant joins the transport WebRTC session
|
||||
@transport.event_handler("on_participant_joined")
|
||||
async def on_new_participant_joined(transport, participant):
|
||||
participant_name = participant["info"]["userName"] or ''
|
||||
# Queue a TextFrame that will get spoken by the TTS service (Eleven Labs)
|
||||
await task.queue_frames([TextFrame(f"Hello there, {participant_name}!"), EndFrame()])
|
||||
|
||||
# Run the pipeline task
|
||||
await runner.run(task)
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(main())
|
||||
```
|
||||
|
||||
Run it with:
|
||||
|
||||
```shell
|
||||
python app.py
|
||||
```
|
||||
|
||||
Daily provides a prebuilt WebRTC user interface. Whilst the app is running, you can visit at `https://<yourdomain>.daily.co/<room_url>` and listen to the bot say hello!
|
||||
|
||||
|
||||
## WebRTC for production use
|
||||
|
||||
WebSockets are fine for server-to-server communication or for initial development. But for production use, you’ll need client-server audio to use a protocol designed for real-time media transport. (For an explanation of the difference between WebSockets and WebRTC, see [this post.](https://www.daily.co/blog/how-to-talk-to-an-llm-with-your-voice/#webrtc))
|
||||
|
||||
One way to get up and running quickly with WebRTC is to sign up for a Daily developer account. Daily gives you SDKs and global infrastructure for audio (and video) routing. Every account gets 10,000 audio/video/transcription minutes free each month.
|
||||
|
||||
Sign up [here](https://dashboard.daily.co/u/signup) and [create a room](https://docs.daily.co/reference/rest-api/rooms) in the developer Dashboard.
|
||||
|
||||
## What is VAD?
|
||||
|
||||
Voice Activity Detection — very important for knowing when a user has finished speaking to your bot. If you are not using press-to-talk, and want Pipecat to detect when the user has finished talking, VAD is an essential component for a natural feeling conversation.
|
||||
|
||||
Pipecast makes use of WebRTC VAD by default when using a WebRTC transport layer. Optionally, you can use Silero VAD for improved accuracy at the cost of higher CPU usage.
|
||||
|
||||
```shell
|
||||
pip install pipecat-ai[silero]
|
||||
```
|
||||
|
||||
The first time your run your bot with Silero, startup may take a while whilst it downloads and caches the model in the background. You can check the progress of this in the console.
|
||||
|
||||
|
||||
## Hacking on the framework itself
|
||||
|
||||
_Note that you may need to set up a virtual environment before following the instructions below. For instance, you might need to run the following from the root of the repo:_
|
||||
|
||||
```shell
|
||||
python3 -m venv venv
|
||||
source venv/bin/activate
|
||||
```
|
||||
|
||||
From the root of this repo, run the following:
|
||||
|
||||
```shell
|
||||
pip install -r dev-requirements.txt -r {env}-requirements.txt
|
||||
python -m build
|
||||
```
|
||||
|
||||
This builds the package. To use the package locally (eg to run sample files), run
|
||||
|
||||
```shell
|
||||
pip install --editable .
|
||||
```
|
||||
|
||||
If you want to use this package from another directory, you can run:
|
||||
|
||||
```shell
|
||||
pip install path_to_this_repo
|
||||
```
|
||||
|
||||
### Running tests
|
||||
|
||||
To run all tests, from the root directory:
|
||||
From the root directory, run:
|
||||
|
||||
```bash
|
||||
uv run pytest
|
||||
```shell
|
||||
pytest --doctest-modules --ignore-glob="*to_be_updated*" src tests
|
||||
```
|
||||
|
||||
Run a specific test suite:
|
||||
## Setting up your editor
|
||||
|
||||
```bash
|
||||
uv run pytest tests/test_name.py
|
||||
```
|
||||
This project uses strict [PEP 8](https://peps.python.org/pep-0008/) formatting.
|
||||
|
||||
### Setting up your editor
|
||||
### Emacs
|
||||
|
||||
This project uses strict [PEP 8](https://peps.python.org/pep-0008/) formatting via [Ruff](https://github.com/astral-sh/ruff).
|
||||
|
||||
#### Emacs
|
||||
|
||||
You can use [use-package](https://github.com/jwiegley/use-package) to install [emacs-lazy-ruff](https://github.com/christophermadsen/emacs-lazy-ruff) package and configure `ruff` arguments:
|
||||
You can use [use-package](https://github.com/jwiegley/use-package) to install [py-autopep8](https://codeberg.org/ideasman42/emacs-py-autopep8) package and configure `autopep8` arguments:
|
||||
|
||||
```elisp
|
||||
(use-package lazy-ruff
|
||||
(use-package py-autopep8
|
||||
:ensure t
|
||||
:hook ((python-mode . lazy-ruff-mode))
|
||||
:defer t
|
||||
:hook ((python-mode . py-autopep8-mode))
|
||||
:config
|
||||
(setq lazy-ruff-format-command "ruff format")
|
||||
(setq lazy-ruff-check-command "ruff check --select I"))
|
||||
(setq py-autopep8-options '("-a" "-a", "--max-line-length=100")))
|
||||
```
|
||||
|
||||
`ruff` was installed in the `venv` environment described before, so you should be able to use [pyvenv-auto](https://github.com/ryotaro612/pyvenv-auto) to automatically load that environment inside Emacs.
|
||||
`autopep8` was installed in the `venv` environment described before, so you should be able to use [pyvenv-auto](https://github.com/ryotaro612/pyvenv-auto) to automatically load that environment inside Emacs.
|
||||
|
||||
```elisp
|
||||
(use-package pyvenv-auto
|
||||
:ensure t
|
||||
:defer t
|
||||
:hook ((python-mode . pyvenv-auto-run)))
|
||||
|
||||
```
|
||||
|
||||
#### Visual Studio Code
|
||||
### Visual Studio Code
|
||||
|
||||
Install the
|
||||
[Ruff](https://marketplace.visualstudio.com/items?itemName=charliermarsh.ruff) extension. Then edit the user settings (_Ctrl-Shift-P_ `Open User Settings (JSON)`) and set it as the default Python formatter, and enable formatting on save:
|
||||
[autopep8](https://marketplace.visualstudio.com/items?itemName=ms-python.autopep8) extension. Then edit the user settings (_Ctrl-Shift-P_ `Open User Settings (JSON)`) and set it as the default Python formatter, enable formatting on save and configure `autopep8` arguments:
|
||||
|
||||
```json
|
||||
"[python]": {
|
||||
"editor.defaultFormatter": "charliermarsh.ruff",
|
||||
"editor.defaultFormatter": "ms-python.autopep8",
|
||||
"editor.formatOnSave": true
|
||||
}
|
||||
},
|
||||
"autopep8.args": [
|
||||
"-a",
|
||||
"-a",
|
||||
"--max-line-length=100"
|
||||
],
|
||||
```
|
||||
|
||||
#### PyCharm
|
||||
|
||||
`ruff` was installed in the `venv` environment described before, now to enable autoformatting on save, go to `File` -> `Settings` -> `Tools` -> `File Watchers` and add a new watcher with the following settings:
|
||||
|
||||
1. **Name**: `Ruff formatter`
|
||||
2. **File type**: `Python`
|
||||
3. **Working directory**: `$ContentRoot$`
|
||||
4. **Arguments**: `format $FilePath$`
|
||||
5. **Program**: `$PyInterpreterDirectory$/ruff`
|
||||
|
||||
## 🤝 Contributing
|
||||
|
||||
We welcome contributions from the community! Whether you're fixing bugs, improving documentation, or adding new features, here's how you can help:
|
||||
|
||||
- **Found a bug?** Open an [issue](https://github.com/pipecat-ai/pipecat/issues)
|
||||
- **Have a feature idea?** Start a [discussion](https://discord.gg/pipecat)
|
||||
- **Want to contribute code?** Check our [CONTRIBUTING.md](CONTRIBUTING.md) guide
|
||||
- **Documentation improvements?** [Docs](https://github.com/pipecat-ai/docs) PRs are always welcome
|
||||
|
||||
Before submitting a pull request, please check existing issues and PRs to avoid duplicates.
|
||||
|
||||
We aim to review all contributions promptly and provide constructive feedback to help get your changes merged.
|
||||
|
||||
## 🛟 Getting help
|
||||
## Getting help
|
||||
|
||||
➡️ [Join our Discord](https://discord.gg/pipecat)
|
||||
|
||||
➡️ [Read the docs](https://docs.pipecat.ai)
|
||||
|
||||
➡️ [Reach us on X](https://x.com/pipecat_ai)
|
||||
|
||||
11
codecov.yml
11
codecov.yml
@@ -1,11 +0,0 @@
|
||||
coverage:
|
||||
range: 50..90 # coverage lower than 50 is red, higher than 90 green, between color code
|
||||
|
||||
status:
|
||||
project:
|
||||
default:
|
||||
target: auto # auto % coverage target
|
||||
threshold: 5% # allow for 5% reduction of coverage without failing
|
||||
|
||||
# do not run coverage on patch nor changes
|
||||
patch: false
|
||||
7
dev-requirements.txt
Normal file
7
dev-requirements.txt
Normal file
@@ -0,0 +1,7 @@
|
||||
autopep8~=2.1.0
|
||||
build~=1.2.1
|
||||
grpcio-tools~=1.62.2
|
||||
pip-tools~=7.4.1
|
||||
pytest~=8.2.0
|
||||
setuptools~=69.5.1
|
||||
setuptools_scm~=8.1.0
|
||||
@@ -1,20 +0,0 @@
|
||||
# Minimal makefile for Sphinx documentation
|
||||
#
|
||||
|
||||
# You can set these variables from the command line, and also
|
||||
# from the environment for the first two.
|
||||
SPHINXOPTS ?=
|
||||
SPHINXBUILD ?= sphinx-build
|
||||
SOURCEDIR = .
|
||||
BUILDDIR = _build
|
||||
|
||||
# Put it first so that "make" without argument is like "make help".
|
||||
help:
|
||||
@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
|
||||
|
||||
.PHONY: help Makefile
|
||||
|
||||
# Catch-all target: route all unknown targets to Sphinx using the new
|
||||
# "make mode" option. $(O) is meant as a shortcut for $(SPHINXOPTS).
|
||||
%: Makefile
|
||||
@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
|
||||
@@ -1,109 +0,0 @@
|
||||
# Pipecat Documentation
|
||||
|
||||
This directory contains the source files for auto-generating Pipecat's server API reference documentation.
|
||||
|
||||
## Setup
|
||||
|
||||
1. Install documentation dependencies:
|
||||
|
||||
```bash
|
||||
pip install -r requirements.txt
|
||||
```
|
||||
|
||||
2. Make the build scripts executable:
|
||||
|
||||
```bash
|
||||
chmod +x build-docs.sh rtd-test.py
|
||||
```
|
||||
|
||||
## Building Documentation
|
||||
|
||||
From this directory, you can build the documentation in several ways:
|
||||
|
||||
### Local Build
|
||||
|
||||
```bash
|
||||
# Using the build script (automatically opens docs when done)
|
||||
./build-docs.sh
|
||||
|
||||
# Or directly with sphinx-build
|
||||
sphinx-build -b html . _build/html -W --keep-going
|
||||
```
|
||||
|
||||
### ReadTheDocs Test Build
|
||||
|
||||
To test the documentation build process exactly as it would run on ReadTheDocs:
|
||||
|
||||
```bash
|
||||
./rtd-test.py
|
||||
```
|
||||
|
||||
This script:
|
||||
|
||||
- Creates a fresh virtual environment
|
||||
- Installs all dependencies as specified in requirements files
|
||||
- Handles conflicting dependencies (like grpcio versions for Riva and PlayHT)
|
||||
- Builds the documentation in an isolated environment
|
||||
- Provides detailed logging of the build process
|
||||
|
||||
Use this script to verify your documentation will build correctly on ReadTheDocs before pushing changes.
|
||||
|
||||
## Viewing Documentation
|
||||
|
||||
The built documentation will be available at `_build/html/index.html`. To open:
|
||||
|
||||
```bash
|
||||
# On MacOS
|
||||
open _build/html/index.html
|
||||
|
||||
# On Linux
|
||||
xdg-open _build/html/index.html
|
||||
|
||||
# On Windows
|
||||
start _build/html/index.html
|
||||
```
|
||||
|
||||
## Directory Structure
|
||||
|
||||
```
|
||||
.
|
||||
├── api/ # Auto-generated API documentation
|
||||
├── _build/ # Built documentation
|
||||
├── _static/ # Static files (images, css, etc.)
|
||||
├── conf.py # Sphinx configuration
|
||||
├── index.rst # Main documentation entry point
|
||||
├── requirements-base.txt # Base documentation dependencies
|
||||
├── requirements-riva.txt # Riva-specific dependencies
|
||||
├── requirements-playht.txt # PlayHT-specific dependencies
|
||||
├── build-docs.sh # Local build script
|
||||
└── rtd-test.py # ReadTheDocs test build script
|
||||
```
|
||||
|
||||
## Notes
|
||||
|
||||
- Documentation is auto-generated from Python docstrings
|
||||
- Service modules are automatically detected and included
|
||||
- The build process matches our ReadTheDocs configuration
|
||||
- Warnings are treated as errors (-W flag) to maintain consistency
|
||||
- The --keep-going flag ensures all errors are reported
|
||||
- Dependencies are split into multiple requirements files to handle version conflicts
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
If you encounter missing service modules:
|
||||
|
||||
1. Verify the service is installed with its extras: `pip install pipecat-ai[service-name]`
|
||||
2. Check the build logs for import errors
|
||||
3. Ensure the service module is properly initialized in the package
|
||||
4. Run `./rtd-test.py` to test in an isolated environment matching ReadTheDocs
|
||||
|
||||
For dependency conflicts:
|
||||
|
||||
1. Check the requirements files for version specifications
|
||||
2. Use `rtd-test.py` to verify dependency resolution
|
||||
3. Consider adding service-specific requirements files if needed
|
||||
|
||||
For more information:
|
||||
|
||||
- [ReadTheDocs Configuration](.readthedocs.yaml)
|
||||
- [Sphinx Documentation](https://www.sphinx-doc.org/)
|
||||
@@ -1,27 +0,0 @@
|
||||
#!/bin/bash
|
||||
|
||||
# Build docs using uv
|
||||
echo "Installing dependencies with uv..."
|
||||
uv sync --group docs --all-extras --no-extra krisp --no-extra gstreamer --no-extra ultravox --no-extra local_smart_turn --no-extra moondream --no-extra riva --no-extra mlx-whisper
|
||||
|
||||
# Check if sphinx-build is available
|
||||
if ! uv run sphinx-build --version &> /dev/null; then
|
||||
echo "Error: sphinx-build is not available" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Clean previous build
|
||||
rm -rf _build
|
||||
|
||||
echo "Building documentation..."
|
||||
# Build docs matching ReadTheDocs configuration
|
||||
uv run sphinx-build -b html -d _build/doctrees . _build/html -W --keep-going
|
||||
|
||||
if [ $? -eq 0 ]; then
|
||||
echo "Documentation built successfully!"
|
||||
# Open docs (MacOS)
|
||||
open _build/html/index.html
|
||||
else
|
||||
echo "Documentation build failed!" >&2
|
||||
exit 1
|
||||
fi
|
||||
210
docs/api/conf.py
210
docs/api/conf.py
@@ -1,210 +0,0 @@
|
||||
import logging
|
||||
import os
|
||||
import sys
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
|
||||
# Configure logging
|
||||
logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
|
||||
logger = logging.getLogger("sphinx-build")
|
||||
|
||||
# Add source directory to path
|
||||
docs_dir = Path(__file__).parent
|
||||
project_root = docs_dir.parent.parent
|
||||
sys.path.insert(0, str(project_root / "src"))
|
||||
|
||||
# Project information
|
||||
project = "pipecat-ai"
|
||||
current_year = datetime.now().year
|
||||
copyright = f"2024-{current_year}, Daily" if current_year > 2024 else "2024, Daily"
|
||||
author = "Daily"
|
||||
|
||||
# General configuration
|
||||
extensions = [
|
||||
"sphinx.ext.autodoc",
|
||||
"sphinx.ext.napoleon",
|
||||
"sphinx.ext.viewcode",
|
||||
"sphinx.ext.intersphinx",
|
||||
]
|
||||
|
||||
suppress_warnings = [
|
||||
"autodoc.mocked_object",
|
||||
"toc.not_included",
|
||||
]
|
||||
|
||||
# Napoleon settings
|
||||
napoleon_google_docstring = True
|
||||
napoleon_include_init_with_doc = True
|
||||
|
||||
# AutoDoc settings
|
||||
autodoc_default_options = {
|
||||
"members": True,
|
||||
"member-order": "bysource",
|
||||
"undoc-members": False,
|
||||
"exclude-members": "__weakref__,model_config",
|
||||
"show-inheritance": True,
|
||||
}
|
||||
|
||||
# Mock imports for optional dependencies
|
||||
autodoc_mock_imports = [
|
||||
# Krisp - has build issues on some platforms
|
||||
"pipecat_ai_krisp",
|
||||
"krisp",
|
||||
# System-specific GUI libraries
|
||||
"_tkinter",
|
||||
"tkinter",
|
||||
# Platform-specific audio libraries (if needed)
|
||||
"gi",
|
||||
"gi.require_version",
|
||||
"gi.repository",
|
||||
# OpenCV - sometimes has import issues during docs build
|
||||
"cv2",
|
||||
# Heavy ML packages excluded from ReadTheDocs
|
||||
# ultravox dependencies
|
||||
"vllm",
|
||||
"vllm.engine.arg_utils",
|
||||
# local-smart-turn dependencies
|
||||
"coremltools",
|
||||
"coremltools.models",
|
||||
"coremltools.models.MLModel",
|
||||
"torch",
|
||||
"torch.nn",
|
||||
"torch.nn.functional",
|
||||
"torchaudio",
|
||||
# moondream dependencies
|
||||
"transformers",
|
||||
"transformers.AutoTokenizer",
|
||||
"transformers.AutoFeatureExtractor",
|
||||
"AutoFeatureExtractor",
|
||||
"timm",
|
||||
"einops",
|
||||
"intel_extension_for_pytorch",
|
||||
"huggingface_hub",
|
||||
# riva dependencies
|
||||
"riva",
|
||||
"riva.client",
|
||||
"riva.client.Auth",
|
||||
"riva.client.ASRService",
|
||||
"riva.client.StreamingRecognitionConfig",
|
||||
"riva.client.RecognitionConfig",
|
||||
"riva.client.AudioEncoding",
|
||||
"riva.client.proto.riva_tts_pb2",
|
||||
"riva.client.SpeechSynthesisService",
|
||||
# MLX dependencies (Apple Silicon specific)
|
||||
"mlx",
|
||||
"mlx_whisper", # Note: might need underscore format too
|
||||
]
|
||||
|
||||
# HTML output settings
|
||||
html_theme = "sphinx_rtd_theme"
|
||||
html_static_path = ["_static"] if os.path.exists("_static") else []
|
||||
autodoc_typehints = "signature" # Show type hints in the signature only, not in the docstring
|
||||
html_show_sphinx = False
|
||||
|
||||
|
||||
def import_core_modules():
|
||||
"""Import core pipecat modules for autodoc to discover."""
|
||||
core_modules = [
|
||||
"pipecat",
|
||||
"pipecat.frames",
|
||||
"pipecat.pipeline",
|
||||
"pipecat.processors",
|
||||
"pipecat.services",
|
||||
"pipecat.transports",
|
||||
"pipecat.audio",
|
||||
"pipecat.adapters",
|
||||
"pipecat.clocks",
|
||||
"pipecat.metrics",
|
||||
"pipecat.observers",
|
||||
"pipecat.runner",
|
||||
"pipecat.serializers",
|
||||
"pipecat.sync",
|
||||
"pipecat.transcriptions",
|
||||
"pipecat.utils",
|
||||
]
|
||||
|
||||
for module_name in core_modules:
|
||||
try:
|
||||
__import__(module_name)
|
||||
logger.info(f"Successfully imported {module_name}")
|
||||
except ImportError as e:
|
||||
logger.warning(f"Failed to import {module_name}: {e}")
|
||||
|
||||
|
||||
def clean_title(title: str) -> str:
|
||||
"""Automatically clean module titles."""
|
||||
# Remove everything after space (like 'module', 'processor', etc.)
|
||||
title = title.split(" ")[0]
|
||||
|
||||
# Get the last part of the dot-separated path
|
||||
parts = title.split(".")
|
||||
title = parts[-1]
|
||||
|
||||
return title
|
||||
|
||||
|
||||
def setup(app):
|
||||
"""Generate API documentation during Sphinx build."""
|
||||
from sphinx.ext.apidoc import main
|
||||
|
||||
docs_dir = Path(__file__).parent
|
||||
project_root = docs_dir.parent.parent
|
||||
output_dir = str(docs_dir / "api")
|
||||
source_dir = str(project_root / "src" / "pipecat")
|
||||
|
||||
# Clean existing files
|
||||
if Path(output_dir).exists():
|
||||
import shutil
|
||||
|
||||
shutil.rmtree(output_dir)
|
||||
logger.info(f"Cleaned existing documentation in {output_dir}")
|
||||
|
||||
logger.info(f"Generating API documentation...")
|
||||
logger.info(f"Output directory: {output_dir}")
|
||||
logger.info(f"Source directory: {source_dir}")
|
||||
|
||||
excludes = [
|
||||
str(project_root / "src/pipecat/pipeline/to_be_updated"),
|
||||
str(project_root / "src/pipecat/examples"),
|
||||
str(project_root / "src/pipecat/tests"),
|
||||
"**/test_*.py",
|
||||
"**/tests/*.py",
|
||||
]
|
||||
|
||||
try:
|
||||
main(
|
||||
[
|
||||
"-f", # Force overwriting
|
||||
"-e", # Don't generate empty files
|
||||
"-M", # Put module documentation before submodule documentation
|
||||
"--no-toc", # Don't create a table of contents file
|
||||
"--separate", # Put documentation for each module in its own page
|
||||
"--module-first", # Module documentation before submodule documentation
|
||||
"--implicit-namespaces", # Added: Handle implicit namespace packages
|
||||
"-o",
|
||||
output_dir,
|
||||
source_dir,
|
||||
]
|
||||
+ excludes
|
||||
)
|
||||
|
||||
logger.info("API documentation generated successfully!")
|
||||
|
||||
# Process generated RST files to update titles
|
||||
for rst_file in Path(output_dir).glob("**/*.rst"): # Changed to recursive glob
|
||||
content = rst_file.read_text()
|
||||
lines = content.split("\n")
|
||||
|
||||
# Find and clean up the title
|
||||
if lines and "=" in lines[1]: # Title is typically the first line
|
||||
old_title = lines[0]
|
||||
new_title = clean_title(old_title)
|
||||
content = content.replace(old_title, new_title)
|
||||
rst_file.write_text(content)
|
||||
logger.info(f"Updated title: {old_title} -> {new_title}")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error generating API documentation: {e}", exc_info=True)
|
||||
|
||||
|
||||
import_core_modules()
|
||||
@@ -1,35 +0,0 @@
|
||||
Pipecat API Reference
|
||||
=====================
|
||||
|
||||
Welcome to the Pipecat API reference.
|
||||
|
||||
Use the navigation on the left to browse modules, or search using the search box.
|
||||
|
||||
**New to Pipecat?** Check out the `main documentation <https://docs.pipecat.ai>`_ for tutorials, guides, and client SDK information.
|
||||
|
||||
Quick Links
|
||||
-----------
|
||||
|
||||
* `GitHub Repository <https://github.com/pipecat-ai/pipecat>`_
|
||||
* `Join our Community <https://discord.gg/pipecat>`_
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 2
|
||||
:caption: API Reference
|
||||
:hidden:
|
||||
|
||||
Adapters <api/pipecat.adapters>
|
||||
Audio <api/pipecat.audio>
|
||||
Clocks <api/pipecat.clocks>
|
||||
Frames <api/pipecat.frames>
|
||||
Metrics <api/pipecat.metrics>
|
||||
Observers <api/pipecat.observers>
|
||||
Pipeline <api/pipecat.pipeline>
|
||||
Processors <api/pipecat.processors>
|
||||
Runner <api/pipecat.runner>
|
||||
Serializers <api/pipecat.serializers>
|
||||
Services <api/pipecat.services>
|
||||
Sync <api/pipecat.sync>
|
||||
Transcriptions <api/pipecat.transcriptions>
|
||||
Transports <api/pipecat.transports>
|
||||
Utils <api/pipecat.utils>
|
||||
@@ -1,35 +0,0 @@
|
||||
@ECHO OFF
|
||||
|
||||
pushd %~dp0
|
||||
|
||||
REM Command file for Sphinx documentation
|
||||
|
||||
if "%SPHINXBUILD%" == "" (
|
||||
set SPHINXBUILD=sphinx-build
|
||||
)
|
||||
set SOURCEDIR=.
|
||||
set BUILDDIR=_build
|
||||
|
||||
%SPHINXBUILD% >NUL 2>NUL
|
||||
if errorlevel 9009 (
|
||||
echo.
|
||||
echo.The 'sphinx-build' command was not found. Make sure you have Sphinx
|
||||
echo.installed, then set the SPHINXBUILD environment variable to point
|
||||
echo.to the full path of the 'sphinx-build' executable. Alternatively you
|
||||
echo.may add the Sphinx directory to PATH.
|
||||
echo.
|
||||
echo.If you don't have Sphinx installed, grab it from
|
||||
echo.https://www.sphinx-doc.org/
|
||||
exit /b 1
|
||||
)
|
||||
|
||||
if "%1" == "" goto help
|
||||
|
||||
%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
|
||||
goto end
|
||||
|
||||
:help
|
||||
%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
|
||||
|
||||
:end
|
||||
popd
|
||||
@@ -1,38 +0,0 @@
|
||||
#!/bin/bash
|
||||
set -e
|
||||
|
||||
# Configuration
|
||||
DOCS_DIR=$(pwd)
|
||||
PROJECT_ROOT=$(cd ../../ && pwd)
|
||||
TEST_DIR="/tmp/rtd-test-$(date +%Y%m%d_%H%M%S)"
|
||||
|
||||
echo "Creating test directory: $TEST_DIR"
|
||||
mkdir -p "$TEST_DIR"
|
||||
cd "$TEST_DIR"
|
||||
|
||||
# Create virtual environment
|
||||
python -m venv venv
|
||||
source venv/bin/activate
|
||||
|
||||
echo "Installing build dependencies..."
|
||||
pip install --upgrade pip wheel setuptools
|
||||
|
||||
echo "Installing documentation dependencies..."
|
||||
pip install -r "$DOCS_DIR/requirements.txt"
|
||||
|
||||
echo "Building documentation..."
|
||||
cd "$DOCS_DIR"
|
||||
sphinx-build -b html . "_build/html"
|
||||
|
||||
echo "Build complete. Check _build/html directory for output."
|
||||
|
||||
# Print summary
|
||||
echo -e "\n=== Build Summary ==="
|
||||
echo "Documentation: $DOCS_DIR/_build/html"
|
||||
echo "Test environment: $TEST_DIR"
|
||||
echo -e "\nTo view the documentation:"
|
||||
echo "open $DOCS_DIR/_build/html/index.html"
|
||||
|
||||
# Print installed packages for verification
|
||||
echo -e "\n=== Installed Packages ==="
|
||||
pip freeze | grep -E "sphinx|pipecat"
|
||||
110
docs/frame.md
110
docs/frame.md
@@ -1,110 +0,0 @@
|
||||
# Understanding Different Frame Types in the Pipecat System
|
||||
|
||||
In the Pipecat system, frames are used to represent different types of data and control signals that flow through the pipeline. Understanding these frame types is crucial for working with the system effectively. This tutorial will cover the main categories of frames and their specific uses.
|
||||
|
||||
## 1. Base Frame Classes
|
||||
|
||||
### Frame
|
||||
The `Frame` class is the base class for all frames. It includes:
|
||||
- `id`: A unique identifier
|
||||
- `name`: A descriptive name
|
||||
- `pts`: Presentation timestamp (optional)
|
||||
|
||||
### DataFrame
|
||||
`DataFrame` is a subclass of `Frame` and serves as a base for most data-carrying frames.
|
||||
|
||||
## 2. Audio Frames
|
||||
|
||||
### AudioRawFrame
|
||||
Represents a chunk of audio with properties:
|
||||
- `audio`: Raw audio data
|
||||
- `sample_rate`: Audio sample rate
|
||||
- `num_channels`: Number of audio channels
|
||||
|
||||
Subclasses include:
|
||||
- `InputAudioRawFrame`: For audio from input sources
|
||||
- `OutputAudioRawFrame`: For audio to be played by output devices
|
||||
- `TTSAudioRawFrame`: For audio generated by Text-to-Speech services
|
||||
|
||||
## 3. Image Frames
|
||||
|
||||
### ImageRawFrame
|
||||
Represents an image with properties:
|
||||
- `image`: Raw image data
|
||||
- `size`: Image dimensions
|
||||
- `format`: Image format (e.g., JPEG, PNG)
|
||||
|
||||
Subclasses include:
|
||||
- `InputImageRawFrame`: For images from input sources
|
||||
- `OutputImageRawFrame`: For images to be displayed
|
||||
- `UserImageRawFrame`: For images associated with a specific user
|
||||
- `VisionImageRawFrame`: For images with associated text for description
|
||||
- `URLImageRawFrame`: For images with an associated URL
|
||||
|
||||
### SpriteFrame
|
||||
Represents an animated sprite, containing a list of `ImageRawFrame` objects.
|
||||
|
||||
## 4. Text and Transcription Frames
|
||||
|
||||
### TextFrame
|
||||
Represents a chunk of text, used for various purposes in the pipeline.
|
||||
|
||||
### TranscriptionFrame
|
||||
A specialized `TextFrame` for speech transcriptions, including:
|
||||
- `user_id`: ID of the speaking user
|
||||
- `timestamp`: When the transcription was generated
|
||||
- `language`: Detected language of the speech
|
||||
|
||||
### InterimTranscriptionFrame
|
||||
Similar to `TranscriptionFrame`, but for interim (not final) transcriptions.
|
||||
|
||||
## 5. LLM (Language Model) Frames
|
||||
|
||||
### LLMMessagesFrame
|
||||
Contains a list of messages for an LLM service to process.
|
||||
|
||||
### LLMMessagesAppendFrame and LLMMessagesUpdateFrame
|
||||
Used to modify the current context of LLM messages.
|
||||
|
||||
### LLMSetToolsFrame
|
||||
Specifies tools (functions) available for the LLM to use.
|
||||
|
||||
### LLMEnablePromptCachingFrame
|
||||
Controls prompt caching in certain LLMs.
|
||||
|
||||
## 6. System and Control Frames
|
||||
|
||||
### SystemFrame
|
||||
Base class for system-level frames.
|
||||
|
||||
Important system frames include:
|
||||
- `StartFrame`: Initiates a pipeline
|
||||
- `CancelFrame`: Stops a pipeline immediately
|
||||
- `ErrorFrame`: Notifies of errors (with `FatalErrorFrame` for unrecoverable errors)
|
||||
- `EndTaskFrame` and `CancelTaskFrame`: Control pipeline tasks
|
||||
- `StartInterruptionFrame` and `StopInterruptionFrame`: Indicate user speech for interruptions
|
||||
|
||||
### ControlFrame
|
||||
Base class for control-flow frames.
|
||||
|
||||
Notable control frames:
|
||||
- `EndFrame`: Signals the end of a pipeline
|
||||
- `LLMFullResponseStartFrame` and `LLMFullResponseEndFrame`: Bracket LLM responses
|
||||
- `UserStartedSpeakingFrame` and `UserStoppedSpeakingFrame`: Indicate user speech activity
|
||||
- `BotStartedSpeakingFrame` and `BotStoppedSpeakingFrame`: Indicate bot speech activity
|
||||
- `TTSStartedFrame` and `TTSStoppedFrame`: Bracket Text-to-Speech responses
|
||||
|
||||
## 7. Special Purpose Frames
|
||||
|
||||
### MetricsFrame
|
||||
Contains performance metrics data.
|
||||
|
||||
### FunctionCallInProgressFrame and FunctionCallResultFrame
|
||||
Used for handling LLM function (tool) calls.
|
||||
|
||||
### ServiceUpdateSettingsFrame
|
||||
Base class for updating service settings, with specific subclasses for LLM, TTS, and STT services.
|
||||
|
||||
## Conclusion
|
||||
|
||||
Understanding these frame types is essential for working with the Pipecat system. Each frame type serves a specific purpose in the pipeline, whether it's carrying data (like audio or images), controlling the flow of the pipeline, or managing system-level operations. By using the appropriate frame types, you can effectively process and transmit various kinds of information through your pipeline.
|
||||
38
dot-env.template
Normal file
38
dot-env.template
Normal file
@@ -0,0 +1,38 @@
|
||||
# Anthropic
|
||||
ANTHROPIC_API_KEY=...
|
||||
|
||||
# Azure
|
||||
AZURE_SPEECH_REGION=...
|
||||
AZURE_SPEECH_API_KEY=...
|
||||
|
||||
AZURE_CHATGPT_API_KEY=...
|
||||
AZURE_CHATGPT_ENDPOINT=https://...
|
||||
AZURE_CHATGPT_MODEL=...
|
||||
|
||||
AZURE_DALLE_API_KEY=...
|
||||
AZURE_DALLE_ENDPOINT=https://...
|
||||
AZURE_DALLE_MODEL=...
|
||||
|
||||
# Daily
|
||||
DAILY_API_KEY=...
|
||||
DAILY_SAMPLE_ROOM_URL=https://...
|
||||
|
||||
# ElevenLabs
|
||||
ELEVENLABS_API_KEY=...
|
||||
ELEVENLABS_VOICE_ID=...
|
||||
|
||||
# Fal
|
||||
FAL_KEY=...
|
||||
|
||||
# Fireworks
|
||||
FIREWORKS_API_KEY=...
|
||||
|
||||
# PlayHT
|
||||
PLAY_HT_USER_ID=...
|
||||
PLAY_HT_API_KEY=...
|
||||
|
||||
# OpenAI
|
||||
OPENAI_API_KEY=...
|
||||
|
||||
#OpenPipe
|
||||
OPENPIPE_API_KEY=...
|
||||
142
env.example
142
env.example
@@ -1,142 +0,0 @@
|
||||
# Anthropic
|
||||
ANTHROPIC_API_KEY=...
|
||||
|
||||
# Async
|
||||
ASYNCAI_API_KEY=...
|
||||
ASYNCAI_VOICE_ID=...
|
||||
|
||||
# AWS
|
||||
AWS_SECRET_ACCESS_KEY=...
|
||||
AWS_ACCESS_KEY_ID=...
|
||||
AWS_REGION=...
|
||||
|
||||
# Azure
|
||||
AZURE_SPEECH_REGION=...
|
||||
AZURE_SPEECH_API_KEY=...
|
||||
|
||||
AZURE_CHATGPT_API_KEY=...
|
||||
AZURE_CHATGPT_ENDPOINT=https://...
|
||||
AZURE_CHATGPT_MODEL=...
|
||||
|
||||
AZURE_DALLE_API_KEY=...
|
||||
AZURE_DALLE_ENDPOINT=https://...
|
||||
AZURE_DALLE_MODEL=...
|
||||
|
||||
# Cartesia
|
||||
CARTESIA_API_KEY=...
|
||||
|
||||
# Daily
|
||||
DAILY_API_KEY=...
|
||||
DAILY_SAMPLE_ROOM_URL=https://...
|
||||
|
||||
# Deepgram
|
||||
DEEPGRAM_API_KEY=...
|
||||
|
||||
# ElevenLabs
|
||||
ELEVENLABS_API_KEY=...
|
||||
ELEVENLABS_VOICE_ID=...
|
||||
|
||||
# Neuphonic
|
||||
NEUPHONIC_API_KEY=...
|
||||
|
||||
# Fal
|
||||
FAL_KEY=...
|
||||
|
||||
# Fireworks
|
||||
FIREWORKS_API_KEY=...
|
||||
|
||||
# Gladia
|
||||
GLADIA_API_KEY=...
|
||||
GLADIA_REGION=...
|
||||
|
||||
# Google
|
||||
GOOGLE_API_KEY=...
|
||||
GOOGLE_CLOUD_PROJECT_ID=...
|
||||
GOOGLE_TEST_CREDENTIALS=...
|
||||
GOOGLE_VERTEX_TEST_CREDENTIALS=...
|
||||
|
||||
# LMNT
|
||||
LMNT_API_KEY=...
|
||||
LMNT_VOICE_ID=...
|
||||
|
||||
# PlayHT
|
||||
PLAY_HT_USER_ID=...
|
||||
PLAY_HT_API_KEY=...
|
||||
|
||||
# OpenAI
|
||||
OPENAI_API_KEY=...
|
||||
|
||||
# OpenPipe
|
||||
OPENPIPE_API_KEY=...
|
||||
|
||||
# Tavus
|
||||
TAVUS_API_KEY=...
|
||||
TAVUS_REPLICA_ID=...
|
||||
TAVUS_PERSONA_ID=...
|
||||
|
||||
# Simli
|
||||
SIMLI_API_KEY=...
|
||||
SIMLI_FACE_ID=...
|
||||
|
||||
# Krisp
|
||||
KRISP_MODEL_PATH=...
|
||||
|
||||
# DeepSeek
|
||||
DEEPSEEK_API_KEY=...
|
||||
|
||||
# Groq
|
||||
GROQ_API_KEY=...
|
||||
|
||||
# Grok
|
||||
GROK_API_KEY=...
|
||||
|
||||
# Inworld
|
||||
INWORLD_API_KEY=...
|
||||
|
||||
# Together.ai
|
||||
TOGETHER_API_KEY=...
|
||||
|
||||
# Cerebras
|
||||
CEREBRAS_API_KEY=...
|
||||
|
||||
# Fish Audio
|
||||
FISH_API_KEY=...
|
||||
|
||||
# Assembly AI
|
||||
ASSEMBLYAI_API_KEY=...
|
||||
|
||||
# OpenRouter
|
||||
OPENROUTER_API_KEY=...
|
||||
|
||||
# Piper
|
||||
PIPER_BASE_URL=...
|
||||
|
||||
# Smart turn
|
||||
LOCAL_SMART_TURN_MODEL_PATH=...
|
||||
FAL_SMART_TURN_API_KEY=...
|
||||
|
||||
# Twilio
|
||||
TWILIO_ACCOUNT_SID=...
|
||||
TWILIO_AUTH_TOKEN=...
|
||||
|
||||
# MiniMax
|
||||
MINIMAX_API_KEY=...
|
||||
MINIMAX_GROUP_ID=...
|
||||
|
||||
# Sarvam AI
|
||||
SARVAM_API_KEY=...
|
||||
|
||||
# Soniox
|
||||
SONIOX_API_KEY=
|
||||
|
||||
# Speechmatics
|
||||
SPEECHMATICS_API_KEY=...
|
||||
|
||||
# SambaNova
|
||||
SAMBANOVA_API_KEY=...
|
||||
|
||||
# Sentry
|
||||
SENTRY_DSN=...
|
||||
|
||||
# Heygen
|
||||
HEYGEN_API_KEY=...
|
||||
@@ -1,31 +1,85 @@
|
||||
# Pipecat Examples
|
||||
|
||||
This directory contains examples to help you learn how to build with Pipecat.
|
||||
|
||||
## Getting Started
|
||||
# Pipecat — Examples
|
||||
|
||||
New to Pipecat? Start here:
|
||||
## Foundational snippets
|
||||
Small snippets that build on each other, introducing one or two concepts at a time.
|
||||
|
||||
- **[Quickstart](quickstart/)** - Get your first voice AI bot running in 5 minutes _(coming soon)_
|
||||
- **[Client/Server Web](client-server-web/)** - Learn to build web applications with Pipecat's client SDKs _(coming soon)_
|
||||
- **[Phone Bot with Twilio](phone-bot-twilio/)** - Connect your bot to a phone number _(coming soon)_
|
||||
➡️ [Take a look](https://github.com/pipecat-ai/pipecat/tree/main/examples/foundational)
|
||||
|
||||
## Foundational Examples
|
||||
## Chatbot examples
|
||||
Collection of self-contained real-time voice and video AI demo applications built with Pipecat.
|
||||
|
||||
Single-file examples that introduce core Pipecat concepts one at a time. These examples:
|
||||
### Quickstart
|
||||
|
||||
- Build on each other progressively
|
||||
- Focus on specific features or integrations
|
||||
- Are used for testing with every Pipecat release
|
||||
Each project has its own set of dependencies and configuration variables. They intentionally avoids shared code across projects — you can grab whichever demo folder you want to work with as a starting point.
|
||||
|
||||
See the **[Foundational Examples README](foundational/)** for the complete list.
|
||||
We recommend you start with a virtual environment:
|
||||
|
||||
## More Advanced Examples
|
||||
```shell
|
||||
cd pipecat-ai/examples/simple-chatbot
|
||||
|
||||
Ready to explore complex use cases? Visit **[pipecat-examples](https://github.com/pipecat-ai/pipecat-examples)** for:
|
||||
python -m venv venv
|
||||
|
||||
- Production-ready applications
|
||||
- Multi-platform client implementations
|
||||
- Telephony integrations
|
||||
- Multimodal and creative applications
|
||||
- Deployment and monitoring examples
|
||||
source venv/bin/activate
|
||||
|
||||
pip install -r requirements.txt
|
||||
```
|
||||
|
||||
Next, follow the steps in the README for each demo.
|
||||
|
||||
ℹ️ Make sure you `pip install -r requirements.txt` for each demo project, so you can be sure to have the necessary service dependencies that extend the functionality of Pipecat. You can read more about the framework architecture [here](https://github.com/pipecat-ai/pipecat/tree/main/docs).
|
||||
|
||||
## Projects:
|
||||
|
||||
| Project | Description | Services |
|
||||
| -------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------- |
|
||||
| [Simple Chatbot](simple-chatbot) | Basic voice-driven conversational bot. A good starting point for learning the flow of the framework. | Deepgram, OpenAI, Daily, Daily Prebuilt UI |
|
||||
| [Storytelling Chatbot](storytelling-chatbot) | Stitches together multiple third-party services to create a collaborative storytime experience. | Deepgram, ElevenLabs, Open AI, Fal, Daily, Custom UI |
|
||||
| [Translation Chatbot](translation-chatbot) | Listens for user speech, then translates that speech to Spanish and speaks the translation back. Demonstrates multi-participant use-cases. | Deepgram, Azure, OpenAI, Daily, Daily Prebuilt UI |
|
||||
| [Moondream Chatbot](moondream-chatbot) | Demonstrates how to add vision capabilities to GPT4. **Note: works best with a GPU** | Deepgram, OpenAI, Moondream, Daily, Daily Prebuilt UI |
|
||||
| Function-calling Chatbot (TBC) | A chatbot that can call functions in response to user input. | Deepgram, OpenAI, Fireworks, Daily, Daily Prebuilt UI |
|
||||
| [Dialin Chatbot](dialin-chatbot) | A chatbot that connects to an incoming phone call from Daily or Twilio. | Deepgram, OpenAI, ElevenLabs, Daily, Twilio |
|
||||
|
||||
> [!IMPORTANT]
|
||||
> These example projects use Daily as a WebRTC transport and can be joined using their hosted Prebuilt UI.
|
||||
> It provides a quick way to join a real-time session with your bot and test your ideas without building any frontend code. If you'd like to see an example of a custom UI, try Storybot.
|
||||
|
||||
|
||||
## FAQ
|
||||
|
||||
### Deployment
|
||||
|
||||
For each of these demos we've included a `Dockerfile`. Out of the box, this should provide everything needed to get the respective demo running on a VM:
|
||||
|
||||
```shell
|
||||
docker build username/app:tag .
|
||||
|
||||
docker run -p 7860:7860 --env-file ./.env username/app:tag
|
||||
|
||||
docker push ...
|
||||
```
|
||||
|
||||
### SSL
|
||||
|
||||
If you're working with a custom UI (such as with the Storytelling Chatbot), it's important to ensure your deployment platform supports HTTPS, as accessing user devices such as mics and webcams requires SSL.
|
||||
|
||||
If you try to run a custom UI without SSL, you may see an error in the console telling you that `navigator` is undefined, or no devices are available.
|
||||
|
||||
### Are these examples production ready?
|
||||
|
||||
Yes, kind of.
|
||||
|
||||
These demos attempt to keep things simple and are unopinionated regarding environment or scalability.
|
||||
|
||||
We're using FastAPI to spawn a subprocess for the bots / agents — useful for small tests, but not so great for production grade apps with many concurrent users. You can see how this works in each project's `start` endpoint in `server.py`.
|
||||
|
||||
Creating virtualized worker pools and on-demand instances is out of scope for these examples, but we hope to add some examples to this repo soon!
|
||||
|
||||
For projects that have CUDA as a requirement, such as Moondream Chatbot, be sure to deploy to a GPU-powered platform (such as [fly.io](https://fly.io) or [Runpod](https://runpod.io).)
|
||||
|
||||
## Getting help
|
||||
|
||||
➡️ [Join our Discord](https://discord.gg/pipecat)
|
||||
|
||||
➡️ [Reach us on Twitter](https://x.com/pipecat_ai)
|
||||
|
||||
3
examples/dialin-chatbot/.dockerignore
Normal file
3
examples/dialin-chatbot/.dockerignore
Normal file
@@ -0,0 +1,3 @@
|
||||
**/.DS_Store
|
||||
.env
|
||||
.env.*
|
||||
165
examples/dialin-chatbot/.gitignore
vendored
Normal file
165
examples/dialin-chatbot/.gitignore
vendored
Normal file
@@ -0,0 +1,165 @@
|
||||
# Byte-compiled / optimized / DLL files
|
||||
__pycache__/
|
||||
*.py[cod]
|
||||
*$py.class
|
||||
|
||||
# C extensions
|
||||
*.so
|
||||
|
||||
# Distribution / packaging
|
||||
.Python
|
||||
build/
|
||||
develop-eggs/
|
||||
dist/
|
||||
downloads/
|
||||
eggs/
|
||||
.eggs/
|
||||
lib/
|
||||
lib64/
|
||||
parts/
|
||||
sdist/
|
||||
var/
|
||||
wheels/
|
||||
share/python-wheels/
|
||||
*.egg-info/
|
||||
.installed.cfg
|
||||
*.egg
|
||||
MANIFEST
|
||||
|
||||
# PyInstaller
|
||||
# Usually these files are written by a python script from a template
|
||||
# before PyInstaller builds the exe, so as to inject date/other infos into it.
|
||||
*.manifest
|
||||
*.spec
|
||||
|
||||
# Installer logs
|
||||
pip-log.txt
|
||||
pip-delete-this-directory.txt
|
||||
|
||||
# Unit test / coverage reports
|
||||
htmlcov/
|
||||
.tox/
|
||||
.nox/
|
||||
.coverage
|
||||
.coverage.*
|
||||
.cache
|
||||
nosetests.xml
|
||||
coverage.xml
|
||||
*.cover
|
||||
*.py,cover
|
||||
.hypothesis/
|
||||
.pytest_cache/
|
||||
cover/
|
||||
|
||||
# Translations
|
||||
*.mo
|
||||
*.pot
|
||||
|
||||
# Django stuff:
|
||||
*.log
|
||||
local_settings.py
|
||||
db.sqlite3
|
||||
db.sqlite3-journal
|
||||
|
||||
# Flask stuff:
|
||||
instance/
|
||||
.webassets-cache
|
||||
|
||||
# Scrapy stuff:
|
||||
.scrapy
|
||||
|
||||
# Sphinx documentation
|
||||
docs/_build/
|
||||
|
||||
# PyBuilder
|
||||
.pybuilder/
|
||||
target/
|
||||
|
||||
# Jupyter Notebook
|
||||
.ipynb_checkpoints
|
||||
|
||||
# IPython
|
||||
profile_default/
|
||||
ipython_config.py
|
||||
|
||||
# pyenv
|
||||
# For a library or package, you might want to ignore these files since the code is
|
||||
# intended to run in multiple environments; otherwise, check them in:
|
||||
# .python-version
|
||||
|
||||
# pipenv
|
||||
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
|
||||
# However, in case of collaboration, if having platform-specific dependencies or dependencies
|
||||
# having no cross-platform support, pipenv may install dependencies that don't work, or not
|
||||
# install all needed dependencies.
|
||||
#Pipfile.lock
|
||||
|
||||
# poetry
|
||||
# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
|
||||
# This is especially recommended for binary packages to ensure reproducibility, and is more
|
||||
# commonly ignored for libraries.
|
||||
# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
|
||||
#poetry.lock
|
||||
|
||||
# pdm
|
||||
# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
|
||||
#pdm.lock
|
||||
# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
|
||||
# in version control.
|
||||
# https://pdm.fming.dev/#use-with-ide
|
||||
.pdm.toml
|
||||
|
||||
# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
|
||||
__pypackages__/
|
||||
|
||||
# Celery stuff
|
||||
celerybeat-schedule
|
||||
celerybeat.pid
|
||||
|
||||
# SageMath parsed files
|
||||
*.sage.py
|
||||
|
||||
# Environments
|
||||
.env
|
||||
.venv
|
||||
env/
|
||||
venv/
|
||||
ENV/
|
||||
env.bak/
|
||||
venv.bak/
|
||||
|
||||
# Spyder project settings
|
||||
.spyderproject
|
||||
.spyproject
|
||||
|
||||
# Rope project settings
|
||||
.ropeproject
|
||||
|
||||
# mkdocs documentation
|
||||
/site
|
||||
|
||||
# mypy
|
||||
.mypy_cache/
|
||||
.dmypy.json
|
||||
dmypy.json
|
||||
|
||||
# Pyre type checker
|
||||
.pyre/
|
||||
|
||||
# pytype static type analyzer
|
||||
.pytype/
|
||||
|
||||
# Cython debug symbols
|
||||
cython_debug/
|
||||
|
||||
# PyCharm
|
||||
# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
|
||||
# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
|
||||
# and can be added to the global gitignore or merged into this file. For a more nuclear
|
||||
# option (not recommended) you can uncomment the following to ignore the entire idea folder.
|
||||
#.idea/
|
||||
runpod.toml
|
||||
|
||||
# custom script to recursively upgrade items in requirements.py
|
||||
upgrade_requirements.py
|
||||
.DS_Store
|
||||
40
examples/dialin-chatbot/Dockerfile
Normal file
40
examples/dialin-chatbot/Dockerfile
Normal file
@@ -0,0 +1,40 @@
|
||||
FROM python:3.11-bullseye
|
||||
|
||||
ARG DEBIAN_FRONTEND=noninteractive
|
||||
ARG USE_PERSISTENT_DATA
|
||||
ENV PYTHONUNBUFFERED=1
|
||||
# Expose FastAPI port
|
||||
ENV FAST_API_PORT=7860
|
||||
EXPOSE 7860
|
||||
|
||||
# Install system dependencies
|
||||
RUN apt-get update && apt-get install --no-install-recommends -y \
|
||||
build-essential \
|
||||
git \
|
||||
ffmpeg \
|
||||
google-perftools \
|
||||
ca-certificates curl gnupg \
|
||||
&& apt-get clean && rm -rf /var/lib/apt/lists/*
|
||||
|
||||
# Set up a new user named "user" with user ID 1000
|
||||
RUN useradd -m -u 1000 user
|
||||
|
||||
# Set home to the user's home directory
|
||||
ENV HOME=/home/user \
|
||||
PATH=/home/user/.local/bin:$PATH \
|
||||
PYTHONPATH=$HOME/app \
|
||||
PYTHONUNBUFFERED=1
|
||||
|
||||
# Switch to the "user" user
|
||||
USER user
|
||||
|
||||
# Set the working directory to the user's home directory
|
||||
WORKDIR $HOME/app
|
||||
|
||||
# Install Python dependencies
|
||||
COPY *.py .
|
||||
COPY ./requirements.txt requirements.txt
|
||||
RUN pip3 install --no-cache-dir --upgrade -r requirements.txt
|
||||
|
||||
# Start the FastAPI server
|
||||
CMD python3 bot_runner.py --host "0.0.0.0" --port ${FAST_API_PORT}
|
||||
85
examples/dialin-chatbot/README.md
Normal file
85
examples/dialin-chatbot/README.md
Normal file
@@ -0,0 +1,85 @@
|
||||
<div align="center">
|
||||
<img alt="pipecat" width="300px" height="auto" src="image.png">
|
||||
</div>
|
||||
|
||||
# Dialin example
|
||||
|
||||
Example project that demonstrates how to add phone number dialin to your Pipecat bots. We include examples for both Daily (`bot_daily.py`) and Twilio (`bot_twilio.py`), depending on who you want to use as a phone vendor.
|
||||
|
||||
- 🔁 Transport: Daily WebRTC
|
||||
- 💬 Speech-to-Text: Deepgram via Daily transport
|
||||
- 🤖 LLM: GPT4-o / OpenAI
|
||||
- 🔉 Text-to-Speech: ElevenLabs
|
||||
|
||||
#### Should I use Daily or Twilio as a vendor?
|
||||
|
||||
If you're starting from scratch, using Daily to provision phone numbers alongside Daily as a transport offers some convenience (such as automatic call forwarding.)
|
||||
|
||||
If you already have Twilio numbers and workflows that you want to connect to your Pipecat bots, there is some additional configuration required (you'll need to create a `on_dialin_ready` and use the Twilio client to trigger the forward.)
|
||||
|
||||
You can read more about this, as well as see respective walkthroughs in our docs.
|
||||
|
||||
## Setup
|
||||
|
||||
```shell
|
||||
# Install the requirements
|
||||
pip install -r requirements.txt
|
||||
|
||||
# Setup your env
|
||||
mv env.example .env
|
||||
```
|
||||
|
||||
## Using Daily numbers
|
||||
|
||||
Run `bot_runner.py` to handle incoming HTTP requests:
|
||||
|
||||
`python bot_runner.py --host localhost`
|
||||
|
||||
Then target the following URL:
|
||||
|
||||
`POST /daily_start_bot`
|
||||
|
||||
For more configuration options, please consult Daily's API documentation.
|
||||
|
||||
|
||||
## Using Twilio numbers
|
||||
|
||||
As above, but target the following URL:
|
||||
|
||||
`POST /twilio_start_bot`
|
||||
|
||||
For more configuration options, please consult Twilio's API documentation.
|
||||
|
||||
## Deployment example
|
||||
|
||||
A Dockerfile is included in this demo for convenience. Here is an example of how to build and deploy your bot to [fly.io](https://fly.io).
|
||||
|
||||
*Please note: This demo spawns agents as subprocesses for convenience / demonstration purposes. You would likely not want to do this in production as it would limit concurrency to available system resources. For more information on how to deploy your bots using VMs, refer to the Pipecat documentation.*
|
||||
|
||||
### Build the docker image
|
||||
|
||||
`docker build -t tag:project .`
|
||||
|
||||
### Launch the fly project
|
||||
|
||||
`mv fly.example.toml fly.toml`
|
||||
|
||||
`fly launch` (using the included fly.toml)
|
||||
|
||||
### Setup your secrets on Fly
|
||||
|
||||
Set the necessary secrets (found in `env.example`)
|
||||
|
||||
`fly secrets set DAILY_API_KEY=... OPENAI_API_KEY=... ELEVENLABS_API_KEY=... ELEVENLABS_VOICE_ID=...`
|
||||
|
||||
If you're using Twilio as a number vendor:
|
||||
|
||||
`fly secrets set TWILIO_ACCOUNT_SID=... TWILIO_AUTH_TOKEN=...`
|
||||
|
||||
### Deploy!
|
||||
|
||||
`fly deploy`
|
||||
|
||||
## Need to do something more advanced?
|
||||
|
||||
This demo covers the basics of bot telephony. If you want to know more about working with PSTN / SIP, please ping us on [Discord](https://discord.gg/pipecat).
|
||||
111
examples/dialin-chatbot/bot_daily.py
Normal file
111
examples/dialin-chatbot/bot_daily.py
Normal file
@@ -0,0 +1,111 @@
|
||||
import asyncio
|
||||
import aiohttp
|
||||
import os
|
||||
import sys
|
||||
import argparse
|
||||
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_response import LLMAssistantResponseAggregator, LLMUserResponseAggregator
|
||||
from pipecat.frames.frames import (
|
||||
LLMMessagesFrame,
|
||||
EndFrame
|
||||
)
|
||||
from pipecat.services.elevenlabs import ElevenLabsTTSService
|
||||
from pipecat.services.openai import OpenAILLMService
|
||||
from pipecat.transports.services.daily import DailyParams, DailyTransport, DailyDialinSettings
|
||||
from pipecat.vad.silero import SileroVADAnalyzer
|
||||
from loguru import logger
|
||||
|
||||
from dotenv import load_dotenv
|
||||
load_dotenv(override=True)
|
||||
|
||||
logger.remove(0)
|
||||
logger.add(sys.stderr, level="DEBUG")
|
||||
|
||||
daily_api_key = os.getenv("DAILY_API_KEY", "")
|
||||
daily_api_url = os.getenv("DAILY_API_URL", "https://api.daily.co/v1")
|
||||
|
||||
|
||||
async def main(room_url: str, token: str, callId: str, callDomain: str):
|
||||
async with aiohttp.ClientSession() as session:
|
||||
# diallin_settings are only needed if Daily's SIP URI is used
|
||||
# If you are handling this via Twilio, Telnyx, set this to None
|
||||
# and handle call-forwarding when on_dialin_ready fires.
|
||||
diallin_settings = DailyDialinSettings(
|
||||
call_id=callId,
|
||||
call_domain=callDomain
|
||||
)
|
||||
|
||||
transport = DailyTransport(
|
||||
room_url,
|
||||
token,
|
||||
"Chatbot",
|
||||
DailyParams(
|
||||
api_url=daily_api_url,
|
||||
api_key=daily_api_key,
|
||||
dialin_settings=diallin_settings,
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
camera_out_enabled=False,
|
||||
vad_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
transcription_enabled=True,
|
||||
)
|
||||
)
|
||||
|
||||
tts = ElevenLabsTTSService(
|
||||
aiohttp_session=session,
|
||||
api_key=os.getenv("ELEVENLABS_API_KEY", ""),
|
||||
voice_id=os.getenv("ELEVENLABS_VOICE_ID", ""),
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
model="gpt-4o")
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are Chatbot, a friendly, helpful robot. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way, but keep your responses brief. Start by saying 'Oh, hello! Who dares dial me at this hour?!'.",
|
||||
},
|
||||
]
|
||||
|
||||
tma_in = LLMUserResponseAggregator(messages)
|
||||
tma_out = LLMAssistantResponseAggregator(messages)
|
||||
|
||||
pipeline = Pipeline([
|
||||
transport.input(),
|
||||
tma_in,
|
||||
llm,
|
||||
tts,
|
||||
transport.output(),
|
||||
tma_out,
|
||||
])
|
||||
|
||||
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
|
||||
|
||||
@transport.event_handler("on_first_participant_joined")
|
||||
async def on_first_participant_joined(transport, participant):
|
||||
transport.capture_participant_transcription(participant["id"])
|
||||
await task.queue_frames([LLMMessagesFrame(messages)])
|
||||
|
||||
@transport.event_handler("on_participant_left")
|
||||
async def on_participant_left(transport, participant, reason):
|
||||
await task.queue_frame(EndFrame())
|
||||
|
||||
runner = PipelineRunner()
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser(description="Pipecat Simple ChatBot")
|
||||
parser.add_argument("-u", type=str, help="Room URL")
|
||||
parser.add_argument("-t", type=str, help="Token")
|
||||
parser.add_argument("-i", type=str, help="Call ID")
|
||||
parser.add_argument("-d", type=str, help="Call Domain")
|
||||
config = parser.parse_args()
|
||||
|
||||
asyncio.run(main(config.u, config.t, config.i, config.d))
|
||||
220
examples/dialin-chatbot/bot_runner.py
Normal file
220
examples/dialin-chatbot/bot_runner.py
Normal file
@@ -0,0 +1,220 @@
|
||||
"""
|
||||
bot_runner.py
|
||||
|
||||
HTTP service that listens for incoming calls from either Daily or Twilio,
|
||||
provisioning a room and starting a Pipecat bot in response.
|
||||
|
||||
Refer to README for more information.
|
||||
"""
|
||||
import os
|
||||
import argparse
|
||||
import subprocess
|
||||
from pipecat.transports.services.helpers.daily_rest import DailyRESTHelper, DailyRoomObject, DailyRoomProperties, DailyRoomSipParams, DailyRoomParams
|
||||
from fastapi import FastAPI, Request, HTTPException
|
||||
from fastapi.middleware.cors import CORSMiddleware
|
||||
from fastapi.responses import JSONResponse, PlainTextResponse
|
||||
from twilio.twiml.voice_response import VoiceResponse
|
||||
|
||||
from dotenv import load_dotenv
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
# ------------ Configuration ------------ #
|
||||
|
||||
MAX_SESSION_TIME = 5 * 60 # 5 minutes
|
||||
REQUIRED_ENV_VARS = ['OPENAI_API_KEY', 'DAILY_API_KEY',
|
||||
'ELEVENLABS_API_KEY', 'ELEVENLABS_VOICE_ID']
|
||||
|
||||
daily_rest_helper = DailyRESTHelper(
|
||||
os.getenv("DAILY_API_KEY", ""),
|
||||
os.getenv("DAILY_API_URL", 'https://api.daily.co/v1'))
|
||||
|
||||
|
||||
# ----------------- API ----------------- #
|
||||
|
||||
app = FastAPI()
|
||||
|
||||
app.add_middleware(
|
||||
CORSMiddleware,
|
||||
allow_origins=["*"],
|
||||
allow_credentials=True,
|
||||
allow_methods=["*"],
|
||||
allow_headers=["*"]
|
||||
)
|
||||
|
||||
"""
|
||||
Create Daily room, tell the bot if the room is created for Twilio's SIP or Daily's SIP (vendor).
|
||||
When the vendor is Daily, the bot handles the call forwarding automatically,
|
||||
i.e, forwards the call from the "hold music state" to the Daily Room's SIP URI.
|
||||
|
||||
Alternatively, when the vendor is Twilio (not Daily), the bot is responsible for
|
||||
updating the state on Twilio. So when `dialin-ready` fires, it takes appropriate
|
||||
action using the Twilio Client library.
|
||||
"""
|
||||
|
||||
|
||||
def _create_daily_room(room_url, callId, callDomain=None, vendor="daily"):
|
||||
if not room_url:
|
||||
params = DailyRoomParams(
|
||||
properties=DailyRoomProperties(
|
||||
# Note: these are the default values, except for the display name
|
||||
sip=DailyRoomSipParams(
|
||||
display_name="dialin-user",
|
||||
video=False,
|
||||
sip_mode="dial-in",
|
||||
num_endpoints=1
|
||||
)
|
||||
)
|
||||
)
|
||||
|
||||
print(f"Creating new room...")
|
||||
room: DailyRoomObject = daily_rest_helper.create_room(params=params)
|
||||
|
||||
else:
|
||||
# Check passed room URL exist (we assume that it already has a sip set up!)
|
||||
try:
|
||||
print(f"Joining existing room: {room_url}")
|
||||
room: DailyRoomObject = daily_rest_helper.get_room_from_url(
|
||||
room_url)
|
||||
except Exception:
|
||||
raise HTTPException(
|
||||
status_code=500, detail=f"Room not found: {room_url}")
|
||||
|
||||
print(f"Daily room: {room.url} {room.config.sip_endpoint}")
|
||||
|
||||
# Give the agent a token to join the session
|
||||
token = daily_rest_helper.get_token(room.url, MAX_SESSION_TIME)
|
||||
|
||||
if not room or not token:
|
||||
raise HTTPException(
|
||||
status_code=500, detail=f"Failed to get room or token token")
|
||||
|
||||
# Spawn a new agent, and join the user session
|
||||
# Note: this is mostly for demonstration purposes (refer to 'deployment' in docs)
|
||||
if vendor == "daily":
|
||||
bot_proc = f"python3 -m bot_daily -u {room.url} -t {token} -i {
|
||||
callId} -d {callDomain}"
|
||||
else:
|
||||
bot_proc = f"python3 -m bot_twilio -u {room.url} -t {
|
||||
token} -i {callId} -s {room.config.sip_endpoint}"
|
||||
|
||||
try:
|
||||
subprocess.Popen(
|
||||
[bot_proc],
|
||||
shell=True,
|
||||
bufsize=1,
|
||||
cwd=os.path.dirname(os.path.abspath(__file__))
|
||||
)
|
||||
except Exception as e:
|
||||
raise HTTPException(
|
||||
status_code=500, detail=f"Failed to start subprocess: {e}")
|
||||
|
||||
return room
|
||||
|
||||
|
||||
@app.post("/twilio_start_bot", response_class=PlainTextResponse)
|
||||
async def twilio_start_bot(request: Request):
|
||||
print(f"POST /twilio_voice_bot")
|
||||
|
||||
# twilio_start_bot is invoked directly by Twilio (as a web hook).
|
||||
# On Twilio, under Active Numbers, pick the phone number
|
||||
# Click Configure and under Voice Configuration,
|
||||
# "a call comes in" choose webhook and point the URL to
|
||||
# where this code is hosted.
|
||||
data = {}
|
||||
try:
|
||||
# shouldnt have received json, twilio sends form data
|
||||
form_data = await request.form()
|
||||
data = dict(form_data)
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
room_url = os.getenv("DAILY_SAMPLE_ROOM_URL", None)
|
||||
callId = data.get('CallSid')
|
||||
|
||||
if not callId:
|
||||
raise HTTPException(
|
||||
status_code=500, detail="Missing 'CallSid' in request")
|
||||
|
||||
print("CallId: %s" % callId)
|
||||
|
||||
# create room and tell the bot to join the created room
|
||||
# note: Twilio does not require a callDomain
|
||||
room: DailyRoomObject = _create_daily_room(
|
||||
room_url, callId, None, "twilio")
|
||||
|
||||
print(f"Put Twilio on hold...")
|
||||
# We have the room and the SIP URI,
|
||||
# but we do not know if the Daily SIP Worker and the Bot have joined the call
|
||||
# put the call on hold until the 'on_dialin_ready' fires.
|
||||
# Then, the bot will update the called sid with the sip uri.
|
||||
# http://com.twilio.music.classical.s3.amazonaws.com/BusyStrings.mp3
|
||||
resp = VoiceResponse()
|
||||
resp.play(
|
||||
url="http://com.twilio.sounds.music.s3.amazonaws.com/MARKOVICHAMP-Borghestral.mp3", loop=10)
|
||||
return str(resp)
|
||||
|
||||
|
||||
@app.post("/daily_start_bot")
|
||||
async def daily_start_bot(request: Request) -> JSONResponse:
|
||||
# The /daily_start_bot is invoked when a call is received on Daily's SIP URI
|
||||
# daily_start_bot will create the room, put the call on hold until
|
||||
# the bot and sip worker are ready. Daily will automatically
|
||||
# forward the call to the SIP URi when dialin_ready fires.
|
||||
|
||||
# Use specified room URL, or create a new one if not specified
|
||||
room_url = os.getenv("DAILY_SAMPLE_ROOM_URL", None)
|
||||
# Get the dial-in properties from the request
|
||||
try:
|
||||
data = await request.json()
|
||||
if "test" in data:
|
||||
# Pass through any webhook checks
|
||||
return JSONResponse({"test": True})
|
||||
callId = data.get("callId", None)
|
||||
callDomain = data.get("callDomain", None)
|
||||
except Exception:
|
||||
raise HTTPException(
|
||||
status_code=500,
|
||||
detail="Missing properties 'callId' or 'callDomain'")
|
||||
|
||||
print(f"CallId: {callId}, CallDomain: {callDomain}")
|
||||
room: DailyRoomObject = _create_daily_room(
|
||||
room_url, callId, callDomain, "daily")
|
||||
|
||||
# Grab a token for the user to join with
|
||||
return JSONResponse({
|
||||
"room_url": room.url,
|
||||
"sipUri": room.config.sip_endpoint
|
||||
})
|
||||
|
||||
# ----------------- Main ----------------- #
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
# Check environment variables
|
||||
for env_var in REQUIRED_ENV_VARS:
|
||||
if env_var not in os.environ:
|
||||
raise Exception(f"Missing environment variable: {env_var}.")
|
||||
|
||||
parser = argparse.ArgumentParser(description="Pipecat Bot Runner")
|
||||
parser.add_argument("--host", type=str,
|
||||
default=os.getenv("HOST", "0.0.0.0"), help="Host address")
|
||||
parser.add_argument("--port", type=int,
|
||||
default=os.getenv("PORT", 7860), help="Port number")
|
||||
parser.add_argument("--reload", action="store_true",
|
||||
default=True, help="Reload code on change")
|
||||
|
||||
config = parser.parse_args()
|
||||
|
||||
try:
|
||||
import uvicorn
|
||||
|
||||
uvicorn.run(
|
||||
"bot_runner:app",
|
||||
host=config.host,
|
||||
port=config.port,
|
||||
reload=config.reload
|
||||
)
|
||||
|
||||
except KeyboardInterrupt:
|
||||
print("Pipecat runner shutting down...")
|
||||
125
examples/dialin-chatbot/bot_twilio.py
Normal file
125
examples/dialin-chatbot/bot_twilio.py
Normal file
@@ -0,0 +1,125 @@
|
||||
import asyncio
|
||||
import aiohttp
|
||||
import os
|
||||
import sys
|
||||
import argparse
|
||||
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_response import LLMAssistantResponseAggregator, LLMUserResponseAggregator
|
||||
from pipecat.frames.frames import (
|
||||
LLMMessagesFrame,
|
||||
EndFrame
|
||||
)
|
||||
from pipecat.services.elevenlabs import ElevenLabsTTSService
|
||||
from pipecat.services.openai import OpenAILLMService
|
||||
from pipecat.transports.services.daily import DailyParams, DailyTransport
|
||||
from pipecat.vad.silero import SileroVADAnalyzer
|
||||
|
||||
from twilio.rest import Client
|
||||
|
||||
from loguru import logger
|
||||
|
||||
from dotenv import load_dotenv
|
||||
load_dotenv(override=True)
|
||||
|
||||
logger.remove(0)
|
||||
logger.add(sys.stderr, level="DEBUG")
|
||||
|
||||
|
||||
twilio_account_sid = os.getenv('TWILIO_ACCOUNT_SID')
|
||||
twilio_auth_token = os.getenv('TWILIO_AUTH_TOKEN')
|
||||
twilioclient = Client(twilio_account_sid, twilio_auth_token)
|
||||
|
||||
daily_api_key = os.getenv("DAILY_API_KEY", "")
|
||||
|
||||
|
||||
async def main(room_url: str, token: str, callId: str, sipUri: str):
|
||||
async with aiohttp.ClientSession() as session:
|
||||
# diallin_settings are only needed if Daily's SIP URI is used
|
||||
# If you are handling this via Twilio, Telnyx, set this to None
|
||||
# and handle call-forwarding when on_dialin_ready fires.
|
||||
transport = DailyTransport(
|
||||
room_url,
|
||||
token,
|
||||
"Chatbot",
|
||||
DailyParams(
|
||||
api_key=daily_api_key,
|
||||
dialin_settings=None, # Not required for Twilio
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
camera_out_enabled=False,
|
||||
vad_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
transcription_enabled=True,
|
||||
)
|
||||
)
|
||||
|
||||
tts = ElevenLabsTTSService(
|
||||
aiohttp_session=session,
|
||||
api_key=os.getenv("ELEVENLABS_API_KEY", ""),
|
||||
voice_id=os.getenv("ELEVENLABS_VOICE_ID", ""),
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
model="gpt-4o")
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are Chatbot, a friendly, helpful robot. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way, but keep your responses brief. Start by saying 'Hello! Who dares dial me at this hour?!'.",
|
||||
},
|
||||
]
|
||||
|
||||
tma_in = LLMUserResponseAggregator(messages)
|
||||
tma_out = LLMAssistantResponseAggregator(messages)
|
||||
|
||||
pipeline = Pipeline([
|
||||
transport.input(),
|
||||
tma_in,
|
||||
llm,
|
||||
tts,
|
||||
transport.output(),
|
||||
tma_out,
|
||||
])
|
||||
|
||||
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
|
||||
|
||||
@transport.event_handler("on_first_participant_joined")
|
||||
async def on_first_participant_joined(transport, participant):
|
||||
transport.capture_participant_transcription(participant["id"])
|
||||
await task.queue_frames([LLMMessagesFrame(messages)])
|
||||
|
||||
@transport.event_handler("on_participant_left")
|
||||
async def on_participant_left(transport, participant, reason):
|
||||
await task.queue_frame(EndFrame())
|
||||
|
||||
@transport.event_handler("on_dialin_ready")
|
||||
async def on_dialin_ready(transport, cdata):
|
||||
# For Twilio, Telnyx, etc. You need to update the state of the call
|
||||
# and forward it to the sip_uri..
|
||||
print(f"Forwarding call: {callId} {sipUri}")
|
||||
|
||||
try:
|
||||
# The TwiML is updated using Twilio's client library
|
||||
call = twilioclient.calls(callId).update(
|
||||
twiml=f'<Response><Dial><Sip>{sipUri}</Sip></Dial></Response>'
|
||||
)
|
||||
except Exception as e:
|
||||
raise Exception(f"Failed to forward call: {str(e)}")
|
||||
|
||||
runner = PipelineRunner()
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser(description="Pipecat Simple ChatBot")
|
||||
parser.add_argument("-u", type=str, help="Room URL")
|
||||
parser.add_argument("-t", type=str, help="Token")
|
||||
parser.add_argument("-i", type=str, help="Call ID")
|
||||
parser.add_argument("-s", type=str, help="SIP URI")
|
||||
config = parser.parse_args()
|
||||
|
||||
asyncio.run(main(config.u, config.t, config.i, config.s))
|
||||
8
examples/dialin-chatbot/env.example
Normal file
8
examples/dialin-chatbot/env.example
Normal file
@@ -0,0 +1,8 @@
|
||||
DAILY_SAMPLE_ROOM_URL=https://yourdomain.daily.co/yourroom # (optional: for joining the bot to the same room repeatedly for local dev)
|
||||
DAILY_API_KEY=.
|
||||
DAILY_API_URL=api.daily.co/v1
|
||||
OPENAI_API_KEY=
|
||||
ELEVENLABS_API_KEY=
|
||||
ELEVENLABS_VOICE_ID=
|
||||
TWILIO_ACCOUNT_SID=
|
||||
TWILIO_AUTH_TOKEN=
|
||||
19
examples/dialin-chatbot/fly.example.toml
Normal file
19
examples/dialin-chatbot/fly.example.toml
Normal file
@@ -0,0 +1,19 @@
|
||||
# fly.toml app configuration file generated for pipecat-dialin-demo on 2024-06-03T15:57:57+02:00
|
||||
#
|
||||
# See https://fly.io/docs/reference/configuration/ for information about how to use this file.
|
||||
#
|
||||
|
||||
app = 'pipecat-dialin-demo'
|
||||
primary_region = 'sjc'
|
||||
|
||||
[build]
|
||||
|
||||
[http_service]
|
||||
internal_port = 7860
|
||||
force_https = true
|
||||
auto_stop_machines = true
|
||||
auto_start_machines = true
|
||||
min_machines_running = 1
|
||||
|
||||
[[vm]]
|
||||
size = 'performance-1x'
|
||||
BIN
examples/dialin-chatbot/image.png
Normal file
BIN
examples/dialin-chatbot/image.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 19 KiB |
7
examples/dialin-chatbot/requirements.txt
Normal file
7
examples/dialin-chatbot/requirements.txt
Normal file
@@ -0,0 +1,7 @@
|
||||
pipecat-ai[daily,openai,silero]
|
||||
fastapi
|
||||
uvicorn
|
||||
requests
|
||||
python-dotenv
|
||||
loguru
|
||||
twilio
|
||||
@@ -1,70 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import os
|
||||
|
||||
import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.frames.frames import EndFrame, TTSSpeakFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.piper.tts import PiperTTSService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(audio_out_enabled=True),
|
||||
"twilio": lambda: FastAPIWebsocketParams(audio_out_enabled=True),
|
||||
"webrtc": lambda: TransportParams(audio_out_enabled=True),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
# Create an HTTP session
|
||||
async with aiohttp.ClientSession() as session:
|
||||
tts = PiperTTSService(
|
||||
base_url=os.getenv("PIPER_BASE_URL"), aiohttp_session=session, sample_rate=24000
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
Pipeline([tts, transport.output()]),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
# Register an event handler so we can play the audio when the client joins
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
await task.queue_frames([TTSSpeakFrame(f"Hello there!"), EndFrame()])
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
@@ -1,71 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import os
|
||||
|
||||
import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.frames.frames import EndFrame, TTSSpeakFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.rime.tts import RimeHttpTTSService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(audio_out_enabled=True),
|
||||
"twilio": lambda: FastAPIWebsocketParams(audio_out_enabled=True),
|
||||
"webrtc": lambda: TransportParams(audio_out_enabled=True),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
# Create an HTTP session
|
||||
async with aiohttp.ClientSession() as session:
|
||||
tts = RimeHttpTTSService(
|
||||
api_key=os.getenv("RIME_API_KEY", ""),
|
||||
voice_id="rex",
|
||||
aiohttp_session=session,
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
Pipeline([tts, transport.output()]),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
# Register an event handler so we can play the audio when the client joins
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
await task.queue_frames([TTSSpeakFrame(f"Hello there!"), EndFrame()])
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
@@ -1,68 +1,56 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
# Copyright (c) 2024, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import asyncio
|
||||
import aiohttp
|
||||
import os
|
||||
import sys
|
||||
|
||||
from pipecat.frames.frames import EndFrame, TextFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.services.elevenlabs import ElevenLabsTTSService
|
||||
from pipecat.transports.services.daily import DailyParams, DailyTransport
|
||||
|
||||
from runner import configure
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.frames.frames import EndFrame, TTSSpeakFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
from dotenv import load_dotenv
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(audio_out_enabled=True),
|
||||
"twilio": lambda: FastAPIWebsocketParams(audio_out_enabled=True),
|
||||
"webrtc": lambda: TransportParams(audio_out_enabled=True),
|
||||
}
|
||||
logger.remove(0)
|
||||
logger.add(sys.stderr, level="DEBUG")
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
async def main(room_url):
|
||||
async with aiohttp.ClientSession() as session:
|
||||
transport = DailyTransport(
|
||||
room_url, None, "Say One Thing", DailyParams(audio_out_enabled=True))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
tts = ElevenLabsTTSService(
|
||||
aiohttp_session=session,
|
||||
api_key=os.getenv("ELEVENLABS_API_KEY"),
|
||||
voice_id=os.getenv("ELEVENLABS_VOICE_ID"),
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
Pipeline([tts, transport.output()]),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
runner = PipelineRunner()
|
||||
|
||||
# Register an event handler so we can play the audio when the client joins
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
await task.queue_frames([TTSSpeakFrame(f"Hello there!"), EndFrame()])
|
||||
task = PipelineTask(Pipeline([tts, transport.output()]))
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
# Register an event handler so we can play the audio when the
|
||||
# participant joins.
|
||||
@transport.event_handler("on_participant_joined")
|
||||
async def on_new_participant_joined(transport, participant):
|
||||
participant_name = participant["info"]["userName"] or ''
|
||||
await task.queue_frames([TextFrame(f"Hello there, {participant_name}!"), EndFrame()])
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
(url, token) = configure()
|
||||
asyncio.run(main(url))
|
||||
|
||||
@@ -1,23 +1,25 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
# Copyright (c) 2024, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import asyncio
|
||||
import aiohttp
|
||||
import os
|
||||
import sys
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.frames.frames import EndFrame, TTSSpeakFrame
|
||||
from pipecat.frames.frames import EndFrame, TextFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.transports.local.audio import LocalAudioTransport, LocalAudioTransportParams
|
||||
from pipecat.services.elevenlabs import ElevenLabsTTSService
|
||||
from pipecat.transports.base_transport import TransportParams
|
||||
from pipecat.transports.local.audio import LocalAudioTransport
|
||||
|
||||
from loguru import logger
|
||||
|
||||
from dotenv import load_dotenv
|
||||
load_dotenv(override=True)
|
||||
|
||||
logger.remove(0)
|
||||
@@ -25,24 +27,26 @@ logger.add(sys.stderr, level="DEBUG")
|
||||
|
||||
|
||||
async def main():
|
||||
transport = LocalAudioTransport(LocalAudioTransportParams(audio_out_enabled=True))
|
||||
async with aiohttp.ClientSession() as session:
|
||||
transport = LocalAudioTransport(TransportParams(audio_out_enabled=True))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
tts = ElevenLabsTTSService(
|
||||
aiohttp_session=session,
|
||||
api_key=os.getenv("ELEVENLABS_API_KEY"),
|
||||
voice_id=os.getenv("ELEVENLABS_VOICE_ID"),
|
||||
)
|
||||
|
||||
pipeline = Pipeline([tts, transport.output()])
|
||||
pipeline = Pipeline([tts, transport.output()])
|
||||
|
||||
task = PipelineTask(pipeline)
|
||||
task = PipelineTask(pipeline)
|
||||
|
||||
async def say_something():
|
||||
await asyncio.sleep(1)
|
||||
await task.queue_frames([TTSSpeakFrame("Hello there, how is it going!"), EndFrame()])
|
||||
async def say_something():
|
||||
await asyncio.sleep(1)
|
||||
await task.queue_frames([TextFrame("Hello there!"), EndFrame()])
|
||||
|
||||
runner = PipelineRunner(handle_sigint=False if sys.platform == "win32" else True)
|
||||
runner = PipelineRunner()
|
||||
|
||||
await asyncio.gather(runner.run(task), say_something())
|
||||
await asyncio.gather(runner.run(task), say_something())
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
@@ -1,62 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import asyncio
|
||||
import os
|
||||
import sys
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.frames.frames import TextFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.runner.livekit import configure
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.transports.services.livekit import LiveKitParams, LiveKitTransport
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
logger.remove(0)
|
||||
logger.add(sys.stderr, level="DEBUG")
|
||||
|
||||
|
||||
async def main():
|
||||
(url, token, room_name) = await configure()
|
||||
|
||||
transport = LiveKitTransport(
|
||||
url=url,
|
||||
token=token,
|
||||
room_name=room_name,
|
||||
params=LiveKitParams(audio_out_enabled=True),
|
||||
)
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
|
||||
runner = PipelineRunner()
|
||||
|
||||
task = PipelineTask(Pipeline([tts, transport.output()]))
|
||||
|
||||
# Register an event handler so we can play the audio when the
|
||||
# participant joins.
|
||||
@transport.event_handler("on_first_participant_joined")
|
||||
async def on_first_participant_joined(transport, participant_id):
|
||||
await asyncio.sleep(1)
|
||||
await task.queue_frame(
|
||||
TextFrame(
|
||||
"Hello there! How are you doing today? Would you like to talk about the weather?"
|
||||
)
|
||||
)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(main())
|
||||
@@ -1,65 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.frames.frames import EndFrame, TTSSpeakFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.riva.tts import FastPitchTTSService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(audio_out_enabled=True),
|
||||
"twilio": lambda: FastAPIWebsocketParams(audio_out_enabled=True),
|
||||
"webrtc": lambda: TransportParams(audio_out_enabled=True),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
tts = FastPitchTTSService(api_key=os.getenv("NVIDIA_API_KEY"))
|
||||
|
||||
task = PipelineTask(
|
||||
Pipeline([tts, transport.output()]),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
# Register an event handler so we can play the audio when the client joins
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
await task.queue_frames([TTSSpeakFrame(f"Hello there!"), EndFrame()])
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
@@ -1,82 +1,68 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
# Copyright (c) 2024, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import asyncio
|
||||
import aiohttp
|
||||
import os
|
||||
import sys
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.frames.frames import EndFrame
|
||||
from pipecat.frames.frames import EndFrame, LLMMessagesFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.processors.aggregators.openai_llm_context import (
|
||||
OpenAILLMContext,
|
||||
OpenAILLMContextFrame,
|
||||
)
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
from pipecat.services.elevenlabs import ElevenLabsTTSService
|
||||
from pipecat.services.openai import OpenAILLMService
|
||||
from pipecat.transports.services.daily import DailyParams, DailyTransport
|
||||
|
||||
from runner import configure
|
||||
|
||||
from loguru import logger
|
||||
|
||||
from dotenv import load_dotenv
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(audio_out_enabled=True),
|
||||
"twilio": lambda: FastAPIWebsocketParams(audio_out_enabled=True),
|
||||
"webrtc": lambda: TransportParams(audio_out_enabled=True),
|
||||
}
|
||||
logger.remove(0)
|
||||
logger.add(sys.stderr, level="DEBUG")
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
async def main(room_url):
|
||||
async with aiohttp.ClientSession() as session:
|
||||
transport = DailyTransport(
|
||||
room_url,
|
||||
None,
|
||||
"Say One Thing From an LLM",
|
||||
DailyParams(audio_out_enabled=True))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
tts = ElevenLabsTTSService(
|
||||
aiohttp_session=session,
|
||||
api_key=os.getenv("ELEVENLABS_API_KEY"),
|
||||
voice_id=os.getenv("ELEVENLABS_VOICE_ID"),
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
model="gpt-4o")
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are an LLM in a WebRTC session, and this is a 'hello world' demo. Say hello to the world.",
|
||||
}
|
||||
]
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are an LLM in a WebRTC session, and this is a 'hello world' demo. Say hello to the world.",
|
||||
}]
|
||||
|
||||
task = PipelineTask(
|
||||
Pipeline([llm, tts, transport.output()]),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
runner = PipelineRunner()
|
||||
|
||||
# Register an event handler so we can play the audio when the client joins
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
await task.queue_frames([OpenAILLMContextFrame(OpenAILLMContext(messages)), EndFrame()])
|
||||
task = PipelineTask(Pipeline([llm, tts, transport.output()]))
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
@transport.event_handler("on_first_participant_joined")
|
||||
async def on_first_participant_joined(transport, participant):
|
||||
await task.queue_frames([LLMMessagesFrame(messages), EndFrame()])
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
(url, token) = configure()
|
||||
asyncio.run(main(url))
|
||||
|
||||
@@ -1,83 +1,68 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
# Copyright (c) 2024, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import os
|
||||
|
||||
import asyncio
|
||||
import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
import os
|
||||
import sys
|
||||
|
||||
from pipecat.frames.frames import TextFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.fal.image import FalImageGenService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
from pipecat.services.fal import FalImageGenService
|
||||
from pipecat.transports.services.daily import DailyParams, DailyTransport
|
||||
|
||||
from runner import configure
|
||||
|
||||
from loguru import logger
|
||||
|
||||
from dotenv import load_dotenv
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
video_out_enabled=True,
|
||||
video_out_width=1024,
|
||||
video_out_height=1024,
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
video_out_enabled=True,
|
||||
video_out_width=1024,
|
||||
video_out_height=1024,
|
||||
),
|
||||
}
|
||||
logger.remove(0)
|
||||
logger.add(sys.stderr, level="DEBUG")
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
# Create an HTTP session
|
||||
async def main(room_url):
|
||||
async with aiohttp.ClientSession() as session:
|
||||
transport = DailyTransport(
|
||||
room_url,
|
||||
None,
|
||||
"Show a still frame image",
|
||||
DailyParams(
|
||||
camera_out_enabled=True,
|
||||
camera_out_width=1024,
|
||||
camera_out_height=1024
|
||||
)
|
||||
)
|
||||
|
||||
imagegen = FalImageGenService(
|
||||
params=FalImageGenService.InputParams(image_size="square_hd"),
|
||||
params=FalImageGenService.InputParams(
|
||||
image_size="square_hd"
|
||||
),
|
||||
aiohttp_session=session,
|
||||
key=os.getenv("FAL_KEY"),
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
Pipeline([imagegen, transport.output()]),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
runner = PipelineRunner()
|
||||
|
||||
# Register an event handler so we can play the audio when the client joins
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
await task.queue_frame(TextFrame("a cat in the style of picasso"))
|
||||
task = PipelineTask(Pipeline([imagegen, transport.output()]))
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
@transport.event_handler("on_first_participant_joined")
|
||||
async def on_first_participant_joined(transport, participant):
|
||||
# Note that we do not put an EndFrame() item in the pipeline for this demo.
|
||||
# This means that the bot will stay in the channel until it times out.
|
||||
# An EndFrame() in the pipeline would cause the transport to shut
|
||||
# down.
|
||||
await task.queue_frames([TextFrame("a cat in the style of picasso")])
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
(url, token) = configure()
|
||||
asyncio.run(main(url))
|
||||
|
||||
@@ -1,25 +1,27 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
# Copyright (c) 2024, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import asyncio
|
||||
import aiohttp
|
||||
import os
|
||||
import sys
|
||||
import tkinter as tk
|
||||
|
||||
import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
import tkinter as tk
|
||||
|
||||
from pipecat.frames.frames import TextFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.services.fal.image import FalImageGenService
|
||||
from pipecat.transports.local.tk import TkLocalTransport, TkTransportParams
|
||||
from pipecat.services.fal import FalImageGenService
|
||||
from pipecat.transports.base_transport import TransportParams
|
||||
from pipecat.transports.local.tk import TkLocalTransport
|
||||
|
||||
from loguru import logger
|
||||
|
||||
from dotenv import load_dotenv
|
||||
load_dotenv(override=True)
|
||||
|
||||
logger.remove(0)
|
||||
@@ -33,11 +35,15 @@ async def main():
|
||||
|
||||
transport = TkLocalTransport(
|
||||
tk_root,
|
||||
TkTransportParams(video_out_enabled=True, video_out_width=1024, video_out_height=1024),
|
||||
)
|
||||
TransportParams(
|
||||
camera_out_enabled=True,
|
||||
camera_out_width=1024,
|
||||
camera_out_height=1024))
|
||||
|
||||
imagegen = FalImageGenService(
|
||||
params=FalImageGenService.InputParams(image_size="square_hd"),
|
||||
params=FalImageGenService.InputParams(
|
||||
image_size="square_hd"
|
||||
),
|
||||
aiohttp_session=session,
|
||||
key=os.getenv("FAL_KEY"),
|
||||
)
|
||||
@@ -50,7 +56,7 @@ async def main():
|
||||
runner = PipelineRunner()
|
||||
|
||||
async def run_tk():
|
||||
while not task.has_finished():
|
||||
while runner.is_active():
|
||||
tk_root.update()
|
||||
tk_root.update_idletasks()
|
||||
await asyncio.sleep(0.1)
|
||||
|
||||
@@ -1,84 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.frames.frames import TextFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.google.image import GoogleImageGenService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
video_out_enabled=True,
|
||||
video_out_width=1024,
|
||||
video_out_height=1024,
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
video_out_enabled=True,
|
||||
video_out_width=1024,
|
||||
video_out_height=1024,
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
imagegen = GoogleImageGenService(
|
||||
api_key=os.getenv("GOOGLE_API_KEY"),
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
Pipeline([imagegen, transport.output()]),
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
# Register an event handler so we can play the audio when the client joins
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
await task.queue_frame(TextFrame("a cat in the style of picasso"))
|
||||
await task.queue_frame(TextFrame("a dog in the style of picasso"))
|
||||
await task.queue_frame(TextFrame("a fish in the style of picasso"))
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
@@ -1,172 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import argparse
|
||||
import asyncio
|
||||
import os
|
||||
from contextlib import asynccontextmanager
|
||||
from typing import Dict
|
||||
|
||||
import uvicorn
|
||||
from dotenv import load_dotenv
|
||||
from fastapi import BackgroundTasks, FastAPI
|
||||
from fastapi.responses import RedirectResponse
|
||||
from loguru import logger
|
||||
from pipecat_ai_small_webrtc_prebuilt.frontend import SmallWebRTCPrebuiltUI
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import TransportParams
|
||||
from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
|
||||
from pipecat.transports.network.webrtc_connection import IceServer, SmallWebRTCConnection
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
app = FastAPI()
|
||||
|
||||
# Store connections by pc_id
|
||||
pcs_map: Dict[str, SmallWebRTCConnection] = {}
|
||||
|
||||
ice_servers = [
|
||||
IceServer(
|
||||
urls="stun:stun.l.google.com:19302",
|
||||
)
|
||||
]
|
||||
|
||||
# Mount the frontend at /
|
||||
app.mount("/client", SmallWebRTCPrebuiltUI)
|
||||
|
||||
|
||||
async def run_example(webrtc_connection: SmallWebRTCConnection):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
# Create a transport using the WebRTC connection
|
||||
transport = SmallWebRTCTransport(
|
||||
webrtc_connection=webrtc_connection,
|
||||
params=TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
)
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt,
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=False)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
@app.get("/", include_in_schema=False)
|
||||
async def root_redirect():
|
||||
return RedirectResponse(url="/client/")
|
||||
|
||||
|
||||
@app.post("/api/offer")
|
||||
async def offer(request: dict, background_tasks: BackgroundTasks):
|
||||
pc_id = request.get("pc_id")
|
||||
|
||||
if pc_id and pc_id in pcs_map:
|
||||
pipecat_connection = pcs_map[pc_id]
|
||||
logger.info(f"Reusing existing connection for pc_id: {pc_id}")
|
||||
await pipecat_connection.renegotiate(
|
||||
sdp=request["sdp"],
|
||||
type=request["type"],
|
||||
restart_pc=request.get("restart_pc", False),
|
||||
)
|
||||
else:
|
||||
pipecat_connection = SmallWebRTCConnection(ice_servers)
|
||||
await pipecat_connection.initialize(sdp=request["sdp"], type=request["type"])
|
||||
|
||||
@pipecat_connection.event_handler("closed")
|
||||
async def handle_disconnected(webrtc_connection: SmallWebRTCConnection):
|
||||
logger.info(f"Discarding peer connection for pc_id: {webrtc_connection.pc_id}")
|
||||
pcs_map.pop(webrtc_connection.pc_id, None)
|
||||
|
||||
# Run example function with SmallWebRTC transport arguments.
|
||||
background_tasks.add_task(run_example, pipecat_connection)
|
||||
|
||||
answer = pipecat_connection.get_answer()
|
||||
# Updating the peer connection inside the map
|
||||
pcs_map[answer["pc_id"]] = pipecat_connection
|
||||
|
||||
return answer
|
||||
|
||||
|
||||
@asynccontextmanager
|
||||
async def lifespan(app: FastAPI):
|
||||
yield # Run app
|
||||
coros = [pc.disconnect() for pc in pcs_map.values()]
|
||||
await asyncio.gather(*coros)
|
||||
pcs_map.clear()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser(description="Pipecat Bot Runner")
|
||||
parser.add_argument(
|
||||
"--host", default="localhost", help="Host for HTTP server (default: localhost)"
|
||||
)
|
||||
parser.add_argument(
|
||||
"--port", type=int, default=7860, help="Port for HTTP server (default: 7860)"
|
||||
)
|
||||
args = parser.parse_args()
|
||||
|
||||
uvicorn.run(app, host=args.host, port=args.port)
|
||||
86
examples/foundational/04-utterance-and-speech.py
Normal file
86
examples/foundational/04-utterance-and-speech.py
Normal file
@@ -0,0 +1,86 @@
|
||||
#
|
||||
# Copyright (c) 2024, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import aiohttp
|
||||
import asyncio
|
||||
import os
|
||||
import sys
|
||||
|
||||
from pipecat.pipeline.merge_pipeline import SequentialMergePipeline
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
|
||||
from pipecat.frames.frames import EndPipeFrame, LLMMessagesFrame, TextFrame
|
||||
from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.services.azure import AzureLLMService, AzureTTSService
|
||||
from pipecat.services.elevenlabs import ElevenLabsTTSService
|
||||
from pipecat.services.transport_services import TransportServiceOutput
|
||||
from pipecat.services.transports.daily_transport import DailyTransport
|
||||
|
||||
from runner import configure
|
||||
|
||||
from loguru import logger
|
||||
|
||||
from dotenv import load_dotenv
|
||||
load_dotenv(override=True)
|
||||
|
||||
logger.remove(0)
|
||||
logger.add(sys.stderr, level="DEBUG")
|
||||
|
||||
|
||||
async def main(room_url: str):
|
||||
async with aiohttp.ClientSession() as session:
|
||||
transport = DailyTransport(room_url, None, "Static And Dynamic Speech")
|
||||
|
||||
meeting = TransportServiceOutput(transport, mic_enabled=True)
|
||||
|
||||
llm = AzureLLMService(
|
||||
api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
|
||||
endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
|
||||
model=os.getenv("AZURE_CHATGPT_MODEL"),
|
||||
)
|
||||
azure_tts = AzureTTSService(
|
||||
api_key=os.getenv("AZURE_SPEECH_API_KEY"),
|
||||
region=os.getenv("AZURE_SPEECH_REGION"),
|
||||
)
|
||||
|
||||
elevenlabs_tts = ElevenLabsTTSService(
|
||||
aiohttp_session=session,
|
||||
api_key=os.getenv("ELEVENLABS_API_KEY"),
|
||||
voice_id=os.getenv("ELEVENLABS_VOICE_ID"),
|
||||
)
|
||||
|
||||
messages = [{"role": "system",
|
||||
"content": "tell the user a joke about llamas"}]
|
||||
|
||||
# Start a task to run the LLM to create a joke, and convert the LLM
|
||||
# output to audio frames. This task will run in parallel with generating
|
||||
# and speaking the audio for static text, so there's no delay to speak
|
||||
# the LLM response.
|
||||
llm_pipeline = Pipeline([llm, elevenlabs_tts])
|
||||
llm_task = PipelineTask(llm_pipeline)
|
||||
await llm_task.queue_frames([LLMMessagesFrame(messages), EndPipeFrame()])
|
||||
|
||||
simple_tts_pipeline = Pipeline([azure_tts])
|
||||
await simple_tts_pipeline.queue_frames(
|
||||
[
|
||||
TextFrame("My friend the LLM is going to tell a joke about llamas."),
|
||||
EndPipeFrame(),
|
||||
]
|
||||
)
|
||||
|
||||
merge_pipeline = SequentialMergePipeline(
|
||||
[simple_tts_pipeline, llm_pipeline])
|
||||
|
||||
await asyncio.gather(
|
||||
transport.run(merge_pipeline),
|
||||
simple_tts_pipeline.run_pipeline(),
|
||||
llm_pipeline.run_pipeline(),
|
||||
)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
(url, token) = configure()
|
||||
asyncio.run(main(url))
|
||||
@@ -1,101 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import asyncio
|
||||
import os
|
||||
import sys
|
||||
|
||||
import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.daily import configure
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.services.daily import DailyLogLevel, DailyParams, DailyTransport
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
logger.remove(0)
|
||||
logger.add(sys.stderr, level="DEBUG")
|
||||
|
||||
|
||||
async def main():
|
||||
async with aiohttp.ClientSession() as session:
|
||||
(room_url, token) = await configure(session)
|
||||
|
||||
transport = DailyTransport(
|
||||
room_url,
|
||||
token,
|
||||
"Respond bot",
|
||||
DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
transcription_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
)
|
||||
transport.set_log_level(DailyLogLevel.Info)
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
)
|
||||
|
||||
@transport.event_handler("on_first_participant_joined")
|
||||
async def on_first_participant_joined(transport, participant):
|
||||
await transport.capture_participant_transcription(participant["id"])
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_participant_left")
|
||||
async def on_participant_left(transport, participant, reason):
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner()
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(main())
|
||||
@@ -1,135 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import asyncio
|
||||
import json
|
||||
import os
|
||||
import sys
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.frames.frames import (
|
||||
BotInterruptionFrame,
|
||||
TextFrame,
|
||||
TranscriptionFrame,
|
||||
UserStartedSpeakingFrame,
|
||||
UserStoppedSpeakingFrame,
|
||||
)
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.livekit import configure
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.services.livekit import LiveKitParams, LiveKitTransport
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
logger.remove(0)
|
||||
logger.add(sys.stderr, level="DEBUG")
|
||||
|
||||
|
||||
async def main():
|
||||
(url, token, room_name) = await configure()
|
||||
|
||||
transport = LiveKitTransport(
|
||||
url=url,
|
||||
token=token,
|
||||
room_name=room_name,
|
||||
params=LiveKitParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
)
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. "
|
||||
"Your goal is to demonstrate your capabilities in a succinct way. "
|
||||
"Your output will be converted to audio so don't include special characters in your answers. "
|
||||
"Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt,
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
)
|
||||
|
||||
# Register an event handler so we can play the audio when the
|
||||
# participant joins.
|
||||
@transport.event_handler("on_first_participant_joined")
|
||||
async def on_first_participant_joined(transport, participant_id):
|
||||
await asyncio.sleep(1)
|
||||
await task.queue_frame(
|
||||
TextFrame(
|
||||
"Hello there! How are you doing today? Would you like to talk about the weather?"
|
||||
)
|
||||
)
|
||||
|
||||
# Register an event handler to receive data from the participant via text chat
|
||||
# in the LiveKit room. This will be used to as transcription frames and
|
||||
# interrupt the bot and pass it to llm for processing and
|
||||
# then pass back to the participant as audio output.
|
||||
@transport.event_handler("on_data_received")
|
||||
async def on_data_received(transport, data, participant_id):
|
||||
logger.info(f"Received data from participant {participant_id}: {data}")
|
||||
# convert data from bytes to string
|
||||
json_data = json.loads(data)
|
||||
|
||||
await task.queue_frames(
|
||||
[
|
||||
BotInterruptionFrame(),
|
||||
UserStartedSpeakingFrame(),
|
||||
TranscriptionFrame(
|
||||
user_id=participant_id,
|
||||
timestamp=json_data["timestamp"],
|
||||
text=json_data["message"],
|
||||
),
|
||||
UserStoppedSpeakingFrame(),
|
||||
],
|
||||
)
|
||||
|
||||
runner = PipelineRunner()
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(main())
|
||||
@@ -1,45 +1,51 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
# Copyright (c) 2024, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import asyncio
|
||||
import aiohttp
|
||||
import os
|
||||
import sys
|
||||
|
||||
from dataclasses import dataclass
|
||||
|
||||
import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.frames.frames import (
|
||||
DataFrame,
|
||||
AppFrame,
|
||||
EndFrame,
|
||||
Frame,
|
||||
ImageRawFrame,
|
||||
LLMFullResponseStartFrame,
|
||||
TextFrame,
|
||||
LLMMessagesFrame,
|
||||
TextFrame
|
||||
)
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.sync_parallel_pipeline import SyncParallelPipeline
|
||||
from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.processors.aggregators.openai_llm_context import (
|
||||
OpenAILLMContext,
|
||||
OpenAILLMContextFrame,
|
||||
)
|
||||
from pipecat.processors.aggregators.sentence import SentenceAggregator
|
||||
from pipecat.pipeline.parallel_task import ParallelTask
|
||||
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaHttpTTSService
|
||||
from pipecat.services.fal.image import FalImageGenService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
from pipecat.processors.aggregators.gated import GatedAggregator
|
||||
from pipecat.processors.aggregators.llm_response import LLMFullResponseAggregator
|
||||
from pipecat.processors.aggregators.sentence import SentenceAggregator
|
||||
from pipecat.services.openai import OpenAILLMService
|
||||
from pipecat.services.elevenlabs import ElevenLabsTTSService
|
||||
from pipecat.services.fal import FalImageGenService
|
||||
from pipecat.transports.services.daily import DailyParams, DailyTransport
|
||||
|
||||
from runner import configure
|
||||
|
||||
from loguru import logger
|
||||
|
||||
from dotenv import load_dotenv
|
||||
load_dotenv(override=True)
|
||||
|
||||
logger.remove(0)
|
||||
logger.add(sys.stderr, level="DEBUG")
|
||||
|
||||
|
||||
@dataclass
|
||||
class MonthFrame(DataFrame):
|
||||
class MonthFrame(AppFrame):
|
||||
month: str
|
||||
|
||||
def __str__(self):
|
||||
@@ -67,72 +73,58 @@ class MonthPrepender(FrameProcessor):
|
||||
await self.push_frame(frame, direction)
|
||||
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_out_enabled=True,
|
||||
video_out_enabled=True,
|
||||
video_out_width=1024,
|
||||
video_out_height=1024,
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_out_enabled=True,
|
||||
video_out_enabled=True,
|
||||
video_out_width=1024,
|
||||
video_out_height=1024,
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
"""Run the Calendar Month Narration bot using WebRTC transport.
|
||||
|
||||
Args:
|
||||
webrtc_connection: The WebRTC connection to use
|
||||
room_name: Optional room name for display purposes
|
||||
"""
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
# Create an HTTP session for API calls
|
||||
async def main(room_url):
|
||||
async with aiohttp.ClientSession() as session:
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
|
||||
tts = CartesiaHttpTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
transport = DailyTransport(
|
||||
room_url,
|
||||
None,
|
||||
"Month Narration Bot",
|
||||
DailyParams(
|
||||
audio_out_enabled=True,
|
||||
camera_out_enabled=True,
|
||||
camera_out_width=1024,
|
||||
camera_out_height=1024
|
||||
)
|
||||
)
|
||||
|
||||
tts = ElevenLabsTTSService(
|
||||
aiohttp_session=session,
|
||||
api_key=os.getenv("ELEVENLABS_API_KEY"),
|
||||
voice_id=os.getenv("ELEVENLABS_VOICE_ID"),
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
model="gpt-4o")
|
||||
|
||||
imagegen = FalImageGenService(
|
||||
params=FalImageGenService.InputParams(image_size="square_hd"),
|
||||
params=FalImageGenService.InputParams(
|
||||
image_size="square_hd"
|
||||
),
|
||||
aiohttp_session=session,
|
||||
key=os.getenv("FAL_KEY"),
|
||||
)
|
||||
|
||||
gated_aggregator = GatedAggregator(
|
||||
gate_open_fn=lambda frame: isinstance(frame, ImageRawFrame),
|
||||
gate_close_fn=lambda frame: isinstance(frame, LLMFullResponseStartFrame),
|
||||
start_open=False
|
||||
)
|
||||
|
||||
sentence_aggregator = SentenceAggregator()
|
||||
month_prepender = MonthPrepender()
|
||||
llm_full_response_aggregator = LLMFullResponseAggregator()
|
||||
|
||||
# With `SyncParallelPipeline` we synchronize audio and images by pushing
|
||||
# them basically in order (e.g. I1 A1 A1 A1 I2 A2 A2 A2 A2 I3 A3). To do
|
||||
# that, each pipeline runs concurrently and `SyncParallelPipeline` will
|
||||
# wait for the input frame to be processed.
|
||||
#
|
||||
# Note that `SyncParallelPipeline` requires the last processor in each
|
||||
# of the pipelines to be synchronous. In this case, we use
|
||||
# `CartesiaHttpTTSService` and `FalImageGenService` which make HTTP
|
||||
# requests and wait for the response.
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
llm, # LLM
|
||||
sentence_aggregator, # Aggregates LLM output into full sentences
|
||||
SyncParallelPipeline( # Run pipelines in parallel aggregating the result
|
||||
[month_prepender, tts], # Create "Month: sentence" and output audio
|
||||
[imagegen], # Generate image
|
||||
),
|
||||
transport.output(), # Transport output
|
||||
]
|
||||
)
|
||||
pipeline = Pipeline([
|
||||
llm, # LLM
|
||||
sentence_aggregator, # Aggregates LLM output into full sentences
|
||||
ParallelTask( # Run pipelines in parallel aggregating the result
|
||||
[month_prepender, tts], # Create "Month: sentence" and output audio
|
||||
[llm_full_response_aggregator, imagegen] # Aggregate full LLM response
|
||||
),
|
||||
gated_aggregator, # Queues everything until an image is available
|
||||
transport.output() # Transport output
|
||||
])
|
||||
|
||||
frames = []
|
||||
for month in [
|
||||
@@ -156,37 +148,19 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
}
|
||||
]
|
||||
frames.append(MonthFrame(month=month))
|
||||
frames.append(OpenAILLMContextFrame(OpenAILLMContext(messages)))
|
||||
frames.append(LLMMessagesFrame(messages))
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
frames.append(EndFrame())
|
||||
|
||||
# Set up transport event handlers
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Start the month narration once connected
|
||||
await task.queue_frames(frames)
|
||||
runner = PipelineRunner()
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
task = PipelineTask(pipeline)
|
||||
|
||||
await task.queue_frames(frames)
|
||||
|
||||
# Run the pipeline
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
(url, token) = configure()
|
||||
asyncio.run(main(url))
|
||||
|
||||
@@ -1,39 +1,32 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
# Copyright (c) 2024, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import aiohttp
|
||||
import asyncio
|
||||
import os
|
||||
import sys
|
||||
|
||||
import tkinter as tk
|
||||
|
||||
import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.frames.frames import (
|
||||
Frame,
|
||||
OutputAudioRawFrame,
|
||||
TextFrame,
|
||||
TTSAudioRawFrame,
|
||||
URLImageRawFrame,
|
||||
)
|
||||
from pipecat.frames.frames import AudioRawFrame, Frame, URLImageRawFrame, LLMMessagesFrame, TextFrame
|
||||
from pipecat.pipeline.parallel_pipeline import ParallelPipeline
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.sync_parallel_pipeline import SyncParallelPipeline
|
||||
from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.processors.aggregators.openai_llm_context import (
|
||||
OpenAILLMContext,
|
||||
OpenAILLMContextFrame,
|
||||
)
|
||||
from pipecat.processors.aggregators.sentence import SentenceAggregator
|
||||
from pipecat.processors.aggregators.llm_response import LLMFullResponseAggregator
|
||||
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
|
||||
from pipecat.services.cartesia.tts import CartesiaHttpTTSService
|
||||
from pipecat.services.fal.image import FalImageGenService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.local.tk import TkLocalTransport, TkTransportParams
|
||||
from pipecat.services.openai import OpenAILLMService
|
||||
from pipecat.services.elevenlabs import ElevenLabsTTSService
|
||||
from pipecat.services.fal import FalImageGenService
|
||||
from pipecat.transports.base_transport import TransportParams
|
||||
from pipecat.transports.local.tk import TkLocalTransport
|
||||
|
||||
from loguru import logger
|
||||
|
||||
from dotenv import load_dotenv
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -49,12 +42,7 @@ async def main():
|
||||
runner = PipelineRunner()
|
||||
|
||||
async def get_month_data(month):
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": f"Describe a nature photograph suitable for use in a calendar, for the month of {month}. Include only the image description with no preamble. Limit the description to one sentence, please.",
|
||||
}
|
||||
]
|
||||
messages = [{"role": "system", "content": f"Describe a nature photograph suitable for use in a calendar, for the month of {month}. Include only the image description with no preamble. Limit the description to one sentence, please.", }]
|
||||
|
||||
class ImageDescription(FrameProcessor):
|
||||
def __init__(self):
|
||||
@@ -72,17 +60,14 @@ async def main():
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
self.audio = bytearray()
|
||||
self.frame = None
|
||||
|
||||
async def process_frame(self, frame: Frame, direction: FrameDirection):
|
||||
await super().process_frame(frame, direction)
|
||||
|
||||
if isinstance(frame, TTSAudioRawFrame):
|
||||
if isinstance(frame, AudioRawFrame):
|
||||
self.audio.extend(frame.audio)
|
||||
self.frame = OutputAudioRawFrame(
|
||||
bytes(self.audio), frame.sample_rate, frame.num_channels
|
||||
)
|
||||
await self.push_frame(frame, direction)
|
||||
self.frame = AudioRawFrame(
|
||||
bytes(self.audio), frame.sample_rate, frame.num_channels)
|
||||
|
||||
class ImageGrabber(FrameProcessor):
|
||||
def __init__(self):
|
||||
@@ -94,22 +79,24 @@ async def main():
|
||||
|
||||
if isinstance(frame, URLImageRawFrame):
|
||||
self.frame = frame
|
||||
await self.push_frame(frame, direction)
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
model="gpt-4o")
|
||||
|
||||
tts = CartesiaHttpTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
tts = ElevenLabsTTSService(
|
||||
aiohttp_session=session,
|
||||
api_key=os.getenv("ELEVENLABS_API_KEY"),
|
||||
voice_id=os.getenv("ELEVENLABS_VOICE_ID"))
|
||||
|
||||
imagegen = FalImageGenService(
|
||||
params=FalImageGenService.InputParams(image_size="square_hd"),
|
||||
params=FalImageGenService.InputParams(
|
||||
image_size="square_hd"
|
||||
),
|
||||
aiohttp_session=session,
|
||||
key=os.getenv("FAL_KEY"),
|
||||
)
|
||||
key=os.getenv("FAL_KEY"))
|
||||
|
||||
sentence_aggregator = SentenceAggregator()
|
||||
aggregator = LLMFullResponseAggregator()
|
||||
|
||||
description = ImageDescription()
|
||||
|
||||
@@ -117,30 +104,16 @@ async def main():
|
||||
|
||||
image_grabber = ImageGrabber()
|
||||
|
||||
# With `SyncParallelPipeline` we synchronize audio and images by
|
||||
# pushing them basically in order (e.g. I1 A1 A1 A1 I2 A2 A2 A2 A2
|
||||
# I3 A3). To do that, each pipeline runs concurrently and
|
||||
# `SyncParallelPipeline` will wait for the input frame to be
|
||||
# processed.
|
||||
#
|
||||
# Note that `SyncParallelPipeline` requires the last processor in
|
||||
# each of the pipelines to be synchronous. In this case, we use
|
||||
# `CartesiaHttpTTSService` and `FalImageGenService` which make HTTP
|
||||
# requests and wait for the response.
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
llm, # LLM
|
||||
sentence_aggregator, # Aggregates LLM output into full sentences
|
||||
description, # Store sentence
|
||||
SyncParallelPipeline(
|
||||
[tts, audio_grabber], # Generate and store audio for the given sentence
|
||||
[imagegen, image_grabber], # Generate and storeimage for the given sentence
|
||||
),
|
||||
]
|
||||
)
|
||||
pipeline = Pipeline([
|
||||
llm,
|
||||
aggregator,
|
||||
description,
|
||||
ParallelPipeline([tts, audio_grabber],
|
||||
[imagegen, image_grabber])
|
||||
])
|
||||
|
||||
task = PipelineTask(pipeline)
|
||||
await task.queue_frame(OpenAILLMContextFrame(OpenAILLMContext(messages)))
|
||||
await task.queue_frame(LLMMessagesFrame(messages))
|
||||
await task.stop_when_done()
|
||||
|
||||
await runner.run(task)
|
||||
@@ -154,23 +127,24 @@ async def main():
|
||||
|
||||
transport = TkLocalTransport(
|
||||
tk_root,
|
||||
TkTransportParams(
|
||||
TransportParams(
|
||||
audio_out_enabled=True,
|
||||
video_out_enabled=True,
|
||||
video_out_width=1024,
|
||||
video_out_height=1024,
|
||||
),
|
||||
)
|
||||
camera_out_enabled=True,
|
||||
camera_out_width=1024,
|
||||
camera_out_height=1024))
|
||||
|
||||
pipeline = Pipeline([transport.output()])
|
||||
|
||||
task = PipelineTask(pipeline)
|
||||
|
||||
# We only specify a few months as we create tasks all at once and we
|
||||
# might get rate limited otherwise.
|
||||
# We only specify 5 months as we create tasks all at once and we might
|
||||
# get rate limited otherwise.
|
||||
months: list[str] = [
|
||||
"January",
|
||||
"February",
|
||||
# "March",
|
||||
# "April",
|
||||
# "May",
|
||||
]
|
||||
|
||||
# We create one task per month. This will be executed concurrently.
|
||||
|
||||
@@ -1,150 +1,103 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
# Copyright (c) 2024, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import asyncio
|
||||
import aiohttp
|
||||
import os
|
||||
import sys
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.frames.frames import Frame, MetricsFrame
|
||||
from pipecat.metrics.metrics import (
|
||||
LLMUsageMetricsData,
|
||||
ProcessingMetricsData,
|
||||
TTFBMetricsData,
|
||||
TTSUsageMetricsData,
|
||||
)
|
||||
from pipecat.frames.frames import LLMMessagesFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.processors.aggregators.llm_response import (
|
||||
LLMAssistantResponseAggregator,
|
||||
LLMUserResponseAggregator,
|
||||
)
|
||||
from pipecat.processors.logger import FrameLogger
|
||||
from pipecat.services.elevenlabs import ElevenLabsTTSService
|
||||
from pipecat.services.openai import OpenAILLMService
|
||||
from pipecat.transports.services.daily import DailyParams, DailyTransport
|
||||
from pipecat.vad.silero import SileroVADAnalyzer
|
||||
|
||||
from runner import configure
|
||||
|
||||
from loguru import logger
|
||||
|
||||
from dotenv import load_dotenv
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
class MetricsLogger(FrameProcessor):
|
||||
async def process_frame(self, frame: Frame, direction: FrameDirection):
|
||||
await super().process_frame(frame, direction)
|
||||
|
||||
if isinstance(frame, MetricsFrame):
|
||||
for d in frame.data:
|
||||
if isinstance(d, TTFBMetricsData):
|
||||
print(f"!!! MetricsFrame: {frame}, ttfb: {d.value}")
|
||||
elif isinstance(d, ProcessingMetricsData):
|
||||
print(f"!!! MetricsFrame: {frame}, processing: {d.value}")
|
||||
elif isinstance(d, LLMUsageMetricsData):
|
||||
tokens = d.value
|
||||
print(
|
||||
f"!!! MetricsFrame: {frame}, tokens: {tokens.prompt_tokens}, characters: {tokens.completion_tokens}"
|
||||
)
|
||||
elif isinstance(d, TTSUsageMetricsData):
|
||||
print(f"!!! MetricsFrame: {frame}, characters: {d.value}")
|
||||
await self.push_frame(frame, direction)
|
||||
logger.remove(0)
|
||||
logger.add(sys.stderr, level="DEBUG")
|
||||
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
async def main(room_url: str, token):
|
||||
async with aiohttp.ClientSession() as session:
|
||||
transport = DailyTransport(
|
||||
room_url,
|
||||
token,
|
||||
"Respond bot",
|
||||
DailyParams(
|
||||
audio_out_enabled=True,
|
||||
transcription_enabled=True,
|
||||
vad_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer()
|
||||
)
|
||||
)
|
||||
|
||||
tts = ElevenLabsTTSService(
|
||||
aiohttp_session=session,
|
||||
api_key=os.getenv("ELEVENLABS_API_KEY"),
|
||||
voice_id=os.getenv("ELEVENLABS_VOICE_ID"),
|
||||
)
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
model="gpt-4o")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
fl = FrameLogger("!!! after LLM", "red")
|
||||
fltts = FrameLogger("@@@ out of tts", "green")
|
||||
flend = FrameLogger("### out of the end", "magenta")
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
|
||||
ml = MetricsLogger()
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(),
|
||||
stt,
|
||||
context_aggregator.user(),
|
||||
llm,
|
||||
tts,
|
||||
ml,
|
||||
transport.output(),
|
||||
context_aggregator.assistant(),
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
)
|
||||
tma_in = LLMUserResponseAggregator(messages)
|
||||
tma_out = LLMAssistantResponseAggregator(messages)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
pipeline = Pipeline([
|
||||
transport.input(),
|
||||
tma_in,
|
||||
llm,
|
||||
fl,
|
||||
tts,
|
||||
fltts,
|
||||
transport.output(),
|
||||
tma_out,
|
||||
flend
|
||||
])
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
task = PipelineTask(pipeline)
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
@transport.event_handler("on_first_participant_joined")
|
||||
async def on_first_participant_joined(transport, participant):
|
||||
transport.capture_participant_transcription(participant["id"])
|
||||
# Kick off the conversation.
|
||||
messages.append(
|
||||
{"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMMessagesFrame(messages)])
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
await runner.run(task)
|
||||
runner = PipelineRunner()
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
(url, token) = configure()
|
||||
asyncio.run(main(url, token))
|
||||
|
||||
@@ -1,37 +1,41 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
# Copyright (c) 2024, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import asyncio
|
||||
import aiohttp
|
||||
import os
|
||||
import sys
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
from PIL import Image
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.frames.frames import (
|
||||
BotStartedSpeakingFrame,
|
||||
BotStoppedSpeakingFrame,
|
||||
Frame,
|
||||
OutputImageRawFrame,
|
||||
)
|
||||
from pipecat.frames.frames import ImageRawFrame, Frame, SystemFrame, TextFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.processors.aggregators.llm_response import (
|
||||
LLMAssistantResponseAggregator,
|
||||
LLMUserResponseAggregator,
|
||||
)
|
||||
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
from pipecat.services.openai import OpenAILLMService
|
||||
from pipecat.services.elevenlabs import ElevenLabsTTSService
|
||||
from pipecat.transports.services.daily import DailyTransport
|
||||
from pipecat.vad.silero import SileroVADAnalyzer
|
||||
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
from runner import configure
|
||||
|
||||
from loguru import logger
|
||||
|
||||
from dotenv import load_dotenv
|
||||
load_dotenv(override=True)
|
||||
|
||||
logger.remove(0)
|
||||
logger.add(sys.stderr, level="DEBUG")
|
||||
|
||||
|
||||
class ImageSyncAggregator(FrameProcessor):
|
||||
def __init__(self, speaking_path: str, waiting_path: str):
|
||||
@@ -47,121 +51,78 @@ class ImageSyncAggregator(FrameProcessor):
|
||||
async def process_frame(self, frame: Frame, direction: FrameDirection):
|
||||
await super().process_frame(frame, direction)
|
||||
|
||||
if isinstance(frame, BotStartedSpeakingFrame):
|
||||
await self.push_frame(
|
||||
OutputImageRawFrame(
|
||||
image=self._speaking_image_bytes,
|
||||
size=(1024, 1024),
|
||||
format=self._speaking_image_format,
|
||||
)
|
||||
if not isinstance(frame, SystemFrame):
|
||||
await self.push_frame(ImageRawFrame(image=self._speaking_image_bytes, size=(1024, 1024), format=self._speaking_image_format))
|
||||
await self.push_frame(frame)
|
||||
await self.push_frame(ImageRawFrame(image=self._waiting_image_bytes, size=(1024, 1024), format=self._waiting_image_format))
|
||||
else:
|
||||
await self.push_frame(frame)
|
||||
|
||||
|
||||
async def main(room_url: str, token):
|
||||
async with aiohttp.ClientSession() as session:
|
||||
transport = DailyTransport(
|
||||
room_url,
|
||||
token,
|
||||
"Respond bot",
|
||||
DailyParams(
|
||||
audio_out_enabled=True,
|
||||
camera_out_width=1024,
|
||||
camera_out_height=1024,
|
||||
transcription_enabled=True,
|
||||
vad_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer()
|
||||
)
|
||||
)
|
||||
|
||||
elif isinstance(frame, BotStoppedSpeakingFrame):
|
||||
await self.push_frame(
|
||||
OutputImageRawFrame(
|
||||
image=self._waiting_image_bytes,
|
||||
size=(1024, 1024),
|
||||
format=self._waiting_image_format,
|
||||
)
|
||||
)
|
||||
tts = ElevenLabsTTSService(
|
||||
aiohttp_session=session,
|
||||
api_key=os.getenv("ELEVENLABS_API_KEY"),
|
||||
voice_id=os.getenv("ELEVENLABS_VOICE_ID"),
|
||||
)
|
||||
|
||||
await self.push_frame(frame)
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
model="gpt-4o")
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
video_out_enabled=True,
|
||||
video_out_width=1024,
|
||||
video_out_height=1024,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
video_out_enabled=True,
|
||||
video_out_width=1024,
|
||||
video_out_height=1024,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
tma_in = LLMUserResponseAggregator(messages)
|
||||
tma_out = LLMAssistantResponseAggregator(messages)
|
||||
|
||||
image_sync_aggregator = ImageSyncAggregator(
|
||||
os.path.join(os.path.dirname(__file__), "assets", "speaking.png"),
|
||||
os.path.join(os.path.dirname(__file__), "assets", "waiting.png"),
|
||||
)
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
image_sync_aggregator = ImageSyncAggregator(
|
||||
os.path.join(os.path.dirname(__file__), "assets", "speaking.png"),
|
||||
os.path.join(os.path.dirname(__file__), "assets", "waiting.png"),
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
pipeline = Pipeline([
|
||||
transport.input(),
|
||||
stt,
|
||||
context_aggregator.user(),
|
||||
image_sync_aggregator,
|
||||
tma_in,
|
||||
llm,
|
||||
tts,
|
||||
image_sync_aggregator,
|
||||
transport.output(),
|
||||
context_aggregator.assistant(),
|
||||
]
|
||||
)
|
||||
tma_out
|
||||
])
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
task = PipelineTask(pipeline)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
@transport.event_handler("on_first_participant_joined")
|
||||
async def on_first_participant_joined(transport, participant):
|
||||
participant_name = participant["info"]["userName"] or ''
|
||||
transport.capture_participant_transcription(participant["id"])
|
||||
await task.queue_frames([TextFrame(f"Hi, this is {participant_name}.")])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
runner = PipelineRunner()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
(url, token) = configure()
|
||||
asyncio.run(main(url, token))
|
||||
|
||||
@@ -1,120 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaHttpTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaHttpTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt,
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
@@ -1,119 +1,98 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
# Copyright (c) 2024, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import asyncio
|
||||
import aiohttp
|
||||
import os
|
||||
import sys
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.frames.frames import LLMMessagesFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
from pipecat.processors.aggregators.llm_response import (
|
||||
LLMAssistantResponseAggregator, LLMUserResponseAggregator)
|
||||
from pipecat.services.elevenlabs import ElevenLabsTTSService
|
||||
from pipecat.services.openai import OpenAILLMService
|
||||
from pipecat.transports.services.daily import DailyParams, DailyTransport
|
||||
from pipecat.vad.silero import SileroVADAnalyzer
|
||||
|
||||
from runner import configure
|
||||
|
||||
from loguru import logger
|
||||
|
||||
from dotenv import load_dotenv
|
||||
load_dotenv(override=True)
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
logger.remove(0)
|
||||
logger.add(sys.stderr, level="DEBUG")
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
async def main(room_url: str, token):
|
||||
async with aiohttp.ClientSession() as session:
|
||||
transport = DailyTransport(
|
||||
room_url,
|
||||
token,
|
||||
"Respond bot",
|
||||
DailyParams(
|
||||
audio_out_enabled=True,
|
||||
transcription_enabled=True,
|
||||
vad_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer()
|
||||
)
|
||||
)
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
tts = ElevenLabsTTSService(
|
||||
aiohttp_session=session,
|
||||
api_key=os.getenv("ELEVENLABS_API_KEY"),
|
||||
voice_id=os.getenv("ELEVENLABS_VOICE_ID"),
|
||||
)
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
model="gpt-4o")
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt,
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
tma_in = LLMUserResponseAggregator(messages)
|
||||
tma_out = LLMAssistantResponseAggregator(messages)
|
||||
|
||||
pipeline = Pipeline([
|
||||
transport.input(), # Transport user input
|
||||
tma_in, # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
tma_out # Assistant spoken responses
|
||||
])
|
||||
|
||||
task = PipelineTask(pipeline, PipelineParams(
|
||||
allow_interruptions=True,
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
report_only_initial_ttfb=True,
|
||||
))
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
@transport.event_handler("on_first_participant_joined")
|
||||
async def on_first_participant_joined(transport, participant):
|
||||
transport.capture_participant_transcription(participant["id"])
|
||||
# Kick off the conversation.
|
||||
messages.append(
|
||||
{"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMMessagesFrame(messages)])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
runner = PipelineRunner()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
(url, token) = configure()
|
||||
asyncio.run(main(url, token))
|
||||
|
||||
95
examples/foundational/07a-interruptible-anthropic.py
Normal file
95
examples/foundational/07a-interruptible-anthropic.py
Normal file
@@ -0,0 +1,95 @@
|
||||
#
|
||||
# Copyright (c) 2024, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import asyncio
|
||||
import aiohttp
|
||||
import os
|
||||
import sys
|
||||
|
||||
from pipecat.frames.frames import LLMMessagesFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_response import (
|
||||
LLMAssistantResponseAggregator, LLMUserResponseAggregator)
|
||||
from pipecat.services.elevenlabs import ElevenLabsTTSService
|
||||
from pipecat.services.anthropic import AnthropicLLMService
|
||||
from pipecat.transports.services.daily import DailyParams, DailyTransport
|
||||
from pipecat.vad.silero import SileroVADAnalyzer
|
||||
|
||||
from runner import configure
|
||||
|
||||
from loguru import logger
|
||||
|
||||
from dotenv import load_dotenv
|
||||
load_dotenv(override=True)
|
||||
|
||||
logger.remove(0)
|
||||
logger.add(sys.stderr, level="DEBUG")
|
||||
|
||||
|
||||
async def main(room_url: str, token):
|
||||
async with aiohttp.ClientSession() as session:
|
||||
transport = DailyTransport(
|
||||
room_url,
|
||||
token,
|
||||
"Respond bot",
|
||||
DailyParams(
|
||||
audio_out_enabled=True,
|
||||
transcription_enabled=True,
|
||||
vad_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer()
|
||||
)
|
||||
)
|
||||
|
||||
tts = ElevenLabsTTSService(
|
||||
aiohttp_session=session,
|
||||
api_key=os.getenv("ELEVENLABS_API_KEY"),
|
||||
voice_id=os.getenv("ELEVENLABS_VOICE_ID"),
|
||||
)
|
||||
|
||||
llm = AnthropicLLMService(
|
||||
api_key=os.getenv("ANTHROPIC_API_KEY"),
|
||||
model="claude-3-opus-20240229")
|
||||
|
||||
# todo: think more about how to handle system prompts in a more general way. OpenAI,
|
||||
# Google, and Anthropic all have slightly different approaches to providing a system
|
||||
# prompt.
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative, helpful, and brief way. Say hello.",
|
||||
},
|
||||
]
|
||||
|
||||
tma_in = LLMUserResponseAggregator(messages)
|
||||
tma_out = LLMAssistantResponseAggregator(messages)
|
||||
|
||||
pipeline = Pipeline([
|
||||
transport.input(), # Transport user input
|
||||
tma_in, # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
tma_out # Assistant spoken responses
|
||||
])
|
||||
|
||||
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
|
||||
|
||||
@transport.event_handler("on_first_participant_joined")
|
||||
async def on_first_participant_joined(transport, participant):
|
||||
transport.capture_participant_transcription(participant["id"])
|
||||
# Kick off the conversation.
|
||||
await task.queue_frames([LLMMessagesFrame(messages)])
|
||||
|
||||
runner = PipelineRunner()
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
(url, token) = configure()
|
||||
asyncio.run(main(url, token))
|
||||
@@ -1,178 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_response import (
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.elevenlabs.tts import ElevenLabsTTSService
|
||||
from pipecat.services.openai.base_llm import BaseOpenAILLMService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.services.speechmatics.stt import SpeechmaticsSTTService
|
||||
from pipecat.transcriptions.language import Language
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
"""Speechmatics STT Service Example
|
||||
|
||||
This example demonstrates using Speechmatics Speech-to-Text service with speaker diarization and intelligent speaker management. Key features:
|
||||
|
||||
1. Speaker Diarization
|
||||
- Automatically identifies and distinguishes between different speakers
|
||||
- First speaker is identified as 'S1', others get subsequent IDs
|
||||
- Uses `enable_diarization` parameter to manage speaker detection
|
||||
|
||||
2. Smart Speaker Control
|
||||
- `focus_speakers` parameter lets you target specific speakers (e.g. ["S1"])
|
||||
- Other speakers will be wrapped in PASSIVE tags
|
||||
- Only processes speech from focused speakers
|
||||
- Words from all speakers are wrapped with XML tags for clear speaker identification
|
||||
- Other speakers' speech only sent when focused speaker is active
|
||||
|
||||
3. Voice Activity Detection
|
||||
- Built-in VAD using `enable_vad` parameter
|
||||
- Remove `vad_analyzer` from `transport` config to use module's VAD
|
||||
- Emits speaker started/stopped events
|
||||
|
||||
4. Configuration Options
|
||||
- `operating_point` parameter defaults to `ENHANCED` for optimal accuracy
|
||||
- Configurable `end_of_utterance_silence_trigger` (default 0.5s)
|
||||
- Customizable speaker formatting
|
||||
- Additional diarization settings available
|
||||
|
||||
For detailed information about operating points and configuration:
|
||||
https://docs.speechmatics.com/rt-api-ref
|
||||
"""
|
||||
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = SpeechmaticsSTTService(
|
||||
api_key=os.getenv("SPEECHMATICS_API_KEY"),
|
||||
params=SpeechmaticsSTTService.InputParams(
|
||||
language=Language.EN,
|
||||
enable_vad=True,
|
||||
enable_diarization=True,
|
||||
focus_speakers=["S1"],
|
||||
end_of_utterance_silence_trigger=0.5,
|
||||
speaker_active_format="<{speaker_id}>{text}</{speaker_id}>",
|
||||
speaker_passive_format="<PASSIVE><{speaker_id}>{text}</{speaker_id}></PASSIVE>",
|
||||
),
|
||||
)
|
||||
|
||||
tts = ElevenLabsTTSService(
|
||||
api_key=os.getenv("ELEVENLABS_API_KEY"),
|
||||
voice_id=os.getenv("ELEVENLABS_VOICE_ID"),
|
||||
model="eleven_turbo_v2_5",
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
params=BaseOpenAILLMService.InputParams(temperature=0.75),
|
||||
)
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": (
|
||||
"You are a helpful British assistant called Alfred. "
|
||||
"Your goal is to demonstrate your capabilities in a succinct way. "
|
||||
"Your output will be converted to audio so don't include special characters in your answers. "
|
||||
"Always include punctuation in your responses. "
|
||||
"Give very short replies - do not give longer replies unless strictly necessary. "
|
||||
"Respond to what the user said in a concise, funny, creative and helpful way. "
|
||||
"Use `<Sn/>` tags to identify different speakers - do not use tags in your replies. "
|
||||
"Do not respond to speakers within `<PASSIVE/>` tags unless explicitly asked to. "
|
||||
),
|
||||
},
|
||||
]
|
||||
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(aggregation_timeout=0.005),
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt,
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Say a short hello to the user."})
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
@@ -1,161 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_response import (
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.elevenlabs.tts import ElevenLabsTTSService
|
||||
from pipecat.services.openai.base_llm import BaseOpenAILLMService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.services.speechmatics.stt import SpeechmaticsSTTService
|
||||
from pipecat.transcriptions.language import Language
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
"""Run example using Speechmatics STT.
|
||||
|
||||
This example will use diarization within our STT service and output the words spoken by
|
||||
each individual speaker and wrap them with XML tags for the LLM to process. Note the
|
||||
instructions in the system context for the LLM. This greatly improves the conversation
|
||||
experience by allowing the LLM to understand who is speaking in a multi-party call.
|
||||
|
||||
By default, this example will use our ENHANCED operating point, which is optimized for
|
||||
high accuracy. You can change this by setting the `operating_point` parameter to a different
|
||||
value.
|
||||
|
||||
For more information on operating points, see the Speechmatics documentation:
|
||||
https://docs.speechmatics.com/rt-api-ref
|
||||
"""
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = SpeechmaticsSTTService(
|
||||
api_key=os.getenv("SPEECHMATICS_API_KEY"),
|
||||
params=SpeechmaticsSTTService.InputParams(
|
||||
language=Language.EN,
|
||||
enable_diarization=True,
|
||||
end_of_utterance_silence_trigger=0.5,
|
||||
speaker_active_format="<{speaker_id}>{text}</{speaker_id}>",
|
||||
),
|
||||
)
|
||||
|
||||
tts = ElevenLabsTTSService(
|
||||
api_key=os.getenv("ELEVENLABS_API_KEY"),
|
||||
voice_id=os.getenv("ELEVENLABS_VOICE_ID"),
|
||||
model="eleven_turbo_v2_5",
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
params=BaseOpenAILLMService.InputParams(temperature=0.75),
|
||||
)
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": (
|
||||
"You are a helpful British assistant called Alfred. "
|
||||
"Your goal is to demonstrate your capabilities in a succinct way. "
|
||||
"Your output will be converted to audio so don't include special characters in your answers. "
|
||||
"Always include punctuation in your responses. "
|
||||
"Give very short replies - do not give longer replies unless strictly necessary. "
|
||||
"Respond to what the user said in a concise, funny, creative and helpful way. "
|
||||
"Use `<Sn/>` tags to identify different speakers - do not use tags in your replies."
|
||||
),
|
||||
},
|
||||
]
|
||||
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(aggregation_timeout=0.005),
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Say a short hello to the user."})
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
@@ -1,118 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.services.soniox.stt import SonioxSTTService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = SonioxSTTService(
|
||||
api_key=os.getenv("SONIOX_API_KEY"),
|
||||
)
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt,
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
@@ -1,133 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
import os
|
||||
|
||||
import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.inworld.tts import InworldTTSService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
# Create an HTTP session
|
||||
async with aiohttp.ClientSession() as session:
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
# Inworld TTS Service - Unified streaming and non-streaming
|
||||
# Set streaming=True for real-time audio, streaming=False for complete audio generation
|
||||
streaming = True # Toggle this to switch between modes
|
||||
|
||||
tts = InworldTTSService(
|
||||
api_key=os.getenv("INWORLD_API_KEY", ""),
|
||||
aiohttp_session=session,
|
||||
voice_id="Ashley",
|
||||
model="inworld-tts-1",
|
||||
streaming=streaming, # True: real-time chunks, False: complete audio then playback
|
||||
params=InworldTTSService.InputParams(
|
||||
temperature=0.8,
|
||||
),
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are very knowledgable about dogs. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
@@ -1,125 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
import os
|
||||
|
||||
import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.asyncai.tts import AsyncAIHttpTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
# Create an HTTP session
|
||||
async with aiohttp.ClientSession() as session:
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = AsyncAIHttpTTSService(
|
||||
api_key=os.getenv("ASYNCAI_API_KEY", ""),
|
||||
voice_id=os.getenv("ASYNCAI_VOICE_ID", "e0f39dc4-f691-4e78-bba5-5c636692cc04"),
|
||||
aiohttp_session=session,
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt,
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
@@ -1,121 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.asyncai.tts import AsyncAITTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = AsyncAITTSService(
|
||||
api_key=os.getenv("ASYNCAI_API_KEY", ""),
|
||||
voice_id=os.getenv("ASYNCAI_VOICE_ID", "e0f39dc4-f691-4e78-bba5-5c636692cc04"),
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt,
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
@@ -1,44 +1,43 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
# Copyright (c) 2024, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
import asyncio
|
||||
import os
|
||||
import sys
|
||||
|
||||
import aiohttp
|
||||
|
||||
from pipecat.frames.frames import LLMMessagesFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_response import (
|
||||
LLMAssistantResponseAggregator, LLMUserResponseAggregator)
|
||||
from pipecat.processors.frameworks.langchain import LangchainProcessor
|
||||
from pipecat.services.elevenlabs import ElevenLabsTTSService
|
||||
from pipecat.transports.services.daily import DailyParams, DailyTransport
|
||||
from pipecat.vad.silero import SileroVADAnalyzer
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder
|
||||
from langchain_community.chat_message_histories import ChatMessageHistory
|
||||
from langchain_core.chat_history import BaseChatMessageHistory
|
||||
from langchain_core.runnables.history import RunnableWithMessageHistory
|
||||
from langchain_openai import ChatOpenAI
|
||||
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.frames.frames import LLMMessagesUpdateFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_response import (
|
||||
LLMAssistantContextAggregator,
|
||||
LLMUserContextAggregator,
|
||||
)
|
||||
from pipecat.processors.aggregators.openai_llm_context import (
|
||||
OpenAILLMContext,
|
||||
)
|
||||
from pipecat.processors.frameworks.langchain import LangchainProcessor
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
from runner import configure
|
||||
|
||||
from dotenv import load_dotenv
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
logger.remove(0)
|
||||
logger.add(sys.stderr, level="DEBUG")
|
||||
|
||||
message_store = {}
|
||||
|
||||
|
||||
@@ -48,110 +47,79 @@ def get_session_history(session_id: str) -> BaseChatMessageHistory:
|
||||
return message_store[session_id]
|
||||
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
|
||||
prompt = ChatPromptTemplate.from_messages(
|
||||
[
|
||||
(
|
||||
"system",
|
||||
"Be nice and helpful. Answer very briefly and without special characters like `#` or `*`. "
|
||||
"Your response will be synthesized to voice and those characters will create unnatural sounds.",
|
||||
async def main(room_url: str, token):
|
||||
async with aiohttp.ClientSession() as session:
|
||||
transport = DailyTransport(
|
||||
room_url,
|
||||
token,
|
||||
"Respond bot",
|
||||
DailyParams(
|
||||
audio_out_enabled=True,
|
||||
transcription_enabled=True,
|
||||
vad_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
MessagesPlaceholder("chat_history"),
|
||||
("human", "{input}"),
|
||||
]
|
||||
)
|
||||
chain = prompt | ChatOpenAI(model="gpt-4.1", temperature=0.7)
|
||||
history_chain = RunnableWithMessageHistory(
|
||||
chain,
|
||||
get_session_history,
|
||||
history_messages_key="chat_history",
|
||||
input_messages_key="input",
|
||||
)
|
||||
lc = LangchainProcessor(history_chain)
|
||||
)
|
||||
|
||||
context = OpenAILLMContext()
|
||||
tma_in = LLMUserContextAggregator(context=context)
|
||||
tma_out = LLMAssistantContextAggregator(context=context)
|
||||
tts = ElevenLabsTTSService(
|
||||
aiohttp_session=session,
|
||||
api_key=os.getenv("ELEVENLABS_API_KEY"),
|
||||
voice_id=os.getenv("ELEVENLABS_VOICE_ID"),
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt,
|
||||
tma_in, # User responses
|
||||
lc, # Langchain
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
tma_out, # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
prompt = ChatPromptTemplate.from_messages(
|
||||
[
|
||||
("system",
|
||||
"Be nice and helpful. Answer very briefly and without special characters like `#` or `*`. "
|
||||
"Your response will be synthesized to voice and those characters will create unnatural sounds.",
|
||||
),
|
||||
MessagesPlaceholder("chat_history"),
|
||||
("human", "{input}"),
|
||||
])
|
||||
chain = prompt | ChatOpenAI(model="gpt-4o", temperature=0.7)
|
||||
history_chain = RunnableWithMessageHistory(
|
||||
chain,
|
||||
get_session_history,
|
||||
history_messages_key="chat_history",
|
||||
input_messages_key="input")
|
||||
lc = LangchainProcessor(history_chain)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
tma_in = LLMUserResponseAggregator()
|
||||
tma_out = LLMAssistantResponseAggregator()
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
# An `OpenAILLMContextFrame` will be picked up by the LangchainProcessor using
|
||||
# only the content of the last message to inject it in the prompt defined
|
||||
# above. So no role is required here.
|
||||
messages = [({"content": "Please briefly introduce yourself to the user."})]
|
||||
await task.queue_frames([LLMMessagesUpdateFrame(messages, run_llm=True)])
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
tma_in, # User responses
|
||||
lc, # Langchain
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
tma_out, # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
@transport.event_handler("on_first_participant_joined")
|
||||
async def on_first_participant_joined(transport, participant):
|
||||
transport.capture_participant_transcription(participant["id"])
|
||||
lc.set_participant_id(participant["id"])
|
||||
# Kick off the conversation.
|
||||
# the `LLMMessagesFrame` will be picked up by the LangchainProcessor using
|
||||
# only the content of the last message to inject it in the prompt defined
|
||||
# above. So no role is required here.
|
||||
messages = [(
|
||||
{
|
||||
"content": "Please briefly introduce yourself to the user."
|
||||
}
|
||||
)]
|
||||
await task.queue_frames([LLMMessagesFrame(messages)])
|
||||
|
||||
await runner.run(task)
|
||||
runner = PipelineRunner()
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
(url, token) = configure()
|
||||
asyncio.run(main(url, token))
|
||||
|
||||
@@ -1,132 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
import os
|
||||
|
||||
from deepgram import LiveOptions
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.frames.frames import (
|
||||
BotInterruptionFrame,
|
||||
StopInterruptionFrame,
|
||||
UserStartedSpeakingFrame,
|
||||
UserStoppedSpeakingFrame,
|
||||
)
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.deepgram.tts import DeepgramTTSService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(
|
||||
api_key=os.getenv("DEEPGRAM_API_KEY"),
|
||||
live_options=LiveOptions(vad_events=True, utterance_end_ms="1000"),
|
||||
)
|
||||
|
||||
tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-2-andromeda-en")
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@stt.event_handler("on_speech_started")
|
||||
async def on_speech_started(stt, *args, **kwargs):
|
||||
await task.queue_frames([BotInterruptionFrame(), UserStartedSpeakingFrame()])
|
||||
|
||||
@stt.event_handler("on_utterance_end")
|
||||
async def on_utterance_end(stt, *args, **kwargs):
|
||||
await task.queue_frames([StopInterruptionFrame(), UserStoppedSpeakingFrame()])
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
@@ -1,118 +1,97 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
# Copyright (c) 2024, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
import asyncio
|
||||
import aiohttp
|
||||
import os
|
||||
import sys
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.frames.frames import LLMMessagesFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.deepgram.tts import DeepgramTTSService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
from pipecat.processors.aggregators.llm_response import (
|
||||
LLMAssistantResponseAggregator, LLMUserResponseAggregator)
|
||||
from pipecat.services.deepgram import DeepgramSTTService, DeepgramTTSService
|
||||
from pipecat.services.openai import OpenAILLMService
|
||||
from pipecat.transports.services.daily import DailyParams, DailyTransport
|
||||
from pipecat.vad.silero import SileroVADAnalyzer
|
||||
|
||||
from runner import configure
|
||||
|
||||
from loguru import logger
|
||||
|
||||
from dotenv import load_dotenv
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
logger.remove(0)
|
||||
logger.add(sys.stderr, level="DEBUG")
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
async def main(room_url: str, token):
|
||||
async with aiohttp.ClientSession() as session:
|
||||
transport = DailyTransport(
|
||||
room_url,
|
||||
token,
|
||||
"Respond bot",
|
||||
DailyParams(
|
||||
audio_out_enabled=True,
|
||||
vad_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
vad_audio_passthrough=True
|
||||
)
|
||||
)
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-2-andromeda-en")
|
||||
tts = DeepgramTTSService(
|
||||
aiohttp_session=session,
|
||||
api_key=os.getenv("DEEPGRAM_API_KEY"),
|
||||
voice="aura-helios-en"
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
model="gpt-4o")
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
tma_in = LLMUserResponseAggregator(messages)
|
||||
tma_out = LLMAssistantResponseAggregator(messages)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
pipeline = Pipeline([
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
tma_in, # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
tma_out # Assistant spoken responses
|
||||
])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
@transport.event_handler("on_first_participant_joined")
|
||||
async def on_first_participant_joined(transport, participant):
|
||||
transport.capture_participant_transcription(participant["id"])
|
||||
# Kick off the conversation.
|
||||
messages.append(
|
||||
{"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMMessagesFrame(messages)])
|
||||
|
||||
await runner.run(task)
|
||||
runner = PipelineRunner()
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
(url, token) = configure()
|
||||
asyncio.run(main(url, token))
|
||||
|
||||
94
examples/foundational/07d-interruptible-cartesia.py
Normal file
94
examples/foundational/07d-interruptible-cartesia.py
Normal file
@@ -0,0 +1,94 @@
|
||||
#
|
||||
# Copyright (c) 2024, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import asyncio
|
||||
import os
|
||||
import sys
|
||||
|
||||
from pipecat.frames.frames import LLMMessagesFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_response import (
|
||||
LLMAssistantResponseAggregator, LLMUserResponseAggregator)
|
||||
from pipecat.services.cartesia import CartesiaTTSService
|
||||
from pipecat.services.openai import OpenAILLMService
|
||||
from pipecat.transports.services.daily import DailyParams, DailyTransport
|
||||
from pipecat.vad.silero import SileroVADAnalyzer
|
||||
|
||||
|
||||
from runner import configure
|
||||
|
||||
from loguru import logger
|
||||
|
||||
from dotenv import load_dotenv
|
||||
load_dotenv(override=True)
|
||||
|
||||
logger.remove(0)
|
||||
logger.add(sys.stderr, level="DEBUG")
|
||||
|
||||
|
||||
async def main(room_url: str, token):
|
||||
transport = DailyTransport(
|
||||
room_url,
|
||||
token,
|
||||
"Respond bot",
|
||||
DailyParams(
|
||||
audio_out_enabled=True,
|
||||
audio_out_sample_rate=44100,
|
||||
transcription_enabled=True,
|
||||
vad_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer()
|
||||
)
|
||||
)
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_name="British Lady",
|
||||
output_format="pcm_44100"
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
model="gpt-4o")
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
tma_in = LLMUserResponseAggregator(messages)
|
||||
tma_out = LLMAssistantResponseAggregator(messages)
|
||||
|
||||
pipeline = Pipeline([
|
||||
transport.input(), # Transport user input
|
||||
tma_in, # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
tma_out # Assistant spoken responses
|
||||
])
|
||||
|
||||
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
|
||||
|
||||
@transport.event_handler("on_first_participant_joined")
|
||||
async def on_first_participant_joined(transport, participant):
|
||||
transport.capture_participant_transcription(participant["id"])
|
||||
# Kick off the conversation.
|
||||
messages.append(
|
||||
{"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMMessagesFrame(messages)])
|
||||
|
||||
runner = PipelineRunner()
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
(url, token) = configure()
|
||||
asyncio.run(main(url, token))
|
||||
@@ -1,125 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
import os
|
||||
|
||||
import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.elevenlabs.tts import ElevenLabsHttpTTSService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
# Create an HTTP session
|
||||
async with aiohttp.ClientSession() as session:
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = ElevenLabsHttpTTSService(
|
||||
api_key=os.getenv("ELEVENLABS_API_KEY", ""),
|
||||
voice_id=os.getenv("ELEVENLABS_VOICE_ID", ""),
|
||||
aiohttp_session=session,
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt,
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
@@ -1,121 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.elevenlabs.tts import ElevenLabsTTSService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = ElevenLabsTTSService(
|
||||
api_key=os.getenv("ELEVENLABS_API_KEY", ""),
|
||||
voice_id=os.getenv("ELEVENLABS_VOICE_ID", ""),
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt,
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
@@ -1,121 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.services.playht.tts import PlayHTHttpTTSService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = PlayHTHttpTTSService(
|
||||
user_id=os.getenv("PLAYHT_USER_ID"),
|
||||
api_key=os.getenv("PLAYHT_API_KEY"),
|
||||
voice_url="s3://voice-cloning-zero-shot/d9ff78ba-d016-47f6-b0ef-dd630f59414e/female-cs/manifest.json",
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt,
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
@@ -1,67 +1,58 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
# Copyright (c) 2024, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
import asyncio
|
||||
import os
|
||||
import sys
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.frames.frames import LLMMessagesFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.services.playht.tts import PlayHTTTSService
|
||||
from pipecat.transcriptions.language import Language
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
from pipecat.processors.aggregators.llm_response import (
|
||||
LLMAssistantResponseAggregator, LLMUserResponseAggregator)
|
||||
from pipecat.services.playht import PlayHTTTSService
|
||||
from pipecat.services.openai import OpenAILLMService
|
||||
from pipecat.transports.services.daily import DailyParams, DailyTransport
|
||||
from pipecat.vad.silero import SileroVADAnalyzer
|
||||
|
||||
from runner import configure
|
||||
|
||||
from loguru import logger
|
||||
|
||||
from dotenv import load_dotenv
|
||||
load_dotenv(override=True)
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
logger.remove(0)
|
||||
logger.add(sys.stderr, level="DEBUG")
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
async def main(room_url: str, token):
|
||||
transport = DailyTransport(
|
||||
room_url,
|
||||
token,
|
||||
"Respond bot",
|
||||
DailyParams(
|
||||
audio_out_enabled=True,
|
||||
audio_out_sample_rate=16000,
|
||||
transcription_enabled=True,
|
||||
vad_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer()
|
||||
)
|
||||
)
|
||||
|
||||
tts = PlayHTTTSService(
|
||||
user_id=os.getenv("PLAYHT_USER_ID"),
|
||||
api_key=os.getenv("PLAYHT_API_KEY"),
|
||||
voice_url="s3://voice-cloning-zero-shot/e46b4027-b38d-4d24-b292-38fbca2be0ef/original/manifest.json",
|
||||
params=PlayHTTTSService.InputParams(language=Language.EN),
|
||||
voice_url="s3://voice-cloning-zero-shot/801a663f-efd0-4254-98d0-5c175514c3e8/jennifer/manifest.json",
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
model="gpt-4o")
|
||||
|
||||
messages = [
|
||||
{
|
||||
@@ -70,54 +61,33 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
tma_in = LLMUserResponseAggregator(messages)
|
||||
tma_out = LLMAssistantResponseAggregator(messages)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt,
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
pipeline = Pipeline([
|
||||
transport.input(), # Transport user input
|
||||
tma_in, # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
tma_out # Assistant spoken responses
|
||||
])
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
@transport.event_handler("on_first_participant_joined")
|
||||
async def on_first_participant_joined(transport, participant):
|
||||
transport.capture_participant_transcription(participant["id"])
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
messages.append(
|
||||
{"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMMessagesFrame(messages)])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner()
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
(url, token) = configure()
|
||||
asyncio.run(main(url, token))
|
||||
|
||||
@@ -1,55 +1,48 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
# Copyright (c) 2024, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
import asyncio
|
||||
import os
|
||||
import sys
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.frames.frames import LLMMessagesFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.azure.llm import AzureLLMService
|
||||
from pipecat.services.azure.stt import AzureSTTService
|
||||
from pipecat.services.azure.tts import AzureTTSService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
from pipecat.processors.aggregators.llm_response import (
|
||||
LLMAssistantResponseAggregator, LLMUserResponseAggregator)
|
||||
from pipecat.services.azure import AzureLLMService, AzureSTTService, AzureTTSService
|
||||
from pipecat.transports.services.daily import DailyParams, DailyTransport
|
||||
from pipecat.vad.silero import SileroVADAnalyzer
|
||||
|
||||
|
||||
from runner import configure
|
||||
|
||||
from loguru import logger
|
||||
|
||||
from dotenv import load_dotenv
|
||||
load_dotenv(override=True)
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
logger.remove(0)
|
||||
logger.add(sys.stderr, level="DEBUG")
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
async def main(room_url: str, token):
|
||||
transport = DailyTransport(
|
||||
room_url,
|
||||
token,
|
||||
"Respond bot",
|
||||
DailyParams(
|
||||
audio_out_enabled=True,
|
||||
audio_out_sample_rate=16000,
|
||||
vad_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
vad_audio_passthrough=True,
|
||||
)
|
||||
)
|
||||
|
||||
stt = AzureSTTService(
|
||||
api_key=os.getenv("AZURE_SPEECH_API_KEY"),
|
||||
@@ -74,54 +67,34 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
},
|
||||
]
|
||||
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
tma_in = LLMUserResponseAggregator(messages)
|
||||
tma_out = LLMAssistantResponseAggregator(messages)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
pipeline = Pipeline([
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
tma_in, # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
tma_out # Assistant spoken responses
|
||||
])
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
@transport.event_handler("on_first_participant_joined")
|
||||
async def on_first_participant_joined(transport, participant):
|
||||
transport.capture_participant_transcription(participant["id"])
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
messages.append(
|
||||
{"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMMessagesFrame(messages)])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner()
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
(url, token) = configure()
|
||||
asyncio.run(main(url, token))
|
||||
|
||||
92
examples/foundational/07g-interruptible-openai-tts.py
Normal file
92
examples/foundational/07g-interruptible-openai-tts.py
Normal file
@@ -0,0 +1,92 @@
|
||||
#
|
||||
# Copyright (c) 2024, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import asyncio
|
||||
import os
|
||||
import sys
|
||||
|
||||
from pipecat.frames.frames import LLMMessagesFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_response import (
|
||||
LLMAssistantResponseAggregator, LLMUserResponseAggregator)
|
||||
from pipecat.services.openai import OpenAITTSService
|
||||
from pipecat.services.openai import OpenAILLMService
|
||||
from pipecat.transports.services.daily import DailyParams, DailyTransport
|
||||
from pipecat.vad.silero import SileroVADAnalyzer
|
||||
|
||||
from runner import configure
|
||||
|
||||
from loguru import logger
|
||||
|
||||
from dotenv import load_dotenv
|
||||
load_dotenv(override=True)
|
||||
|
||||
logger.remove(0)
|
||||
logger.add(sys.stderr, level="DEBUG")
|
||||
|
||||
|
||||
async def main(room_url: str, token):
|
||||
transport = DailyTransport(
|
||||
room_url,
|
||||
token,
|
||||
"Respond bot",
|
||||
DailyParams(
|
||||
audio_out_enabled=True,
|
||||
audio_out_sample_rate=24000,
|
||||
transcription_enabled=True,
|
||||
vad_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer()
|
||||
)
|
||||
)
|
||||
|
||||
tts = OpenAITTSService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
voice="alloy"
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
model="gpt-4o")
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
tma_in = LLMUserResponseAggregator(messages)
|
||||
tma_out = LLMAssistantResponseAggregator(messages)
|
||||
|
||||
pipeline = Pipeline([
|
||||
transport.input(), # Transport user input
|
||||
tma_in, # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
tma_out # Assistant spoken responses
|
||||
])
|
||||
|
||||
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
|
||||
|
||||
@transport.event_handler("on_first_participant_joined")
|
||||
async def on_first_participant_joined(transport, participant):
|
||||
transport.capture_participant_transcription(participant["id"])
|
||||
# Kick off the conversation.
|
||||
messages.append(
|
||||
{"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMMessagesFrame(messages)])
|
||||
|
||||
runner = PipelineRunner()
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
(url, token) = configure()
|
||||
asyncio.run(main(url, token))
|
||||
@@ -1,122 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.services.openai.stt import OpenAISTTService
|
||||
from pipecat.services.openai.tts import OpenAITTSService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = OpenAISTTService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
model="gpt-4o-transcribe",
|
||||
prompt="Expect words related to dogs, such as breed names.",
|
||||
)
|
||||
|
||||
tts = OpenAITTSService(api_key=os.getenv("OPENAI_API_KEY"), voice="ballad")
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are very knowledgable about dogs. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
audio_out_sample_rate=24000,
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
@@ -1,126 +1,102 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
# Copyright (c) 2024, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
import asyncio
|
||||
import aiohttp
|
||||
import os
|
||||
import time
|
||||
import sys
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.frames.frames import LLMMessagesFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openpipe.llm import OpenPipeLLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
from pipecat.processors.aggregators.llm_response import (
|
||||
LLMAssistantResponseAggregator,
|
||||
LLMUserResponseAggregator,
|
||||
)
|
||||
from pipecat.services.elevenlabs import ElevenLabsTTSService
|
||||
from pipecat.services.openpipe import OpenPipeLLMService
|
||||
from pipecat.transports.services.daily import DailyParams, DailyTransport
|
||||
from pipecat.vad.silero import SileroVADAnalyzer
|
||||
|
||||
from runner import configure
|
||||
|
||||
from loguru import logger
|
||||
import time
|
||||
|
||||
from dotenv import load_dotenv
|
||||
load_dotenv(override=True)
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
logger.remove(0)
|
||||
logger.add(sys.stderr, level="DEBUG")
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
async def main(room_url: str, token):
|
||||
async with aiohttp.ClientSession() as session:
|
||||
transport = DailyTransport(
|
||||
room_url,
|
||||
token,
|
||||
"Respond bot",
|
||||
DailyParams(
|
||||
audio_out_enabled=True,
|
||||
transcription_enabled=True,
|
||||
vad_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer()
|
||||
)
|
||||
)
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
tts = ElevenLabsTTSService(
|
||||
aiohttp_session=session,
|
||||
api_key=os.getenv("ELEVENLABS_API_KEY"),
|
||||
voice_id=os.getenv("ELEVENLABS_VOICE_ID"),
|
||||
)
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
timestamp = int(time.time())
|
||||
llm = OpenPipeLLMService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
openpipe_api_key=os.getenv("OPENPIPE_API_KEY"),
|
||||
model="gpt-4o",
|
||||
tags={
|
||||
"conversation_id": f"pipecat-{timestamp}"
|
||||
}
|
||||
)
|
||||
|
||||
timestamp = int(time.time())
|
||||
llm = OpenPipeLLMService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
openpipe_api_key=os.getenv("OPENPIPE_API_KEY"),
|
||||
tags={"conversation_id": f"pipecat-{timestamp}"},
|
||||
)
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt,
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
)
|
||||
tma_in = LLMUserResponseAggregator(messages)
|
||||
tma_out = LLMAssistantResponseAggregator(messages)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
pipeline = Pipeline([
|
||||
transport.input(), # Transport user input
|
||||
tma_in, # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
tma_out # Assistant spoken responses
|
||||
])
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
@transport.event_handler("on_first_participant_joined")
|
||||
async def on_first_participant_joined(transport, participant):
|
||||
transport.capture_participant_transcription(participant["id"])
|
||||
# Kick off the conversation.
|
||||
messages.append(
|
||||
{"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([LLMMessagesFrame(messages)])
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
runner = PipelineRunner()
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
(url, token) = configure()
|
||||
asyncio.run(main(url, token))
|
||||
|
||||
@@ -1,124 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
import os
|
||||
|
||||
import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.services.xtts.tts import XTTSService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
# Create an HTTP session
|
||||
async with aiohttp.ClientSession() as session:
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = XTTSService(
|
||||
aiohttp_session=session,
|
||||
voice_id="Claribel Dervla",
|
||||
base_url="http://localhost:8000",
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt,
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
@@ -1,129 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.gladia.config import GladiaInputParams, LanguageConfig
|
||||
from pipecat.services.gladia.stt import GladiaSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transcriptions.language import Language
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = GladiaSTTService(
|
||||
api_key=os.getenv("GLADIA_API_KEY", ""),
|
||||
region=os.getenv("GLADIA_REGION"),
|
||||
params=GladiaInputParams(
|
||||
language_config=LanguageConfig(
|
||||
languages=[Language.EN],
|
||||
)
|
||||
),
|
||||
)
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY", ""),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY", ""))
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": f"You are a helpful LLM. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
@@ -1,117 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.lmnt.tts import LmntTTSService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = LmntTTSService(api_key=os.getenv("LMNT_API_KEY"), voice_id="morgan")
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt,
|
||||
context_aggregator.user(), # User respones
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
@@ -1,122 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_response import LLMUserAggregatorParams
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.groq.llm import GroqLLMService
|
||||
from pipecat.services.groq.stt import GroqSTTService
|
||||
from pipecat.services.groq.tts import GroqTTSService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = GroqSTTService(api_key=os.getenv("GROQ_API_KEY"))
|
||||
|
||||
llm = GroqLLMService(
|
||||
api_key=os.getenv("GROQ_API_KEY"), model="meta-llama/llama-4-maverick-17b-128e-instruct"
|
||||
)
|
||||
|
||||
tts = GroqTTSService(api_key=os.getenv("GROQ_API_KEY"))
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(
|
||||
context, user_params=LLMUserAggregatorParams(aggregation_timeout=0.05)
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt,
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
@@ -1,123 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.aws.llm import AWSBedrockLLMService
|
||||
from pipecat.services.aws.stt import AWSTranscribeSTTService
|
||||
from pipecat.services.aws.tts import AWSPollyTTSService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = AWSTranscribeSTTService()
|
||||
|
||||
tts = AWSPollyTTSService(
|
||||
region="us-west-2", # only specific regions support generative TTS
|
||||
voice_id="Joanna",
|
||||
params=AWSPollyTTSService.InputParams(engine="generative", rate="1.1"),
|
||||
)
|
||||
|
||||
llm = AWSBedrockLLMService(
|
||||
aws_region="us-west-2",
|
||||
model="us.anthropic.claude-3-5-haiku-20241022-v1:0",
|
||||
params=AWSBedrockLLMService.InputParams(temperature=0.8, latency="optimized"),
|
||||
)
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "user", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
@@ -1,130 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.google.llm import GoogleLLMService
|
||||
from pipecat.services.google.stt import GoogleSTTService
|
||||
from pipecat.services.google.tts import GoogleTTSService
|
||||
from pipecat.transcriptions.language import Language
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = GoogleSTTService(
|
||||
params=GoogleSTTService.InputParams(languages=Language.EN_US),
|
||||
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
|
||||
)
|
||||
|
||||
tts = GoogleTTSService(
|
||||
voice_id="en-US-Chirp3-HD-Charon",
|
||||
params=GoogleTTSService.InputParams(language=Language.EN_US),
|
||||
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
|
||||
)
|
||||
|
||||
llm = GoogleLLMService(
|
||||
api_key=os.getenv("GOOGLE_API_KEY"),
|
||||
model="gemini-2.5-flash",
|
||||
# turn on thinking if you want it
|
||||
# params=GoogleLLMService.InputParams(extra={"thinking_config": {"thinking_budget": 4096}}),)
|
||||
)
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
context_aggregator.user(), # User respones
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
@@ -1,123 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.assemblyai.stt import AssemblyAISTTService
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = AssemblyAISTTService(
|
||||
api_key=os.getenv("ASSEMBLYAI_API_KEY"),
|
||||
)
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
@@ -1,121 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.filters.krisp_filter import KrispFilter
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.deepgram.tts import DeepgramTTSService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
audio_in_filter=KrispFilter(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
audio_in_filter=KrispFilter(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
audio_in_filter=KrispFilter(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-helios-en")
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt, # STT
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
@@ -1,126 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
import os
|
||||
|
||||
import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.services.rime.tts import RimeHttpTTSService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
|
||||
from pipecat.transports.services.daily import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
# We store functions so objects (e.g. SileroVADAnalyzer) don't get
|
||||
# instantiated. The function will be called when the desired transport gets
|
||||
# selected.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
# Create an HTTP session
|
||||
async with aiohttp.ClientSession() as session:
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = RimeHttpTTSService(
|
||||
api_key=os.getenv("RIME_API_KEY", ""),
|
||||
voice_id="luna",
|
||||
model="arcana",
|
||||
aiohttp_session=session,
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
|
||||
},
|
||||
]
|
||||
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(), # Transport user input
|
||||
stt,
|
||||
context_aggregator.user(), # User responses
|
||||
llm, # LLM
|
||||
tts, # TTS
|
||||
transport.output(), # Transport bot output
|
||||
context_aggregator.assistant(), # Assistant spoken responses
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user