Compare commits
1 Commits
hush/rtviS
...
cb/extra-l
| Author | SHA1 | Date | |
|---|---|---|---|
|
b8e2227a21 |
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
|
||||
54
.github/workflows/coverage.yaml
vendored
54
.github/workflows/coverage.yaml
vendored
@@ -1,54 +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: Set up Python
|
||||
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 dev-requirements.txt and test-requirements.txt which
|
||||
# contain all dependencies needed to run the tests.
|
||||
key: venv-${{ runner.os }}-${{ steps.setup_python.outputs.python-version}}-${{ hashFiles('dev-requirements.txt') }}-${{ hashFiles('test-requirements.txt') }}
|
||||
path: .venv
|
||||
- name: Install system packages
|
||||
id: install_system_packages
|
||||
run: |
|
||||
sudo apt-get install -y portaudio19-dev
|
||||
- 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 -r test-requirements.txt
|
||||
- name: Run tests with coverage
|
||||
run: |
|
||||
source .venv/bin/activate
|
||||
coverage run
|
||||
coverage xml
|
||||
- name: Upload coverage to Codecov
|
||||
uses: codecov/codecov-action@v5
|
||||
with:
|
||||
token: ${{ secrets.CODECOV_TOKEN }}
|
||||
slug: pipecat-ai/pipecat
|
||||
21
.gitignore
vendored
21
.gitignore
vendored
@@ -7,7 +7,7 @@ venv
|
||||
/.idea
|
||||
#*#
|
||||
|
||||
# Distribution / Packaging
|
||||
# Distribution / packaging
|
||||
.Python
|
||||
build/
|
||||
develop-eggs/
|
||||
@@ -30,23 +30,8 @@ MANIFEST
|
||||
.env
|
||||
fly.toml
|
||||
|
||||
# Examples
|
||||
examples/telnyx-chatbot/templates/streams.xml
|
||||
examples/twilio-chatbot/templates/streams.xml
|
||||
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
|
||||
# Example files
|
||||
pipecat/examples/twilio-chatbot/templates/streams.xml
|
||||
|
||||
# Documentation
|
||||
docs/api/_build/
|
||||
|
||||
@@ -1,8 +1,7 @@
|
||||
repos:
|
||||
- repo: https://github.com/astral-sh/ruff-pre-commit
|
||||
rev: v0.9.7
|
||||
- repo: local
|
||||
hooks:
|
||||
- id: ruff
|
||||
language_version: python3
|
||||
args: [ --select, I, ]
|
||||
- id: ruff-format
|
||||
- id: ruff-format-hook
|
||||
name: Check ruff formatting
|
||||
entry: sh scripts/pre-commit.sh
|
||||
language: system
|
||||
|
||||
1141
CHANGELOG.md
1141
CHANGELOG.md
File diff suppressed because it is too large
Load Diff
@@ -26,52 +26,11 @@ git commit -m "Description of your changes"
|
||||
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!
|
||||
9. **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:
|
||||
|
||||
- Class docstrings should fully document all parameters used in `__init__`
|
||||
- We don't require separate docstrings for `__init__` methods when parameters are documented in the class docstring
|
||||
- Property methods should have docstrings explaining their purpose and return value
|
||||
|
||||
Example of correctly documented class:
|
||||
|
||||
```python
|
||||
class MyClass:
|
||||
"""Class description.
|
||||
|
||||
Additional details about the class.
|
||||
|
||||
Args:
|
||||
param1: Description of first parameter.
|
||||
param2: Description of second parameter.
|
||||
"""
|
||||
|
||||
def __init__(self, param1, param2):
|
||||
# No docstring required here as parameters are documented above
|
||||
self.param1 = param1
|
||||
self.param2 = param2
|
||||
|
||||
@property
|
||||
def some_property(self) -> str:
|
||||
"""Get the formatted property value.
|
||||
|
||||
Returns:
|
||||
A string representation of the property.
|
||||
"""
|
||||
return f"Property: {self.param1}"
|
||||
```
|
||||
|
||||
# Contributor Covenant Code of Conduct
|
||||
|
||||
@@ -92,23 +51,23 @@ diverse, inclusive, and healthy community.
|
||||
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,
|
||||
* 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
|
||||
* 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
|
||||
* 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,
|
||||
* 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
|
||||
* Other conduct which could reasonably be considered inappropriate in a
|
||||
professional setting
|
||||
|
||||
## Enforcement Responsibilities
|
||||
@@ -203,4 +162,4 @@ For answers to common questions about this code of conduct, see the FAQ at
|
||||
[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
|
||||
[translations]: https://www.contributor-covenant.org/translations
|
||||
234
README.md
234
README.md
@@ -1,72 +1,43 @@
|
||||
<h1><div align="center">
|
||||
<img alt="pipecat" width="300px" height="auto" src="https://raw.githubusercontent.com/pipecat-ai/pipecat/main/pipecat.png">
|
||||
<img alt="pipecat" width="300px" height="auto" src="https://raw.githubusercontent.com/pipecat-ai/pipecat/main/pipecat.png">
|
||||
</div></h1>
|
||||
|
||||
[](https://pypi.org/project/pipecat-ai)  [](https://codecov.io/gh/pipecat-ai/pipecat) [](https://docs.pipecat.ai) [](https://discord.gg/pipecat)
|
||||
[](https://pypi.org/project/pipecat-ai)  [](https://docs.pipecat.ai) [](https://discord.gg/pipecat) <a href="https://app.commanddash.io/agent/github_pipecat-ai_pipecat"><img src="https://img.shields.io/badge/AI-Code%20Agent-EB9FDA"></a>
|
||||
|
||||
# 🎙️ Pipecat: Real-Time Voice & Multimodal AI Agents
|
||||
Pipecat is an open source Python framework for building voice and multimodal conversational agents. It handles the complex orchestration of AI services, network transport, audio processing, and multimodal interactions, letting you focus on creating engaging experiences.
|
||||
|
||||
**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.
|
||||
## What you can build
|
||||
|
||||
## 🚀 What You Can Build
|
||||
- **Voice Assistants**: [Natural, real-time conversations with AI](https://demo.dailybots.ai/)
|
||||
- **Interactive Agents**: Personal coaches and meeting assistants
|
||||
- **Multimodal Apps**: Combine voice, video, images, and text
|
||||
- **Creative Tools**: [Story-telling experiences](https://storytelling-chatbot.fly.dev/) and social companions
|
||||
- **Business Solutions**: [Customer intake flows](https://www.youtube.com/watch?v=lDevgsp9vn0) and support bots
|
||||
- **Complex conversational flows**: [Refer to Pipecat Flows](https://github.com/pipecat-ai/pipecat-flows) to learn more
|
||||
|
||||
- **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
|
||||
## See it in action
|
||||
|
||||
<p float="left">
|
||||
<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="400" /></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="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/tree/main/examples/translation-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat/main/examples/translation-chatbot/image.png" width="400" /></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="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
|
||||
## Key features
|
||||
|
||||
You can connect to Pipecat from any platform using our official SDKs:
|
||||
- **Voice-first Design**: Built-in speech recognition, TTS, and conversation handling
|
||||
- **Flexible Integration**: Works with popular AI services (OpenAI, ElevenLabs, etc.)
|
||||
- **Pipeline Architecture**: Build complex apps from simple, reusable components
|
||||
- **Real-time Processing**: Frame-based pipeline architecture for fluid interactions
|
||||
- **Production Ready**: Enterprise-grade WebRTC and Websocket support
|
||||
|
||||
| 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 |
|
||||
💡 Looking to build structured conversations? Check out [Pipecat Flows](https://github.com/pipecat-ai/pipecat-flows) for managing complex conversational states and transitions.
|
||||
|
||||
## 🧩 Available services
|
||||
## Getting started
|
||||
|
||||
| Category | Services |
|
||||
| ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| Speech-to-Text | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [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), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [Parakeet (NVIDIA)](https://docs.pipecat.ai/server/services/stt/parakeet), [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), [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), [Together AI](https://docs.pipecat.ai/server/services/llm/together) |
|
||||
| Text-to-Speech | [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), [FastPitch (NVIDIA)](https://docs.pipecat.ai/server/services/tts/fastpitch), [Fish](https://docs.pipecat.ai/server/services/tts/fish), [Google](https://docs.pipecat.ai/server/services/tts/google), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [Neuphonic](https://docs.pipecat.ai/server/services/tts/neuphonic), [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), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts) |
|
||||
| Speech-to-Speech | [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 |
|
||||
| Video | [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 | [Canonical AI](https://docs.pipecat.ai/server/services/analytics/canonical), [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.
|
||||
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.
|
||||
|
||||
```shell
|
||||
# Install the module
|
||||
@@ -82,71 +53,150 @@ To keep things lightweight, only the core framework is included by default. If y
|
||||
pip install "pipecat-ai[option,...]"
|
||||
```
|
||||
|
||||
## 🧪 Code examples
|
||||
### Available services
|
||||
|
||||
| Category | Services | Install Command Example |
|
||||
| ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------- |
|
||||
| Speech-to-Text | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper) | `pip install "pipecat-ai[deepgram]"` |
|
||||
| LLMs | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [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), [Together AI](https://docs.pipecat.ai/server/services/llm/together) | `pip install "pipecat-ai[openai]"` |
|
||||
| Text-to-Speech | [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), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [PlayHT](https://docs.pipecat.ai/server/services/tts/playht), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts) | `pip install "pipecat-ai[cartesia]"` |
|
||||
| Speech-to-Speech | [Gemini Multimodal Live](https://docs.pipecat.ai/server/services/s2s/gemini), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai) | `pip install "pipecat-ai[openai]"` |
|
||||
| Transport | [Daily (WebRTC)](https://docs.pipecat.ai/server/services/transport/daily), [FastAPI Websocket](https://docs.pipecat.ai/server/services/transport/fastapi-websocket), [WebSocket Server](https://docs.pipecat.ai/server/services/transport/websocket-server), Local | `pip install "pipecat-ai[daily]"` |
|
||||
| Video | [Tavus](https://docs.pipecat.ai/server/services/video/tavus), [Simli](https://docs.pipecat.ai/server/services/video/simli) | `pip install "pipecat-ai[tavus,simli]"` |
|
||||
| Vision & Image | [Moondream](https://docs.pipecat.ai/server/services/vision/moondream), [fal](https://docs.pipecat.ai/server/services/image-generation/fal) | `pip install "pipecat-ai[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) | `pip install "pipecat-ai[silero]"` |
|
||||
| Analytics & Metrics | [Canonical AI](https://docs.pipecat.ai/server/services/analytics/canonical), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry) | `pip install "pipecat-ai[canonical]"` |
|
||||
|
||||
📚 [View full services documentation →](https://docs.pipecat.ai/server/services/supported-services)
|
||||
|
||||
## 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
|
||||
|
||||
## 🛠️ Hacking on the framework itself
|
||||
## A simple voice agent running locally
|
||||
|
||||
1. Set up a virtual environment before following these instructions. From the root of the repo:
|
||||
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 [Cartesia](https://cartesia.ai/) for text-to-speech.
|
||||
|
||||
```shell
|
||||
python3 -m venv venv
|
||||
source venv/bin/activate
|
||||
```
|
||||
```python
|
||||
import asyncio
|
||||
|
||||
2. Install the development dependencies:
|
||||
from pipecat.frames.frames import TextFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.services.cartesia import CartesiaTTSService
|
||||
from pipecat.transports.services.daily import DailyParams, DailyTransport
|
||||
|
||||
```shell
|
||||
pip install -r dev-requirements.txt
|
||||
```
|
||||
async def main():
|
||||
# Use Daily as a real-time media transport (WebRTC)
|
||||
transport = DailyTransport(
|
||||
room_url=...,
|
||||
token="", # leave empty. Note: token is _not_ your api key
|
||||
bot_name="Bot Name",
|
||||
params=DailyParams(audio_out_enabled=True))
|
||||
|
||||
3. Install the git pre-commit hooks (these help ensure your code follows project rules):
|
||||
# Use Cartesia for Text-to-Speech
|
||||
tts = CartesiaTTSService(
|
||||
api_key=...,
|
||||
voice_id=...
|
||||
)
|
||||
|
||||
```shell
|
||||
pre-commit install
|
||||
```
|
||||
# Simple pipeline that will process text to speech and output the result
|
||||
pipeline = Pipeline([tts, transport.output()])
|
||||
|
||||
4. Install the `pipecat-ai` package locally in editable mode:
|
||||
# Create Pipecat processor that can run one or more pipelines tasks
|
||||
runner = PipelineRunner()
|
||||
|
||||
```shell
|
||||
pip install -e .
|
||||
```
|
||||
# Assign the task callable to run the pipeline
|
||||
task = PipelineTask(pipeline)
|
||||
|
||||
> The `-e` or `--editable` option allows you to modify the code without reinstalling.
|
||||
# Register an event handler to play audio when a
|
||||
# participant joins the transport WebRTC session
|
||||
@transport.event_handler("on_first_participant_joined")
|
||||
async def on_first_participant_joined(transport, participant):
|
||||
participant_name = participant.get("info", {}).get("userName", "")
|
||||
# Queue a TextFrame that will get spoken by the TTS service (Cartesia)
|
||||
await task.queue_frame(TextFrame(f"Hello there, {participant_name}!"))
|
||||
|
||||
5. Include optional dependencies as needed. For example:
|
||||
# Register an event handler to exit the application when the user leaves.
|
||||
@transport.event_handler("on_participant_left")
|
||||
async def on_participant_left(transport, participant, reason):
|
||||
await task.cancel()
|
||||
|
||||
```shell
|
||||
pip install -e ".[daily,deepgram,cartesia,openai,silero]"
|
||||
```
|
||||
# Run the pipeline task
|
||||
await runner.run(task)
|
||||
|
||||
6. (Optional) If you want to use this package from another directory:
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(main())
|
||||
```
|
||||
|
||||
```shell
|
||||
pip install "path_to_this_repo[option,...]"
|
||||
```
|
||||
|
||||
### Running tests
|
||||
|
||||
Install the test dependencies:
|
||||
Run it with:
|
||||
|
||||
```shell
|
||||
pip install -r test-requirements.txt
|
||||
python app.py
|
||||
```
|
||||
|
||||
Daily provides a prebuilt WebRTC user interface. While 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.
|
||||
|
||||
## 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
|
||||
```
|
||||
|
||||
This will install the necessary development dependencies. Also, make sure you install the git pre-commit hooks:
|
||||
|
||||
```shell
|
||||
pre-commit install
|
||||
```
|
||||
|
||||
The hooks will just save you time when you submit a PR by making sure your code follows the project rules.
|
||||
|
||||
To use the package locally (e.g. to run sample files), run:
|
||||
|
||||
```shell
|
||||
pip install --editable ".[option,...]"
|
||||
```
|
||||
|
||||
The `--editable` option makes sure you don't have to run `pip install` again and you can just edit the project files locally.
|
||||
|
||||
If you want to use this package from another directory, you can run:
|
||||
|
||||
```shell
|
||||
pip install "path_to_this_repo[option,...]"
|
||||
```
|
||||
|
||||
### Running tests
|
||||
|
||||
From the root directory, run:
|
||||
|
||||
```shell
|
||||
pytest
|
||||
```
|
||||
|
||||
### Setting up your editor
|
||||
## Setting up your editor
|
||||
|
||||
This project uses strict [PEP 8](https://peps.python.org/pep-0008/) formatting via [Ruff](https://github.com/astral-sh/ruff).
|
||||
|
||||
#### Emacs
|
||||
### 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:
|
||||
|
||||
@@ -168,7 +218,7 @@ You can use [use-package](https://github.com/jwiegley/use-package) to install [e
|
||||
: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:
|
||||
@@ -180,7 +230,7 @@ Install the
|
||||
}
|
||||
```
|
||||
|
||||
#### PyCharm
|
||||
### 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:
|
||||
|
||||
@@ -190,7 +240,7 @@ Install the
|
||||
4. **Arguments**: `format $FilePath$`
|
||||
5. **Program**: `$PyInterpreterDirectory$/ruff`
|
||||
|
||||
## 🤝 Contributing
|
||||
## Contributing
|
||||
|
||||
We welcome contributions from the community! Whether you're fixing bugs, improving documentation, or adding new features, here's how you can help:
|
||||
|
||||
@@ -203,7 +253,7 @@ Before submitting a pull request, please check existing issues and PRs to avoid
|
||||
|
||||
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)
|
||||
|
||||
|
||||
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
|
||||
@@ -1,13 +1,11 @@
|
||||
build~=1.2.2
|
||||
coverage~=7.6.12
|
||||
grpcio-tools~=1.67.1
|
||||
grpcio-tools~=1.69.0
|
||||
pip-tools~=7.4.1
|
||||
pre-commit~=4.0.1
|
||||
pyright~=1.1.397
|
||||
pyright~=1.1.392
|
||||
pytest~=8.3.4
|
||||
pytest-asyncio~=0.25.3
|
||||
pytest-aiohttp==1.1.0
|
||||
ruff~=0.11.1
|
||||
setuptools~=70.0.0
|
||||
pytest-asyncio~=0.25.2
|
||||
ruff~=0.9.1
|
||||
setuptools~=75.8.0
|
||||
setuptools_scm~=8.1.0
|
||||
python-dotenv~=1.0.1
|
||||
|
||||
22
docs/ISSUE_TEMPLATE.md
Normal file
22
docs/ISSUE_TEMPLATE.md
Normal file
@@ -0,0 +1,22 @@
|
||||
# Description
|
||||
Is this reporting a bug or feature request?
|
||||
|
||||
|
||||
If reporting a bug, please fill out the following:
|
||||
|
||||
### Environment
|
||||
- pipecat-ai version:
|
||||
- python version:
|
||||
- OS:
|
||||
|
||||
### Issue description
|
||||
Provide a clear description of the issue.
|
||||
|
||||
### Repro steps
|
||||
List the steps to reproduce the issue.
|
||||
|
||||
### Expected behavior
|
||||
|
||||
### Actual behavior
|
||||
|
||||
### Logs
|
||||
@@ -50,13 +50,6 @@ autodoc_mock_imports = [
|
||||
"pyht.protos",
|
||||
"pyht.protos.api_pb2",
|
||||
"pipecat_ai_playht", # PlayHT wrapper
|
||||
"aiortc",
|
||||
"aiortc.mediastreams",
|
||||
"cv2",
|
||||
"av",
|
||||
"pyneuphonic",
|
||||
"mem0",
|
||||
"mlx_whisper",
|
||||
"anthropic",
|
||||
"assemblyai",
|
||||
"boto3",
|
||||
@@ -75,6 +68,7 @@ autodoc_mock_imports = [
|
||||
"openpipe",
|
||||
"simli",
|
||||
"soundfile",
|
||||
# Existing mocks
|
||||
"pipecat_ai_krisp",
|
||||
"pyaudio",
|
||||
"_tkinter",
|
||||
@@ -85,66 +79,6 @@ autodoc_mock_imports = [
|
||||
"pydantic.Field",
|
||||
"pydantic._internal._model_construction",
|
||||
"pydantic._internal._fields",
|
||||
# Moondream dependencies
|
||||
"torch",
|
||||
"transformers",
|
||||
"intel_extension_for_pytorch",
|
||||
# Ultravox dependencies
|
||||
"huggingface_hub",
|
||||
"vllm",
|
||||
"vllm.engine.arg_utils",
|
||||
"transformers.AutoTokenizer",
|
||||
# Langchain dependencies
|
||||
"langchain_core",
|
||||
"langchain_core.messages",
|
||||
"langchain_core.runnables",
|
||||
"langchain_core.messages.AIMessageChunk",
|
||||
"langchain_core.runnables.Runnable",
|
||||
# LiveKit dependencies
|
||||
"livekit",
|
||||
"livekit.rtc",
|
||||
"livekit_api",
|
||||
"livekit_protocol",
|
||||
"tenacity",
|
||||
"tenacity.retry",
|
||||
"tenacity.stop_after_attempt",
|
||||
"tenacity.wait_exponential",
|
||||
"rtc",
|
||||
"rtc.Room",
|
||||
"rtc.RoomOptions",
|
||||
"rtc.AudioSource",
|
||||
"rtc.LocalAudioTrack",
|
||||
"rtc.TrackPublishOptions",
|
||||
"rtc.TrackSource",
|
||||
"rtc.AudioStream",
|
||||
"rtc.AudioFrameEvent",
|
||||
"rtc.AudioFrame",
|
||||
"rtc.Track",
|
||||
"rtc.TrackKind",
|
||||
"rtc.RemoteParticipant",
|
||||
"rtc.RemoteTrackPublication",
|
||||
"rtc.DataPacket",
|
||||
# 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",
|
||||
# Local CoreML Smart Turn dependencies
|
||||
"coremltools",
|
||||
"coremltools.models",
|
||||
"coremltools.models.MLModel",
|
||||
"torch",
|
||||
"torch.nn",
|
||||
"torch.nn.functional",
|
||||
"transformers",
|
||||
"transformers.AutoFeatureExtractor",
|
||||
# Also add specific classes that are imported
|
||||
"AutoFeatureExtractor",
|
||||
]
|
||||
|
||||
# HTML output settings
|
||||
@@ -176,25 +110,12 @@ def verify_modules():
|
||||
},
|
||||
}
|
||||
|
||||
# Skip importing modules that are in autodoc_mock_imports
|
||||
skipped_modules = set(autodoc_mock_imports)
|
||||
|
||||
missing = []
|
||||
for category, modules in required_modules.items():
|
||||
if isinstance(modules, dict):
|
||||
# Handle nested structure
|
||||
for subcategory, submodules in modules.items():
|
||||
for module in submodules:
|
||||
# Check if module is in autodoc_mock_imports
|
||||
if (
|
||||
f"pipecat.{category}.{subcategory}.{module}" in skipped_modules
|
||||
or module in skipped_modules
|
||||
):
|
||||
logger.info(
|
||||
f"Skipping import of mocked module: pipecat.{category}.{subcategory}.{module}"
|
||||
)
|
||||
continue
|
||||
|
||||
try:
|
||||
__import__(f"pipecat.{category}.{subcategory}.{module}")
|
||||
logger.info(
|
||||
@@ -208,11 +129,6 @@ def verify_modules():
|
||||
else:
|
||||
# Handle flat structure
|
||||
for module in modules:
|
||||
# Check if module is in autodoc_mock_imports
|
||||
if f"pipecat.{category}.{module}" in skipped_modules or module in skipped_modules:
|
||||
logger.info(f"Skipping import of mocked module: pipecat.{category}.{module}")
|
||||
continue
|
||||
|
||||
try:
|
||||
__import__(f"pipecat.{category}.{module}")
|
||||
logger.info(f"Successfully imported pipecat.{category}.{module}")
|
||||
|
||||
@@ -45,10 +45,8 @@ Transport & Serialization
|
||||
Utilities
|
||||
~~~~~~~~~
|
||||
|
||||
* :mod:`Adapters <pipecat.adapters>`
|
||||
* :mod:`Clocks <pipecat.clocks>`
|
||||
* :mod:`Metrics <pipecat.metrics>`
|
||||
* :mod:`Observers <pipecat.observers>`
|
||||
* :mod:`Sync <pipecat.sync>`
|
||||
* :mod:`Transcriptions <pipecat.transcriptions>`
|
||||
* :mod:`Utils <pipecat.utils>`
|
||||
@@ -58,12 +56,10 @@ Utilities
|
||||
: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>
|
||||
Serializers <api/pipecat.serializers>
|
||||
|
||||
@@ -12,43 +12,29 @@ pipecat-ai[aws]
|
||||
pipecat-ai[azure]
|
||||
pipecat-ai[canonical]
|
||||
pipecat-ai[cartesia]
|
||||
pipecat-ai[cerebras]
|
||||
pipecat-ai[deepseek]
|
||||
pipecat-ai[daily]
|
||||
pipecat-ai[deepgram]
|
||||
pipecat-ai[elevenlabs]
|
||||
pipecat-ai[fal]
|
||||
pipecat-ai[fireworks]
|
||||
pipecat-ai[fish]
|
||||
pipecat-ai[gladia]
|
||||
pipecat-ai[google]
|
||||
pipecat-ai[grok]
|
||||
pipecat-ai[groq]
|
||||
# pipecat-ai[krisp] # Mocked
|
||||
pipecat-ai[koala]
|
||||
# pipecat-ai[langchain] # Mocked
|
||||
# pipecat-ai[livekit] # Mocked
|
||||
# pipecat-ai[krisp] # Mocked instead
|
||||
pipecat-ai[langchain]
|
||||
pipecat-ai[livekit]
|
||||
pipecat-ai[lmnt]
|
||||
pipecat-ai[local]
|
||||
# pipecat-ai[local-smart-turn] # Mocked
|
||||
# pipecat-ai[mem0] # Mocked
|
||||
# pipecat-ai[mlx-whisper] # Mocked
|
||||
# pipecat-ai[moondream] # Mocked
|
||||
pipecat-ai[moondream]
|
||||
pipecat-ai[nim]
|
||||
# pipecat-ai[neuphonic] # Mocked
|
||||
pipecat-ai[noisereduce]
|
||||
pipecat-ai[openai]
|
||||
# pipecat-ai[openpipe]
|
||||
# pipecat-ai[playht] # Mocked due to grpcio conflict with riva
|
||||
pipecat-ai[qwen]
|
||||
pipecat-ai[remote-smart-turn]
|
||||
# pipecat-ai[riva] # Mocked
|
||||
pipecat-ai[riva]
|
||||
pipecat-ai[silero]
|
||||
pipecat-ai[simli]
|
||||
pipecat-ai[soundfile]
|
||||
pipecat-ai[tavus]
|
||||
pipecat-ai[together]
|
||||
# pipecat-ai[ultravox] # Mocked
|
||||
# pipecat-ai[webrtc] # Mocked
|
||||
pipecat-ai[websocket]
|
||||
pipecat-ai[whisper]
|
||||
@@ -18,9 +18,6 @@ AZURE_DALLE_API_KEY=...
|
||||
AZURE_DALLE_ENDPOINT=https://...
|
||||
AZURE_DALLE_MODEL=...
|
||||
|
||||
# Cartesia
|
||||
CARTESIA_API_KEY=...
|
||||
|
||||
# Daily
|
||||
DAILY_API_KEY=...
|
||||
DAILY_SAMPLE_ROOM_URL=https://...
|
||||
@@ -29,9 +26,6 @@ DAILY_SAMPLE_ROOM_URL=https://...
|
||||
ELEVENLABS_API_KEY=...
|
||||
ELEVENLABS_VOICE_ID=...
|
||||
|
||||
# Neuphonic
|
||||
NEUPHONIC_API_KEY=...
|
||||
|
||||
# Fal
|
||||
FAL_KEY=...
|
||||
|
||||
@@ -90,14 +84,3 @@ 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=
|
||||
File diff suppressed because it is too large
Load Diff
@@ -12,7 +12,7 @@
|
||||
"license": "ISC",
|
||||
"description": "",
|
||||
"devDependencies": {
|
||||
"vite": "^6.0.9"
|
||||
"vite": "^6.0.2"
|
||||
},
|
||||
"dependencies": {
|
||||
"@daily-co/daily-js": "0.74.0"
|
||||
|
||||
@@ -1 +0,0 @@
|
||||
22.14
|
||||
@@ -1,60 +0,0 @@
|
||||
# React Native Implementation
|
||||
|
||||
Basic implementation using the [Pipecat React Native SDK](https://docs.pipecat.ai/client/react-native/introduction).
|
||||
|
||||
## Usage
|
||||
|
||||
### Expo requirements
|
||||
|
||||
This project cannot be used with an [Expo Go](https://docs.expo.dev/workflow/expo-go/) app because [it requires custom native code](https://docs.expo.io/workflow/customizing/).
|
||||
|
||||
When a project requires custom native code or a config plugin, we need to transition from using [Expo Go](https://docs.expo.dev/workflow/expo-go/)
|
||||
to a [development build](https://docs.expo.dev/development/introduction/).
|
||||
|
||||
More details about the custom native code used by this demo can be found in [rn-daily-js-expo-config-plugin](https://github.com/daily-co/rn-daily-js-expo-config-plugin).
|
||||
|
||||
### Building remotely
|
||||
|
||||
If you do not have experience with Xcode and Android Studio builds or do not have them installed locally on your computer, you will need to follow [this guide from Expo to use EAS Build](https://docs.expo.dev/development/create-development-builds/#create-and-install-eas-build).
|
||||
|
||||
### Building locally
|
||||
|
||||
You will need to have installed locally on your computer:
|
||||
- [Xcode](https://developer.apple.com/xcode/) to build for iOS;
|
||||
- [Android Studio](https://developer.android.com/studio) to build for Android;
|
||||
|
||||
#### Install the demo dependencies
|
||||
|
||||
```bash
|
||||
# Use the version of node specified in .nvmrc
|
||||
nvm i
|
||||
|
||||
# Install dependencies
|
||||
npm i
|
||||
|
||||
# Before a native app can be compiled, the native source code must be generated.
|
||||
npx expo prebuild
|
||||
|
||||
# Configure the environment variable to connect to the local server
|
||||
cp env.example .env
|
||||
# edit .env and add your local ip address, for example: http://192.168.1.16:7860
|
||||
```
|
||||
|
||||
#### Running on Android
|
||||
|
||||
After plugging in an Android device [configured for debugging](https://developer.android.com/studio/debug/dev-options), run the following command:
|
||||
|
||||
```
|
||||
npm run android
|
||||
```
|
||||
|
||||
#### Running on iOS
|
||||
|
||||
Run the following command:
|
||||
|
||||
```
|
||||
npm run ios
|
||||
```
|
||||
|
||||
#### Connect to the server
|
||||
Use the http://localhost:5173 in your app.
|
||||
@@ -1,75 +0,0 @@
|
||||
{
|
||||
"expo": {
|
||||
"name": "bot-ready-rn",
|
||||
"slug": "bot-ready-rn",
|
||||
"version": "1.0.0",
|
||||
"orientation": "portrait",
|
||||
"icon": "./assets/icon.png",
|
||||
"userInterfaceStyle": "light",
|
||||
"splash": {
|
||||
"image": "./assets/splash.png",
|
||||
"resizeMode": "contain",
|
||||
"backgroundColor": "#ffffff"
|
||||
},
|
||||
"updates": {
|
||||
"fallbackToCacheTimeout": 0
|
||||
},
|
||||
"assetBundlePatterns": [
|
||||
"**/*"
|
||||
],
|
||||
"ios": {
|
||||
"supportsTablet": true,
|
||||
"bitcode": false,
|
||||
"bundleIdentifier": "co.daily.expo.BotReady",
|
||||
"infoPlist": {
|
||||
"UIBackgroundModes": [
|
||||
"voip"
|
||||
]
|
||||
},
|
||||
"appleTeamId": "EEBGKV9N3N"
|
||||
},
|
||||
"android": {
|
||||
"adaptiveIcon": {
|
||||
"foregroundImage": "./assets/adaptive-icon.png",
|
||||
"backgroundColor": "#FFFFFF"
|
||||
},
|
||||
"package": "co.daily.expo.BotReady",
|
||||
"permissions": [
|
||||
"android.permission.ACCESS_NETWORK_STATE",
|
||||
"android.permission.BLUETOOTH",
|
||||
"android.permission.CAMERA",
|
||||
"android.permission.INTERNET",
|
||||
"android.permission.MODIFY_AUDIO_SETTINGS",
|
||||
"android.permission.RECORD_AUDIO",
|
||||
"android.permission.SYSTEM_ALERT_WINDOW",
|
||||
"android.permission.WAKE_LOCK",
|
||||
"android.permission.FOREGROUND_SERVICE",
|
||||
"android.permission.FOREGROUND_SERVICE_CAMERA",
|
||||
"android.permission.FOREGROUND_SERVICE_MICROPHONE",
|
||||
"android.permission.FOREGROUND_SERVICE_MEDIA_PROJECTION",
|
||||
"android.permission.POST_NOTIFICATIONS"
|
||||
]
|
||||
},
|
||||
"web": {
|
||||
"favicon": "./assets/favicon.png"
|
||||
},
|
||||
"plugins": [
|
||||
"@config-plugins/react-native-webrtc",
|
||||
"@daily-co/config-plugin-rn-daily-js",
|
||||
[
|
||||
"expo-build-properties",
|
||||
{
|
||||
"android": {
|
||||
"minSdkVersion": 24,
|
||||
"compileSdkVersion": 35,
|
||||
"targetSdkVersion": 34,
|
||||
"buildToolsVersion": "35.0.0"
|
||||
},
|
||||
"ios": {
|
||||
"deploymentTarget": "15.1"
|
||||
}
|
||||
}
|
||||
]
|
||||
]
|
||||
}
|
||||
}
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 17 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 1.4 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 22 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 46 KiB |
@@ -1,7 +0,0 @@
|
||||
module.exports = function(api) {
|
||||
api.cache(true);
|
||||
return {
|
||||
presets: ['babel-preset-expo'],
|
||||
plugins: [["module:react-native-dotenv"]],
|
||||
};
|
||||
};
|
||||
@@ -1 +0,0 @@
|
||||
API_BASE_URL=http://YOUR_LOCAL_IP:7860
|
||||
@@ -1,7 +0,0 @@
|
||||
import { registerRootComponent } from "expo";
|
||||
|
||||
import App from "./src/App";
|
||||
|
||||
// registerRootComponent calls AppRegistry.registerComponent('main', () => App);
|
||||
// It also ensures that the environment is set up appropriately
|
||||
registerRootComponent(App);
|
||||
@@ -1,4 +0,0 @@
|
||||
// Learn more https://docs.expo.io/guides/customizing-metro
|
||||
const { getDefaultConfig } = require('expo/metro-config');
|
||||
|
||||
module.exports = getDefaultConfig(__dirname);
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,31 +0,0 @@
|
||||
{
|
||||
"name": "bot-ready-rn",
|
||||
"version": "1.0.0",
|
||||
"scripts": {
|
||||
"start": "expo start --dev-client",
|
||||
"android": "expo run:android --device",
|
||||
"ios": "expo run:ios --device",
|
||||
"web": "expo start --web"
|
||||
},
|
||||
"dependencies": {
|
||||
"@config-plugins/react-native-webrtc": "^10.0.0",
|
||||
"@daily-co/config-plugin-rn-daily-js": "0.0.7",
|
||||
"@daily-co/react-native-daily-js": "^0.70.0",
|
||||
"@daily-co/react-native-webrtc": "^118.0.3-daily.2",
|
||||
"@react-native-async-storage/async-storage": "1.23.1",
|
||||
"expo": "^52.0.0",
|
||||
"expo-build-properties": "~0.13.1",
|
||||
"expo-dev-client": "~5.0.5",
|
||||
"expo-splash-screen": "~0.29.16",
|
||||
"expo-status-bar": "~2.0.0",
|
||||
"react": "18.3.1",
|
||||
"react-native": "0.76.3",
|
||||
"react-native-background-timer": "^2.4.1",
|
||||
"react-native-dotenv": "^3.4.11",
|
||||
"react-native-get-random-values": "^1.11.0"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@babel/core": "^7.12.9"
|
||||
},
|
||||
"private": true
|
||||
}
|
||||
@@ -1,121 +0,0 @@
|
||||
import React, { useState, useEffect } from 'react';
|
||||
import {SafeAreaView, View, Text, Button, StyleSheet, ScrollView} from 'react-native';
|
||||
import Daily from "@daily-co/react-native-daily-js";
|
||||
import { API_BASE_URL } from "@env";
|
||||
|
||||
const CallScreen = () => {
|
||||
const [connectionStatus, setConnectionStatus] = useState('Disconnected');
|
||||
const [isConnected, setIsConnected] = useState(false);
|
||||
const [callObject, setCallObject] = useState(null);
|
||||
const [logs, setLogs] = useState([]);
|
||||
|
||||
useEffect(() => {
|
||||
if (callObject) {
|
||||
setupTrackListeners(callObject);
|
||||
}
|
||||
}, [callObject]);
|
||||
|
||||
const log = (message) => {
|
||||
setLogs((prevLogs) => [...prevLogs, `${new Date().toISOString()} - ${message}`]);
|
||||
console.log(message);
|
||||
};
|
||||
|
||||
const setupTrackListeners = (callObject) => {
|
||||
callObject.on("joined-meeting", () => {
|
||||
setConnectionStatus('Connected');
|
||||
setIsConnected(true);
|
||||
log('Client connected');
|
||||
});
|
||||
callObject.on("left-meeting", () => {
|
||||
setConnectionStatus('Disconnected');
|
||||
setIsConnected(false);
|
||||
log('Client disconnected');
|
||||
});
|
||||
callObject.on("participant-left", () => {
|
||||
// When the bot leaves, we are also disconnecting from the call
|
||||
disconnect().catch((err) => {
|
||||
log(`Failed to disconnect ${err}`);
|
||||
})
|
||||
});
|
||||
// Trigger so the bot can start sending audio
|
||||
callObject.on("track-started", (evt) => {
|
||||
if (evt.track.kind === "audio" && evt.participant.local === false) {
|
||||
handleEventToConsole(evt)
|
||||
log("Sending the message that will trigger the bot to play the audio.")
|
||||
callObject.sendAppMessage("playable")
|
||||
}
|
||||
});
|
||||
callObject.on("error", (evt) => log(`Error: ${evt.error}`));
|
||||
// Other events just for awareness
|
||||
callObject.on("track-stopped", handleEventToConsole);
|
||||
callObject.on("participant-joined", handleEventToConsole);
|
||||
callObject.on("participant-updated", handleEventToConsole);
|
||||
};
|
||||
|
||||
const handleEventToConsole = (evt) => {
|
||||
log(`Received event: ${evt.action}`);
|
||||
};
|
||||
|
||||
const connect = async () => {
|
||||
try {
|
||||
const callObject = Daily.createCallObject({ subscribeToTracksAutomatically: true });
|
||||
setCallObject(callObject);
|
||||
const connectionUrl = `${API_BASE_URL}/connect`
|
||||
const res = await fetch(connectionUrl, { method: "POST", headers: { "Content-Type": "application/json" } });
|
||||
const roomInfo = await res.json();
|
||||
await callObject.join({ url: roomInfo.room_url });
|
||||
} catch (error) {
|
||||
log(`Error connecting: ${error.message}`);
|
||||
}
|
||||
};
|
||||
|
||||
const disconnect = async () => {
|
||||
if (callObject) {
|
||||
try {
|
||||
await callObject.leave();
|
||||
await callObject.destroy();
|
||||
setCallObject(null);
|
||||
} catch (error) {
|
||||
log(`Error disconnecting: ${error.message}`);
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
return (
|
||||
<SafeAreaView style={styles.safeArea}>
|
||||
<View style={styles.container}>
|
||||
<View style={styles.statusBar}>
|
||||
<Text>Status: <Text style={styles.status}>{connectionStatus}</Text></Text>
|
||||
<View style={styles.controls}>
|
||||
<Button
|
||||
title={isConnected ? "Disconnect" : "Connect"}
|
||||
onPress={isConnected ? disconnect : connect}
|
||||
/>
|
||||
</View>
|
||||
</View>
|
||||
|
||||
<View style={styles.debugPanel}>
|
||||
<Text style={styles.debugTitle}>Debug Info</Text>
|
||||
<ScrollView style={styles.debugLog}>
|
||||
{logs.map((logEntry, index) => (
|
||||
<Text key={index} style={styles.logText}>{logEntry}</Text>
|
||||
))}
|
||||
</ScrollView>
|
||||
</View>
|
||||
</View>
|
||||
</SafeAreaView>
|
||||
);
|
||||
};
|
||||
|
||||
const styles = StyleSheet.create({
|
||||
safeArea: { flex: 1, backgroundColor: '#f0f0f0', padding: 20 },
|
||||
container: { flex: 1, margin: 20 },
|
||||
statusBar: { flexDirection: 'row', justifyContent: 'space-between', alignItems: 'center', padding: 10, backgroundColor: '#fff', borderRadius: 8, marginBottom: 20 },
|
||||
status: { fontWeight: 'bold' },
|
||||
controls: { flexDirection: 'row', gap: 10 },
|
||||
debugPanel: { height: '80%', backgroundColor: '#fff', borderRadius: 8, padding: 20},
|
||||
debugTitle: { fontSize: 16, fontWeight: 'bold' },
|
||||
debugLog: { height: '100%', overflow: 'scroll', backgroundColor: '#f8f8f8', padding: 10, borderRadius: 4, fontFamily: 'monospace', fontSize: 12, lineHeight: 1.4 },
|
||||
});
|
||||
|
||||
export default CallScreen;
|
||||
@@ -6,7 +6,6 @@
|
||||
|
||||
import argparse
|
||||
import os
|
||||
from typing import Optional
|
||||
|
||||
import aiohttp
|
||||
|
||||
@@ -19,7 +18,7 @@ async def configure(aiohttp_session: aiohttp.ClientSession):
|
||||
|
||||
|
||||
async def configure_with_args(
|
||||
aiohttp_session: aiohttp.ClientSession, parser: Optional[argparse.ArgumentParser] = None
|
||||
aiohttp_session: aiohttp.ClientSession, parser: argparse.ArgumentParser | None = None
|
||||
):
|
||||
if not parser:
|
||||
parser = argparse.ArgumentParser(description="Daily AI SDK Bot Sample")
|
||||
|
||||
@@ -18,7 +18,7 @@ from pipecat.frames.frames import AudioRawFrame, EndFrame, OutputAudioRawFrame,
|
||||
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.services.cartesia import CartesiaTTSService
|
||||
from pipecat.transports.services.daily import DailyParams, DailyTransport
|
||||
|
||||
load_dotenv(override=True)
|
||||
@@ -31,15 +31,16 @@ logger.add(sys.stderr, level="DEBUG")
|
||||
class SilenceFrame(OutputAudioRawFrame):
|
||||
def __init__(
|
||||
self,
|
||||
*,
|
||||
sample_rate: int,
|
||||
duration: float,
|
||||
audio: bytes = None,
|
||||
sample_rate: int = 16000,
|
||||
num_channels: int = 1,
|
||||
duration: float = 0.1,
|
||||
):
|
||||
# Initialize the parent class with the silent frame's data
|
||||
super().__init__(
|
||||
audio=self.create_silent_audio_frame(sample_rate, 1, duration).audio,
|
||||
audio=self.create_silent_audio_frame(sample_rate, num_channels, duration).audio,
|
||||
sample_rate=sample_rate,
|
||||
num_channels=1,
|
||||
num_channels=num_channels,
|
||||
)
|
||||
|
||||
@staticmethod
|
||||
@@ -64,7 +65,7 @@ async def main():
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22", # British Lady
|
||||
)
|
||||
|
||||
runner = PipelineRunner()
|
||||
@@ -79,10 +80,7 @@ async def main():
|
||||
return
|
||||
await task.queue_frames(
|
||||
[
|
||||
SilenceFrame(
|
||||
sample_rate=task.params.audio_out_sample_rate,
|
||||
duration=0.5,
|
||||
),
|
||||
SilenceFrame(duration=0.5),
|
||||
TTSSpeakFrame(f"Hello there, how are you doing today ?"),
|
||||
EndFrame(),
|
||||
]
|
||||
|
||||
@@ -21,9 +21,9 @@ 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.audio.audio_buffer_processor import AudioBufferProcessor
|
||||
from pipecat.services.canonical.metrics import CanonicalMetricsService
|
||||
from pipecat.services.elevenlabs.tts import ElevenLabsTTSService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.services.canonical import CanonicalMetricsService
|
||||
from pipecat.services.elevenlabs import ElevenLabsTTSService
|
||||
from pipecat.services.openai import OpenAILLMService
|
||||
from pipecat.transports.services.daily import DailyParams, DailyTransport
|
||||
|
||||
load_dotenv(override=True)
|
||||
@@ -43,7 +43,9 @@ async def main():
|
||||
DailyParams(
|
||||
audio_out_enabled=True,
|
||||
audio_in_enabled=True,
|
||||
video_out_enabled=False,
|
||||
camera_out_enabled=False,
|
||||
vad_enabled=True,
|
||||
vad_audio_passthrough=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
transcription_enabled=True,
|
||||
#
|
||||
@@ -63,6 +65,7 @@ async def main():
|
||||
# English
|
||||
#
|
||||
voice_id="cgSgspJ2msm6clMCkdW9",
|
||||
aiohttp_session=session,
|
||||
#
|
||||
# Spanish
|
||||
#
|
||||
@@ -70,7 +73,7 @@ async def main():
|
||||
# voice_id="gD1IexrzCvsXPHUuT0s3",
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
|
||||
|
||||
messages = [
|
||||
{
|
||||
@@ -111,17 +114,16 @@ async def main():
|
||||
llm,
|
||||
tts,
|
||||
transport.output(),
|
||||
canonical, # uploads audio buffer to Canonical AI for metrics
|
||||
audio_buffer_processor, # captures audio into a buffer
|
||||
canonical, # uploads audio buffer to Canonical AI for metrics
|
||||
context_aggregator.assistant(),
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
|
||||
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
|
||||
|
||||
@transport.event_handler("on_first_participant_joined")
|
||||
async def on_first_participant_joined(transport, participant):
|
||||
await audio_buffer_processor.start_recording()
|
||||
await transport.capture_participant_transcription(participant["id"])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
|
||||
@@ -23,8 +23,8 @@ 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.audio.audio_buffer_processor import AudioBufferProcessor
|
||||
from pipecat.services.elevenlabs.tts import ElevenLabsTTSService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.services.elevenlabs import ElevenLabsTTSService
|
||||
from pipecat.services.openai import OpenAILLMService
|
||||
from pipecat.transports.services.daily import DailyParams, DailyTransport
|
||||
|
||||
load_dotenv(override=True)
|
||||
@@ -32,16 +32,10 @@ load_dotenv(override=True)
|
||||
logger.remove(0)
|
||||
logger.add(sys.stderr, level="DEBUG")
|
||||
|
||||
# Create the recordings directory if it doesn't exist
|
||||
os.makedirs("recordings", exist_ok=True)
|
||||
|
||||
|
||||
async def save_audio(audio: bytes, sample_rate: int, num_channels: int, name: str):
|
||||
async def save_audio(audio: bytes, sample_rate: int, num_channels: int):
|
||||
if len(audio) > 0:
|
||||
filename = os.path.join(
|
||||
"recordings",
|
||||
f"{name}_conversation_recording{datetime.datetime.now().strftime('%Y%m%d_%H%M%S')}.wav",
|
||||
)
|
||||
filename = f"conversation_recording{datetime.datetime.now().strftime('%Y%m%d_%H%M%S')}.wav"
|
||||
with io.BytesIO() as buffer:
|
||||
with wave.open(buffer, "wb") as wf:
|
||||
wf.setsampwidth(2)
|
||||
@@ -66,7 +60,9 @@ async def main():
|
||||
DailyParams(
|
||||
audio_out_enabled=True,
|
||||
audio_in_enabled=True,
|
||||
video_out_enabled=False,
|
||||
camera_out_enabled=False,
|
||||
vad_enabled=True,
|
||||
vad_audio_passthrough=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
transcription_enabled=True,
|
||||
#
|
||||
@@ -86,6 +82,7 @@ async def main():
|
||||
# English
|
||||
#
|
||||
voice_id="cgSgspJ2msm6clMCkdW9",
|
||||
aiohttp_session=session,
|
||||
#
|
||||
# Spanish
|
||||
#
|
||||
@@ -93,7 +90,7 @@ async def main():
|
||||
# voice_id="gD1IexrzCvsXPHUuT0s3",
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
|
||||
|
||||
messages = [
|
||||
{
|
||||
@@ -112,9 +109,8 @@ async def main():
|
||||
context = OpenAILLMContext(messages)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
|
||||
# NOTE: Watch out! This will save all the conversation in memory. You
|
||||
# can pass `buffer_size` to get periodic callbacks.
|
||||
audiobuffer = AudioBufferProcessor(enable_turn_audio=True)
|
||||
# Save audio every 10 seconds.
|
||||
audiobuffer = AudioBufferProcessor(buffer_size=480000)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
@@ -128,23 +124,14 @@ async def main():
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
|
||||
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
|
||||
|
||||
@audiobuffer.event_handler("on_audio_data")
|
||||
async def on_audio_data(buffer, audio, sample_rate, num_channels):
|
||||
await save_audio(audio, sample_rate, num_channels, "full")
|
||||
|
||||
@audiobuffer.event_handler("on_user_turn_audio_data")
|
||||
async def on_user_turn_audio_data(buffer, audio, sample_rate, num_channels):
|
||||
await save_audio(audio, sample_rate, num_channels, "user")
|
||||
|
||||
@audiobuffer.event_handler("on_bot_turn_audio_data")
|
||||
async def on_bot_turn_audio_data(buffer, audio, sample_rate, num_channels):
|
||||
await save_audio(audio, sample_rate, num_channels, "bot")
|
||||
await save_audio(audio, sample_rate, num_channels)
|
||||
|
||||
@transport.event_handler("on_first_participant_joined")
|
||||
async def on_first_participant_joined(transport, participant):
|
||||
await audiobuffer.start_recording()
|
||||
await transport.capture_participant_transcription(participant["id"])
|
||||
await task.queue_frames([context_aggregator.user().get_context_frame()])
|
||||
|
||||
|
||||
@@ -1,9 +1,3 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import argparse
|
||||
import asyncio
|
||||
import os
|
||||
@@ -18,8 +12,8 @@ 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.elevenlabs.tts import ElevenLabsTTSService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.services.elevenlabs import ElevenLabsTTSService
|
||||
from pipecat.services.openai import OpenAILLMService
|
||||
from pipecat.transports.services.daily import DailyParams, DailyTransport
|
||||
|
||||
load_dotenv(override=True)
|
||||
@@ -41,7 +35,8 @@ async def main(room_url: str, token: str):
|
||||
api_key=daily_api_key,
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
video_out_enabled=False,
|
||||
camera_out_enabled=False,
|
||||
vad_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
transcription_enabled=True,
|
||||
),
|
||||
@@ -52,7 +47,7 @@ async def main(room_url: str, token: str):
|
||||
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 = [
|
||||
{
|
||||
@@ -75,7 +70,7 @@ async def main(room_url: str, token: str):
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
|
||||
task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
|
||||
|
||||
@transport.event_handler("on_first_participant_joined")
|
||||
async def on_first_participant_joined(transport, participant):
|
||||
|
||||
@@ -1,9 +1,3 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import os
|
||||
|
||||
import aiohttp
|
||||
|
||||
@@ -1,9 +1,3 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import asyncio
|
||||
import os
|
||||
import sys
|
||||
@@ -16,8 +10,8 @@ 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.openai.llm import OpenAILLMService
|
||||
from pipecat.services.cartesia import CartesiaTTSService
|
||||
from pipecat.services.openai import OpenAILLMService
|
||||
from pipecat.transports.services.daily import DailyParams, DailyTransport
|
||||
|
||||
load_dotenv(override=True)
|
||||
@@ -32,18 +26,18 @@ async def main(room_url: str, token: str):
|
||||
token,
|
||||
"bot",
|
||||
DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
transcription_enabled=True,
|
||||
vad_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
)
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY", ""), voice_id="71a7ad14-091c-4e8e-a314-022ece01c121"
|
||||
api_key=os.getenv("CARTESIA_API_KEY", ""), voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22"
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
|
||||
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
|
||||
|
||||
messages = [
|
||||
{
|
||||
@@ -68,7 +62,7 @@ async def main(room_url: str, token: str):
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
PipelineParams(
|
||||
allow_interruptions=True,
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
|
||||
@@ -1,4 +1,5 @@
|
||||
python-dotenv==1.0.1
|
||||
modal==0.71.3
|
||||
pipecat-ai[daily,silero,cartesia,openai]
|
||||
pipecat-ai[daily,silero,cartesia,openai]==0.0.52
|
||||
fastapi==0.115.6
|
||||
aiohttp==3.11.11
|
||||
|
||||
@@ -1,178 +0,0 @@
|
||||
# Handling PSTN/SIP Dial-in on Pipecat Cloud
|
||||
|
||||
This repository contains two server implementations for handling
|
||||
the pinless dial-in workflow in Pipecat Cloud. This is the companion to the
|
||||
Pipecat Cloud [pstn_sip starter image](https://github.com/daily-co/pipecat-cloud-images/tree/main/pipecat-starters/pstn_sip).
|
||||
In addition you can use `/api/dial` to trigger dial-out, and
|
||||
eventually, call-transfers.
|
||||
|
||||
1. [FastAPI Server](fastapi-webhook-server/README.md) -
|
||||
A FastAPI implementation that handles PSTN (Public Switched Telephone
|
||||
Network) and SIP (Session Initiation Protocol) calls using the Daily API.
|
||||
|
||||
2. [Next.js Serverless](nextjs-webhook-server/README.md) -
|
||||
A Next.js API implementation designed for deployment on Vercel's
|
||||
serverless platform.
|
||||
|
||||
Both implementations provide:
|
||||
|
||||
- HMAC signature validation for pinless webhook
|
||||
- Structured logging
|
||||
- Support for dial-in and dial-out settings
|
||||
- Voicemail detection and call transfer functionality (coming soon)
|
||||
- Test request handling
|
||||
|
||||
## Choosing an Implementation
|
||||
|
||||
- Use the **FastAPI Server** if you:
|
||||
|
||||
- Need a standalone server
|
||||
- Prefer Python and FastAPI
|
||||
- Want to deploy to traditional hosting platforms
|
||||
|
||||
- Use the **Next.js Serverless** implementation if you:
|
||||
- Want serverless deployment
|
||||
- Prefer JavaScript/TypeScript
|
||||
- Already use Next.js and Vercel for other projects
|
||||
- Need quick scaling and zero maintenance
|
||||
|
||||
## Prerequisites
|
||||
|
||||
### Environment Variables
|
||||
|
||||
Both implementations require similar environment variables:
|
||||
|
||||
- `PIPECAT_CLOUD_API_KEY`: Pipecat Cloud API Key, begins with pk\_\*
|
||||
- `AGENT_NAME`: Your Daily agent name
|
||||
- `PINLESS_HMAC_SECRET`: Your HMAC secret for request verification
|
||||
- `LOG_LEVEL`: (Optional) Logging level (defaults to 'info')
|
||||
|
||||
See the individual README files in each implementation directory for
|
||||
specific setup instructions.
|
||||
|
||||
### Phone number setup
|
||||
|
||||
You can buy a phone number through the Pipecat Cloud Dashboard:
|
||||
|
||||
1. Go to `Settings` > `Telephony`
|
||||
2. Follow the UI to purchase a phone number
|
||||
3. Configure the webhook URL to receive incoming calls (e.g. `https://my-webhook-url.com/api/dial`)
|
||||
|
||||
Or purchase the number using Daily's
|
||||
[PhoneNumbers API](https://docs.daily.co/reference/rest-api/phone-numbers).
|
||||
|
||||
```bash
|
||||
curl --request POST \
|
||||
--url https://api.daily.co/v1/domain-dialin-config \
|
||||
--header 'Authorization: Bearer $TOKEN' \
|
||||
--header 'Content-Type: application/json' \
|
||||
--data-raw '{
|
||||
"type": "pinless_dialin",
|
||||
"name_prefix": "Customer1",
|
||||
"phone_number": "+1PURCHASED_NUM",
|
||||
"room_creation_api": "https://example.com/api/dial",
|
||||
"hold_music_url": "https://example.com/static/ringtone.mp3",
|
||||
"timeout_config": {
|
||||
"message": "No agent is available right now"
|
||||
}
|
||||
}'
|
||||
```
|
||||
|
||||
The API will return a static SIP URI (`sip_uri`) that can be called
|
||||
from other SIP services.
|
||||
|
||||
### `room_creation_api`
|
||||
|
||||
To make and receive calls currently you have to host a server that
|
||||
handles incoming calls. In the coming weeks, incoming calls will be
|
||||
directly handled within Daily and we will expose an endpoint similar
|
||||
to `{service}/start` that will manage this for you.
|
||||
|
||||
In the meantime, the server described below serves as the webhook
|
||||
handler for the `room_creation_api`. Configure your pinless phone
|
||||
number or SIP interconnect to the `ngrok` tunnel or
|
||||
the actual server URL, append `/api/dial` to the webhook URL.
|
||||
|
||||
## Example curl commands
|
||||
|
||||
Note: Replace `http://localhost:3000` with your actual server URL and
|
||||
phone numbers with valid values for your use case.
|
||||
|
||||
### Dialin Request
|
||||
|
||||
The server will receive a request when a call is received from Daily.
|
||||
|
||||
### Dialout Request
|
||||
|
||||
Dial a number, will use any purchased number
|
||||
|
||||
```bash
|
||||
curl -X POST http://localhost:3000/api/dial \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{
|
||||
"dialout_settings": [
|
||||
{
|
||||
"phoneNumber": "+1234567890",
|
||||
}
|
||||
]
|
||||
}'
|
||||
```
|
||||
|
||||
Dial a number with callerId, which is the UUID of a purchased number.
|
||||
|
||||
```bash
|
||||
curl -X POST http://localhost:3000/api/dial \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{
|
||||
"dialout_settings": [
|
||||
{
|
||||
"phoneNumber": "+1234567890",
|
||||
"callerId": "purchased_phone_uuid"
|
||||
}
|
||||
]
|
||||
}'
|
||||
```
|
||||
|
||||
Dial a number
|
||||
|
||||
```bash
|
||||
curl -X POST http://localhost:3000/api/dial \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{
|
||||
"dialout_settings": [
|
||||
{
|
||||
"phoneNumber": "+1234567890",
|
||||
"callerId": "purchased_phone_uuid"
|
||||
}
|
||||
]
|
||||
}'
|
||||
```
|
||||
|
||||
### Advanced Request with Voicemail Detection
|
||||
|
||||
```bash
|
||||
curl -X POST http://localhost:3000/api/dial \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{
|
||||
"To": "+1234567890",
|
||||
"From": "+1987654321",
|
||||
"callId": "call-uuid-123",
|
||||
"callDomain": "domain-uuid-456",
|
||||
"dialout_settings": [
|
||||
{
|
||||
"phoneNumber": "+1234567890",
|
||||
"callerId": "purchased_phone_uuid"
|
||||
}
|
||||
],
|
||||
"voicemail_detection": {
|
||||
"testInPrebuilt": true
|
||||
},
|
||||
"call_transfer": {
|
||||
"mode": "dialout",
|
||||
"speakSummary": true,
|
||||
"storeSummary": true,
|
||||
"operatorNumber": "+1234567890",
|
||||
"testInPrebuilt": true
|
||||
}
|
||||
}'
|
||||
```
|
||||
@@ -1,98 +0,0 @@
|
||||
# FastAPI server for handling Daily PSTN/SIP Webhook
|
||||
|
||||
A FastAPI server that handles PSTN (Public Switched Telephone Network) and SIP (Session Initiation Protocol) calls using the Daily API.
|
||||
|
||||
## Setup
|
||||
|
||||
1. Clone the repository
|
||||
|
||||
2. Navigate to the `fastapi-webhook-server` directory:
|
||||
|
||||
```bash
|
||||
cd fastapi-webhook-server
|
||||
```
|
||||
|
||||
3. Install dependencies:
|
||||
|
||||
```bash
|
||||
pip install -r requirements.txt
|
||||
```
|
||||
|
||||
4. Copy `env.example` to `.env`:
|
||||
|
||||
```bash
|
||||
cp env.example .env
|
||||
```
|
||||
|
||||
5. Update `.env` with your credentials:
|
||||
|
||||
- `AGENT_NAME`: Your Daily agent name
|
||||
- `PIPECAT_CLOUD_API_KEY`: Your Daily API key
|
||||
- `PINLESS_HMAC_SECRET`: Your HMAC secret for request verification
|
||||
|
||||
## Running the Server
|
||||
|
||||
Start the server:
|
||||
|
||||
```bash
|
||||
python server.py
|
||||
```
|
||||
|
||||
The server will run on `http://localhost:7860` and you can expose it via ngrok for testing:
|
||||
|
||||
```bash
|
||||
`ngrok http 7860`
|
||||
```
|
||||
|
||||
> Tip: Use a subdomain for a consistent URL (e.g. `ngrok http -subdomain=mydomain http://localhost:7860`)
|
||||
|
||||
## API Endpoints
|
||||
|
||||
### GET /
|
||||
|
||||
Health check endpoint that returns a "Hello, World!" message.
|
||||
|
||||
### POST /api/dial
|
||||
|
||||
Initiates a PSTN/SIP call with the following request body format:
|
||||
|
||||
```json
|
||||
{
|
||||
"To": "+14152251493",
|
||||
"From": "+14158483432",
|
||||
"callId": "string-contains-uuid",
|
||||
"callDomain": "string-contains-uuid",
|
||||
"dialout_settings": [
|
||||
{
|
||||
"phoneNumber": "+14158483432",
|
||||
"callerId": "+14152251493"
|
||||
}
|
||||
],
|
||||
"voicemail_detection": {
|
||||
"testInPrebuilt": true
|
||||
},
|
||||
"call_transfer": {
|
||||
"mode": "dialout",
|
||||
"speakSummary": true,
|
||||
"storeSummary": true,
|
||||
"operatorNumber": "+14152250006",
|
||||
"testInPrebuilt": true
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
#### Response
|
||||
|
||||
Returns a JSON object containing:
|
||||
|
||||
- `status`: Success/failure status
|
||||
- `data`: Response from Daily API
|
||||
- `room_properties`: Properties of the created Daily room
|
||||
|
||||
## Error Handling
|
||||
|
||||
- 401: Invalid signature
|
||||
- 400: Invalid authorization header (e.g. missing Daily API key in bot.py)
|
||||
- 405: Method not allowed (e.g. incorrect route on the webhook URL)
|
||||
- 500: Server errors (missing API key, network issues)
|
||||
- Other status codes are passed through from the Daily API
|
||||
@@ -1,3 +0,0 @@
|
||||
AGENT_NAME="your-agent-name"
|
||||
PIPECAT_CLOUD_API_KEY="your-daily-api-key"
|
||||
PINLESS_HMAC_SECRET="hmac-secret-pinless-dialin"
|
||||
@@ -1,6 +0,0 @@
|
||||
fastapi
|
||||
uvicorn
|
||||
python-dotenv
|
||||
requests
|
||||
pydantic
|
||||
loguru
|
||||
@@ -1,202 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
# server.py
|
||||
|
||||
|
||||
import base64 # for calculating hmac signature
|
||||
import hmac
|
||||
import os # for accessing environment variables
|
||||
import time # for setting expiration time
|
||||
from typing import Any, Dict, List, Optional
|
||||
|
||||
import requests
|
||||
from dotenv import load_dotenv
|
||||
from fastapi import FastAPI, HTTPException, Request
|
||||
from loguru import logger
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
app = FastAPI()
|
||||
|
||||
|
||||
class RoomRequest(BaseModel):
|
||||
test: Optional[str] = Field(None, alias="Test", description="Test field")
|
||||
To: Optional[str] = Field(None, alias="to", description="Destination phone number")
|
||||
From: Optional[str] = Field(None, alias="from", description="Source phone number")
|
||||
callId: Optional[str] = Field(None, alias="call_id", description="Unique call identifier")
|
||||
callDomain: Optional[str] = Field(
|
||||
None, alias="call_domain", description="Call domain identifier"
|
||||
)
|
||||
dialout_settings: Optional[List[Dict[str, Any]]] = Field(
|
||||
None, description="An array of phone numbers or SIP URIs to dialout to"
|
||||
)
|
||||
voicemail_detection: Optional[Dict[str, Any]] = Field(
|
||||
None, description="A flag to perform voicemail or answeing-machine detection"
|
||||
)
|
||||
call_transfer: Optional[Dict[str, Any]] = Field(None, description="to initiate a call transfer")
|
||||
|
||||
class Config:
|
||||
populate_by_name = True
|
||||
alias_generator = None
|
||||
|
||||
|
||||
"""
|
||||
body can contain any fields, but for handling PSTN/SIP,
|
||||
we recommend sending the following custom values:
|
||||
dialin, dialout, voicemail detection, and call transfer
|
||||
|
||||
|
||||
"To": "+14152251493",
|
||||
"From": "+14158483432",
|
||||
"callId": "string-contains-uuid",
|
||||
"callDomain": "string-contains-uuid"
|
||||
These need to be remapped to dialin_settings
|
||||
|
||||
"dialout_settings": [
|
||||
{"phoneNumber": "+14158483432", "callerId": "+14152251493"},
|
||||
{"sipUri": "sip:username@sip.hostname"}
|
||||
],
|
||||
},
|
||||
|
||||
voicemail_detection:{
|
||||
testInPrebuilt: true
|
||||
},
|
||||
|
||||
"call_transfer": {
|
||||
"mode": "dialout",
|
||||
"speakSummary": true,
|
||||
"storeSummary": true,
|
||||
"operatorNumber": "+14152250006",
|
||||
"testInPrebuilt": true
|
||||
}
|
||||
"""
|
||||
|
||||
|
||||
@app.get("/")
|
||||
async def read_root():
|
||||
return {"message": "Hello, World!"}
|
||||
|
||||
|
||||
@app.post("/api/dial")
|
||||
async def dial(request: RoomRequest, raw_request: Request):
|
||||
logger.info("Incoming request to /dial:")
|
||||
logger.info(f"Headers: {dict(raw_request.headers)}")
|
||||
raw_body = await raw_request.body()
|
||||
raw_body_str = raw_body.decode()
|
||||
logger.info(f"Raw body: {raw_body_str}")
|
||||
logger.info(f"Parsed body: {request.dict()}")
|
||||
|
||||
# calculate signature and compare/verify
|
||||
hmac_secret = os.getenv("PINLESS_HMAC_SECRET")
|
||||
timestamp = raw_request.headers.get("x-pinless-timestamp")
|
||||
signature = raw_request.headers.get("x-pinless-signature")
|
||||
|
||||
if not hmac_secret:
|
||||
logger.debug("Skipping HMAC validation - PINLESS_HMAC_SECRET not set")
|
||||
elif timestamp and signature:
|
||||
message = timestamp + "." + raw_body_str
|
||||
|
||||
base64_decoded_secret = base64.b64decode(hmac_secret)
|
||||
computed_signature = base64.b64encode(
|
||||
hmac.new(base64_decoded_secret, message.encode(), "sha256").digest()
|
||||
).decode()
|
||||
|
||||
if computed_signature != signature:
|
||||
logger.error(f"Invalid signature. Expected {signature}, got {computed_signature}")
|
||||
raise HTTPException(status_code=401, detail="Invalid signature")
|
||||
else:
|
||||
logger.debug("Skipping HMAC validation - no signature headers present")
|
||||
|
||||
if request.test == "test":
|
||||
logger.debug("Test request received")
|
||||
return {"status": "success", "message": "Test request received"}
|
||||
|
||||
dialin_settings = None
|
||||
# these fields are camelCase in the request
|
||||
required_fields = ["To", "From", "callId", "callDomain"]
|
||||
if all(
|
||||
field in request.dict() and request.dict()[field] is not None for field in required_fields
|
||||
):
|
||||
# transform from camelCase to snake_case because daily-python expects snake_case
|
||||
dialin_settings = {
|
||||
"From": request.From,
|
||||
"To": request.To,
|
||||
"call_id": request.callId,
|
||||
"call_domain": request.callDomain,
|
||||
# transform from camelCase to snake_case
|
||||
}
|
||||
logger.debug(f"Populated dialin_settings from request: {dialin_settings}")
|
||||
|
||||
daily_room_properties = {
|
||||
"enable_dialout": request.dialout_settings is not None,
|
||||
}
|
||||
|
||||
if dialin_settings is not None:
|
||||
sip_config = {
|
||||
"display_name": request.From,
|
||||
"sip_mode": "dial-in",
|
||||
"num_endpoints": 2 if request.call_transfer is not None else 1,
|
||||
"codecs": {"audio": ["OPUS"]},
|
||||
}
|
||||
daily_room_properties["sip"] = sip_config
|
||||
|
||||
# Setting default expiry to 5 minutes from now
|
||||
daily_room_properties["exp"] = int(time.time()) + (5 * 60)
|
||||
|
||||
logger.debug(f"Daily room properties: {daily_room_properties}")
|
||||
payload = {
|
||||
"createDailyRoom": True,
|
||||
"dailyRoomProperties": daily_room_properties,
|
||||
"body": {
|
||||
"dialin_settings": dialin_settings,
|
||||
"dialout_settings": request.dialout_settings,
|
||||
"voicemail_detection": request.voicemail_detection,
|
||||
"call_transfer": request.call_transfer,
|
||||
},
|
||||
}
|
||||
|
||||
pcc_api_key = os.getenv("PIPECAT_CLOUD_API_KEY")
|
||||
agent_name = os.getenv("AGENT_NAME", "my-first-agent")
|
||||
|
||||
if not pcc_api_key:
|
||||
raise HTTPException(status_code=500, detail="DAILY_API_KEY environment variable is not set")
|
||||
|
||||
headers = {"Authorization": f"Bearer {pcc_api_key}", "Content-Type": "application/json"}
|
||||
|
||||
url = f"https://api.pipecat.daily.co/v1/public/{agent_name}/start"
|
||||
|
||||
logger.debug(f"Making API call to Daily: {url} {headers} {payload}")
|
||||
|
||||
try:
|
||||
response = requests.post(url, json=payload, headers=headers)
|
||||
response.raise_for_status()
|
||||
response_data = response.json()
|
||||
logger.debug(f"Response: {response_data}")
|
||||
return {
|
||||
"status": "success",
|
||||
"data": response_data,
|
||||
"room_properties": daily_room_properties,
|
||||
}
|
||||
except requests.exceptions.HTTPError as e:
|
||||
# Pass through the status code and error details from the Daily API
|
||||
status_code = e.response.status_code
|
||||
error_detail = e.response.json() if e.response.content else str(e)
|
||||
logger.error(f"HTTP error: {error_detail}")
|
||||
raise HTTPException(status_code=status_code, detail=error_detail)
|
||||
except requests.exceptions.RequestException as e:
|
||||
logger.error(f"Request error: {str(e)}")
|
||||
raise HTTPException(status_code=500, detail=str(e))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
try:
|
||||
import uvicorn
|
||||
|
||||
uvicorn.run(app, host="0.0.0.0", port=7860)
|
||||
except KeyboardInterrupt:
|
||||
logger.info("Server stopped manually")
|
||||
@@ -1,53 +0,0 @@
|
||||
# dependencies
|
||||
/node_modules
|
||||
/.pnp
|
||||
.pnp.js
|
||||
|
||||
# testing
|
||||
/coverage
|
||||
|
||||
# next.js
|
||||
/.next/
|
||||
/out/
|
||||
|
||||
# production
|
||||
/build
|
||||
|
||||
# misc
|
||||
.DS_Store
|
||||
*.pem
|
||||
|
||||
# debug
|
||||
npm-debug.log*
|
||||
yarn-debug.log*
|
||||
yarn-error.log*
|
||||
.pnpm-debug.log*
|
||||
|
||||
# local env files
|
||||
.env*.local
|
||||
|
||||
# vercel
|
||||
.vercel
|
||||
|
||||
# typescript
|
||||
*.tsbuildinfo
|
||||
next-env.d.ts
|
||||
|
||||
# IDE specific files
|
||||
.idea/
|
||||
.vscode/
|
||||
*.swp
|
||||
*.swo
|
||||
|
||||
# Logs
|
||||
logs
|
||||
*.log
|
||||
|
||||
# OS generated files
|
||||
.DS_Store
|
||||
.DS_Store?
|
||||
._*
|
||||
.Spotlight-V100
|
||||
.Trashes
|
||||
ehthumbs.db
|
||||
Thumbs.db
|
||||
@@ -1,115 +0,0 @@
|
||||
# Next.js server for handling Daily PSTN/SIP Webhook
|
||||
|
||||
Next.js API routes for handling Daily PSTN/SIP Pipecat requests.
|
||||
|
||||
## Features
|
||||
|
||||
- API endpoint for handling Daily PSTN/SIP Pipecat requests
|
||||
- HMAC signature validation
|
||||
- Structured logging with Pino
|
||||
- Support for dial-in and dial-out settings
|
||||
- Voicemail detection and call transfer functionality
|
||||
- Test request handling
|
||||
|
||||
## Setup
|
||||
|
||||
1. Clone the repository
|
||||
|
||||
2. Navigate to the `nextjs-webhook-server` directory:
|
||||
|
||||
```bash
|
||||
cd nextjs-webhook-server
|
||||
```
|
||||
|
||||
3. Install dependencies:
|
||||
|
||||
```bash
|
||||
npm install
|
||||
```
|
||||
|
||||
4. Create `.env.local` file with your credentials:
|
||||
|
||||
```bash
|
||||
cp env.local.example .env.local
|
||||
```
|
||||
|
||||
5. Update your `.env` with your secrets:
|
||||
|
||||
```bash
|
||||
PIPECAT_CLOUD_API_KEY=pk_*
|
||||
AGENT_NAME=my-first-agent
|
||||
PINLESS_HMAC_SECRET=your_hmac_secret
|
||||
LOG_LEVEL=info
|
||||
```
|
||||
|
||||
### Running the server
|
||||
|
||||
Run the development server:
|
||||
|
||||
```bash
|
||||
npm run dev
|
||||
```
|
||||
|
||||
The server will run on `http://localhost:7860` and you can expose it via ngrok for testing:
|
||||
|
||||
```bash
|
||||
`ngrok http 7860`
|
||||
```
|
||||
|
||||
> Tip: Use a subdomain for a consistent URL (e.g. `ngrok http -subdomain=mydomain http://localhost:7860`)
|
||||
|
||||
## API Endpoints
|
||||
|
||||
### GET /api
|
||||
|
||||
Returns a simple "Hello, World!" message with a cute cat emoji to verify the server is running.
|
||||
|
||||
### POST /api/dial
|
||||
|
||||
Handles dial-in and dial-out requests for Pipecat Cloud.
|
||||
|
||||
#### Test Requests
|
||||
|
||||
The endpoint handles test requests when a webhook is configured. Send a request with `"Test": "test"` to verify your setup:
|
||||
|
||||
```json
|
||||
{
|
||||
"Test": "test"
|
||||
}
|
||||
```
|
||||
|
||||
#### Production Request Format
|
||||
|
||||
```json
|
||||
{
|
||||
// for dial-in from webhook
|
||||
"To": "+14152251493",
|
||||
"From": "+14158483432",
|
||||
"callId": "string-contains-uuid",
|
||||
"callDomain": "string-contains-uuid",
|
||||
// for making a dial out to a phone or SIP
|
||||
"dialout_settings": [
|
||||
{ "phoneNumber": "+14158483432", "callerId": "purchased_phone_uuid" },
|
||||
{ "sipUri": "sip:username@sip.hostname.com" }
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
## Deployment
|
||||
|
||||
The application is configured for Vercel deployment:
|
||||
|
||||
1. Push your code to a Git repository
|
||||
2. Import your project in Vercel dashboard
|
||||
3. Configure environment variables:
|
||||
- `PIPECAT_CLOUD_API_KEY`
|
||||
- `AGENT_NAME`
|
||||
- `PINLESS_HMAC_SECRET`
|
||||
- `LOG_LEVEL` (optional, defaults to 'info')
|
||||
4. Deploy!
|
||||
|
||||
## Security
|
||||
|
||||
- HMAC signature validation for request authentication
|
||||
- Environment variables for sensitive credentials
|
||||
- Method validation (POST only for /dial)
|
||||
@@ -1,4 +0,0 @@
|
||||
AGENT_NAME=my-first-agent
|
||||
PIPECAT_CLOUD_API_KEY=your_daily_api_key
|
||||
PINLESS_HMAC_SECRET=your_hmac_secret
|
||||
LOG_LEVEL="info"
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,22 +0,0 @@
|
||||
{
|
||||
"name": "my-daily-app",
|
||||
"version": "0.1.0",
|
||||
"private": true,
|
||||
"scripts": {
|
||||
"dev": "next dev -p 7860",
|
||||
"build": "next build",
|
||||
"start": "next start -p 7860",
|
||||
"lint": "next lint"
|
||||
},
|
||||
"dependencies": {
|
||||
"axios": "^1.6.0",
|
||||
"next": "^14.0.0",
|
||||
"pino": "^8.15.0",
|
||||
"react": "^18.2.0",
|
||||
"react-dom": "^18.2.0"
|
||||
},
|
||||
"devDependencies": {
|
||||
"eslint": "^8.46.0",
|
||||
"eslint-config-next": "^14.0.0"
|
||||
}
|
||||
}
|
||||
@@ -1,176 +0,0 @@
|
||||
import { logger } from '../../lib/utils';
|
||||
import axios from 'axios';
|
||||
import crypto from 'crypto';
|
||||
|
||||
const validateSignature = (body, signature, timestamp, secret) => {
|
||||
// Skip if any required fields are missing
|
||||
if (!signature || !timestamp || !secret) {
|
||||
logger.warn('Missing required fields for HMAC validation');
|
||||
return true;
|
||||
}
|
||||
|
||||
try {
|
||||
const decodedSecret = Buffer.from(secret, 'base64');
|
||||
const hmac = crypto.createHmac('sha256', decodedSecret);
|
||||
const signatureData = `${timestamp}.${body}`;
|
||||
const computedSignature = hmac.update(signatureData).digest('base64');
|
||||
|
||||
logger.debug('Signature validation:', {
|
||||
timestamp,
|
||||
signatureData: signatureData.substring(0, 50) + '...',
|
||||
computedSignature,
|
||||
receivedSignature: signature
|
||||
});
|
||||
|
||||
return computedSignature === signature;
|
||||
} catch (error) {
|
||||
logger.error('Error validating signature:', error);
|
||||
return true; // Allow request to proceed on error
|
||||
}
|
||||
};
|
||||
|
||||
export default async function handler(req, res) {
|
||||
// Only allow POST requests
|
||||
if (req.method !== 'POST') {
|
||||
return res.status(405).json({ error: 'Method not allowed' });
|
||||
}
|
||||
|
||||
try {
|
||||
logger.info('Incoming request to /api/dial:');
|
||||
logger.info(`Headers: ${JSON.stringify(req.headers)}`);
|
||||
|
||||
const rawBody = JSON.stringify(req.body);
|
||||
logger.info(`Raw body: ${rawBody}`);
|
||||
|
||||
const signature = req.headers['x-pinless-signature'];
|
||||
const timestamp = req.headers['x-pinless-timestamp'];
|
||||
|
||||
if (signature && timestamp) {
|
||||
logger.info('Validating HMAC signature');
|
||||
if (!validateSignature(rawBody, signature, timestamp, process.env.PINLESS_HMAC_SECRET)) {
|
||||
logger.error('Invalid HMAC signature', { signature, timestamp });
|
||||
return res.status(401).json({
|
||||
error: 'Invalid signature',
|
||||
message: 'Invalid HMAC signature'
|
||||
});
|
||||
}
|
||||
} else {
|
||||
logger.info('Skipping HMAC validation - no signature headers present');
|
||||
}
|
||||
|
||||
// Extract request data
|
||||
const {
|
||||
Test: test,
|
||||
To,
|
||||
From,
|
||||
callId,
|
||||
callDomain,
|
||||
dialout_settings,
|
||||
voicemail_detection,
|
||||
call_transfer
|
||||
} = req.body;
|
||||
|
||||
// Handle test requests when a webhook is configured
|
||||
if (test === 'test') {
|
||||
logger.debug('Test request received');
|
||||
return res.status(200).json({ status: 'success', message: 'Test request received' });
|
||||
}
|
||||
|
||||
// Process dialin settings
|
||||
let dialin_settings = null;
|
||||
const requiredFields = ['To', 'From', 'callId', 'callDomain'];
|
||||
|
||||
if (requiredFields.every(field => req.body[field] !== undefined && req.body[field] !== null)) {
|
||||
dialin_settings = {
|
||||
// snake_case because pipecat expects this format
|
||||
From,
|
||||
To,
|
||||
call_id: callId,
|
||||
call_domain: callDomain,
|
||||
};
|
||||
logger.debug(`Populated dialin_settings from request: ${JSON.stringify(dialin_settings)}`);
|
||||
}
|
||||
|
||||
// Set up Daily room properties
|
||||
const daily_room_properties = {
|
||||
enable_dialout: dialout_settings !== undefined && dialout_settings !== null,
|
||||
exp: Math.floor(Date.now() / 1000) + (5 * 60), // 5 minutes from now
|
||||
};
|
||||
|
||||
// Configure SIP if dialin settings are provided
|
||||
if (dialin_settings !== null) {
|
||||
const sip_config = {
|
||||
display_name: From,
|
||||
sip_mode: 'dial-in',
|
||||
num_endpoints: call_transfer !== null ? 2 : 1,
|
||||
codecs: {"audio": ["OPUS"]},
|
||||
};
|
||||
daily_room_properties.sip = sip_config;
|
||||
}
|
||||
|
||||
// Prepare payload for {service}/start API call
|
||||
const payload = {
|
||||
createDailyRoom: true,
|
||||
dailyRoomProperties: daily_room_properties,
|
||||
body: {
|
||||
dialin_settings,
|
||||
dialout_settings,
|
||||
voicemail_detection,
|
||||
call_transfer,
|
||||
},
|
||||
};
|
||||
|
||||
logger.debug(`Daily room properties: ${JSON.stringify(daily_room_properties)}`);
|
||||
|
||||
// Get Daily API key and agent name from environment variables
|
||||
const pccApiKey = process.env.PIPECAT_CLOUD_API_KEY;
|
||||
const agentName = process.env.AGENT_NAME || 'my-first-agent';
|
||||
|
||||
if (!pccApiKey) {
|
||||
throw new Error('PIPECAT_CLOUD_API_KEY environment variable is not set');
|
||||
}
|
||||
|
||||
// Set up headers for Daily API call
|
||||
const headers = {
|
||||
'Authorization': `Bearer ${pccApiKey}`,
|
||||
'Content-Type': 'application/json',
|
||||
};
|
||||
|
||||
const url = `https://api.pipecat.daily.co/v1/public/${agentName}/start`;
|
||||
logger.debug(`Making API call to Daily: ${url} ${JSON.stringify(headers)} ${JSON.stringify(payload)}`);
|
||||
|
||||
try {
|
||||
const response = await axios.post(url, payload, { headers });
|
||||
logger.debug(`Response: ${JSON.stringify(response.data)}`);
|
||||
|
||||
return res.status(200).json({
|
||||
status: 'success',
|
||||
data: response.data,
|
||||
room_properties: daily_room_properties,
|
||||
});
|
||||
} catch (error) {
|
||||
if (error.response) {
|
||||
// Pass through status code and error details from the Daily API
|
||||
const statusCode = error.response.status;
|
||||
const errorDetail = error.response.data || error.message;
|
||||
logger.error(`HTTP error: ${JSON.stringify(errorDetail)}`);
|
||||
return res.status(statusCode).json(errorDetail);
|
||||
} else {
|
||||
logger.error(`Request error: ${error.message}`);
|
||||
return res.status(500).json({ error: error.message });
|
||||
}
|
||||
}
|
||||
} catch (error) {
|
||||
logger.error(`Unexpected error: ${error.message}`);
|
||||
return res.status(500).json({ error: 'Internal server error', message: error.message });
|
||||
}
|
||||
}
|
||||
|
||||
// Configure body parser to preserve raw body text
|
||||
export const config = {
|
||||
api: {
|
||||
bodyParser: {
|
||||
sizeLimit: '1mb',
|
||||
},
|
||||
},
|
||||
};
|
||||
@@ -1,6 +0,0 @@
|
||||
import { logger } from '../../lib/utils';
|
||||
|
||||
export default function handler(req, res) {
|
||||
logger.info('Received request to /api');
|
||||
res.status(200).json({ message: 'Hello, World! from ᓚᘏᗢ' });
|
||||
}
|
||||
@@ -1,6 +0,0 @@
|
||||
module.exports = {
|
||||
version: 2,
|
||||
buildCommand: "next build",
|
||||
outputDirectory: ".next",
|
||||
cleanUrls: true
|
||||
};
|
||||
@@ -1,94 +0,0 @@
|
||||
# Python
|
||||
__pycache__/
|
||||
*.py[cod]
|
||||
*$py.class
|
||||
*.so
|
||||
.Python
|
||||
build/
|
||||
dist/
|
||||
*.egg-info/
|
||||
*.egg
|
||||
.installed.cfg
|
||||
.eggs/
|
||||
downloads/
|
||||
lib/
|
||||
lib64/
|
||||
parts/
|
||||
sdist/
|
||||
var/
|
||||
wheels/
|
||||
share/python-wheels/
|
||||
MANIFEST
|
||||
|
||||
# Virtual Environments
|
||||
venv/
|
||||
env/
|
||||
.env
|
||||
.venv/
|
||||
ENV/
|
||||
env.bak/
|
||||
venv.bak/
|
||||
|
||||
# IDE
|
||||
.idea/
|
||||
.vscode/
|
||||
.spyderproject
|
||||
.spyproject
|
||||
.ropeproject
|
||||
|
||||
# Testing and Coverage
|
||||
.coverage
|
||||
.coverage.*
|
||||
htmlcov/
|
||||
.pytest_cache/
|
||||
.tox/
|
||||
.nox/
|
||||
.cache
|
||||
nosetests.xml
|
||||
coverage.xml
|
||||
*.cover
|
||||
.hypothesis/
|
||||
cover/
|
||||
|
||||
# Logs and Databases
|
||||
*.log
|
||||
*.db
|
||||
db.sqlite3
|
||||
db.sqlite3-journal
|
||||
pip-log.txt
|
||||
|
||||
# System Files
|
||||
.DS_Store
|
||||
Thumbs.db
|
||||
desktop.ini
|
||||
*.swp
|
||||
*.swo
|
||||
*.bak
|
||||
*.tmp
|
||||
*~
|
||||
|
||||
# Build and Documentation
|
||||
docs/_build/
|
||||
.pybuilder/
|
||||
target/
|
||||
instance/
|
||||
.webassets-cache
|
||||
.pdm.toml
|
||||
.pdm-python
|
||||
.pdm-build/
|
||||
__pypackages__/
|
||||
|
||||
# Other
|
||||
*.mo
|
||||
*.pot
|
||||
*.sage.py
|
||||
.mypy_cache/
|
||||
.dmypy.json
|
||||
dmypy.json
|
||||
.pyre/
|
||||
.pytype/
|
||||
cython_debug/
|
||||
.ipynb_checkpoints
|
||||
|
||||
# Pipecat cloud
|
||||
.pcc-deploy.toml
|
||||
@@ -1,7 +0,0 @@
|
||||
FROM dailyco/pipecat-base:latest
|
||||
|
||||
COPY ./requirements.txt requirements.txt
|
||||
|
||||
RUN pip install --no-cache-dir --upgrade -r requirements.txt
|
||||
|
||||
COPY ./bot.py bot.py
|
||||
@@ -1,196 +0,0 @@
|
||||
# Pipecat Cloud Starter Project
|
||||
|
||||
[](https://docs.pipecat.daily.co) [](https://discord.gg/dailyco)
|
||||
|
||||
A template voice agent for [Pipecat Cloud](https://www.daily.co/products/pipecat-cloud/) that demonstrates building and deploying a conversational AI agent.
|
||||
|
||||
> **For a detailed step-by-step guide, see our [Quickstart Documentation](https://docs.pipecat.daily.co/quickstart).**
|
||||
|
||||
## Prerequisites
|
||||
|
||||
- Python 3.10+
|
||||
- Linux, MacOS, or Windows Subsystem for Linux (WSL)
|
||||
- [Docker](https://www.docker.com) and a Docker repository (e.g., [Docker Hub](https://hub.docker.com))
|
||||
- A Docker Hub account (or other container registry account)
|
||||
- [Pipecat Cloud](https://pipecat.daily.co) account
|
||||
|
||||
> **Note**: If you haven't installed Docker yet, follow the official installation guides for your platform ([Linux](https://docs.docker.com/engine/install/), [Mac](https://docs.docker.com/desktop/setup/install/mac-install/), [Windows](https://docs.docker.com/desktop/setup/install/windows-install/)). For Docker Hub, [create a free account](https://hub.docker.com/signup) and log in via terminal with `docker login`.
|
||||
|
||||
## Get Started
|
||||
|
||||
### 1. Get the starter project
|
||||
|
||||
Clone the starter project from GitHub:
|
||||
|
||||
```bash
|
||||
git clone https://github.com/daily-co/pipecat-cloud-starter
|
||||
cd pipecat-cloud-starter
|
||||
```
|
||||
|
||||
### 2. Set up your Python environment
|
||||
|
||||
We recommend using a virtual environment to manage your Python dependencies.
|
||||
|
||||
```bash
|
||||
# Create a virtual environment
|
||||
python -m venv .venv
|
||||
|
||||
# Activate it
|
||||
source .venv/bin/activate # On Windows: .venv\Scripts\activate
|
||||
|
||||
# Install the Pipecat Cloud CLI
|
||||
pip install pipecatcloud
|
||||
```
|
||||
|
||||
### 3. Authenticate with Pipecat Cloud
|
||||
|
||||
```bash
|
||||
pcc auth login
|
||||
```
|
||||
|
||||
### 4. Acquire required API keys
|
||||
|
||||
This starter requires the following API keys:
|
||||
|
||||
- **OpenAI API Key**: Get from [platform.openai.com/api-keys](https://platform.openai.com/api-keys)
|
||||
- **Cartesia API Key**: Get from [play.cartesia.ai/keys](https://play.cartesia.ai/keys)
|
||||
- **Daily API Key**: Automatically provided through your Pipecat Cloud account
|
||||
|
||||
### 5. Configure to run locally (optional)
|
||||
|
||||
You can test your agent locally before deploying to Pipecat Cloud:
|
||||
|
||||
```bash
|
||||
# Set environment variables with your API keys
|
||||
export CARTESIA_API_KEY="your_cartesia_key"
|
||||
export DAILY_API_KEY="your_daily_key"
|
||||
export OPENAI_API_KEY="your_openai_key"
|
||||
```
|
||||
|
||||
> Your `DAILY_API_KEY` can be found at [https://pipecat.daily.co](https://pipecat.daily.co) under the `Settings` in the `Daily (WebRTC)` tab.
|
||||
|
||||
First install requirements:
|
||||
|
||||
```bash
|
||||
pip install -r requirements.txt
|
||||
```
|
||||
|
||||
Then, launch the bot.py script locally:
|
||||
|
||||
```bash
|
||||
LOCAL_RUN=1 python bot.py
|
||||
```
|
||||
|
||||
## Deploy & Run
|
||||
|
||||
### 1. Build and push your Docker image
|
||||
|
||||
```bash
|
||||
# Build the image (targeting ARM architecture for cloud deployment)
|
||||
docker build --platform=linux/arm64 -t my-first-agent:latest .
|
||||
|
||||
# Tag with your Docker username and version
|
||||
docker tag my-first-agent:latest your-username/my-first-agent:0.1
|
||||
|
||||
# Push to Docker Hub
|
||||
docker push your-username/my-first-agent:0.1
|
||||
```
|
||||
|
||||
### 2. Create a secret set for your API keys
|
||||
|
||||
The starter project requires API keys for OpenAI and Cartesia:
|
||||
|
||||
```bash
|
||||
# Copy the example env file
|
||||
cp env.example .env
|
||||
|
||||
# Edit .env to add your API keys:
|
||||
# CARTESIA_API_KEY=your_cartesia_key
|
||||
# OPENAI_API_KEY=your_openai_key
|
||||
|
||||
# Create a secret set from your .env file
|
||||
pcc secrets set my-first-agent-secrets --file .env
|
||||
```
|
||||
|
||||
Alternatively, you can create secrets directly via CLI:
|
||||
|
||||
```bash
|
||||
pcc secrets set my-first-agent-secrets \
|
||||
CARTESIA_API_KEY=your_cartesia_key \
|
||||
OPENAI_API_KEY=your_openai_key
|
||||
```
|
||||
|
||||
### 3. Deploy to Pipecat Cloud
|
||||
|
||||
```bash
|
||||
pcc deploy my-first-agent your-username/my-first-agent:0.1 --secrets my-first-agent-secrets
|
||||
```
|
||||
|
||||
> **Note (Optional)**: For a more maintainable approach, you can use the included `pcc-deploy.toml` file:
|
||||
>
|
||||
> ```toml
|
||||
> agent_name = "my-first-agent"
|
||||
> image = "your-username/my-first-agent:0.1"
|
||||
> secret_set = "my-first-agent-secrets"
|
||||
>
|
||||
> [scaling]
|
||||
> min_instances = 0
|
||||
> ```
|
||||
>
|
||||
> Then simply run `pcc deploy` without additional arguments.
|
||||
|
||||
> **Note**: If your repository is private, you'll need to add credentials:
|
||||
>
|
||||
> ```bash
|
||||
> # Create pull secret (you’ll be prompted for credentials)
|
||||
> pcc secrets image-pull-secret pull-secret https://index.docker.io/v1/
|
||||
>
|
||||
> # Deploy with credentials
|
||||
> pcc deploy my-first-agent your-username/my-first-agent:0.1 --credentials pull-secret
|
||||
> ```
|
||||
|
||||
### 4. Check deployment and scaling (optional)
|
||||
|
||||
By default, your agent will use "scale-to-zero" configuration, which means it may have a cold start of around 10 seconds when first used. By default, idle instances are maintained for 5 minutes before being terminated when using scale-to-zero.
|
||||
|
||||
For more responsive testing, you can scale your deployment to keep a minimum of one instance warm:
|
||||
|
||||
```bash
|
||||
# Ensure at least one warm instance is always available
|
||||
pcc deploy my-first-agent your-username/my-first-agent:0.1 --min-instances 1
|
||||
|
||||
# Check the status of your deployment
|
||||
pcc agent status my-first-agent
|
||||
```
|
||||
|
||||
By default, idle instances are maintained for 5 minutes before being terminated when using scale-to-zero.
|
||||
|
||||
### 5. Create an API key
|
||||
|
||||
```bash
|
||||
# Create a public API key for accessing your agent
|
||||
pcc organizations keys create
|
||||
|
||||
# Set it as the default key to use with your agent
|
||||
pcc organizations keys use
|
||||
```
|
||||
|
||||
### 6. Start your agent
|
||||
|
||||
```bash
|
||||
# Start a session with your agent in a Daily room
|
||||
pcc agent start my-first-agent --use-daily
|
||||
```
|
||||
|
||||
This will return a URL, which you can use to connect to your running agent.
|
||||
|
||||
## Documentation
|
||||
|
||||
For more details on Pipecat Cloud and its capabilities:
|
||||
|
||||
- [Pipecat Cloud Documentation](https://docs.pipecat.daily.co)
|
||||
- [Pipecat Project Documentation](https://docs.pipecat.ai)
|
||||
|
||||
## Support
|
||||
|
||||
Join our [Discord community](https://discord.gg/dailyco) for help and discussions.
|
||||
@@ -1,161 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import os
|
||||
|
||||
import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
from pipecatcloud.agent import DailySessionArguments
|
||||
|
||||
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.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.services.daily import DailyParams, DailyTransport
|
||||
|
||||
# Check if we're in local development mode
|
||||
LOCAL_RUN = os.getenv("LOCAL_RUN")
|
||||
if LOCAL_RUN:
|
||||
import asyncio
|
||||
import webbrowser
|
||||
|
||||
try:
|
||||
from local_runner import configure
|
||||
except ImportError:
|
||||
logger.error("Could not import local_runner module. Local development mode may not work.")
|
||||
|
||||
# Load environment variables
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
async def main(room_url: str, token: str):
|
||||
"""Main pipeline setup and execution function.
|
||||
|
||||
Args:
|
||||
room_url: The Daily room URL
|
||||
token: The Daily room token
|
||||
"""
|
||||
logger.debug("Starting bot in room: {}", room_url)
|
||||
|
||||
transport = DailyTransport(
|
||||
room_url,
|
||||
token,
|
||||
"bot",
|
||||
DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
transcription_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(),
|
||||
),
|
||||
)
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"), voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22"
|
||||
)
|
||||
|
||||
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(),
|
||||
context_aggregator.user(),
|
||||
llm,
|
||||
tts,
|
||||
transport.output(),
|
||||
context_aggregator.assistant(),
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
allow_interruptions=True,
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
report_only_initial_ttfb=True,
|
||||
),
|
||||
)
|
||||
|
||||
@transport.event_handler("on_first_participant_joined")
|
||||
async def on_first_participant_joined(transport, participant):
|
||||
logger.info("First participant joined: {}", participant["id"])
|
||||
await transport.capture_participant_transcription(participant["id"])
|
||||
# Kick off the conversation.
|
||||
messages.append(
|
||||
{
|
||||
"role": "system",
|
||||
"content": "Please start with 'Hello World' and introduce yourself to the user.",
|
||||
}
|
||||
)
|
||||
await task.queue_frames([LLMMessagesFrame(messages)])
|
||||
|
||||
@transport.event_handler("on_participant_left")
|
||||
async def on_participant_left(transport, participant, reason):
|
||||
logger.info("Participant left: {}", participant)
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner()
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(args: DailySessionArguments):
|
||||
"""Main bot entry point compatible with the FastAPI route handler.
|
||||
|
||||
Args:
|
||||
room_url: The Daily room URL
|
||||
token: The Daily room token
|
||||
body: The configuration object from the request body
|
||||
session_id: The session ID for logging
|
||||
"""
|
||||
logger.info(f"Bot process initialized {args.room_url} {args.token}")
|
||||
|
||||
try:
|
||||
await main(args.room_url, args.token)
|
||||
logger.info("Bot process completed")
|
||||
except Exception as e:
|
||||
logger.exception(f"Error in bot process: {str(e)}")
|
||||
raise
|
||||
|
||||
|
||||
# Local development functions
|
||||
async def local_main():
|
||||
"""Function for local development testing."""
|
||||
try:
|
||||
async with aiohttp.ClientSession() as session:
|
||||
(room_url, token) = await configure(session)
|
||||
logger.warning("_")
|
||||
logger.warning("_")
|
||||
logger.warning(f"Talk to your voice agent here: {room_url}")
|
||||
logger.warning("_")
|
||||
logger.warning("_")
|
||||
webbrowser.open(room_url)
|
||||
await main(room_url, token)
|
||||
except Exception as e:
|
||||
logger.exception(f"Error in local development mode: {e}")
|
||||
|
||||
|
||||
# Local development entry point
|
||||
if LOCAL_RUN and __name__ == "__main__":
|
||||
try:
|
||||
asyncio.run(local_main())
|
||||
except Exception as e:
|
||||
logger.exception(f"Failed to run in local mode: {e}")
|
||||
@@ -1,2 +0,0 @@
|
||||
CARTESIA_API_KEY=
|
||||
OPENAI_API_KEY=
|
||||
@@ -1,46 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import os
|
||||
|
||||
import aiohttp
|
||||
|
||||
from pipecat.transports.services.helpers.daily_rest import DailyRESTHelper, DailyRoomParams
|
||||
|
||||
|
||||
async def configure(aiohttp_session: aiohttp.ClientSession):
|
||||
(url, token) = await configure_with_args(aiohttp_session)
|
||||
return (url, token)
|
||||
|
||||
|
||||
async def configure_with_args(aiohttp_session: aiohttp.ClientSession = None):
|
||||
key = os.getenv("DAILY_API_KEY")
|
||||
if not key:
|
||||
raise Exception(
|
||||
"No Daily API key specified. set DAILY_API_KEY in your environment to specify a Daily API key, available from https://dashboard.daily.co/developers."
|
||||
)
|
||||
|
||||
daily_rest_helper = DailyRESTHelper(
|
||||
daily_api_key=key,
|
||||
daily_api_url=os.getenv("DAILY_API_URL", "https://api.daily.co/v1"),
|
||||
aiohttp_session=aiohttp_session,
|
||||
)
|
||||
|
||||
room = await daily_rest_helper.create_room(
|
||||
DailyRoomParams(properties={"enable_prejoin_ui": False})
|
||||
)
|
||||
if not room.url:
|
||||
raise HTTPException(status_code=500, detail="Failed to create room")
|
||||
|
||||
url = room.url
|
||||
|
||||
# Create a meeting token for the given room with an expiration 1 hour in
|
||||
# the future.
|
||||
expiry_time: float = 60 * 60
|
||||
|
||||
token = await daily_rest_helper.get_token(url, expiry_time)
|
||||
|
||||
return (url, token)
|
||||
@@ -1,6 +0,0 @@
|
||||
agent_name = "my-first-agent"
|
||||
image = "your-username/my-first-agent:0.1"
|
||||
secret_set = "my-first-agent-secrets"
|
||||
|
||||
[scaling]
|
||||
min_instances = 0
|
||||
@@ -1,3 +0,0 @@
|
||||
pipecatcloud
|
||||
pipecat-ai[cartesia,daily,openai,silero]>=0.0.58
|
||||
python-dotenv~=1.0.1
|
||||
51
examples/fal-smart-turn/.gitignore
vendored
51
examples/fal-smart-turn/.gitignore
vendored
@@ -1,51 +0,0 @@
|
||||
# Python
|
||||
__pycache__/
|
||||
*.py[cod]
|
||||
*$py.class
|
||||
*.so
|
||||
.Python
|
||||
build/
|
||||
dist/
|
||||
*.egg-info/
|
||||
.installed.cfg
|
||||
*.egg
|
||||
.pytest_cache/
|
||||
.coverage
|
||||
.coverage.*
|
||||
.env
|
||||
.venv
|
||||
env/
|
||||
venv/
|
||||
ENV/
|
||||
.mypy_cache/
|
||||
.dmypy.json
|
||||
dmypy.json
|
||||
|
||||
# JavaScript/Node.js
|
||||
node_modules/
|
||||
dist/
|
||||
dist-ssr/
|
||||
*.local
|
||||
.env.local
|
||||
.env.development.local
|
||||
.env.test.local
|
||||
.env.production.local
|
||||
|
||||
# Logs
|
||||
logs/
|
||||
*.log
|
||||
npm-debug.log*
|
||||
yarn-debug.log*
|
||||
yarn-error.log*
|
||||
pnpm-debug.log*
|
||||
|
||||
# Editor/IDE
|
||||
.vscode/*
|
||||
!.vscode/extensions.json
|
||||
.idea/
|
||||
*.swp
|
||||
*.swo
|
||||
.DS_Store
|
||||
|
||||
# Project specific
|
||||
runpod.toml
|
||||
@@ -1,152 +0,0 @@
|
||||
# Smart Turn Detection Demo
|
||||
|
||||
This demo showcases Pipecat's Smart Turn Detection feature - an advanced conversational turn detection system that uses machine learning to identify when a speaker has finished their turn in a conversation. Unlike basic Voice Activity Detection (VAD) which only detects speech vs. silence, Smart Turn detects natural conversational cues like intonation patterns, pacing, and linguistic signals.
|
||||
|
||||
This demo uses the [pipecat-ai/smart-turn](https://huggingface.co/pipecat-ai/smart-turn) model - an open-source, community-driven conversational turn detection model designed to provide more natural turn-taking in voice interactions. The model is being hosted on Fal's infrastructure for GPU acceleration, offering inference times between 50-60ms.
|
||||
|
||||
In the client UI, you can see the transcription messages along with the smart-turn model's prediction results in real-time.
|
||||
|
||||
## Try the demo
|
||||
|
||||
Try the hosted version of the demo here: https://pcc-smart-turn.vercel.app/.
|
||||
|
||||
## Run the demo locally
|
||||
|
||||
### Run the Server
|
||||
|
||||
1. Set up and activate your virtual environment:
|
||||
|
||||
```bash
|
||||
python3 -m venv venv
|
||||
source venv/bin/activate # On Windows: venv\Scripts\activate
|
||||
```
|
||||
|
||||
2. Install dependencies:
|
||||
|
||||
```bash
|
||||
pip install -r requirements.txt
|
||||
```
|
||||
|
||||
3. Create your .env file and set your env vars:
|
||||
|
||||
```bash
|
||||
cp env.example .env
|
||||
```
|
||||
|
||||
Keys to provide:
|
||||
|
||||
- GOOGLE_API_KEY
|
||||
- CARTESIA_API_KEY
|
||||
- DEEPGRAM_API_KEY
|
||||
- DAILY_API_KEY
|
||||
- FAL_SMART_TURN_API_KEY
|
||||
|
||||
4. Run the server:
|
||||
|
||||
```bash
|
||||
LOCAL=1 python server.py
|
||||
```
|
||||
|
||||
### Run the client
|
||||
|
||||
1. Open a new terminal and navigate to the client directory:
|
||||
|
||||
```bash
|
||||
cd client
|
||||
```
|
||||
|
||||
2. Install dependencies:
|
||||
|
||||
```bash
|
||||
npm install
|
||||
```
|
||||
|
||||
3. Create your .env.local file:
|
||||
|
||||
```bash
|
||||
cp env.local.example .env.local
|
||||
```
|
||||
|
||||
> Note: No keys need to be modified. `NEXT_PUBLIC_API_BASE_URL` is already configured for local use.
|
||||
|
||||
4. Start the development server:
|
||||
|
||||
```bash
|
||||
npm run dev
|
||||
```
|
||||
|
||||
5. Open [http://localhost:3000](http://localhost:3000) in your browser.
|
||||
|
||||
## Deploy the app
|
||||
|
||||
### Deploy the server to Pipecat Cloud
|
||||
|
||||
1. Navigate to server
|
||||
|
||||
```bash
|
||||
cd server
|
||||
```
|
||||
|
||||
2. You should already have a .env set up from running locally. If not, do that now.
|
||||
|
||||
3. Update your build and deploy scripts.
|
||||
|
||||
- In build.sh, set `DOCKER_USERNAME` and `AGENT_NAME`.
|
||||
- In pcc-deploy.toml, set `image`, which specifies where your Docker image is stored.
|
||||
|
||||
4. Build your Docker image by running the build script:
|
||||
|
||||
```bash
|
||||
./build.sh
|
||||
```
|
||||
|
||||
> Note: This builds, tags and pushes your docker image and assumes Docker Hub is the container registry.
|
||||
|
||||
5. Make sure you have the Pipecat Cloud CLI installed:
|
||||
|
||||
```bash
|
||||
pip install pipecatcloud
|
||||
```
|
||||
|
||||
6. Login via the Pipecat Cloud CLI:
|
||||
|
||||
```bash
|
||||
pcc auth login
|
||||
```
|
||||
|
||||
> Note: If you don't have an account, sign up at https://pipecat.daily.co.
|
||||
|
||||
7. Add a secrets set:
|
||||
|
||||
```bash
|
||||
pcc secrets set pcc-smart-turn-secrets --file .env
|
||||
```
|
||||
|
||||
8. Deploy your agent:
|
||||
|
||||
```bash
|
||||
pcc deploy
|
||||
```
|
||||
|
||||
> Note: This uses your pcc-deploy.toml settings. Modify as needed.
|
||||
|
||||
### Deploy the client to Vercel
|
||||
|
||||
This project uses TypeScript, React, and Next.js, making it a perfect fit for [Vercel](https://vercel.com/).
|
||||
|
||||
- In your client directory, install Vercel's CLI tool: `npm install -g vercel`
|
||||
- Verify it's installed using `vercel --version`
|
||||
- Log in your Vercel account using `vercel login`
|
||||
- Deploy your client to Vercel using `vercel`
|
||||
|
||||
Follow the vercel prompts to deploy your project.
|
||||
|
||||
### Test your deployed app
|
||||
|
||||
Now with the client and server deployed, you can join the call using your Vercel URL.
|
||||
|
||||
See the debug information for the Smart Turn data. It prints a log line for each smart-turn inference:
|
||||
|
||||
```
|
||||
Smart Turn: COMPLETE, Probability: 95.3%, Model inference: 65.23ms, Server processing: 82.09ms, End-to-end: 245.43ms
|
||||
```
|
||||
41
examples/fal-smart-turn/client/.gitignore
vendored
41
examples/fal-smart-turn/client/.gitignore
vendored
@@ -1,41 +0,0 @@
|
||||
# See https://help.github.com/articles/ignoring-files/ for more about ignoring files.
|
||||
|
||||
# dependencies
|
||||
/node_modules
|
||||
/.pnp
|
||||
.pnp.*
|
||||
.yarn/*
|
||||
!.yarn/patches
|
||||
!.yarn/plugins
|
||||
!.yarn/releases
|
||||
!.yarn/versions
|
||||
|
||||
# testing
|
||||
/coverage
|
||||
|
||||
# next.js
|
||||
/.next/
|
||||
/out/
|
||||
|
||||
# production
|
||||
/build
|
||||
|
||||
# misc
|
||||
.DS_Store
|
||||
*.pem
|
||||
|
||||
# debug
|
||||
npm-debug.log*
|
||||
yarn-debug.log*
|
||||
yarn-error.log*
|
||||
.pnpm-debug.log*
|
||||
|
||||
# env files (can opt-in for committing if needed)
|
||||
.env*
|
||||
|
||||
# vercel
|
||||
.vercel
|
||||
|
||||
# typescript
|
||||
*.tsbuildinfo
|
||||
next-env.d.ts
|
||||
@@ -1,3 +0,0 @@
|
||||
NEXT_PUBLIC_API_BASE_URL=http://localhost:7860
|
||||
PIPECAT_CLOUD_API_KEY=
|
||||
AGENT_NAME=pcc-smart-turn
|
||||
@@ -1,16 +0,0 @@
|
||||
import { dirname } from "path";
|
||||
import { fileURLToPath } from "url";
|
||||
import { FlatCompat } from "@eslint/eslintrc";
|
||||
|
||||
const __filename = fileURLToPath(import.meta.url);
|
||||
const __dirname = dirname(__filename);
|
||||
|
||||
const compat = new FlatCompat({
|
||||
baseDirectory: __dirname,
|
||||
});
|
||||
|
||||
const eslintConfig = [
|
||||
...compat.extends("next/core-web-vitals", "next/typescript"),
|
||||
];
|
||||
|
||||
export default eslintConfig;
|
||||
@@ -1,7 +0,0 @@
|
||||
import type { NextConfig } from "next";
|
||||
|
||||
const nextConfig: NextConfig = {
|
||||
/* config options here */
|
||||
};
|
||||
|
||||
export default nextConfig;
|
||||
5174
examples/fal-smart-turn/client/package-lock.json
generated
5174
examples/fal-smart-turn/client/package-lock.json
generated
File diff suppressed because it is too large
Load Diff
@@ -1,28 +0,0 @@
|
||||
{
|
||||
"name": "my-nextjs-app",
|
||||
"version": "0.1.0",
|
||||
"private": true,
|
||||
"scripts": {
|
||||
"dev": "next dev",
|
||||
"build": "next build",
|
||||
"start": "next start",
|
||||
"lint": "next lint"
|
||||
},
|
||||
"dependencies": {
|
||||
"@pipecat-ai/client-js": "^0.3.5",
|
||||
"@pipecat-ai/client-react": "^0.3.5",
|
||||
"@pipecat-ai/daily-transport": "^0.3.10",
|
||||
"next": "15.3.1",
|
||||
"react": "^19.0.0",
|
||||
"react-dom": "^19.0.0"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@eslint/eslintrc": "^3",
|
||||
"@types/node": "^20",
|
||||
"@types/react": "^19",
|
||||
"@types/react-dom": "^19",
|
||||
"eslint": "^9",
|
||||
"eslint-config-next": "15.2.3",
|
||||
"typescript": "^5"
|
||||
}
|
||||
}
|
||||
@@ -1,7 +0,0 @@
|
||||
<svg width="24" height="24" viewBox="0 0 24 24" fill="none" xmlns="http://www.w3.org/2000/svg">
|
||||
<path d="M3.3088 5.05615C3.64682 4.92779 4.02833 5.02411 4.26653 5.29797L7.36884 8.86461H16.6312L19.7335 5.29797C19.9717 5.02411 20.3532 4.92779 20.6912 5.05615C21.0292 5.18452 21.253 5.51072 21.253 5.87504V13.75H24V15.5H19.5181V8.19909L17.6762 10.3167C17.5115 10.506 17.2738 10.6146 17.0241 10.6146H6.9759C6.72616 10.6146 6.48854 10.506 6.32383 10.3167L4.48193 8.19909V15.5H0V13.75H2.74699V5.87504C2.74699 5.51072 2.97078 5.18452 3.3088 5.05615Z" fill="black"/>
|
||||
<path d="M19.5181 17.25H24V19H19.5181V17.25Z" fill="black"/>
|
||||
<path d="M0 17.25H4.48193V19H0V17.25Z" fill="black"/>
|
||||
<path d="M9.25301 14.3333C9.25301 14.9777 8.73517 15.5 8.09639 15.5C7.4576 15.5 6.93976 14.9777 6.93976 14.3333C6.93976 13.689 7.4576 13.1667 8.09639 13.1667C8.73517 13.1667 9.25301 13.689 9.25301 14.3333Z" fill="black"/>
|
||||
<path d="M17.0602 14.3333C17.0602 14.9777 16.5424 15.5 15.9036 15.5C15.2648 15.5 14.747 14.9777 14.747 14.3333C14.747 13.689 15.2648 13.1667 15.9036 13.1667C16.5424 13.1667 17.0602 13.689 17.0602 14.3333Z" fill="black"/>
|
||||
</svg>
|
||||
|
Before Width: | Height: | Size: 1.1 KiB |
@@ -1,44 +0,0 @@
|
||||
import { NextResponse, NextRequest } from 'next/server';
|
||||
|
||||
export async function POST(request: NextRequest) {
|
||||
const { MY_CUSTOM_DATA } = await request.json();
|
||||
|
||||
try {
|
||||
const response = await fetch(
|
||||
`https://api.pipecat.daily.co/v1/public/${process.env.AGENT_NAME}/start`,
|
||||
{
|
||||
method: 'POST',
|
||||
headers: {
|
||||
Authorization: `Bearer ${process.env.PIPECAT_CLOUD_API_KEY}`,
|
||||
'Content-Type': 'application/json',
|
||||
},
|
||||
body: JSON.stringify({
|
||||
// Create Daily room
|
||||
createDailyRoom: true,
|
||||
// Optionally set Daily room properties
|
||||
dailyRoomProperties: { start_video_off: true },
|
||||
// Optionally pass custom data to the bot
|
||||
body: { MY_CUSTOM_DATA },
|
||||
}),
|
||||
}
|
||||
);
|
||||
|
||||
if (!response.ok) {
|
||||
throw new Error(`API responded with status: ${response.status}`);
|
||||
}
|
||||
|
||||
const data = await response.json();
|
||||
|
||||
// Transform the response to match what RTVI client expects
|
||||
return NextResponse.json({
|
||||
room_url: data.dailyRoom,
|
||||
token: data.dailyToken,
|
||||
});
|
||||
} catch (error) {
|
||||
console.error('API error:', error);
|
||||
return NextResponse.json(
|
||||
{ error: 'Failed to start agent' },
|
||||
{ status: 500 }
|
||||
);
|
||||
}
|
||||
}
|
||||
@@ -1,82 +0,0 @@
|
||||
body {
|
||||
margin: 0;
|
||||
padding: 20px;
|
||||
font-family: Arial, sans-serif;
|
||||
background-color: #f0f0f0;
|
||||
}
|
||||
|
||||
.app {
|
||||
max-width: 1200px;
|
||||
margin: 0 auto;
|
||||
}
|
||||
|
||||
.status-bar {
|
||||
display: flex;
|
||||
justify-content: space-between;
|
||||
align-items: center;
|
||||
padding: 10px;
|
||||
background-color: #fff;
|
||||
border-radius: 8px;
|
||||
margin-bottom: 20px;
|
||||
}
|
||||
|
||||
.controls button {
|
||||
padding: 8px 16px;
|
||||
margin-left: 10px;
|
||||
border: none;
|
||||
border-radius: 4px;
|
||||
cursor: pointer;
|
||||
}
|
||||
|
||||
button:disabled {
|
||||
opacity: 0.5;
|
||||
cursor: not-allowed;
|
||||
}
|
||||
|
||||
.connect-btn {
|
||||
background-color: #4caf50;
|
||||
color: white;
|
||||
}
|
||||
|
||||
.disconnect-btn {
|
||||
background-color: #f44336;
|
||||
color: white;
|
||||
}
|
||||
|
||||
.main-content {
|
||||
background-color: #fff;
|
||||
border-radius: 8px;
|
||||
padding: 20px;
|
||||
margin-bottom: 20px;
|
||||
}
|
||||
|
||||
.bot-container {
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
align-items: center;
|
||||
}
|
||||
|
||||
.video-container {
|
||||
width: 640px;
|
||||
height: 360px;
|
||||
background-color: #ddd;
|
||||
margin-bottom: 20px;
|
||||
border-radius: 8px;
|
||||
overflow: hidden;
|
||||
}
|
||||
|
||||
.video-container video {
|
||||
width: 100%;
|
||||
height: 100%;
|
||||
object-fit: cover;
|
||||
}
|
||||
|
||||
.mic-enabled {
|
||||
background-color: #4caf50;
|
||||
color: white;
|
||||
}
|
||||
|
||||
.mic-disabled {
|
||||
background-color: #f44336;
|
||||
color: white;
|
||||
}
|
||||
@@ -1,27 +0,0 @@
|
||||
import './globals.css';
|
||||
import { RTVIProvider } from '@/providers/RTVIProvider';
|
||||
|
||||
export const metadata = {
|
||||
title: 'Pipecat React Client',
|
||||
description: 'Pipecat RTVI Client using Next.js',
|
||||
icons: {
|
||||
icon: [{ url: '/favicon.svg', type: 'image/svg+xml' }],
|
||||
},
|
||||
};
|
||||
|
||||
export default function RootLayout({
|
||||
children,
|
||||
}: {
|
||||
children: React.ReactNode;
|
||||
}) {
|
||||
return (
|
||||
<html lang="en">
|
||||
<head>
|
||||
<link rel="icon" href="/favicon.svg" type="image/svg+xml" />
|
||||
</head>
|
||||
<body>
|
||||
<RTVIProvider>{children}</RTVIProvider>
|
||||
</body>
|
||||
</html>
|
||||
);
|
||||
}
|
||||
@@ -1,41 +0,0 @@
|
||||
'use client';
|
||||
|
||||
import {
|
||||
RTVIClientAudio,
|
||||
RTVIClientVideo,
|
||||
useRTVIClientTransportState,
|
||||
} from '@pipecat-ai/client-react';
|
||||
import { ConnectButton } from '../components/ConnectButton';
|
||||
import { StatusDisplay } from '../components/StatusDisplay';
|
||||
import { DebugDisplay } from '../components/DebugDisplay';
|
||||
|
||||
function BotVideo() {
|
||||
const transportState = useRTVIClientTransportState();
|
||||
const isConnected = transportState !== 'disconnected';
|
||||
|
||||
return (
|
||||
<div className="bot-container">
|
||||
<div className="video-container">
|
||||
{isConnected && <RTVIClientVideo participant="bot" fit="cover" />}
|
||||
</div>
|
||||
</div>
|
||||
);
|
||||
}
|
||||
|
||||
export default function Home() {
|
||||
return (
|
||||
<div className="app">
|
||||
<div className="status-bar">
|
||||
<StatusDisplay />
|
||||
<ConnectButton />
|
||||
</div>
|
||||
|
||||
<div className="main-content">
|
||||
<BotVideo />
|
||||
</div>
|
||||
|
||||
<DebugDisplay />
|
||||
<RTVIClientAudio />
|
||||
</div>
|
||||
);
|
||||
}
|
||||
@@ -1,40 +0,0 @@
|
||||
import {
|
||||
useRTVIClient,
|
||||
useRTVIClientTransportState,
|
||||
} from '@pipecat-ai/client-react';
|
||||
|
||||
export function ConnectButton() {
|
||||
const client = useRTVIClient();
|
||||
const transportState = useRTVIClientTransportState();
|
||||
const isConnected = ['connected', 'ready'].includes(transportState);
|
||||
|
||||
const handleClick = async () => {
|
||||
if (!client) {
|
||||
console.error('RTVI client is not initialized');
|
||||
return;
|
||||
}
|
||||
|
||||
try {
|
||||
if (isConnected) {
|
||||
await client.disconnect();
|
||||
} else {
|
||||
await client.connect();
|
||||
}
|
||||
} catch (error) {
|
||||
console.error('Connection error:', error);
|
||||
}
|
||||
};
|
||||
|
||||
return (
|
||||
<div className="controls">
|
||||
<button
|
||||
className={isConnected ? 'disconnect-btn' : 'connect-btn'}
|
||||
onClick={handleClick}
|
||||
disabled={
|
||||
!client || ['connecting', 'disconnecting'].includes(transportState)
|
||||
}>
|
||||
{isConnected ? 'Disconnect' : 'Connect'}
|
||||
</button>
|
||||
</div>
|
||||
);
|
||||
}
|
||||
@@ -1,26 +0,0 @@
|
||||
.debug-panel {
|
||||
background-color: #fff;
|
||||
border-radius: 8px;
|
||||
padding: 20px;
|
||||
}
|
||||
|
||||
.debug-panel h3 {
|
||||
margin: 0 0 10px 0;
|
||||
font-size: 16px;
|
||||
font-weight: bold;
|
||||
}
|
||||
|
||||
.debug-log {
|
||||
height: 200px;
|
||||
overflow-y: auto;
|
||||
background-color: #f8f8f8;
|
||||
padding: 10px;
|
||||
border-radius: 4px;
|
||||
font-family: monospace;
|
||||
font-size: 12px;
|
||||
line-height: 1.4;
|
||||
}
|
||||
|
||||
.debug-log div {
|
||||
margin-bottom: 4px;
|
||||
}
|
||||
@@ -1,171 +0,0 @@
|
||||
import { useRef, useCallback } from 'react';
|
||||
import {
|
||||
Participant,
|
||||
RTVIEvent,
|
||||
TransportState,
|
||||
TranscriptData,
|
||||
BotLLMTextData,
|
||||
} from '@pipecat-ai/client-js';
|
||||
import { useRTVIClient, useRTVIClientEvent } from '@pipecat-ai/client-react';
|
||||
import './DebugDisplay.css';
|
||||
|
||||
interface SmartTurnResultData {
|
||||
type: 'smart_turn_result';
|
||||
is_complete: boolean;
|
||||
probability: number;
|
||||
inference_time_ms: number; // Pure model inference time
|
||||
server_total_time_ms: number; // Server processing time
|
||||
e2e_processing_time_ms: number; // Complete end-to-end time
|
||||
}
|
||||
|
||||
export function DebugDisplay() {
|
||||
const debugLogRef = useRef<HTMLDivElement>(null);
|
||||
const client = useRTVIClient();
|
||||
|
||||
const log = useCallback((message: string) => {
|
||||
if (!debugLogRef.current) return;
|
||||
|
||||
const entry = document.createElement('div');
|
||||
entry.textContent = `${new Date().toISOString()} - ${message}`;
|
||||
|
||||
// Add styling based on message type
|
||||
if (message.startsWith('User: ')) {
|
||||
entry.style.color = '#2196F3'; // blue for user
|
||||
} else if (message.startsWith('Bot: ')) {
|
||||
entry.style.color = '#4CAF50'; // green for bot
|
||||
} else if (message.includes('Smart Turn:')) {
|
||||
entry.style.color = '#9C27B0'; // purple for smart turn
|
||||
}
|
||||
|
||||
debugLogRef.current.appendChild(entry);
|
||||
debugLogRef.current.scrollTop = debugLogRef.current.scrollHeight;
|
||||
}, []);
|
||||
|
||||
// Log transport state changes
|
||||
useRTVIClientEvent(
|
||||
RTVIEvent.TransportStateChanged,
|
||||
useCallback(
|
||||
(state: TransportState) => {
|
||||
log(`Transport state changed: ${state}`);
|
||||
},
|
||||
[log]
|
||||
)
|
||||
);
|
||||
|
||||
// Log bot connection events
|
||||
useRTVIClientEvent(
|
||||
RTVIEvent.BotConnected,
|
||||
useCallback(
|
||||
(participant?: Participant) => {
|
||||
log(`Bot connected: ${JSON.stringify(participant)}`);
|
||||
},
|
||||
[log]
|
||||
)
|
||||
);
|
||||
|
||||
useRTVIClientEvent(
|
||||
RTVIEvent.BotDisconnected,
|
||||
useCallback(
|
||||
(participant?: Participant) => {
|
||||
log(`Bot disconnected: ${JSON.stringify(participant)}`);
|
||||
},
|
||||
[log]
|
||||
)
|
||||
);
|
||||
|
||||
// Log track events
|
||||
useRTVIClientEvent(
|
||||
RTVIEvent.TrackStarted,
|
||||
useCallback(
|
||||
(track: MediaStreamTrack, participant?: Participant) => {
|
||||
log(
|
||||
`Track started: ${track.kind} from ${participant?.name || 'unknown'}`
|
||||
);
|
||||
},
|
||||
[log]
|
||||
)
|
||||
);
|
||||
|
||||
useRTVIClientEvent(
|
||||
RTVIEvent.TrackStopped,
|
||||
useCallback(
|
||||
(track: MediaStreamTrack, participant?: Participant) => {
|
||||
log(
|
||||
`Track stopped: ${track.kind} from ${participant?.name || 'unknown'}`
|
||||
);
|
||||
},
|
||||
[log]
|
||||
)
|
||||
);
|
||||
|
||||
// Log bot ready state and check tracks
|
||||
useRTVIClientEvent(
|
||||
RTVIEvent.BotReady,
|
||||
useCallback(() => {
|
||||
log(`Bot ready`);
|
||||
|
||||
if (!client) return;
|
||||
|
||||
const tracks = client.tracks();
|
||||
log(
|
||||
`Available tracks: ${JSON.stringify({
|
||||
local: {
|
||||
audio: !!tracks.local.audio,
|
||||
video: !!tracks.local.video,
|
||||
},
|
||||
bot: {
|
||||
audio: !!tracks.bot?.audio,
|
||||
video: !!tracks.bot?.video,
|
||||
},
|
||||
})}`
|
||||
);
|
||||
}, [client, log])
|
||||
);
|
||||
|
||||
// Log transcripts
|
||||
useRTVIClientEvent(
|
||||
RTVIEvent.UserTranscript,
|
||||
useCallback(
|
||||
(data: TranscriptData) => {
|
||||
// Only log final transcripts
|
||||
if (data.final) {
|
||||
log(`User: ${data.text}`);
|
||||
}
|
||||
},
|
||||
[log]
|
||||
)
|
||||
);
|
||||
|
||||
useRTVIClientEvent(
|
||||
RTVIEvent.BotTranscript,
|
||||
useCallback(
|
||||
(data: BotLLMTextData) => {
|
||||
log(`Bot: ${data.text}`);
|
||||
},
|
||||
[log]
|
||||
)
|
||||
);
|
||||
|
||||
useRTVIClientEvent(
|
||||
RTVIEvent.ServerMessage,
|
||||
useCallback(
|
||||
(data: SmartTurnResultData) => {
|
||||
log(
|
||||
`Smart Turn:
|
||||
${data.is_complete ? 'COMPLETE' : 'INCOMPLETE'},
|
||||
Probability: ${(data.probability * 100).toFixed(1)}%,
|
||||
Model inference: ${data.inference_time_ms?.toFixed(2) || 'N/A'}ms,
|
||||
Server processing: ${data.server_total_time_ms?.toFixed(2) || 'N/A'}ms,
|
||||
End-to-end: ${data.e2e_processing_time_ms?.toFixed(2) || 'N/A'}ms`
|
||||
);
|
||||
},
|
||||
[log]
|
||||
)
|
||||
);
|
||||
return (
|
||||
<div className="debug-panel">
|
||||
<h3>Debug Info</h3>
|
||||
<div ref={debugLogRef} className="debug-log" />
|
||||
</div>
|
||||
);
|
||||
}
|
||||
@@ -1,11 +0,0 @@
|
||||
import { useRTVIClientTransportState } from '@pipecat-ai/client-react';
|
||||
|
||||
export function StatusDisplay() {
|
||||
const transportState = useRTVIClientTransportState();
|
||||
|
||||
return (
|
||||
<div className="status">
|
||||
Status: <span>{transportState}</span>
|
||||
</div>
|
||||
);
|
||||
}
|
||||
@@ -1,43 +0,0 @@
|
||||
'use client';
|
||||
|
||||
import { RTVIClient } from '@pipecat-ai/client-js';
|
||||
import { DailyTransport } from '@pipecat-ai/daily-transport';
|
||||
import { RTVIClientProvider } from '@pipecat-ai/client-react';
|
||||
import { PropsWithChildren, useEffect, useState } from 'react';
|
||||
|
||||
// Get the API base URL from environment variables
|
||||
// Default to "/api" if not specified
|
||||
// "/api" is the default for Next.js API routes and used
|
||||
// for the Pipecat Cloud deployed agent
|
||||
const API_BASE_URL = process.env.NEXT_PUBLIC_API_BASE_URL || '/api';
|
||||
|
||||
console.log('Using API base URL:', API_BASE_URL);
|
||||
|
||||
export function RTVIProvider({ children }: PropsWithChildren) {
|
||||
const [client, setClient] = useState<RTVIClient | null>(null);
|
||||
|
||||
useEffect(() => {
|
||||
const transport = new DailyTransport();
|
||||
|
||||
const rtviClient = new RTVIClient({
|
||||
transport,
|
||||
params: {
|
||||
baseUrl: API_BASE_URL,
|
||||
endpoints: {
|
||||
connect: '/connect',
|
||||
},
|
||||
requestData: { foo: 'bar' },
|
||||
},
|
||||
enableMic: true,
|
||||
enableCam: false,
|
||||
});
|
||||
|
||||
setClient(rtviClient);
|
||||
}, []);
|
||||
|
||||
if (!client) {
|
||||
return null;
|
||||
}
|
||||
|
||||
return <RTVIClientProvider client={client}>{children}</RTVIClientProvider>;
|
||||
}
|
||||
@@ -1,28 +0,0 @@
|
||||
{
|
||||
"compilerOptions": {
|
||||
"target": "ES2017",
|
||||
"lib": ["dom", "dom.iterable", "esnext"],
|
||||
"allowJs": true,
|
||||
"skipLibCheck": true,
|
||||
"strict": true,
|
||||
"noEmit": true,
|
||||
"esModuleInterop": true,
|
||||
"module": "esnext",
|
||||
"moduleResolution": "bundler",
|
||||
"resolveJsonModule": true,
|
||||
"isolatedModules": true,
|
||||
"jsx": "preserve",
|
||||
"incremental": true,
|
||||
"plugins": [
|
||||
{
|
||||
"name": "next"
|
||||
}
|
||||
],
|
||||
"paths": {
|
||||
"@/components/*": ["./src/components/*"],
|
||||
"@/providers/*": ["./src/providers/*"]
|
||||
}
|
||||
},
|
||||
"include": ["next-env.d.ts", "**/*.ts", "**/*.tsx", ".next/types/**/*.ts"],
|
||||
"exclude": ["node_modules"]
|
||||
}
|
||||
@@ -1,8 +0,0 @@
|
||||
FROM dailyco/pipecat-base:latest
|
||||
|
||||
COPY ./requirements.txt requirements.txt
|
||||
|
||||
RUN pip install --no-cache-dir --upgrade -r requirements.txt
|
||||
|
||||
COPY ./assets assets
|
||||
COPY ./bot.py bot.py
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 759 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 884 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 876 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 881 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 866 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 874 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 882 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 885 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 888 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 890 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 898 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 836 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 903 KiB |
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user