Compare commits
1 Commits
aleix/fram
...
update-mod
| Author | SHA1 | Date | |
|---|---|---|---|
|
50b19a9e77 |
48
.github/workflows/android.yaml
vendored
Normal file
48
.github/workflows/android.yaml
vendored
Normal file
@@ -0,0 +1,48 @@
|
||||
name: android
|
||||
|
||||
on:
|
||||
push:
|
||||
branches:
|
||||
- main
|
||||
paths:
|
||||
- "examples/simple-chatbot/client/android/**"
|
||||
pull_request:
|
||||
branches:
|
||||
- "**"
|
||||
paths:
|
||||
- "examples/simple-chatbot/client/android/**"
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
sdk_git_ref:
|
||||
type: string
|
||||
description: "Which git ref of the app to build"
|
||||
|
||||
concurrency:
|
||||
group: build-android-${{ github.event.pull_request.number || github.ref }}
|
||||
cancel-in-progress: true
|
||||
|
||||
jobs:
|
||||
sdk:
|
||||
name: "Simple chatbot demo"
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout repo
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
ref: ${{ github.event.inputs.sdk_git_ref || github.ref }}
|
||||
|
||||
- name: "Install Java"
|
||||
uses: actions/setup-java@v4
|
||||
with:
|
||||
distribution: 'temurin'
|
||||
java-version: '17'
|
||||
|
||||
- name: Build demo app
|
||||
working-directory: examples/simple-chatbot/client/android
|
||||
run: ./gradlew :simple-chatbot-client:assembleDebug
|
||||
|
||||
- name: Upload demo APK
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: Simple Chatbot Android Client
|
||||
path: examples/simple-chatbot/client/android/simple-chatbot-client/build/outputs/apk/debug/simple-chatbot-client-debug.apk
|
||||
34
.github/workflows/build.yaml
vendored
34
.github/workflows/build.yaml
vendored
@@ -21,20 +21,24 @@ jobs:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v3
|
||||
with:
|
||||
version: "latest"
|
||||
|
||||
- name: Set up Python
|
||||
run: uv python install 3.12
|
||||
|
||||
- name: Install development dependencies
|
||||
run: uv sync --group dev
|
||||
|
||||
id: setup_python
|
||||
uses: actions/setup-python@v4
|
||||
with:
|
||||
python-version: '3.10'
|
||||
- name: Setup virtual environment
|
||||
run: |
|
||||
python -m venv .venv
|
||||
- name: Install basic Python dependencies
|
||||
run: |
|
||||
source .venv/bin/activate
|
||||
python -m pip install --upgrade pip
|
||||
pip install -r dev-requirements.txt
|
||||
- name: Build project
|
||||
run: uv build
|
||||
|
||||
- name: Install project in editable mode
|
||||
run: uv pip install --editable .
|
||||
run: |
|
||||
source .venv/bin/activate
|
||||
python -m build
|
||||
- name: Install project and other Python dependencies
|
||||
run: |
|
||||
source .venv/bin/activate
|
||||
pip install --editable .
|
||||
|
||||
37
.github/workflows/coverage.yaml
vendored
37
.github/workflows/coverage.yaml
vendored
@@ -18,28 +18,35 @@ jobs:
|
||||
steps:
|
||||
- name: Checkout repo
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v3
|
||||
with:
|
||||
version: "latest"
|
||||
|
||||
- name: Set up Python
|
||||
run: uv python install 3.12
|
||||
|
||||
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: Install dependencies
|
||||
- name: Setup virtual environment
|
||||
run: |
|
||||
uv sync --group dev --extra anthropic --extra aws --extra google --extra langchain
|
||||
|
||||
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: |
|
||||
uv run coverage run
|
||||
uv run coverage xml
|
||||
|
||||
source .venv/bin/activate
|
||||
coverage run
|
||||
coverage xml
|
||||
- name: Upload coverage to Codecov
|
||||
uses: codecov/codecov-action@v5
|
||||
with:
|
||||
|
||||
35
.github/workflows/format.yaml
vendored
35
.github/workflows/format.yaml
vendored
@@ -17,27 +17,30 @@ concurrency:
|
||||
|
||||
jobs:
|
||||
ruff-format:
|
||||
name: "Code quality checks"
|
||||
name: "Formatting checker"
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout repo
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v3
|
||||
with:
|
||||
version: "latest"
|
||||
|
||||
- name: Set up Python
|
||||
run: uv python install 3.12
|
||||
|
||||
- name: Install development dependencies
|
||||
run: uv sync --group dev
|
||||
|
||||
uses: actions/setup-python@v4
|
||||
with:
|
||||
python-version: "3.10"
|
||||
- name: Setup virtual environment
|
||||
run: |
|
||||
python -m venv .venv
|
||||
- name: Install development Python dependencies
|
||||
run: |
|
||||
source .venv/bin/activate
|
||||
python -m pip install --upgrade pip
|
||||
pip install -r dev-requirements.txt
|
||||
- name: Ruff formatter
|
||||
id: ruff-format
|
||||
run: uv run ruff format --diff
|
||||
|
||||
- name: Ruff linter (all rules)
|
||||
run: |
|
||||
source .venv/bin/activate
|
||||
ruff format --diff
|
||||
- name: Ruff import linter
|
||||
id: ruff-check
|
||||
run: uv run ruff check
|
||||
run: |
|
||||
source .venv/bin/activate
|
||||
ruff check --select I
|
||||
|
||||
174
.github/workflows/generate-changelog.yml
vendored
174
.github/workflows/generate-changelog.yml
vendored
@@ -1,174 +0,0 @@
|
||||
name: Generate Changelog for Release
|
||||
|
||||
on:
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
version:
|
||||
description: "Release version (e.g., 0.0.97)"
|
||||
required: true
|
||||
type: string
|
||||
date:
|
||||
description: "Release date (YYYY-MM-DD format, defaults to today)"
|
||||
required: false
|
||||
type: string
|
||||
default: ""
|
||||
|
||||
permissions:
|
||||
contents: write
|
||||
pull-requests: write
|
||||
|
||||
jobs:
|
||||
generate-changelog:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout repository
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 0
|
||||
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: "3.12"
|
||||
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v4
|
||||
with:
|
||||
enable-cache: true
|
||||
|
||||
- name: Install dependencies
|
||||
run: |
|
||||
uv sync --group dev
|
||||
|
||||
- name: Set release date
|
||||
id: set_date
|
||||
run: |
|
||||
if [ -z "${{ inputs.date }}" ]; then
|
||||
RELEASE_DATE=$(date +%Y-%m-%d)
|
||||
echo "Using today's date: $RELEASE_DATE"
|
||||
else
|
||||
RELEASE_DATE="${{ inputs.date }}"
|
||||
echo "Using provided date: $RELEASE_DATE"
|
||||
fi
|
||||
echo "release_date=$RELEASE_DATE" >> $GITHUB_OUTPUT
|
||||
|
||||
- name: Validate inputs
|
||||
run: |
|
||||
# Validate version format (basic check)
|
||||
if ! [[ "${{ inputs.version }}" =~ ^[0-9]+\.[0-9]+\.[0-9]+.*$ ]]; then
|
||||
echo "Error: Version must be in format X.Y.Z (e.g., 0.0.97)"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Validate date format if provided
|
||||
if [ -n "${{ inputs.date }}" ]; then
|
||||
if ! date -d "${{ inputs.date }}" >/dev/null 2>&1; then
|
||||
# Try macOS date format
|
||||
if ! date -j -f "%Y-%m-%d" "${{ inputs.date }}" >/dev/null 2>&1; then
|
||||
echo "Error: Date must be in YYYY-MM-DD format (e.g., 2025-12-04)"
|
||||
exit 1
|
||||
fi
|
||||
fi
|
||||
fi
|
||||
|
||||
- name: Check for changelog fragments
|
||||
id: check_fragments
|
||||
run: |
|
||||
FRAGMENT_COUNT=$(find changelog -name "*.md" ! -name "_template.md.j2" | wc -l | tr -d ' ')
|
||||
echo "fragment_count=$FRAGMENT_COUNT" >> $GITHUB_OUTPUT
|
||||
|
||||
if [ "$FRAGMENT_COUNT" -eq "0" ]; then
|
||||
echo "❌ Error: No changelog fragments found in changelog/"
|
||||
echo ""
|
||||
echo "Cannot create a release without changelog entries."
|
||||
echo "Add changelog fragments to the changelog/ directory (e.g., 1234.added.md) and try again."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Validate fragment types
|
||||
VALID_TYPES="added changed deprecated removed fixed security other"
|
||||
INVALID_FRAGMENTS=""
|
||||
|
||||
for file in changelog/*.md; do
|
||||
# Skip template
|
||||
if [[ "$file" == "changelog/_template.md.j2" ]]; then
|
||||
continue
|
||||
fi
|
||||
|
||||
# Extract type from filename (e.g., 1234.added.md -> added)
|
||||
filename=$(basename "$file")
|
||||
# Handle both 1234.added.md and 1234.added.2.md patterns
|
||||
type=$(echo "$filename" | sed -E 's/^[0-9]+\.([a-z]+)(\.[0-9]+)?\.md$/\1/')
|
||||
|
||||
# Check if type is valid
|
||||
if ! echo "$VALID_TYPES" | grep -wq "$type"; then
|
||||
INVALID_FRAGMENTS="$INVALID_FRAGMENTS\n - $filename (type: '$type')"
|
||||
fi
|
||||
done
|
||||
|
||||
if [ -n "$INVALID_FRAGMENTS" ]; then
|
||||
echo "❌ Error: Invalid changelog fragment types found:"
|
||||
echo -e "$INVALID_FRAGMENTS"
|
||||
echo ""
|
||||
echo "Valid types are: $VALID_TYPES"
|
||||
echo "Example: 1234.added.md, 5678.fixed.md"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "✓ Found $FRAGMENT_COUNT changelog fragment(s)"
|
||||
echo "has_fragments=true" >> $GITHUB_OUTPUT
|
||||
|
||||
- name: Preview changelog
|
||||
run: |
|
||||
echo "## Preview of changelog for version ${{ inputs.version }}"
|
||||
echo ""
|
||||
uv run towncrier build --draft --version "${{ inputs.version }}" --date "${{ steps.set_date.outputs.release_date }}"
|
||||
|
||||
- name: Build changelog
|
||||
run: |
|
||||
uv run towncrier build --version "${{ inputs.version }}" --date "${{ steps.set_date.outputs.release_date }}" --yes
|
||||
|
||||
- name: Create Pull Request
|
||||
uses: peter-evans/create-pull-request@v7
|
||||
with:
|
||||
token: ${{ secrets.GITHUB_TOKEN }}
|
||||
commit-message: "Update changelog for version ${{ inputs.version }}"
|
||||
title: "Release ${{ inputs.version }} - Changelog Update"
|
||||
body: |
|
||||
## Changelog Update for Release ${{ inputs.version }}
|
||||
|
||||
This PR updates the CHANGELOG.md with all changes for version **${{ inputs.version }}**.
|
||||
|
||||
### Summary
|
||||
- **Version:** ${{ inputs.version }}
|
||||
- **Date:** ${{ steps.set_date.outputs.release_date }}
|
||||
- **Fragments processed:** ${{ steps.check_fragments.outputs.fragment_count }}
|
||||
|
||||
### What this PR does
|
||||
- ✅ Adds new release section to CHANGELOG.md
|
||||
- ✅ Removes processed changelog fragments
|
||||
- ✅ Ready to merge for release
|
||||
|
||||
### Next Steps
|
||||
1. Review the changelog entries below
|
||||
2. Make any necessary edits to CHANGELOG.md if needed
|
||||
3. Merge this PR
|
||||
4. Continue with your release process
|
||||
|
||||
---
|
||||
|
||||
<details>
|
||||
<summary>📋 Preview of changes</summary>
|
||||
|
||||
The changelog has been updated with entries from the following fragments:
|
||||
|
||||
```bash
|
||||
${{ steps.check_fragments.outputs.fragment_count }} fragments processed
|
||||
```
|
||||
|
||||
</details>
|
||||
branch: changelog-${{ inputs.version }}
|
||||
delete-branch: true
|
||||
labels: |
|
||||
changelog
|
||||
release
|
||||
40
.github/workflows/publish.yaml
vendored
40
.github/workflows/publish.yaml
vendored
@@ -5,29 +5,35 @@ on:
|
||||
inputs:
|
||||
gitref:
|
||||
type: string
|
||||
description: 'what git tag to build (e.g. v0.0.74)'
|
||||
description: "what git ref to build"
|
||||
required: true
|
||||
|
||||
jobs:
|
||||
build:
|
||||
name: 'Build and upload wheels'
|
||||
name: "Build and upload wheels"
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout repo
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
ref: ${{ github.event.inputs.gitref }}
|
||||
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v3
|
||||
with:
|
||||
version: 'latest'
|
||||
- name: Set up Python
|
||||
run: uv python install 3.12
|
||||
- name: Install development dependencies
|
||||
run: uv sync --group dev
|
||||
id: setup_python
|
||||
uses: actions/setup-python@v4
|
||||
with:
|
||||
python-version: '3.10'
|
||||
- name: Setup virtual environment
|
||||
run: |
|
||||
python -m venv .venv
|
||||
- name: Install basic Python dependencies
|
||||
run: |
|
||||
source .venv/bin/activate
|
||||
python -m pip install --upgrade pip
|
||||
pip install -r dev-requirements.txt
|
||||
- name: Build project
|
||||
run: uv build
|
||||
run: |
|
||||
source .venv/bin/activate
|
||||
python -m build
|
||||
- name: Upload wheels
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
@@ -35,9 +41,9 @@ jobs:
|
||||
path: ./dist
|
||||
|
||||
publish-to-pypi:
|
||||
name: 'Publish to PyPI'
|
||||
name: "Publish to PyPI"
|
||||
runs-on: ubuntu-latest
|
||||
needs: [build]
|
||||
needs: [ build ]
|
||||
environment:
|
||||
name: pypi
|
||||
url: https://pypi.org/p/pipecat-ai
|
||||
@@ -56,12 +62,12 @@ jobs:
|
||||
print-hash: true
|
||||
|
||||
publish-to-test-pypi:
|
||||
name: 'Publish to Test PyPI'
|
||||
name: "Publish to Test PyPI"
|
||||
runs-on: ubuntu-latest
|
||||
needs: [build]
|
||||
needs: [ build ]
|
||||
environment:
|
||||
name: testpypi
|
||||
url: https://test.pypi.org/p/pipecat-ai
|
||||
url: https://pypi.org/p/pipecat-ai
|
||||
permissions:
|
||||
id-token: write
|
||||
steps:
|
||||
@@ -70,7 +76,7 @@ jobs:
|
||||
with:
|
||||
name: wheels
|
||||
path: ./dist
|
||||
- name: Publish to Test PyPI
|
||||
- name: Publish to PyPI
|
||||
uses: pypa/gh-action-pypi-publish@release/v1
|
||||
with:
|
||||
verbose: true
|
||||
|
||||
33
.github/workflows/publish_test.yaml
vendored
33
.github/workflows/publish_test.yaml
vendored
@@ -4,7 +4,7 @@ on: workflow_dispatch
|
||||
|
||||
jobs:
|
||||
build:
|
||||
name: 'Build and upload wheels'
|
||||
name: "Build and upload wheels"
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout repo
|
||||
@@ -12,16 +12,23 @@ jobs:
|
||||
with:
|
||||
fetch-tags: true
|
||||
fetch-depth: 100
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v3
|
||||
with:
|
||||
version: 'latest'
|
||||
- name: Set up Python
|
||||
run: uv python install 3.12
|
||||
- name: Install development dependencies
|
||||
run: uv sync --group dev
|
||||
id: setup_python
|
||||
uses: actions/setup-python@v4
|
||||
with:
|
||||
python-version: '3.10'
|
||||
- name: Setup virtual environment
|
||||
run: |
|
||||
python -m venv .venv
|
||||
- name: Install basic Python dependencies
|
||||
run: |
|
||||
source .venv/bin/activate
|
||||
python -m pip install --upgrade pip
|
||||
pip install -r dev-requirements.txt
|
||||
- name: Build project
|
||||
run: uv build
|
||||
run: |
|
||||
source .venv/bin/activate
|
||||
python -m build
|
||||
- name: Upload wheels
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
@@ -29,12 +36,12 @@ jobs:
|
||||
path: ./dist
|
||||
|
||||
publish-to-test-pypi:
|
||||
name: 'Publish to Test PyPI'
|
||||
name: "Publish to Test PyPI"
|
||||
runs-on: ubuntu-latest
|
||||
needs: [build]
|
||||
needs: [ build ]
|
||||
environment:
|
||||
name: testpypi
|
||||
url: https://test.pypi.org/p/pipecat-ai
|
||||
url: https://pypi.org/p/pipecat-ai
|
||||
permissions:
|
||||
id-token: write
|
||||
steps:
|
||||
@@ -43,7 +50,7 @@ jobs:
|
||||
with:
|
||||
name: wheels
|
||||
path: ./dist
|
||||
- name: Publish to Test PyPI
|
||||
- name: Publish to PyPI
|
||||
uses: pypa/gh-action-pypi-publish@release/v1
|
||||
with:
|
||||
verbose: true
|
||||
|
||||
60
.github/workflows/python-compatibility.yaml
vendored
60
.github/workflows/python-compatibility.yaml
vendored
@@ -1,60 +0,0 @@
|
||||
name: Python Compatibility Test
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [main, develop]
|
||||
paths: ['pyproject.toml']
|
||||
pull_request:
|
||||
branches: [main, develop]
|
||||
paths: ['pyproject.toml']
|
||||
|
||||
jobs:
|
||||
test-compatibility:
|
||||
runs-on: ubuntu-latest
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
python-version: ['3.10.18', '3.11.13', '3.12.11', '3.13.5']
|
||||
|
||||
name: Python ${{ matrix.python-version }}
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Install system dependencies
|
||||
run: |
|
||||
sudo apt-get update
|
||||
sudo apt-get install -y \
|
||||
portaudio19-dev \
|
||||
libcairo2-dev \
|
||||
libgirepository1.0-dev \
|
||||
pkg-config
|
||||
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v4
|
||||
with:
|
||||
version: 'latest'
|
||||
|
||||
- name: Set up Python ${{ matrix.python-version }}
|
||||
run: |
|
||||
uv python install ${{ matrix.python-version }}
|
||||
uv python pin ${{ matrix.python-version }}
|
||||
|
||||
- name: Test uv sync with all extras (Python < 3.13)
|
||||
if: "!startsWith(matrix.python-version, '3.13.')"
|
||||
run: |
|
||||
uv sync --group dev --all-extras --no-extra krisp
|
||||
|
||||
- name: Test uv sync without PyTorch extras (Python 3.13+)
|
||||
if: startsWith(matrix.python-version, '3.13.')
|
||||
run: |
|
||||
uv sync --group dev --all-extras \
|
||||
--no-extra krisp \
|
||||
--no-extra local-smart-turn \
|
||||
--no-extra moondream \
|
||||
--no-extra mlx-whisper
|
||||
|
||||
- name: Verify installation
|
||||
run: |
|
||||
uv run python --version
|
||||
uv run python -c "import pipecat; print('✅ Pipecat imports successfully')"
|
||||
51
.github/workflows/sync-quickstart.yaml
vendored
51
.github/workflows/sync-quickstart.yaml
vendored
@@ -1,51 +0,0 @@
|
||||
name: Sync Quickstart to pipecat-quickstart repo
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [main]
|
||||
paths:
|
||||
- 'examples/quickstart/**'
|
||||
workflow_dispatch: # Manual trigger
|
||||
|
||||
jobs:
|
||||
sync-quickstart:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout main repo
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 0
|
||||
|
||||
- name: Checkout quickstart repo
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
repository: pipecat-ai/pipecat-quickstart
|
||||
token: ${{ secrets.QUICKSTART_SYNC_TOKEN }}
|
||||
path: quickstart-repo
|
||||
|
||||
- name: Sync files (excluding uv.lock and README.md)
|
||||
run: |
|
||||
# Copy all files except uv.lock and README.md
|
||||
find examples/quickstart -type f \
|
||||
-not -name "README.md" \
|
||||
-not -name "uv.lock" \
|
||||
-exec cp {} quickstart-repo/ \;
|
||||
|
||||
- name: Commit and push changes
|
||||
run: |
|
||||
cd quickstart-repo
|
||||
git config user.name "GitHub Action"
|
||||
git config user.email "action@github.com"
|
||||
git add .
|
||||
|
||||
# Only commit if there are changes
|
||||
if ! git diff --staged --quiet; then
|
||||
git commit -m "Sync from pipecat main repo
|
||||
|
||||
Updated files from examples/quickstart/
|
||||
Commit: ${{ github.sha }}
|
||||
"
|
||||
git push
|
||||
else
|
||||
echo "No changes to sync"
|
||||
fi
|
||||
34
.github/workflows/tests.yaml
vendored
34
.github/workflows/tests.yaml
vendored
@@ -22,23 +22,31 @@ jobs:
|
||||
steps:
|
||||
- name: Checkout repo
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v3
|
||||
with:
|
||||
version: "latest"
|
||||
|
||||
- name: Set up Python
|
||||
run: uv python install 3.12
|
||||
|
||||
id: setup_python
|
||||
uses: actions/setup-python@v4
|
||||
with:
|
||||
python-version: "3.10"
|
||||
- name: Cache virtual environment
|
||||
uses: actions/cache@v3
|
||||
with:
|
||||
# We are hashing dev-requirements.txt and test-requirements.txt which
|
||||
# contain all dependencies needed to run the tests.
|
||||
key: venv-${{ 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: Install dependencies
|
||||
- name: Setup virtual environment
|
||||
run: |
|
||||
uv sync --group dev --extra anthropic --extra aws --extra google --extra langchain
|
||||
|
||||
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: Test with pytest
|
||||
run: |
|
||||
uv run pytest
|
||||
source .venv/bin/activate
|
||||
pytest
|
||||
|
||||
33
.gitignore
vendored
33
.gitignore
vendored
@@ -7,7 +7,7 @@ venv
|
||||
/.idea
|
||||
#*#
|
||||
|
||||
# Distribution / Packaging
|
||||
# Distribution / packaging
|
||||
.Python
|
||||
build/
|
||||
develop-eggs/
|
||||
@@ -30,25 +30,24 @@ MANIFEST
|
||||
.env
|
||||
fly.toml
|
||||
|
||||
# Examples
|
||||
examples/**/node_modules/
|
||||
examples/**/.expo/
|
||||
examples/**/dist/
|
||||
examples/**/npm-debug.*
|
||||
examples/**/*.jks
|
||||
examples/**/*.p8
|
||||
examples/**/*.p12
|
||||
examples/**/*.key
|
||||
examples/**/*.mobileprovision
|
||||
examples/**/*.orig.*
|
||||
examples/**/web-build/
|
||||
# Example files
|
||||
pipecat/examples/twilio-chatbot/templates/streams.xml
|
||||
pipecat/examples/bot-ready-signalling/client/react-native/node_modules/
|
||||
pipecat/examples/bot-ready-signalling/client/react-native/.expo/
|
||||
pipecat/examples/bot-ready-signalling/client/react-native/dist/
|
||||
pipecat/examples/bot-ready-signalling/client/react-native/npm-debug.*
|
||||
pipecat/examples/bot-ready-signalling/client/react-native/*.jks
|
||||
pipecat/examples/bot-ready-signalling/client/react-native/*.p8
|
||||
pipecat/examples/bot-ready-signalling/client/react-native/*.p12
|
||||
pipecat/examples/bot-ready-signalling/client/react-native/*.key
|
||||
pipecat/examples/bot-ready-signalling/client/react-native/*.mobileprovision
|
||||
pipecat/examples/bot-ready-signalling/client/react-native/*.orig.*
|
||||
pipecat/examples/bot-ready-signalling/client/react-native/web-build/
|
||||
|
||||
# macOS
|
||||
.DS_Store
|
||||
|
||||
|
||||
# Documentation
|
||||
docs/api/_build/
|
||||
docs/api/api
|
||||
|
||||
# uv
|
||||
.python-version
|
||||
docs/api/api
|
||||
@@ -1,8 +1,8 @@
|
||||
repos:
|
||||
- repo: https://github.com/astral-sh/ruff-pre-commit
|
||||
rev: v0.12.1
|
||||
rev: v0.9.7
|
||||
hooks:
|
||||
- id: ruff
|
||||
language_version: python3
|
||||
args: [--fix]
|
||||
args: [ --select, I, ]
|
||||
- id: ruff-format
|
||||
|
||||
@@ -9,14 +9,22 @@ build:
|
||||
- python3-dev
|
||||
- libasound2-dev
|
||||
jobs:
|
||||
post_install:
|
||||
- pip install uv
|
||||
- UV_PROJECT_ENVIRONMENT=$READTHEDOCS_VIRTUALENV_PATH uv sync --group docs --all-extras --no-extra krisp --no-extra gstreamer --no-extra local_smart_turn --no-extra moondream --no-extra riva --no-extra mlx-whisper
|
||||
pre_build:
|
||||
- python -m pip install --upgrade pip
|
||||
- pip install wheel setuptools
|
||||
post_build:
|
||||
- echo "Build completed"
|
||||
|
||||
sphinx:
|
||||
configuration: docs/api/conf.py
|
||||
fail_on_warning: false
|
||||
|
||||
python:
|
||||
install:
|
||||
- requirements: docs/api/requirements.txt
|
||||
- method: pip
|
||||
path: .
|
||||
|
||||
search:
|
||||
ranking:
|
||||
api/*: 5
|
||||
|
||||
3605
CHANGELOG.md
3605
CHANGELOG.md
File diff suppressed because it is too large
Load Diff
@@ -1,336 +0,0 @@
|
||||
# Community Integrations Guide
|
||||
|
||||
Pipecat welcomes community-maintained integrations! As our ecosystem grows, we've established a process for any developer to create and maintain their own service integrations while ensuring discoverability for the Pipecat community.
|
||||
|
||||
## Overview
|
||||
|
||||
**What we support:** Community-maintained integrations that live in separate repositories and are maintained by their authors.
|
||||
|
||||
**What we don't do:** The Pipecat team does not code review, test, or maintain community integrations. We provide guidance and list approved integrations for discoverability.
|
||||
|
||||
**Why this approach:** This allows the community to move quickly while keeping the Pipecat core team focused on maintaining the framework itself.
|
||||
|
||||
## Submitting your Integration
|
||||
|
||||
To be listed as an official community integration, follow these steps:
|
||||
|
||||
### Step 1: Build Your Integration
|
||||
|
||||
Create your integration following the patterns and examples shown in the "Integration Patterns and Examples" section below.
|
||||
|
||||
### Step 2: Set Up Your Repository
|
||||
|
||||
Your repository must contain these components:
|
||||
|
||||
- **Source code** - Complete implementation following Pipecat patterns
|
||||
- **Foundational example** - Single file example showing basic usage (see [Pipecat examples](https://github.com/pipecat-ai/pipecat/tree/main/examples/foundational))
|
||||
- **README.md** - Must include:
|
||||
|
||||
- Introduction and explanation of your integration
|
||||
- Installation instructions
|
||||
- Usage instructions with Pipecat Pipeline
|
||||
- How to run your example
|
||||
- Pipecat version compatibility (e.g., "Tested with Pipecat v0.0.86")
|
||||
- Company attribution: If you work for the company providing the service, please mention this in your README. This helps build confidence that the integration will be actively maintained.
|
||||
|
||||
- **LICENSE** - Permissive license (BSD-2 like Pipecat, or equivalent open source terms)
|
||||
- **Code documentation** - Source code with docstrings (we recommend following [Pipecat's docstring conventions](https://github.com/pipecat-ai/pipecat/blob/main/CONTRIBUTING.md#docstring-conventions))
|
||||
- **Changelog** - Maintain a changelog for version updates
|
||||
|
||||
### Step 3: Join Discord
|
||||
|
||||
Join our Discord: https://discord.gg/pipecat
|
||||
|
||||
### Step 4: Submit for Listing
|
||||
|
||||
Submit a pull request to add your integration to our [Community Integrations documentation page](https://docs.pipecat.ai/server/services/community-integrations).
|
||||
|
||||
**To submit:**
|
||||
|
||||
1. Fork the [Pipecat docs repository](https://github.com/pipecat-ai/docs)
|
||||
2. Edit the file `server/services/community-integrations.mdx`
|
||||
3. Add your integration to the appropriate service category table with:
|
||||
- Service name
|
||||
- Link to your repository
|
||||
- Maintainer GitHub username(s)
|
||||
4. Include a link to your demo video (approx 30-60 seconds) in your PR description showing:
|
||||
- Core functionality of your integration
|
||||
- Handling of an interruption (if applicable to service type)
|
||||
5. Submit your pull request
|
||||
|
||||
Once your PR is submitted, post in the `#community-integrations` Discord channel to let us know.
|
||||
|
||||
## Integration Patterns and Examples
|
||||
|
||||
### STT (Speech-to-Text) Services
|
||||
|
||||
#### Websocket-based Services
|
||||
|
||||
**Base class:** `STTService`
|
||||
|
||||
**Examples:**
|
||||
|
||||
- [DeepgramSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/deepgram/stt.py)
|
||||
- [SpeechmaticsSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/speechmatics/stt.py)
|
||||
|
||||
#### File-based Services
|
||||
|
||||
**Base class:** `SegmentedSTTService`
|
||||
|
||||
**Examples:**
|
||||
|
||||
- [NvidiaSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/nvidia/stt.py)
|
||||
- [FalSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/fal/stt.py)
|
||||
|
||||
#### Key requirements:
|
||||
|
||||
- STT services should push `InterimTranscriptionFrames` and `TranscriptionFrames`
|
||||
- If confidence values are available, filter for values >50% confidence
|
||||
|
||||
### LLM (Large Language Model) Services
|
||||
|
||||
#### OpenAI-Compatible Services
|
||||
|
||||
**Base class:** `OpenAILLMService`
|
||||
|
||||
**Examples:**
|
||||
|
||||
- [AzureLLMService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/azure/llm.py)
|
||||
- [GrokLLMService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/grok/llm.py) - Shows overriding the base class where needed
|
||||
|
||||
#### Non-OpenAI Compatible Services
|
||||
|
||||
**Requires:** Full implementation
|
||||
|
||||
**Examples:**
|
||||
|
||||
- [AnthropicLLMService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/anthropic/llm.py)
|
||||
- [GoogleLLMService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/google/llm.py)
|
||||
|
||||
#### Key requirements:
|
||||
|
||||
- **Frame sequence:** Output must follow this frame sequence pattern:
|
||||
|
||||
- `LLMFullResponseStartFrame` - Signals the start of an LLM response
|
||||
- `LLMTextFrame` - Contains LLM content, typically streamed as tokens
|
||||
- `LLMFullResponseEndFrame` - Signals the end of an LLM response
|
||||
|
||||
- **Context aggregation:** Implement context aggregation to collect user and assistant content:
|
||||
- Aggregators come in pairs with a `user()` instance and `assistant()` instance
|
||||
- Context must adhere to the `LLMContext` universal format
|
||||
- Aggregators should handle adding messages, function calls, and images to the context
|
||||
|
||||
### TTS (Text-to-Speech) Services
|
||||
|
||||
#### AudioContextWordTTSService
|
||||
|
||||
**Use for:** Websocket-based services supporting word/timestamp alignment
|
||||
|
||||
**Example:**
|
||||
|
||||
- [CartesiaTTSService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/cartesia/tts.py)
|
||||
|
||||
#### InterruptibleTTSService
|
||||
|
||||
**Use for:** Websocket-based services without word/timestamp alignment, requiring disconnection on interruption
|
||||
|
||||
**Example:**
|
||||
|
||||
- [SarvamTTSService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/sarvam/tts.py)
|
||||
|
||||
#### WordTTSService
|
||||
|
||||
**Use for:** HTTP-based services supporting word/timestamp alignment
|
||||
|
||||
**Example:**
|
||||
|
||||
- [ElevenLabsHttpTTSService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/elevenlabs/tts.py)
|
||||
|
||||
#### TTSService
|
||||
|
||||
**Use for:** HTTP-based services without word/timestamp alignment
|
||||
|
||||
**Example:**
|
||||
|
||||
- [GoogleHttpTTSService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/google/tts.py)
|
||||
|
||||
#### Key requirements:
|
||||
|
||||
- For websocket services, use asyncio WebSocket implementation (required for v13+ support)
|
||||
- Handle idle service timeouts with keepalives
|
||||
- TTSServices push both audio (`TTSRawAudioFrame`) and text (`TTSTextFrame`) frames
|
||||
|
||||
### Telephony Serializers
|
||||
|
||||
Pipecat supports telephony provider integration using websocket connections to exchange MediaStreams. These services use a FrameSerializer to serialize and deserialize inputs from the FastAPIWebsocketTransport.
|
||||
|
||||
**Examples:**
|
||||
|
||||
- [Twilio](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/serializers/twilio.py)
|
||||
- [Telnyx](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/serializers/telnyx.py)
|
||||
|
||||
#### Key requirements:
|
||||
|
||||
- Include hang-up functionality using the provider's native API, ideally using `aiohttp`
|
||||
- Support DTMF (dual-tone multi-frequency) events if the provider supports them:
|
||||
- Deserialize DTMF events from the provider's protocol to `InputDTMFFrame`
|
||||
- Use `KeypadEntry` enum for valid keypad entries (0-9, \*, #, A-D)
|
||||
- Handle invalid DTMF digits gracefully by returning `None`
|
||||
|
||||
### Image Generation Services
|
||||
|
||||
**Base class:** `ImageGenService`
|
||||
|
||||
**Examples:**
|
||||
|
||||
- [FalImageGenService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/fal/image.py)
|
||||
- [GoogleImageGenService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/google/image.py)
|
||||
|
||||
#### Key requirements:
|
||||
|
||||
- Must implement `run_image_gen` method returning an `AsyncGenerator`
|
||||
|
||||
### Vision Services
|
||||
|
||||
Vision services process images and provide analysis such as descriptions, object detection, or visual question answering.
|
||||
|
||||
**Base class:** `VisionService`
|
||||
|
||||
**Example:**
|
||||
|
||||
- [MoondreamVisionService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/moondream/vision.py)
|
||||
|
||||
#### Key requirements:
|
||||
|
||||
- Must implement `run_vision` method that takes an `LLMContext` and returns an `AsyncGenerator[Frame, None]`
|
||||
- The method processes the latest image in the context and yields frames with analysis results
|
||||
- Typically yields `TextFrame` objects containing descriptions or answers
|
||||
|
||||
## Implementation Guidelines
|
||||
|
||||
### Naming Conventions
|
||||
|
||||
- **STT:** `VendorSTTService`
|
||||
- **LLM:** `VendorLLMService`
|
||||
- **TTS:**
|
||||
- Websocket: `VendorTTSService`
|
||||
- HTTP: `VendorHttpTTSService`
|
||||
- **Image:** `VendorImageGenService`
|
||||
- **Vision:** `VendorVisionService`
|
||||
- **Telephony:** `VendorFrameSerializer`
|
||||
|
||||
### Metrics Support
|
||||
|
||||
Enable metrics in your service:
|
||||
|
||||
```python
|
||||
def can_generate_metrics(self) -> bool:
|
||||
"""Check if this service can generate processing metrics.
|
||||
|
||||
Returns:
|
||||
True, as this service supports metrics.
|
||||
"""
|
||||
return True
|
||||
```
|
||||
|
||||
### Dynamic Settings Updates
|
||||
|
||||
STT, LLM, and TTS services support `ServiceUpdateSettingsFrame` for dynamic configuration changes. The base STTService has an `_update_settings()` method that handles settings, and the private `_settings` `Dict` is used to store settings and provide access to the subclass.
|
||||
|
||||
```python
|
||||
async def set_language(self, language: Language):
|
||||
"""Set the recognition language and reconnect.
|
||||
|
||||
Args:
|
||||
language: The language to use for speech recognition.
|
||||
"""
|
||||
logger.info(f"Switching STT language to: [{language}]")
|
||||
self._settings["language"] = language
|
||||
await self._disconnect()
|
||||
await self._connect()
|
||||
```
|
||||
|
||||
Note that, in this example, Deepgram requires the websocket connection be disconnected and reconnected to reinitialize the service with the new value. Consider if your service requires reconnection.
|
||||
|
||||
### Sample Rate Handling
|
||||
|
||||
Sample rates are set via PipelineParams and passed to each frame processor at initialization. The pattern is to _not_ set the sample rate value in the constructor of a given service. Instead, use the `start()` method to initialize sample rates from the frame:
|
||||
|
||||
```python
|
||||
async def start(self, frame: StartFrame):
|
||||
"""Start the service."""
|
||||
await super().start(frame)
|
||||
self._settings["output_format"]["sample_rate"] = self.sample_rate
|
||||
await self._connect()
|
||||
```
|
||||
|
||||
Note that `self.sample_rate` is a `@property` set in the TTSService base class, which provides access to the private sample rate value obtained from the StartFrame.
|
||||
|
||||
### Tracing Decorators
|
||||
|
||||
Use Pipecat's tracing decorators:
|
||||
|
||||
- **STT:** `@traced_stt` - decorate a function that handles `transcript`, `is_final`, `language` as args
|
||||
- **LLM:** `@traced_llm` - decorate the `_process_context()` method
|
||||
- **TTS:** `@traced_tts` - decorate the `run_tts()` method
|
||||
|
||||
## Best Practices
|
||||
|
||||
### Packaging and Distribution
|
||||
|
||||
- Use [uv](https://docs.astral.sh/uv/) for packaging (encouraged)
|
||||
- Consider releasing to PyPI for easier installation
|
||||
- Follow semantic versioning principles
|
||||
- Maintain a changelog
|
||||
|
||||
### HTTP Communication
|
||||
|
||||
For REST-based communication, use aiohttp. Pipecat includes this as a required dependency, so using it prevents adding an additional dependency to your integration.
|
||||
|
||||
### Error Handling
|
||||
|
||||
- Wrap API calls in appropriate try/catch blocks
|
||||
- Handle rate limits and network failures gracefully
|
||||
- Provide meaningful error messages
|
||||
- When errors occur, raise exceptions AND push `ErrorFrame`s to notify the pipeline:
|
||||
|
||||
```python
|
||||
from pipecat.frames.frames import ErrorFrame
|
||||
|
||||
try:
|
||||
# Your API call
|
||||
result = await self._make_api_call()
|
||||
except Exception as e:
|
||||
# Push error frame to pipeline
|
||||
await self.push_error(ErrorFrame(error=f"{self} error: {e}"))
|
||||
# Raise or handle as appropriate
|
||||
raise
|
||||
```
|
||||
|
||||
### Testing
|
||||
|
||||
- Your foundational example serves as a valuable integration-level test
|
||||
- Unit tests are nice to have. As the Pipecat teams provides better guidance, we will encourage unit testing more
|
||||
|
||||
## Disclaimer
|
||||
|
||||
Community integrations are community-maintained and not officially supported by the Pipecat team. Users should evaluate these integrations independently. The Pipecat team reserves the right to remove listings that become unmaintained or problematic.
|
||||
|
||||
## Staying Up to Date
|
||||
|
||||
Pipecat evolves rapidly to support the latest AI technologies and patterns. While we strive to minimize breaking changes, they do occur as the framework matures.
|
||||
|
||||
**We strongly recommend:**
|
||||
|
||||
- Join our Discord at https://discord.gg/pipecat and monitor the `#announcements` channel for release notifications
|
||||
- Follow our changelog: https://github.com/pipecat-ai/pipecat/blob/main/CHANGELOG.md
|
||||
- Test your integration against new Pipecat releases promptly
|
||||
- Update your README with the last tested Pipecat version
|
||||
|
||||
This helps ensure your integration remains compatible and your users have clear expectations about version support.
|
||||
|
||||
## Questions?
|
||||
|
||||
Join our Discord community at https://discord.gg/pipecat and post in the `#community-integrations` channel for guidance and support.
|
||||
|
||||
For additional questions, you can also reach out to us at pipecat-ai@daily.co.
|
||||
277
CONTRIBUTING.md
277
CONTRIBUTING.md
@@ -1,9 +1,5 @@
|
||||
## Contributing to Pipecat
|
||||
|
||||
**Want to add a new service integration?**
|
||||
We encourage community-maintained integrations! Please see our [Community Integration Guide](COMMUNITY_INTEGRATIONS.md) for the process and requirements.
|
||||
|
||||
**Want to contribute to Pipecat core?**
|
||||
We welcome contributions of all kinds! Your help is appreciated. Follow these steps to get involved:
|
||||
|
||||
1. **Fork this repository**: Start by forking the Pipecat Documentation repository to your GitHub account.
|
||||
@@ -17,139 +13,24 @@ We welcome contributions of all kinds! Your help is appreciated. Follow these st
|
||||
git checkout -b your-branch-name
|
||||
```
|
||||
4. **Make your changes**: Edit or add files as necessary.
|
||||
5. **Add a changelog entry**: Create a changelog fragment file (see [Changelog Entries](#changelog-entries) below).
|
||||
6. **Test your changes**: Ensure that your changes look correct and follow the style set in the codebase.
|
||||
7. **Commit your changes**: Once you're satisfied with your changes, commit them with a meaningful message.
|
||||
5. **Test your changes**: Ensure that your changes look correct and follow the style set in the codebase.
|
||||
6. **Commit your changes**: Once you're satisfied with your changes, commit them with a meaningful message.
|
||||
|
||||
```bash
|
||||
git commit -m "Description of your changes"
|
||||
```
|
||||
|
||||
8. **Push your changes**: Push your branch to your forked repository.
|
||||
7. **Push your changes**: Push your branch to your forked repository.
|
||||
|
||||
```bash
|
||||
git push origin your-branch-name
|
||||
```
|
||||
|
||||
9. **Submit a Pull Request (PR)**: Open a PR from your forked repository to the main branch of this repo.
|
||||
8. **Submit a Pull Request (PR)**: Open a PR from your forked repository to the main branch of this repo.
|
||||
> Important: Describe the changes you've made clearly!
|
||||
|
||||
Our maintainers will review your PR, and once everything is good, your contributions will be merged!
|
||||
|
||||
## Changelog Entries
|
||||
|
||||
Every pull request that makes a user-facing change should include a changelog entry. We use a changelog fragment system to avoid merge conflicts.
|
||||
|
||||
### Creating a Changelog Fragment
|
||||
|
||||
1. Create a new file in the `changelog/` directory with this naming pattern:
|
||||
|
||||
```
|
||||
<PR_number>.<type>.md
|
||||
```
|
||||
|
||||
2. Choose the appropriate type:
|
||||
|
||||
- `added.md` - New features
|
||||
- `changed.md` - Changes in existing functionality
|
||||
- `deprecated.md` - Soon-to-be removed features
|
||||
- `removed.md` - Removed features
|
||||
- `fixed.md` - Bug fixes
|
||||
- `security.md` - Security fixes
|
||||
- `other.md` - Other changes (documentation, dependencies, etc.)
|
||||
|
||||
3. Write your changelog entry as a Markdown bullet point. Include the `-` at the start:
|
||||
|
||||
**Example files:**
|
||||
|
||||
`changelog/1234.added.md`:
|
||||
|
||||
```markdown
|
||||
- Added support for Anthropic Claude 3.5 Sonnet with improved streaming performance.
|
||||
```
|
||||
|
||||
`changelog/5678.fixed.md`:
|
||||
|
||||
```markdown
|
||||
- Fixed an issue where audio frames were dropped during high-load scenarios.
|
||||
```
|
||||
|
||||
**For entries with nested bullets:**
|
||||
|
||||
`changelog/1234.changed.md`:
|
||||
|
||||
```markdown
|
||||
- Updated service configuration:
|
||||
|
||||
- Changed default timeout to 30 seconds
|
||||
- Added retry logic for failed connections
|
||||
```
|
||||
|
||||
### Multiple Changes in One PR
|
||||
|
||||
**Different types of changes:** Create separate fragment files for each type:
|
||||
|
||||
```
|
||||
changelog/1234.added.md
|
||||
changelog/1234.fixed.md
|
||||
```
|
||||
|
||||
**Multiple changes of the same type:** Create numbered fragment files:
|
||||
|
||||
```
|
||||
changelog/1234.changed.md
|
||||
changelog/1234.changed.2.md
|
||||
```
|
||||
|
||||
**Related changes:** Use nested bullets in a single fragment:
|
||||
|
||||
```markdown
|
||||
- Updated service configuration:
|
||||
|
||||
- Changed default timeout to 30 seconds
|
||||
- Added retry logic for failed connections
|
||||
```
|
||||
|
||||
**Rule of thumb:** One logical change per fragment file. If changes are unrelated, use separate files.
|
||||
|
||||
### Preview Your Changes
|
||||
|
||||
To see what your changelog entry will look like:
|
||||
|
||||
```bash
|
||||
towncrier build --draft --version Unreleased
|
||||
```
|
||||
|
||||
This won't modify any files, just show you a preview.
|
||||
|
||||
### When to Skip Changelog Entries
|
||||
|
||||
You can skip adding a changelog entry for:
|
||||
|
||||
- Documentation-only changes
|
||||
- Internal refactoring with no user-facing impact
|
||||
- Test-only changes
|
||||
- CI/build configuration changes
|
||||
|
||||
If you're unsure whether your change needs a changelog entry, ask in your PR!
|
||||
|
||||
## Dependency Management
|
||||
|
||||
This project uses [uv](https://docs.astral.sh/uv/) for dependency management. The `uv.lock` file is committed to ensure reproducible builds.
|
||||
|
||||
### Adding or Updating Dependencies
|
||||
|
||||
1. Edit `pyproject.toml` to add/update dependencies
|
||||
2. Run `uv lock` to update the lockfile with new dependency resolution
|
||||
3. Run `uv sync` to install the updated dependencies locally
|
||||
4. Always commit both files together:
|
||||
```bash
|
||||
git add pyproject.toml uv.lock
|
||||
git commit -m "feat: add new dependency for feature X"
|
||||
```
|
||||
|
||||
**Important:** Never manually edit `uv.lock`. It's auto-generated by `uv lock`.
|
||||
|
||||
## Code Style and Documentation
|
||||
|
||||
### Python Code Style
|
||||
@@ -160,150 +41,36 @@ We use Ruff for code linting and formatting. Please ensure your code passes all
|
||||
|
||||
We follow Google-style docstrings with these specific conventions:
|
||||
|
||||
**Regular Classes:**
|
||||
- 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
|
||||
|
||||
- Class docstring describes the class purpose and key functionality
|
||||
- `__init__` method has its own docstring with complete `Args:` section documenting all parameters
|
||||
- All public methods must have docstrings with `Args:` and `Returns:` sections as appropriate
|
||||
|
||||
**Dataclasses:**
|
||||
|
||||
- Class docstring describes the purpose and documents all fields in a `Parameters:` section
|
||||
- No `__init__` docstring (auto-generated)
|
||||
|
||||
**Properties:**
|
||||
|
||||
- Must have docstrings with `Returns:` section
|
||||
|
||||
**Abstract Methods:**
|
||||
|
||||
- Must have docstrings explaining what subclasses should implement
|
||||
|
||||
**`__init__.py` Files:**
|
||||
|
||||
- **Skip docstrings** for pure import/re-export modules
|
||||
- **Add brief docstrings** for top-level packages or those with initialization logic
|
||||
|
||||
**Enums:**
|
||||
|
||||
- Class docstring describes the enumeration purpose
|
||||
- Use `Parameters:` section to document each enum value and its meaning
|
||||
- No `__init__` docstring (Enums don't have custom constructors)
|
||||
|
||||
**Code Examples in Docstrings:**
|
||||
|
||||
- Use `Examples:` as a section header for multiple examples
|
||||
- Use descriptive text followed by double colons (`::`) for each example
|
||||
- **Always include a blank line after the `::"`**
|
||||
- Indent all code consistently within each block
|
||||
- Separate multiple examples with blank lines for readability
|
||||
|
||||
**Lists and Bullets in Docstrings:**
|
||||
|
||||
- Use dashes (`-`) for bullet points, not asterisks (`*`)
|
||||
- **Add a blank line before bullet lists** when they follow a colon
|
||||
- Use section headers like "Supported features:" or "Behavior:" before lists
|
||||
- For complex nested information, consider using paragraph format instead
|
||||
|
||||
**Deprecations:**
|
||||
|
||||
- Use `warnings.warn()` in code for runtime deprecation warnings
|
||||
- Add `.. deprecated::` directive in docstrings for documentation visibility
|
||||
- Include version information and describe current status
|
||||
- Describe parameters in present tense, use directive to indicate deprecation status
|
||||
|
||||
#### Examples:
|
||||
Example of correctly documented class:
|
||||
|
||||
```python
|
||||
# Regular class
|
||||
class MyService(BaseService):
|
||||
"""Description of what the service does.
|
||||
class MyClass:
|
||||
"""Class description.
|
||||
|
||||
Provides detailed explanation of the service's functionality,
|
||||
key features, and usage patterns.
|
||||
Additional details about the class.
|
||||
|
||||
Supported features:
|
||||
|
||||
- Feature one with detailed explanation
|
||||
- Feature two with additional context
|
||||
- Feature three for advanced use cases
|
||||
Args:
|
||||
param1: Description of first parameter.
|
||||
param2: Description of second parameter.
|
||||
"""
|
||||
|
||||
def __init__(self, param1: str, old_param: str = None, **kwargs):
|
||||
"""Initialize the service.
|
||||
|
||||
Args:
|
||||
param1: Description of param1.
|
||||
old_param: Controls legacy behavior.
|
||||
|
||||
.. deprecated:: 1.2.0
|
||||
This parameter no longer has any effect and will be removed in version 2.0.
|
||||
|
||||
**kwargs: Additional arguments passed to parent.
|
||||
"""
|
||||
if old_param is not None:
|
||||
import warnings
|
||||
warnings.warn(
|
||||
"Parameter 'old_param' is deprecated and will be removed in version 2.0.",
|
||||
DeprecationWarning,
|
||||
)
|
||||
super().__init__(**kwargs)
|
||||
def __init__(self, param1, param2):
|
||||
# No docstring required here as parameters are documented above
|
||||
self.param1 = param1
|
||||
self.param2 = param2
|
||||
|
||||
@property
|
||||
def sample_rate(self) -> int:
|
||||
"""Get the current sample rate.
|
||||
def some_property(self) -> str:
|
||||
"""Get the formatted property value.
|
||||
|
||||
Returns:
|
||||
The sample rate in Hz.
|
||||
A string representation of the property.
|
||||
"""
|
||||
return self._sample_rate
|
||||
|
||||
async def process_data(self, data: str) -> bool:
|
||||
"""Process the provided data.
|
||||
|
||||
Args:
|
||||
data: The data to process.
|
||||
|
||||
Returns:
|
||||
True if processing succeeded.
|
||||
"""
|
||||
pass
|
||||
|
||||
# Dataclass with code examples
|
||||
@dataclass
|
||||
class MessageFrame:
|
||||
"""Frame containing messages in OpenAI format.
|
||||
|
||||
Supports both simple and content list message formats.
|
||||
|
||||
Example::
|
||||
|
||||
[
|
||||
{"role": "user", "content": "Hello"},
|
||||
{"role": "assistant", "content": "Hi there!"}
|
||||
]
|
||||
|
||||
Parameters:
|
||||
messages: List of messages in OpenAI format.
|
||||
"""
|
||||
|
||||
messages: List[dict]
|
||||
|
||||
# Enum class
|
||||
class Status(Enum):
|
||||
"""Status codes for processing operations.
|
||||
|
||||
Parameters:
|
||||
PENDING: Operation is queued but not started.
|
||||
RUNNING: Operation is currently in progress.
|
||||
COMPLETED: Operation finished successfully.
|
||||
FAILED: Operation encountered an error.
|
||||
"""
|
||||
|
||||
PENDING = "pending"
|
||||
RUNNING = "running"
|
||||
COMPLETED = "completed"
|
||||
FAILED = "failed"
|
||||
return f"Property: {self.param1}"
|
||||
```
|
||||
|
||||
# Contributor Covenant Code of Conduct
|
||||
|
||||
40
Dockerfile
Normal file
40
Dockerfile
Normal file
@@ -0,0 +1,40 @@
|
||||
# setup
|
||||
FROM python:3.11.5
|
||||
|
||||
WORKDIR /app
|
||||
COPY requirements.txt /app
|
||||
COPY *.py /app
|
||||
COPY pyproject.toml /app
|
||||
|
||||
COPY src/ /app/src/
|
||||
COPY examples/ /app/examples/
|
||||
|
||||
WORKDIR /app
|
||||
RUN ls --recursive /app/
|
||||
RUN pip3 install --upgrade -r requirements.txt
|
||||
RUN python -m build .
|
||||
RUN pip3 install .
|
||||
RUN pip3 install gunicorn
|
||||
# If running on Ubuntu, Azure TTS requires some extra config
|
||||
# https://learn.microsoft.com/en-us/azure/ai-services/speech-service/quickstarts/setup-platform?pivots=programming-language-python&tabs=linux%2Cubuntu%2Cdotnetcli%2Cdotnet%2Cjre%2Cmaven%2Cnodejs%2Cmac%2Cpypi
|
||||
|
||||
RUN wget -O - https://www.openssl.org/source/openssl-1.1.1w.tar.gz | tar zxf -
|
||||
WORKDIR openssl-1.1.1w
|
||||
RUN ./config --prefix=/usr/local
|
||||
RUN make -j $(nproc)
|
||||
RUN make install_sw install_ssldirs
|
||||
RUN ldconfig -v
|
||||
ENV SSL_CERT_DIR=/etc/ssl/certs
|
||||
|
||||
#ENV LD_LIBRARY_PATH=/usr/local/lib:$LD_LIBRARY_PATH
|
||||
RUN apt clean
|
||||
RUN apt-get update
|
||||
RUN apt-get -y install build-essential libssl-dev ca-certificates libasound2 wget
|
||||
|
||||
ENV PYTHONUNBUFFERED=1
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
EXPOSE 8000
|
||||
# run
|
||||
CMD ["gunicorn", "--workers=2", "--log-level", "debug", "--chdir", "examples/server", "--capture-output", "daily-bot-manager:app", "--bind=0.0.0.0:8000"]
|
||||
@@ -1,4 +0,0 @@
|
||||
prune docs
|
||||
prune examples
|
||||
prune scripts
|
||||
prune tests
|
||||
233
README.md
233
README.md
@@ -2,14 +2,12 @@
|
||||
<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://deepwiki.com/pipecat-ai/pipecat)
|
||||
[](https://pypi.org/project/pipecat-ai)  [](https://codecov.io/gh/pipecat-ai/pipecat) [](https://docs.pipecat.ai) [](https://discord.gg/pipecat)
|
||||
|
||||
# 🎙️ Pipecat: Real-Time Voice & Multimodal AI Agents
|
||||
|
||||
**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.
|
||||
|
||||
> Want to dive right in? Try the [quickstart](https://docs.pipecat.ai/getting-started/quickstart).
|
||||
|
||||
## 🚀 What You Can Build
|
||||
|
||||
- **Voice Assistants** – natural, streaming conversations with AI
|
||||
@@ -19,6 +17,8 @@
|
||||
- **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
|
||||
@@ -26,157 +26,164 @@
|
||||
- **Composable Pipelines**: Build complex behavior from modular components
|
||||
- **Real-Time**: Ultra-low latency interaction with different transports (e.g. WebSockets or WebRTC)
|
||||
|
||||
## 🌐 Pipecat Ecosystem
|
||||
|
||||
### 📱 Client SDKs
|
||||
|
||||
Building client applications? You can connect to Pipecat from any platform using our official SDKs:
|
||||
|
||||
<a href="https://docs.pipecat.ai/client/js/introduction">JavaScript</a> | <a href="https://docs.pipecat.ai/client/react/introduction">React</a> | <a href="https://docs.pipecat.ai/client/react-native/introduction">React Native</a> |
|
||||
<a href="https://docs.pipecat.ai/client/ios/introduction">Swift</a> | <a href="https://docs.pipecat.ai/client/android/introduction">Kotlin</a> | <a href="https://docs.pipecat.ai/client/c++/introduction">C++</a> | <a href="https://github.com/pipecat-ai/pipecat-esp32">ESP32</a>
|
||||
|
||||
### 🧭 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.
|
||||
|
||||
### 🪄 Beautiful UIs
|
||||
|
||||
Want to build beautiful and engaging experiences? Checkout the [Voice UI Kit](https://github.com/pipecat-ai/voice-ui-kit), a collection of components, hooks and templates for building voice AI applications quickly.
|
||||
|
||||
### 🛠️ Create and deploy projects
|
||||
|
||||
Create a new project in under a minute with the [Pipecat CLI](https://github.com/pipecat-ai/pipecat-cli). Then use the CLI to monitor and deploy your agent to production.
|
||||
|
||||
### 🔍 Debugging
|
||||
|
||||
Looking for help debugging your pipeline and processors? Check out [Whisker](https://github.com/pipecat-ai/whisker), a real-time Pipecat debugger.
|
||||
|
||||
### 🖥️ Terminal
|
||||
|
||||
Love terminal applications? Check out [Tail](https://github.com/pipecat-ai/tail), a terminal dashboard for Pipecat.
|
||||
|
||||
### 📺️ Pipecat TV Channel
|
||||
|
||||
Catch new features, interviews, and how-tos on our [Pipecat TV](https://www.youtube.com/playlist?list=PLzU2zoMTQIHjqC3v4q2XVSR3hGSzwKFwH) channel.
|
||||
|
||||
## 🎬 See it in action
|
||||
|
||||
<p float="left">
|
||||
<a href="https://github.com/pipecat-ai/pipecat-examples/tree/main/simple-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat-examples/main/simple-chatbot/image.png" width="400" /></a>
|
||||
<a href="https://github.com/pipecat-ai/pipecat-examples/tree/main/storytelling-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat-examples/main/storytelling-chatbot/image.png" width="400" /></a>
|
||||
<a href="https://github.com/pipecat-ai/pipecat/tree/main/examples/simple-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat/main/examples/simple-chatbot/image.png" width="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>
|
||||
<br/>
|
||||
<a href="https://github.com/pipecat-ai/pipecat-examples/tree/main/translation-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat-examples/main/translation-chatbot/image.png" width="400" /></a>
|
||||
<a href="https://github.com/pipecat-ai/pipecat/blob/main/examples/foundational/12-describe-video.py"><img src="https://github.com/pipecat-ai/pipecat/blob/main/examples/foundational/assets/moondream.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="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>
|
||||
</p>
|
||||
|
||||
## 📱 Client SDKs
|
||||
|
||||
You can connect to Pipecat from any platform using our official SDKs:
|
||||
|
||||
| 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 |
|
||||
|
||||
## 🧩 Available services
|
||||
|
||||
| Category | Services |
|
||||
| ------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| Speech-to-Text | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [AWS](https://docs.pipecat.ai/server/services/stt/aws), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Cartesia](https://docs.pipecat.ai/server/services/stt/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/stt/elevenlabs), [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), [Gradium](https://docs.pipecat.ai/server/services/stt/gradium), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [NVIDIA Riva](https://docs.pipecat.ai/server/services/stt/riva), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [SambaNova (Whisper)](https://docs.pipecat.ai/server/services/stt/sambanova), [Sarvam](https://docs.pipecat.ai/server/services/stt/sarvam), [Soniox](https://docs.pipecat.ai/server/services/stt/soniox), [Speechmatics](https://docs.pipecat.ai/server/services/stt/speechmatics), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper) |
|
||||
| LLMs | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [AWS](https://docs.pipecat.ai/server/services/llm/aws), [Azure](https://docs.pipecat.ai/server/services/llm/azure), [Cerebras](https://docs.pipecat.ai/server/services/llm/cerebras), [DeepSeek](https://docs.pipecat.ai/server/services/llm/deepseek), [Fireworks AI](https://docs.pipecat.ai/server/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/server/services/llm/gemini), [Grok](https://docs.pipecat.ai/server/services/llm/grok), [Groq](https://docs.pipecat.ai/server/services/llm/groq), [Mistral](https://docs.pipecat.ai/server/services/llm/mistral), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nim), [Ollama](https://docs.pipecat.ai/server/services/llm/ollama), [OpenAI](https://docs.pipecat.ai/server/services/llm/openai), [OpenRouter](https://docs.pipecat.ai/server/services/llm/openrouter), [Perplexity](https://docs.pipecat.ai/server/services/llm/perplexity), [Qwen](https://docs.pipecat.ai/server/services/llm/qwen), [SambaNova](https://docs.pipecat.ai/server/services/llm/sambanova) [Together AI](https://docs.pipecat.ai/server/services/llm/together) |
|
||||
| Text-to-Speech | [Async](https://docs.pipecat.ai/server/services/tts/asyncai), [AWS](https://docs.pipecat.ai/server/services/tts/aws), [Azure](https://docs.pipecat.ai/server/services/tts/azure), [Cartesia](https://docs.pipecat.ai/server/services/tts/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/tts/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/tts/elevenlabs), [Fish](https://docs.pipecat.ai/server/services/tts/fish), [Google](https://docs.pipecat.ai/server/services/tts/google), [Gradium](https://docs.pipecat.ai/server/services/tts/gradium), [Groq](https://docs.pipecat.ai/server/services/tts/groq), [Hume](https://docs.pipecat.ai/server/services/tts/hume), [Inworld](https://docs.pipecat.ai/server/services/tts/inworld), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [MiniMax](https://docs.pipecat.ai/server/services/tts/minimax), [Neuphonic](https://docs.pipecat.ai/server/services/tts/neuphonic), [NVIDIA Riva](https://docs.pipecat.ai/server/services/tts/riva), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [Piper](https://docs.pipecat.ai/server/services/tts/piper), [PlayHT](https://docs.pipecat.ai/server/services/tts/playht), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [Sarvam](https://docs.pipecat.ai/server/services/tts/sarvam), [Speechmatics](https://docs.pipecat.ai/server/services/tts/speechmatics), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts) |
|
||||
| Speech-to-Speech | [AWS Nova Sonic](https://docs.pipecat.ai/server/services/s2s/aws), [Gemini Multimodal Live](https://docs.pipecat.ai/server/services/s2s/gemini), [Grok Voice Agent](https://docs.pipecat.ai/server/services/s2s/grok), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai), [Ultravox](https://docs.pipecat.ai/server/services/s2s/ultravox), |
|
||||
| Transport | [Daily (WebRTC)](https://docs.pipecat.ai/server/services/transport/daily), [FastAPI Websocket](https://docs.pipecat.ai/server/services/transport/fastapi-websocket), [SmallWebRTCTransport](https://docs.pipecat.ai/server/services/transport/small-webrtc), [WebSocket Server](https://docs.pipecat.ai/server/services/transport/websocket-server), Local |
|
||||
| Serializers | [Plivo](https://docs.pipecat.ai/server/utilities/serializers/plivo), [Twilio](https://docs.pipecat.ai/server/utilities/serializers/twilio), [Telnyx](https://docs.pipecat.ai/server/utilities/serializers/telnyx) |
|
||||
| Video | [HeyGen](https://docs.pipecat.ai/server/services/video/heygen), [Tavus](https://docs.pipecat.ai/server/services/video/tavus), [Simli](https://docs.pipecat.ai/server/services/video/simli) |
|
||||
| Memory | [mem0](https://docs.pipecat.ai/server/services/memory/mem0) |
|
||||
| Vision & Image | [fal](https://docs.pipecat.ai/server/services/image-generation/fal), [Google Imagen](https://docs.pipecat.ai/server/services/image-generation/fal), [Moondream](https://docs.pipecat.ai/server/services/vision/moondream) |
|
||||
| Audio Processing | [Silero VAD](https://docs.pipecat.ai/server/utilities/audio/silero-vad-analyzer), [Krisp](https://docs.pipecat.ai/server/utilities/audio/krisp-filter), [Koala](https://docs.pipecat.ai/server/utilities/audio/koala-filter), [ai-coustics](https://docs.pipecat.ai/server/utilities/audio/aic-filter) |
|
||||
| Analytics & Metrics | [OpenTelemetry](https://docs.pipecat.ai/server/utilities/opentelemetry), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry) |
|
||||
| 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.
|
||||
|
||||
1. Install uv
|
||||
```shell
|
||||
# Install the module
|
||||
pip install pipecat-ai
|
||||
|
||||
```bash
|
||||
curl -LsSf https://astral.sh/uv/install.sh | sh
|
||||
```
|
||||
# Set up your environment
|
||||
cp dot-env.template .env
|
||||
```
|
||||
|
||||
> **Need help?** Refer to the [uv install documentation](https://docs.astral.sh/uv/getting-started/installation/).
|
||||
To keep things lightweight, only the core framework is included by default. If you need support for third-party AI services, you can add the necessary dependencies with:
|
||||
|
||||
2. Install the module
|
||||
|
||||
```bash
|
||||
# For new projects
|
||||
uv init my-pipecat-app
|
||||
cd my-pipecat-app
|
||||
uv add pipecat-ai
|
||||
|
||||
# Or for existing projects
|
||||
uv add pipecat-ai
|
||||
```
|
||||
|
||||
3. Set up your environment
|
||||
|
||||
```bash
|
||||
cp env.example .env
|
||||
```
|
||||
|
||||
4. To keep things lightweight, only the core framework is included by default. If you need support for third-party AI services, you can add the necessary dependencies with:
|
||||
|
||||
```bash
|
||||
uv add "pipecat-ai[option,...]"
|
||||
```
|
||||
|
||||
> **Using pip?** You can still use `pip install pipecat-ai` and `pip install "pipecat-ai[option,...]"` to get set up.
|
||||
```shell
|
||||
pip install "pipecat-ai[option,...]"
|
||||
```
|
||||
|
||||
## 🧪 Code examples
|
||||
|
||||
- [Foundational](https://github.com/pipecat-ai/pipecat/tree/main/examples/foundational) — small snippets that build on each other, introducing one or two concepts at a time
|
||||
- [Example apps](https://github.com/pipecat-ai/pipecat-examples) — complete applications that you can use as starting points for development
|
||||
- [Example apps](https://github.com/pipecat-ai/pipecat/tree/main/examples/) — complete applications that you can use as starting points for development
|
||||
|
||||
## 🛠️ Contributing to the framework
|
||||
## 🛠️ Hacking on the framework itself
|
||||
|
||||
### Prerequisites
|
||||
1. Set up a virtual environment before following these instructions. From the root of the repo:
|
||||
|
||||
**Minimum Python Version:** 3.10
|
||||
**Recommended Python Version:** 3.12
|
||||
|
||||
### Setup Steps
|
||||
|
||||
1. Clone the repository and navigate to it:
|
||||
|
||||
```bash
|
||||
git clone https://github.com/pipecat-ai/pipecat.git
|
||||
cd pipecat
|
||||
```shell
|
||||
python3 -m venv venv
|
||||
source venv/bin/activate
|
||||
```
|
||||
|
||||
2. Install development and testing dependencies:
|
||||
2. Install the development dependencies:
|
||||
|
||||
```bash
|
||||
uv sync --group dev --all-extras \
|
||||
--no-extra gstreamer \
|
||||
--no-extra krisp \
|
||||
--no-extra local \
|
||||
```shell
|
||||
pip install -r dev-requirements.txt
|
||||
```
|
||||
|
||||
3. Install the git pre-commit hooks:
|
||||
3. Install the git pre-commit hooks (these help ensure your code follows project rules):
|
||||
|
||||
```bash
|
||||
uv run pre-commit install
|
||||
```shell
|
||||
pre-commit install
|
||||
```
|
||||
|
||||
> **Note**: Some extras (local, gstreamer) require system dependencies. See documentation if you encounter build errors.
|
||||
4. Install the `pipecat-ai` package locally in editable mode:
|
||||
|
||||
```shell
|
||||
pip install -e .
|
||||
```
|
||||
|
||||
> The `-e` or `--editable` option allows you to modify the code without reinstalling.
|
||||
|
||||
5. Include optional dependencies as needed. For example:
|
||||
|
||||
```shell
|
||||
pip install -e ".[daily,deepgram,cartesia,openai,silero]"
|
||||
```
|
||||
|
||||
6. (Optional) If you want to use this package from another directory:
|
||||
|
||||
```shell
|
||||
pip install "path_to_this_repo[option,...]"
|
||||
```
|
||||
|
||||
### Running tests
|
||||
|
||||
To run all tests, from the root directory:
|
||||
From the root directory, run:
|
||||
|
||||
```bash
|
||||
uv run pytest
|
||||
```shell
|
||||
pytest
|
||||
```
|
||||
|
||||
Run a specific test suite:
|
||||
### Setting up your editor
|
||||
|
||||
```bash
|
||||
uv run pytest tests/test_name.py
|
||||
This project uses strict [PEP 8](https://peps.python.org/pep-0008/) formatting via [Ruff](https://github.com/astral-sh/ruff).
|
||||
|
||||
#### Emacs
|
||||
|
||||
You can use [use-package](https://github.com/jwiegley/use-package) to install [emacs-lazy-ruff](https://github.com/christophermadsen/emacs-lazy-ruff) package and configure `ruff` arguments:
|
||||
|
||||
```elisp
|
||||
(use-package lazy-ruff
|
||||
:ensure t
|
||||
:hook ((python-mode . lazy-ruff-mode))
|
||||
:config
|
||||
(setq lazy-ruff-format-command "ruff format")
|
||||
(setq lazy-ruff-check-command "ruff check --select I"))
|
||||
```
|
||||
|
||||
`ruff` was installed in the `venv` environment described before, so you should be able to use [pyvenv-auto](https://github.com/ryotaro612/pyvenv-auto) to automatically load that environment inside Emacs.
|
||||
|
||||
```elisp
|
||||
(use-package pyvenv-auto
|
||||
:ensure t
|
||||
:defer t
|
||||
:hook ((python-mode . pyvenv-auto-run)))
|
||||
```
|
||||
|
||||
#### 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:
|
||||
|
||||
```json
|
||||
"[python]": {
|
||||
"editor.defaultFormatter": "charliermarsh.ruff",
|
||||
"editor.formatOnSave": true
|
||||
}
|
||||
```
|
||||
|
||||
#### PyCharm
|
||||
|
||||
`ruff` was installed in the `venv` environment described before, now to enable autoformatting on save, go to `File` -> `Settings` -> `Tools` -> `File Watchers` and add a new watcher with the following settings:
|
||||
|
||||
1. **Name**: `Ruff formatter`
|
||||
2. **File type**: `Python`
|
||||
3. **Working directory**: `$ContentRoot$`
|
||||
4. **Arguments**: `format $FilePath$`
|
||||
5. **Program**: `$PyInterpreterDirectory$/ruff`
|
||||
|
||||
## 🤝 Contributing
|
||||
|
||||
We welcome contributions from the community! Whether you're fixing bugs, improving documentation, or adding new features, here's how you can help:
|
||||
|
||||
@@ -1,5 +0,0 @@
|
||||
# Security Policy
|
||||
|
||||
## Reporting a Vulnerability
|
||||
|
||||
Please email `disclosures@daily.co`.
|
||||
@@ -1,42 +0,0 @@
|
||||
- Introducing user turn strategies. User turn strategies indicate when the user turn starts or stops. In conversational agents, these are often referred to as start/stop speaking or turn-taking plans or policies.
|
||||
|
||||
User turn start strategies indicate when the user starts speaking (e.g. using VAD events or when a user says one or more words).
|
||||
|
||||
User turn stop strategies indicate when the user stops speaking (e.g. using an end-of-turn detection model or by observing incoming transcriptions).
|
||||
|
||||
A list of strategies can be specified for both strategies; strategies are evaluated in order until one evaluates to true.
|
||||
|
||||
Available user turn start strategies:
|
||||
- VADUserTurnStartStrategy
|
||||
- TranscriptionUserTurnStartStrategy
|
||||
- MinWordsUserTurnStartStrategy
|
||||
- ExternalUserTurnStartStrategy
|
||||
|
||||
Available user turn stop strategies:
|
||||
- TranscriptionUserTurnStopStrategy
|
||||
- TurnAnalyzerUserTurnStopStrategy
|
||||
- ExternalUserTurnStopStrategy
|
||||
|
||||
The default strategies are:
|
||||
|
||||
- start: [VADUserTurnStartStrategy, TranscriptionUserTurnStartStrategy]
|
||||
- stop: [TranscriptionUserTurnStopStrategy]
|
||||
|
||||
Turn strategies are configured when setting up `LLMContextAggregatorPair`. For example:
|
||||
|
||||
```python
|
||||
context_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[
|
||||
TurnAnalyzerUserTurnStopStrategy(
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams())
|
||||
)
|
||||
],
|
||||
)
|
||||
),
|
||||
)
|
||||
```
|
||||
|
||||
In order to use the user turn strategies you must update to the new universal `LLMContext` and `LLMContextAggregatorPair`.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ `TransportParams.turn_analyzer` is deprecated and might result in unexpected behavior, use `LLMUserAggregator`'s new `turn_start_strategies` parameter instead.
|
||||
@@ -1 +0,0 @@
|
||||
- `FrameProcessor.interruption_strategies` is deprecated, use `LLMUserAggregator`'s new `turn_start_strategies` parameter instead.
|
||||
@@ -1 +0,0 @@
|
||||
- `EmulateUserStartedSpeakingFrame` and `EmulateUserStoppedSpeakingFrame` frames are deprecated.
|
||||
@@ -1 +0,0 @@
|
||||
- Deprecated the `emulated` field in the `UserStartedSpeakingFrame` and `UserStoppedSpeakingFrame` frames.
|
||||
@@ -1 +0,0 @@
|
||||
- The `LLMUserAggregatorParams` and `LLMAssistantAggregatorParams` classes in `pipecat.processors.aggregators.llm_response` are now deprecated. Use the new universal `LLMContext` and `LLMContextAggregatorPair` instead.
|
||||
@@ -1 +0,0 @@
|
||||
- `pipecat.audio.interruptions.MinWordsInterruptionStrategy` is deprecated. Use `pipecat.turns.user_start.MinWordsUserTurnStartStrategy` with `LLMUserAggregator`'s new `turn_start_strategies` parameter instead.
|
||||
@@ -1 +0,0 @@
|
||||
- Added `RNNoiseFilter` for real-time noise suppression using RNNoise neural network via pyrnnoise library.
|
||||
@@ -1,15 +0,0 @@
|
||||
- Updated `SpeechmaticsSTTService` to use new Python Voice SDK with improved VAD,
|
||||
Smart Turn capabilities, and brings dramatic improvements to latency without
|
||||
any impact on accuracy. Use the `turn_detection_mode` parameter to control the
|
||||
endpointing of speech, with `TurnDetectionMode.EXTERNAL` (default),
|
||||
`TurnDetectionMode.ADAPTIVE`, or `TurnDetectionMode.SMART_TURN`.
|
||||
```python
|
||||
stt = SpeechmaticsSTTService(
|
||||
api_key=os.getenv("SPEECHMATICS_API_KEY"),
|
||||
params=SpeechmaticsSTTService.InputParams(
|
||||
language=Language.EN,
|
||||
turn_detection_mode=SpeechmaticsSTTService.TurnDetectionMode.ADAPTIVE,
|
||||
speaker_active_format="<{speaker_id}>{text}</{speaker_id}>",
|
||||
),
|
||||
)
|
||||
```
|
||||
@@ -1,4 +0,0 @@
|
||||
- For `SpeechmaticsSTTService`, the `end_of_utterance_mode` parameter is deprecated.
|
||||
Use the new `turn_detection_mode` parameter instead, with `TurnDetectionMode.EXTERNAL`,
|
||||
`TurnDetectionMode.ADAPTIVE`, or `TurnDetectionMode.SMART_TURN`. The `enable_vad`
|
||||
parameter is also deprecated and is inferred from the `turn_detection_mode`.
|
||||
@@ -1,2 +0,0 @@
|
||||
- Improved error handling in `ElevenLabsRealtimeSTTService`
|
||||
- Fixed an issue in `ElevenLabsRealtimeSTTService` causing an infinite loop that blocks the process if the websocket disconnects due to an error
|
||||
@@ -1 +0,0 @@
|
||||
- `TranscriptionFrame` and `InterimTranscriptionFrame` produced by `DailyTransport` now include the transport source (i.e., the originating audio track).
|
||||
@@ -1 +0,0 @@
|
||||
- `daily-python` updated to 0.23.0.
|
||||
@@ -1,15 +0,0 @@
|
||||
- `OpenAILLMContext` and its associated things (context aggregators, etc.) are now deprecated in favor of the universal `LLMContext` and its associated things.
|
||||
|
||||
From the developer's point of view, switching to using `LLMContext` machinery will usually be a matter of going from this:
|
||||
|
||||
```python
|
||||
context = OpenAILLMContext(messages, tools)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
```
|
||||
|
||||
To this:
|
||||
|
||||
```
|
||||
context = LLMContext(messages, tools)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
```
|
||||
@@ -1,8 +0,0 @@
|
||||
- Added `GrokRealtimeLLMService` for xAI's Grok Voice Agent API with real-time voice conversations:
|
||||
|
||||
- Support for real-time audio streaming with WebSocket connection
|
||||
- Built-in server-side VAD (Voice Activity Detection)
|
||||
- Multiple voice options: Ara, Rex, Sal, Eve, Leo
|
||||
- Built-in tools support: web_search, x_search, file_search
|
||||
- Custom function calling with standard Pipecat tools schema
|
||||
- Configurable audio formats (PCM at 8kHz-48kHz)
|
||||
@@ -1 +0,0 @@
|
||||
- Added an approximation of TTFB for Ultravox.
|
||||
@@ -1,5 +0,0 @@
|
||||
- Updates to Inworld TTS services:
|
||||
|
||||
- Improved `InworldTTSService`'s websocket implementation to better flush and
|
||||
close context to better handle long inputs.
|
||||
- Improved docstrings for `InworldTTSService` and `InworldHttpTTSService`.
|
||||
@@ -1 +0,0 @@
|
||||
- Added a new `AudioContextTTSService` to the TTS service base classes. The `AudioContextWordTTSService` now inherits from `AudioContextTTSService` and `WebsocketWordTTSService`.
|
||||
@@ -1,4 +0,0 @@
|
||||
- `LLMUserAggregator` now exposes the following events:
|
||||
- `on_user_turn_started`: triggered when a user turn starts
|
||||
- `on_user_turn_stopped`: triggered when a user turn ends
|
||||
- `on_user_turn_stop_timeout`: triggered when a user turn does not stop and times out
|
||||
@@ -1,29 +0,0 @@
|
||||
- Introducing user mute strategies. User mute strategies indicate when user input should be muted based on the current system state.
|
||||
|
||||
In conversational agents, user mute strategies are used to prevent user input from interrupting bot speech, tool execution, or other critical system operations.
|
||||
|
||||
A list of strategies can be specified; all strategies are evaluated for every frame so that each strategy can maintain its internal state. A user frame is muted if any of the configured strategies indicates it should be muted.
|
||||
|
||||
Available user mute strategies:
|
||||
|
||||
* `FirstSpeechUserMuteStrategy`
|
||||
* `MuteUntilFirstBotCompleteUserMuteStrategy`
|
||||
* `AlwaysUserMuteStrategy`
|
||||
* `FunctionCallUserMuteStrategy`
|
||||
|
||||
User mute strategies replace the legacy `STTMuteFilter` and provide a more flexible and composable approach to muting user input.
|
||||
|
||||
User mute strategies are configured when setting up the `LLMContextAggregatorPair`. For example:
|
||||
|
||||
```python
|
||||
context_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_mute_strategies=[
|
||||
FirstSpeechUserMuteStrategy(),
|
||||
]
|
||||
),
|
||||
)
|
||||
```
|
||||
|
||||
In order to use user mute strategies you should update to the new universal `LLMContext` and `LLMContextAggregatorPair`.
|
||||
@@ -1 +0,0 @@
|
||||
- `STTMuteFilter` is deprecated and will be removed in a future version. Use `LLMUserAggregator`'s new `user_mute_strategies` instead.
|
||||
@@ -1 +0,0 @@
|
||||
- Fixed a bug in `STTMuteFilter` where the user was not always muted during function calls, especially when there were multiple simultaneous calls.
|
||||
@@ -1 +0,0 @@
|
||||
- `FrameProcessor.interruptions_allowed` is now deprecated, use `LLMUserAggregator`'s new parameter `user_mute_strategies` instead.
|
||||
@@ -1,12 +0,0 @@
|
||||
- `PipelineParams.allow_interruptions` is now deprecated, use `LLMUserAggregator`'s new parameter `turn_start_strategies` instead. For example, to disable interruptions but still get user turns you can do:
|
||||
|
||||
```python
|
||||
context_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
start=[TranscriptionUserTurnStartStrategy(enable_interruptions=False)],
|
||||
),
|
||||
),
|
||||
)
|
||||
```
|
||||
@@ -1 +0,0 @@
|
||||
- Added `use_ssl` parameter to `NvidiaSTTService`, `NvidiaSegmentedSTTService` and `NvidiaTTSService`.
|
||||
@@ -1 +0,0 @@
|
||||
- Updated `DeepgramSTTService` to push user started/stopped speaking and interruption frames when `vad_enabled` is set to true. This centralizes the frames into the service, removing the need to have your application code handle Deepgram's events and push these frames.
|
||||
@@ -1 +0,0 @@
|
||||
- Added `enable_interruptions` constructor argument to all user turn strategies. This tells the `LLMUserAggregator` to push or not push an `InterruptionFrame`.
|
||||
@@ -1 +0,0 @@
|
||||
- Added `52-live-transcription.py` foundational example demonstrating live transcription and translation from English to Spanish. In this example, the bot is not interruptible: as the user continues speaking, English transcriptions are queued, and the bot continuously translates and speaks each queued sentence in Spanish without being interrupted by new user speech.
|
||||
@@ -1 +0,0 @@
|
||||
- Frame processors can now push frames from the top of the pipeline using new methods `queue_task_frame()` and `queue_task_frames()`.
|
||||
@@ -1,16 +0,0 @@
|
||||
{% for section, _ in sections.items() %}
|
||||
{% if sections[section] %}
|
||||
{% for category, val in definitions.items() if category in sections[section]%}
|
||||
### {{ definitions[category]['name'] }}
|
||||
|
||||
{% for text, values in sections[section][category].items() %}
|
||||
{{ text }}
|
||||
(PR {{ values|join(', ') }})
|
||||
|
||||
{% endfor %}
|
||||
{% endfor %}
|
||||
{% else %}
|
||||
No significant changes.
|
||||
|
||||
{% endif %}
|
||||
{% endfor %}
|
||||
13
dev-requirements.txt
Normal file
13
dev-requirements.txt
Normal file
@@ -0,0 +1,13 @@
|
||||
build~=1.2.2
|
||||
coverage~=7.6.12
|
||||
grpcio-tools~=1.67.1
|
||||
pip-tools~=7.4.1
|
||||
pre-commit~=4.0.1
|
||||
pyright~=1.1.397
|
||||
pytest~=8.3.4
|
||||
pytest-asyncio~=0.25.3
|
||||
pytest-aiohttp==1.1.0
|
||||
ruff~=0.11.1
|
||||
setuptools~=70.0.0
|
||||
setuptools_scm~=8.1.0
|
||||
python-dotenv~=1.0.1
|
||||
10
docs/README.md
Normal file
10
docs/README.md
Normal file
@@ -0,0 +1,10 @@
|
||||
# Pipecat Docs
|
||||
|
||||
## [Architecture Overview](architecture.md)
|
||||
|
||||
Learn about the thinking behind the framework's design.
|
||||
|
||||
## [A Frame's Progress](frame-progress.md)
|
||||
|
||||
See how a Frame is processed through a Transport, a Pipeline, and a series of Frame Processors.
|
||||
|
||||
@@ -1,27 +1,10 @@
|
||||
#!/bin/bash
|
||||
|
||||
# Build docs using uv
|
||||
echo "Installing dependencies with uv..."
|
||||
uv sync --group docs --all-extras --no-extra krisp --no-extra gstreamer --no-extra local_smart_turn --no-extra moondream --no-extra riva --no-extra mlx-whisper
|
||||
|
||||
# Check if sphinx-build is available
|
||||
if ! uv run sphinx-build --version &> /dev/null; then
|
||||
echo "Error: sphinx-build is not available" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Clean previous build
|
||||
rm -rf _build
|
||||
|
||||
echo "Building documentation..."
|
||||
# Build docs matching ReadTheDocs configuration
|
||||
uv run sphinx-build -b html -d _build/doctrees . _build/html -W --keep-going
|
||||
sphinx-build -b html -d _build/doctrees . _build/html -W --keep-going
|
||||
|
||||
if [ $? -eq 0 ]; then
|
||||
echo "Documentation built successfully!"
|
||||
# Open docs (MacOS)
|
||||
open _build/html/index.html
|
||||
else
|
||||
echo "Documentation build failed!" >&2
|
||||
exit 1
|
||||
fi
|
||||
# Open docs (MacOS)
|
||||
open _build/html/index.html
|
||||
219
docs/api/conf.py
219
docs/api/conf.py
@@ -1,7 +1,5 @@
|
||||
import logging
|
||||
import os
|
||||
import sys
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
|
||||
# Configure logging
|
||||
@@ -15,8 +13,7 @@ sys.path.insert(0, str(project_root / "src"))
|
||||
|
||||
# Project information
|
||||
project = "pipecat-ai"
|
||||
current_year = datetime.now().year
|
||||
copyright = f"2024-{current_year}, Daily" if current_year > 2024 else "2024, Daily"
|
||||
copyright = "2024, Daily"
|
||||
author = "Daily"
|
||||
|
||||
# General configuration
|
||||
@@ -27,105 +24,130 @@ extensions = [
|
||||
"sphinx.ext.intersphinx",
|
||||
]
|
||||
|
||||
suppress_warnings = [
|
||||
"autodoc.mocked_object",
|
||||
"toc.not_included",
|
||||
]
|
||||
|
||||
# Napoleon settings
|
||||
napoleon_google_docstring = True
|
||||
napoleon_numpy_docstring = False
|
||||
napoleon_include_init_with_doc = True
|
||||
|
||||
# AutoDoc settings
|
||||
autodoc_default_options = {
|
||||
"members": True,
|
||||
"member-order": "bysource",
|
||||
"undoc-members": False,
|
||||
"exclude-members": "__weakref__,model_config",
|
||||
"special-members": "__init__",
|
||||
"undoc-members": True,
|
||||
"exclude-members": "__weakref__",
|
||||
"no-index": True,
|
||||
"show-inheritance": True,
|
||||
}
|
||||
|
||||
# Mock imports for optional dependencies
|
||||
autodoc_mock_imports = [
|
||||
# Krisp - has build issues on some platforms
|
||||
"pipecat_ai_krisp",
|
||||
"riva",
|
||||
"livekit",
|
||||
"pyht", # Base PlayHT package
|
||||
"pyht.async_client", # PlayHT specific imports
|
||||
"pyht.client",
|
||||
"pyht.protos",
|
||||
"pyht.protos.api_pb2",
|
||||
"pipecat_ai_playht", # PlayHT wrapper
|
||||
"vllm",
|
||||
"aiortc",
|
||||
"aiortc.mediastreams",
|
||||
"cv2",
|
||||
"av",
|
||||
"pyneuphonic",
|
||||
"mem0",
|
||||
"mlx_whisper",
|
||||
"anthropic",
|
||||
"assemblyai",
|
||||
"boto3",
|
||||
"azure",
|
||||
"cartesia",
|
||||
"deepgram",
|
||||
"elevenlabs",
|
||||
"fal",
|
||||
"gladia",
|
||||
"google",
|
||||
"krisp",
|
||||
"krisp_audio",
|
||||
# System-specific GUI libraries
|
||||
"langchain",
|
||||
"lmnt",
|
||||
"noisereduce",
|
||||
"openai",
|
||||
"openpipe",
|
||||
"simli",
|
||||
"soundfile",
|
||||
# Existing mocks
|
||||
"pipecat_ai_krisp",
|
||||
"pyaudio",
|
||||
"_tkinter",
|
||||
"tkinter",
|
||||
# Platform-specific audio libraries (if needed)
|
||||
"gi",
|
||||
"gi.require_version",
|
||||
"gi.repository",
|
||||
# OpenCV - sometimes has import issues during docs build
|
||||
"cv2",
|
||||
# Heavy ML packages excluded from ReadTheDocs
|
||||
# local-smart-turn dependencies
|
||||
"coremltools",
|
||||
"coremltools.models",
|
||||
"coremltools.models.MLModel",
|
||||
"torch",
|
||||
"torch.nn",
|
||||
"torch.nn.functional",
|
||||
"torchaudio",
|
||||
# moondream dependencies
|
||||
"transformers",
|
||||
"transformers.AutoTokenizer",
|
||||
"transformers.AutoFeatureExtractor",
|
||||
"AutoFeatureExtractor",
|
||||
"timm",
|
||||
"einops",
|
||||
"intel_extension_for_pytorch",
|
||||
"huggingface_hub",
|
||||
# riva dependencies
|
||||
"riva",
|
||||
"riva.client",
|
||||
"riva.client.Auth",
|
||||
"riva.client.ASRService",
|
||||
"riva.client.StreamingRecognitionConfig",
|
||||
"riva.client.RecognitionConfig",
|
||||
"riva.client.AudioEncoding",
|
||||
"riva.client.proto.riva_tts_pb2",
|
||||
"riva.client.SpeechSynthesisService",
|
||||
# MLX dependencies (Apple Silicon specific)
|
||||
"mlx",
|
||||
"mlx_whisper", # Note: might need underscore format too
|
||||
"daily",
|
||||
"daily_python",
|
||||
"pydantic.BaseModel",
|
||||
"pydantic.Field",
|
||||
"pydantic._internal._model_construction",
|
||||
"pydantic._internal._fields",
|
||||
]
|
||||
|
||||
# HTML output settings
|
||||
html_theme = "sphinx_rtd_theme"
|
||||
html_static_path = ["_static"] if os.path.exists("_static") else []
|
||||
autodoc_typehints = "signature" # Show type hints in the signature only, not in the docstring
|
||||
html_static_path = ["_static"]
|
||||
autodoc_typehints = "description"
|
||||
html_show_sphinx = False
|
||||
|
||||
|
||||
def import_core_modules():
|
||||
"""Import core pipecat modules for autodoc to discover."""
|
||||
core_modules = [
|
||||
"pipecat",
|
||||
"pipecat.frames",
|
||||
"pipecat.pipeline",
|
||||
"pipecat.processors",
|
||||
"pipecat.services",
|
||||
"pipecat.transports",
|
||||
"pipecat.audio",
|
||||
"pipecat.adapters",
|
||||
"pipecat.clocks",
|
||||
"pipecat.metrics",
|
||||
"pipecat.observers",
|
||||
"pipecat.runner",
|
||||
"pipecat.serializers",
|
||||
"pipecat.transcriptions",
|
||||
"pipecat.utils",
|
||||
]
|
||||
def verify_modules():
|
||||
"""Verify that required modules are available."""
|
||||
required_modules = {
|
||||
"services": [
|
||||
"assemblyai",
|
||||
"aws",
|
||||
"cartesia",
|
||||
"deepgram",
|
||||
"google",
|
||||
"lmnt",
|
||||
"riva",
|
||||
"simli",
|
||||
],
|
||||
"serializers": ["livekit"],
|
||||
"vad": ["silero", "vad_analyzer"],
|
||||
"transports": {
|
||||
"services": ["daily", "livekit"],
|
||||
"local": ["audio", "tk"],
|
||||
"network": ["fastapi_websocket", "websocket_server"],
|
||||
},
|
||||
}
|
||||
|
||||
for module_name in core_modules:
|
||||
try:
|
||||
__import__(module_name)
|
||||
logger.info(f"Successfully imported {module_name}")
|
||||
except ImportError as e:
|
||||
logger.warning(f"Failed to import {module_name}: {e}")
|
||||
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:
|
||||
try:
|
||||
__import__(f"pipecat.{category}.{subcategory}.{module}")
|
||||
logger.info(
|
||||
f"Successfully imported pipecat.{category}.{subcategory}.{module}"
|
||||
)
|
||||
except (ImportError, TypeError, NameError) as e:
|
||||
missing.append(f"pipecat.{category}.{subcategory}.{module}")
|
||||
logger.warning(
|
||||
f"Optional module not available: pipecat.{category}.{subcategory}.{module} - {str(e)}"
|
||||
)
|
||||
else:
|
||||
# Handle flat structure
|
||||
for module in modules:
|
||||
try:
|
||||
__import__(f"pipecat.{category}.{module}")
|
||||
logger.info(f"Successfully imported pipecat.{category}.{module}")
|
||||
except (ImportError, TypeError, NameError) as e:
|
||||
missing.append(f"pipecat.{category}.{module}")
|
||||
logger.warning(
|
||||
f"Optional module not available: pipecat.{category}.{module} - {str(e)}"
|
||||
)
|
||||
|
||||
if missing:
|
||||
logger.warning(f"Some optional modules are not available: {missing}")
|
||||
|
||||
|
||||
def clean_title(title: str) -> str:
|
||||
@@ -137,7 +159,36 @@ def clean_title(title: str) -> str:
|
||||
parts = title.split(".")
|
||||
title = parts[-1]
|
||||
|
||||
return title
|
||||
# Special cases for service names and common acronyms
|
||||
special_cases = {
|
||||
"ai": "AI",
|
||||
"aws": "AWS",
|
||||
"api": "API",
|
||||
"vad": "VAD",
|
||||
"assemblyai": "AssemblyAI",
|
||||
"deepgram": "Deepgram",
|
||||
"elevenlabs": "ElevenLabs",
|
||||
"openai": "OpenAI",
|
||||
"openpipe": "OpenPipe",
|
||||
"playht": "PlayHT",
|
||||
"xtts": "XTTS",
|
||||
"lmnt": "LMNT",
|
||||
}
|
||||
|
||||
# Check if the entire title is a special case
|
||||
if title.lower() in special_cases:
|
||||
return special_cases[title.lower()]
|
||||
|
||||
# Otherwise, capitalize each word
|
||||
words = title.split("_")
|
||||
cleaned_words = []
|
||||
for word in words:
|
||||
if word.lower() in special_cases:
|
||||
cleaned_words.append(special_cases[word.lower()])
|
||||
else:
|
||||
cleaned_words.append(word.capitalize())
|
||||
|
||||
return " ".join(cleaned_words)
|
||||
|
||||
|
||||
def setup(app):
|
||||
@@ -162,8 +213,9 @@ def setup(app):
|
||||
|
||||
excludes = [
|
||||
str(project_root / "src/pipecat/pipeline/to_be_updated"),
|
||||
str(project_root / "src/pipecat/examples"),
|
||||
str(project_root / "src/pipecat/tests"),
|
||||
str(project_root / "src/pipecat/processors/gstreamer"),
|
||||
str(project_root / "src/pipecat/services/to_be_updated"),
|
||||
str(project_root / "src/pipecat/vad"), # deprecated
|
||||
"**/test_*.py",
|
||||
"**/tests/*.py",
|
||||
]
|
||||
@@ -204,4 +256,5 @@ def setup(app):
|
||||
logger.error(f"Error generating API documentation: {e}", exc_info=True)
|
||||
|
||||
|
||||
import_core_modules()
|
||||
# Run module verification
|
||||
verify_modules()
|
||||
|
||||
@@ -1,35 +1,81 @@
|
||||
Pipecat API Reference
|
||||
=====================
|
||||
Pipecat API Reference Docs
|
||||
==========================
|
||||
|
||||
Welcome to the Pipecat API reference.
|
||||
Welcome to Pipecat's API reference documentation!
|
||||
|
||||
Use the navigation on the left to browse modules, or search using the search box.
|
||||
|
||||
**New to Pipecat?** Check out the `main documentation <https://docs.pipecat.ai>`_ for tutorials, guides, and client SDK information.
|
||||
Pipecat is an open source framework for building voice and multimodal assistants.
|
||||
It provides a flexible pipeline architecture for connecting various AI services,
|
||||
audio processing, and transport layers.
|
||||
|
||||
Quick Links
|
||||
-----------
|
||||
|
||||
* `GitHub Repository <https://github.com/pipecat-ai/pipecat>`_
|
||||
* `Join our Community <https://discord.gg/pipecat>`_
|
||||
* `Website <https://pipecat.ai>`_
|
||||
|
||||
API Reference
|
||||
-------------
|
||||
|
||||
Core Components
|
||||
~~~~~~~~~~~~~~~
|
||||
|
||||
* :mod:`Frames <pipecat.frames>`
|
||||
* :mod:`Processors <pipecat.processors>`
|
||||
* :mod:`Pipeline <pipecat.pipeline>`
|
||||
|
||||
Audio Processing
|
||||
~~~~~~~~~~~~~~~~
|
||||
|
||||
* :mod:`Audio <pipecat.audio>`
|
||||
|
||||
Services
|
||||
~~~~~~~~
|
||||
|
||||
* :mod:`Services <pipecat.services>`
|
||||
|
||||
Transport & Serialization
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
* :mod:`Transports <pipecat.transports>`
|
||||
* :mod:`Local <pipecat.transports.local>`
|
||||
* :mod:`Network <pipecat.transports.network>`
|
||||
* :mod:`Services <pipecat.transports.services>`
|
||||
* :mod:`Serializers <pipecat.serializers>`
|
||||
|
||||
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>`
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 2
|
||||
:maxdepth: 3
|
||||
:caption: API Reference
|
||||
:hidden:
|
||||
|
||||
Adapters <api/pipecat.adapters>
|
||||
Audio <api/pipecat.audio>
|
||||
Clocks <api/pipecat.clocks>
|
||||
Extensions <api/pipecat.extensions>
|
||||
Frames <api/pipecat.frames>
|
||||
Metrics <api/pipecat.metrics>
|
||||
Observers <api/pipecat.observers>
|
||||
Pipeline <api/pipecat.pipeline>
|
||||
Processors <api/pipecat.processors>
|
||||
Runner <api/pipecat.runner>
|
||||
Serializers <api/pipecat.serializers>
|
||||
Services <api/pipecat.services>
|
||||
Sync <api/pipecat.sync>
|
||||
Transcriptions <api/pipecat.transcriptions>
|
||||
Transports <api/pipecat.transports>
|
||||
Utils <api/pipecat.utils>
|
||||
|
||||
Indices and tables
|
||||
==================
|
||||
|
||||
* :ref:`genindex`
|
||||
* :ref:`modindex`
|
||||
* :ref:`search`
|
||||
51
docs/api/requirements.txt
Normal file
51
docs/api/requirements.txt
Normal file
@@ -0,0 +1,51 @@
|
||||
# Sphinx dependencies
|
||||
sphinx>=8.1.3
|
||||
sphinx-rtd-theme
|
||||
sphinx-markdown-builder
|
||||
sphinx-autodoc-typehints
|
||||
toml
|
||||
|
||||
# Install all extras individually to ensure they're properly resolved
|
||||
pipecat-ai[anthropic]
|
||||
pipecat-ai[assemblyai]
|
||||
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]
|
||||
pipecat-ai[livekit]
|
||||
pipecat-ai[lmnt]
|
||||
pipecat-ai[local]
|
||||
# pipecat-ai[mem0] # Mocked
|
||||
# pipecat-ai[mlx-whisper] # 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[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]
|
||||
17
docs/architecture.md
Normal file
17
docs/architecture.md
Normal file
@@ -0,0 +1,17 @@
|
||||
# Pipecat architecture guide
|
||||
|
||||
## Frames
|
||||
|
||||
Frames can represent discrete chunks of data, for instance a chunk of text, a chunk of audio, or an image. They can also be used to as control flow, for instance a frame that indicates that there is no more data available, or that a user started or stopped talking. They can also represent more complex data structures, such as a message array used for an LLM completion.
|
||||
|
||||
## FrameProcessors
|
||||
|
||||
Frame processors operate on frames. Every frame processor implements a `process_frame` method that consumes one frame and produces zero or more frames. Frame processors can do simple transforms, such as concatenating text fragments into sentences, or they can treat frames as input for an AI Service, and emit chat completions based on message arrays or transform text into audio or images.
|
||||
|
||||
## Pipelines
|
||||
|
||||
Pipelines are lists of frame processors linked together. Frame processors can push frames upstream or downstream to their peers. A very simple pipeline might chain an LLM frame processor to a text-to-speech frame processor, with a transport as an output.
|
||||
|
||||
## Transports
|
||||
|
||||
Transports provide input and output frame processors to receive or send frames respectively. For example, the `DailyTransport` does this with a WebRTC session joined to a Daily.co room.
|
||||
46
docs/frame-progress.md
Normal file
46
docs/frame-progress.md
Normal file
@@ -0,0 +1,46 @@
|
||||
# A Frame's Progress
|
||||
|
||||
1. A user says “Hello, LLM” and the cloud transcription service delivers a transcription to the Transport.
|
||||
|
||||
|
||||
2. The Transport places a Transcription frame in the Pipeline’s source queue.
|
||||
|
||||
|
||||
3. The Pipeline passes the Transcription frame to the first Frame Processor in its list, the LLM User Message Aggregator.
|
||||
|
||||
|
||||
4. The LLM User Message Aggregator updates the LLM Context with a `{“user”: “Hello LLM”}` message.
|
||||
|
||||
|
||||
5. The LLM User Message Aggregator yields an LLM Message Frame, containing the updated LLM Context. The Pipeline passes this frame to the LLM Frame Processor.
|
||||
|
||||
|
||||
6. The LLM Frame Processor creates a streaming chat completion based on the LLM context and yields the first chunk of a response, Text Frame with the value “Hi, “. The Pipeline passes this frame to the TTS Frame Processor. The TTS Frame Processor aggregates this response but doesn’t yield anything, yet, because it’s waiting for a full sentence.
|
||||
|
||||
|
||||
7. The LLM Frame Processor yields another Text Frame with the value “there.”. The Pipeline passes this frame to the TTS Frame Processor.
|
||||
|
||||
|
||||
8. The TTS Frame Processor now has a full sentence, so it starts streaming audio based on “Hi, there.” It yields the first chunk of streaming audio as an Audio frame, which the Pipeline passes to the LLM Assistant Message Aggregator.
|
||||
|
||||
|
||||
9. The LLM Assistant Message Aggregator doesn’t do anything with Audio frames, so it immediately yields the frame, unchanged. This is the convention for all Frame Processors: frames that the processor doesn’t process should be immediately yielded.
|
||||
|
||||
|
||||
10. The Pipeline places the first Audio frame in its sink queue, which is being watched by the Transport. Since the frame is now in a queue, the Pipeline can continue processing other frames. Note that the source and sink queues form a sort of “boundary of concurrent processing” between a Pipeline and the outside world. In a Pipeline, Frames are processed sequentially; once a Frame is on a queue it can be processed in parallel with the frames being processed by the Pipeline. TODO: link to a more in-depth section about this.
|
||||
|
||||
|
||||
11. The TTS Frame Processor yields another Audio frame as the Transport transmits the first Audio frame.
|
||||
|
||||
|
||||
12. As before, the LLM Assistant Message Aggregator immediately yields the Audio frame and the Pipeline places the Audio frame in the sink queue.
|
||||
|
||||
|
||||
13. The TTS Frame Processor has no more frames to yield. The LLM Frame Processor emits an LLM Response End Frame, which the Pipeline passes to the TTS Frame Processor.
|
||||
|
||||
|
||||
14. The TTS Frame Processor immediately yields the LLM Response End Frame, so the Pipeline passes it along to the LLM Assistant Message Aggregator. The LLM Assistant Message Aggregator updates the LLM Context with the full response from the LLM. TODO TODO: I realized I forgot that the TSS Frame Processor also yields the Text frames that the LLM emitted so that the LLM Assistant Message Aggregator could accumulate them, arrggh.
|
||||
|
||||
|
||||
15. The system is quiet, and waiting for the next message from the Transport.
|
||||
|
||||
110
docs/frame.md
Normal file
110
docs/frame.md
Normal file
@@ -0,0 +1,110 @@
|
||||
# Understanding Different Frame Types in the Pipecat System
|
||||
|
||||
In the Pipecat system, frames are used to represent different types of data and control signals that flow through the pipeline. Understanding these frame types is crucial for working with the system effectively. This tutorial will cover the main categories of frames and their specific uses.
|
||||
|
||||
## 1. Base Frame Classes
|
||||
|
||||
### Frame
|
||||
The `Frame` class is the base class for all frames. It includes:
|
||||
- `id`: A unique identifier
|
||||
- `name`: A descriptive name
|
||||
- `pts`: Presentation timestamp (optional)
|
||||
|
||||
### DataFrame
|
||||
`DataFrame` is a subclass of `Frame` and serves as a base for most data-carrying frames.
|
||||
|
||||
## 2. Audio Frames
|
||||
|
||||
### AudioRawFrame
|
||||
Represents a chunk of audio with properties:
|
||||
- `audio`: Raw audio data
|
||||
- `sample_rate`: Audio sample rate
|
||||
- `num_channels`: Number of audio channels
|
||||
|
||||
Subclasses include:
|
||||
- `InputAudioRawFrame`: For audio from input sources
|
||||
- `OutputAudioRawFrame`: For audio to be played by output devices
|
||||
- `TTSAudioRawFrame`: For audio generated by Text-to-Speech services
|
||||
|
||||
## 3. Image Frames
|
||||
|
||||
### ImageRawFrame
|
||||
Represents an image with properties:
|
||||
- `image`: Raw image data
|
||||
- `size`: Image dimensions
|
||||
- `format`: Image format (e.g., JPEG, PNG)
|
||||
|
||||
Subclasses include:
|
||||
- `InputImageRawFrame`: For images from input sources
|
||||
- `OutputImageRawFrame`: For images to be displayed
|
||||
- `UserImageRawFrame`: For images associated with a specific user
|
||||
- `VisionImageRawFrame`: For images with associated text for description
|
||||
- `URLImageRawFrame`: For images with an associated URL
|
||||
|
||||
### SpriteFrame
|
||||
Represents an animated sprite, containing a list of `ImageRawFrame` objects.
|
||||
|
||||
## 4. Text and Transcription Frames
|
||||
|
||||
### TextFrame
|
||||
Represents a chunk of text, used for various purposes in the pipeline.
|
||||
|
||||
### TranscriptionFrame
|
||||
A specialized `TextFrame` for speech transcriptions, including:
|
||||
- `user_id`: ID of the speaking user
|
||||
- `timestamp`: When the transcription was generated
|
||||
- `language`: Detected language of the speech
|
||||
|
||||
### InterimTranscriptionFrame
|
||||
Similar to `TranscriptionFrame`, but for interim (not final) transcriptions.
|
||||
|
||||
## 5. LLM (Language Model) Frames
|
||||
|
||||
### LLMMessagesFrame
|
||||
Contains a list of messages for an LLM service to process.
|
||||
|
||||
### LLMMessagesAppendFrame and LLMMessagesUpdateFrame
|
||||
Used to modify the current context of LLM messages.
|
||||
|
||||
### LLMSetToolsFrame
|
||||
Specifies tools (functions) available for the LLM to use.
|
||||
|
||||
### LLMEnablePromptCachingFrame
|
||||
Controls prompt caching in certain LLMs.
|
||||
|
||||
## 6. System and Control Frames
|
||||
|
||||
### SystemFrame
|
||||
Base class for system-level frames.
|
||||
|
||||
Important system frames include:
|
||||
- `StartFrame`: Initiates a pipeline
|
||||
- `CancelFrame`: Stops a pipeline immediately
|
||||
- `ErrorFrame`: Notifies of errors (with `FatalErrorFrame` for unrecoverable errors)
|
||||
- `EndTaskFrame` and `CancelTaskFrame`: Control pipeline tasks
|
||||
- `StartInterruptionFrame` and `StopInterruptionFrame`: Indicate user speech for interruptions
|
||||
|
||||
### ControlFrame
|
||||
Base class for control-flow frames.
|
||||
|
||||
Notable control frames:
|
||||
- `EndFrame`: Signals the end of a pipeline
|
||||
- `LLMFullResponseStartFrame` and `LLMFullResponseEndFrame`: Bracket LLM responses
|
||||
- `UserStartedSpeakingFrame` and `UserStoppedSpeakingFrame`: Indicate user speech activity
|
||||
- `BotStartedSpeakingFrame` and `BotStoppedSpeakingFrame`: Indicate bot speech activity
|
||||
- `TTSStartedFrame` and `TTSStoppedFrame`: Bracket Text-to-Speech responses
|
||||
|
||||
## 7. Special Purpose Frames
|
||||
|
||||
### MetricsFrame
|
||||
Contains performance metrics data.
|
||||
|
||||
### FunctionCallInProgressFrame and FunctionCallResultFrame
|
||||
Used for handling LLM function (tool) calls.
|
||||
|
||||
### ServiceUpdateSettingsFrame
|
||||
Base class for updating service settings, with specific subclasses for LLM, TTS, and STT services.
|
||||
|
||||
## Conclusion
|
||||
|
||||
Understanding these frame types is essential for working with the Pipecat system. Each frame type serves a specific purpose in the pipeline, whether it's carrying data (like audio or images), controlling the flow of the pipeline, or managing system-level operations. By using the appropriate frame types, you can effectively process and transmit various kinds of information through your pipeline.
|
||||
BIN
docs/images/frame-progress-01.png
Normal file
BIN
docs/images/frame-progress-01.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 98 KiB |
BIN
docs/images/frame-progress-02.png
Normal file
BIN
docs/images/frame-progress-02.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 91 KiB |
BIN
docs/images/frame-progress-03.png
Normal file
BIN
docs/images/frame-progress-03.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 92 KiB |
BIN
docs/images/frame-progress-04.png
Normal file
BIN
docs/images/frame-progress-04.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 92 KiB |
BIN
docs/images/frame-progress-05.png
Normal file
BIN
docs/images/frame-progress-05.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 98 KiB |
BIN
docs/images/frame-progress-06.png
Normal file
BIN
docs/images/frame-progress-06.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 94 KiB |
BIN
docs/images/frame-progress-07.png
Normal file
BIN
docs/images/frame-progress-07.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 94 KiB |
BIN
docs/images/frame-progress-08.png
Normal file
BIN
docs/images/frame-progress-08.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 95 KiB |
BIN
docs/images/frame-progress-09.png
Normal file
BIN
docs/images/frame-progress-09.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 94 KiB |
BIN
docs/images/frame-progress-10.png
Normal file
BIN
docs/images/frame-progress-10.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 96 KiB |
BIN
docs/images/frame-progress-11.png
Normal file
BIN
docs/images/frame-progress-11.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 110 KiB |
BIN
docs/images/frame-progress-12.png
Normal file
BIN
docs/images/frame-progress-12.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 102 KiB |
BIN
docs/images/frame-progress-13.png
Normal file
BIN
docs/images/frame-progress-13.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 111 KiB |
BIN
docs/images/frame-progress-14.png
Normal file
BIN
docs/images/frame-progress-14.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 117 KiB |
BIN
docs/images/frame-progress-15.png
Normal file
BIN
docs/images/frame-progress-15.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 98 KiB |
99
dot-env.template
Normal file
99
dot-env.template
Normal file
@@ -0,0 +1,99 @@
|
||||
# Anthropic
|
||||
ANTHROPIC_API_KEY=...
|
||||
|
||||
# AWS
|
||||
AWS_SECRET_ACCESS_KEY=...
|
||||
AWS_ACCESS_KEY_ID=...
|
||||
AWS_REGION=...
|
||||
|
||||
# Azure
|
||||
AZURE_SPEECH_REGION=...
|
||||
AZURE_SPEECH_API_KEY=...
|
||||
|
||||
AZURE_CHATGPT_API_KEY=...
|
||||
AZURE_CHATGPT_ENDPOINT=https://...
|
||||
AZURE_CHATGPT_MODEL=...
|
||||
|
||||
AZURE_DALLE_API_KEY=...
|
||||
AZURE_DALLE_ENDPOINT=https://...
|
||||
AZURE_DALLE_MODEL=...
|
||||
|
||||
# Cartesia
|
||||
CARTESIA_API_KEY=...
|
||||
|
||||
# Daily
|
||||
DAILY_API_KEY=...
|
||||
DAILY_SAMPLE_ROOM_URL=https://...
|
||||
|
||||
# ElevenLabs
|
||||
ELEVENLABS_API_KEY=...
|
||||
ELEVENLABS_VOICE_ID=...
|
||||
|
||||
# Neuphonic
|
||||
NEUPHONIC_API_KEY=...
|
||||
|
||||
# Fal
|
||||
FAL_KEY=...
|
||||
|
||||
# Fireworks
|
||||
FIREWORKS_API_KEY=...
|
||||
|
||||
# Gladia
|
||||
GLADIA_API_KEY=...
|
||||
|
||||
# LMNT
|
||||
LMNT_API_KEY=...
|
||||
LMNT_VOICE_ID=...
|
||||
|
||||
# PlayHT
|
||||
PLAY_HT_USER_ID=...
|
||||
PLAY_HT_API_KEY=...
|
||||
|
||||
# OpenAI
|
||||
OPENAI_API_KEY=...
|
||||
|
||||
# OpenPipe
|
||||
OPENPIPE_API_KEY=...
|
||||
|
||||
# Tavus
|
||||
TAVUS_API_KEY=...
|
||||
TAVUS_REPLICA_ID=...
|
||||
TAVUS_PERSONA_ID=...
|
||||
|
||||
# Simli
|
||||
SIMLI_API_KEY=...
|
||||
SIMLI_FACE_ID=...
|
||||
|
||||
# Krisp
|
||||
KRISP_MODEL_PATH=...
|
||||
|
||||
# DeepSeek
|
||||
DEEPSEEK_API_KEY=...
|
||||
|
||||
# Groq
|
||||
GROQ_API_KEY=...
|
||||
|
||||
# Grok
|
||||
GROK_API_KEY=...
|
||||
|
||||
# Together.ai
|
||||
TOGETHER_API_KEY=...
|
||||
|
||||
# Cerebras
|
||||
CEREBRAS_API_KEY=...
|
||||
|
||||
# Fish Audio
|
||||
FISH_API_KEY=...
|
||||
|
||||
# Assembly AI
|
||||
ASSEMBLYAI_API_KEY=...
|
||||
|
||||
# OpenRouter
|
||||
OPENROUTER_API_KEY=...
|
||||
|
||||
# Piper
|
||||
PIPER_BASE_URL=...
|
||||
|
||||
# Smart turn
|
||||
LOCAL_SMART_TURN_MODEL_PATH=
|
||||
REMOTE_SMART_TURN_URL=
|
||||
201
env.example
201
env.example
@@ -1,201 +0,0 @@
|
||||
# AI-COUSTICS
|
||||
AICOUSTICS_LICENSE_KEY=...
|
||||
|
||||
# Anthropic
|
||||
ANTHROPIC_API_KEY=...
|
||||
|
||||
# Assembly AI
|
||||
ASSEMBLYAI_API_KEY=...
|
||||
|
||||
# Async
|
||||
ASYNCAI_API_KEY=...
|
||||
ASYNCAI_VOICE_ID=...
|
||||
|
||||
# AWS
|
||||
AWS_SECRET_ACCESS_KEY=...
|
||||
AWS_ACCESS_KEY_ID=...
|
||||
AWS_REGION=...
|
||||
|
||||
# Azure
|
||||
AZURE_SPEECH_REGION=...
|
||||
AZURE_SPEECH_API_KEY=...
|
||||
|
||||
AZURE_CHATGPT_API_KEY=...
|
||||
AZURE_CHATGPT_ENDPOINT=https://...
|
||||
AZURE_CHATGPT_MODEL=...
|
||||
|
||||
AZURE_REALTIME_API_KEY=...
|
||||
AZURE_REALTIME_BASE_URL=...
|
||||
|
||||
AZURE_DALLE_API_KEY=...
|
||||
AZURE_DALLE_ENDPOINT=https://...
|
||||
AZURE_DALLE_MODEL=...
|
||||
|
||||
# Cartesia
|
||||
CARTESIA_API_KEY=...
|
||||
CARTESIA_VOICE_ID=...
|
||||
|
||||
# Cerebras
|
||||
CEREBRAS_API_KEY=...
|
||||
|
||||
# Daily
|
||||
DAILY_API_KEY=...
|
||||
DAILY_SAMPLE_ROOM_URL=https://...
|
||||
|
||||
# Deepgram
|
||||
DEEPGRAM_API_KEY=...
|
||||
SAGEMAKER_ENDPOINT_NAME=...
|
||||
|
||||
# DeepSeek
|
||||
DEEPSEEK_API_KEY=...
|
||||
|
||||
# ElevenLabs
|
||||
ELEVENLABS_API_KEY=...
|
||||
ELEVENLABS_VOICE_ID=...
|
||||
|
||||
# Fal
|
||||
FAL_KEY=...
|
||||
|
||||
# Fireworks
|
||||
FIREWORKS_API_KEY=...
|
||||
|
||||
# Fish Audio
|
||||
FISH_API_KEY=...
|
||||
|
||||
# Gladia
|
||||
GLADIA_API_KEY=...
|
||||
GLADIA_REGION=...
|
||||
|
||||
# Google
|
||||
GOOGLE_API_KEY=...
|
||||
GOOGLE_VERTEX_TEST_CREDENTIALS=...
|
||||
GOOGLE_CLOUD_PROJECT_ID=...
|
||||
GOOGLE_CLOUD_LOCATION=...
|
||||
GOOGLE_TEST_CREDENTIALS=...
|
||||
|
||||
# Gradium
|
||||
GRAPDIUM_API_KEY=...
|
||||
|
||||
# Grok
|
||||
GROK_API_KEY=...
|
||||
|
||||
# Groq
|
||||
GROQ_API_KEY=...
|
||||
|
||||
# Heygen
|
||||
HEYGEN_API_KEY=...
|
||||
HEYGEN_LIVE_AVATAR_API_KEY=...
|
||||
|
||||
# Hume
|
||||
HUME_API_KEY=...
|
||||
HUME_VOICE_ID=...
|
||||
|
||||
# Inworld
|
||||
INWORLD_API_KEY=...
|
||||
|
||||
# Krisp
|
||||
KRISP_MODEL_PATH=...
|
||||
|
||||
# Krisp Viva
|
||||
KRISP_VIVA_MODEL_PATH=...
|
||||
|
||||
# LiveKit
|
||||
LIVEKIT_API_KEY=...
|
||||
LIVEKIT_API_SECRET=...
|
||||
|
||||
# LMNT
|
||||
LMNT_API_KEY=...
|
||||
LMNT_VOICE_ID=...
|
||||
|
||||
# MiniMax
|
||||
MINIMAX_API_KEY=...
|
||||
MINIMAX_GROUP_ID=...
|
||||
|
||||
# Mistral
|
||||
MISTRAL_API_KEY=...
|
||||
|
||||
# Neuphonic
|
||||
NEUPHONIC_API_KEY=...
|
||||
|
||||
# NVIDIA
|
||||
NVIDIA_API_KEY=...
|
||||
|
||||
# OpenAI
|
||||
OPENAI_API_KEY=...
|
||||
|
||||
# OpenPipe
|
||||
OPENPIPE_API_KEY=...
|
||||
|
||||
# OpenRouter
|
||||
OPENROUTER_API_KEY=...
|
||||
|
||||
# Perplexity
|
||||
PERPLEXITY_API_KEY=...
|
||||
|
||||
# Picovoice Koala
|
||||
KOALA_ACCESS_KEY=...
|
||||
|
||||
# Piper
|
||||
PIPER_BASE_URL=...
|
||||
|
||||
# PlayHT
|
||||
PLAYHT_USER_ID=...
|
||||
PLAYHT_API_KEY=...
|
||||
|
||||
# Plivo
|
||||
PLIVO_AUTH_ID=...
|
||||
PLIVO_AUTH_TOKEN=...
|
||||
|
||||
# Qwen
|
||||
QWEN_API_KEY=...
|
||||
|
||||
# Rime
|
||||
RIME_API_KEY=...
|
||||
RIME_VOICE_ID=...
|
||||
|
||||
# SambaNova
|
||||
SAMBANOVA_API_KEY=...
|
||||
|
||||
# Sarvam AI
|
||||
SARVAM_API_KEY=...
|
||||
|
||||
# Sentry
|
||||
SENTRY_DSN=...
|
||||
|
||||
# Simli
|
||||
SIMLI_API_KEY=...
|
||||
SIMLI_FACE_ID=...
|
||||
|
||||
# Smart turn
|
||||
LOCAL_SMART_TURN_MODEL_PATH=...
|
||||
FAL_SMART_TURN_API_KEY=...
|
||||
|
||||
# Soniox
|
||||
SONIOX_API_KEY=...
|
||||
|
||||
# Speechmatics
|
||||
SPEECHMATICS_API_KEY=...
|
||||
|
||||
# Tavus
|
||||
TAVUS_API_KEY=...
|
||||
TAVUS_REPLICA_ID=...
|
||||
|
||||
# Telnyx
|
||||
TELNYX_API_KEY=...
|
||||
TELNYX_ACCOUNT_SID=...
|
||||
|
||||
# Together.ai
|
||||
TOGETHER_API_KEY=...
|
||||
|
||||
# Twilio
|
||||
TWILIO_ACCOUNT_SID=...
|
||||
TWILIO_AUTH_TOKEN=...
|
||||
|
||||
# Ultravox Realtime
|
||||
ULTRAVOX_API_KEY=...
|
||||
|
||||
# WhatsApp
|
||||
WHATSAPP_TOKEN=...
|
||||
WHATSAPP_WEBHOOK_VERIFICATION_TOKEN=...
|
||||
WHATSAPP_PHONE_NUMBER_ID=...
|
||||
WHATSAPP_APP_SECRET=...
|
||||
@@ -1,31 +1,88 @@
|
||||
# Pipecat Examples
|
||||
|
||||
This directory contains examples to help you learn how to build with Pipecat.
|
||||
|
||||
## Getting Started
|
||||
# Pipecat — Examples
|
||||
|
||||
New to Pipecat? Start here:
|
||||
## Foundational snippets
|
||||
Small snippets that build on each other, introducing one or two concepts at a time.
|
||||
|
||||
- **[Quickstart](quickstart/)** - Get your first voice AI bot running in 5 minutes _(coming soon)_
|
||||
- **[Client/Server Web](client-server-web/)** - Learn to build web applications with Pipecat's client SDKs _(coming soon)_
|
||||
- **[Phone Bot with Twilio](phone-bot-twilio/)** - Connect your bot to a phone number _(coming soon)_
|
||||
➡️ [Take a look](https://github.com/pipecat-ai/pipecat/tree/main/examples/foundational)
|
||||
|
||||
## Foundational Examples
|
||||
## Chatbot examples
|
||||
Collection of self-contained real-time voice and video AI demo applications built with Pipecat.
|
||||
|
||||
Single-file examples that introduce core Pipecat concepts one at a time. These examples:
|
||||
### Quickstart
|
||||
|
||||
- Build on each other progressively
|
||||
- Focus on specific features or integrations
|
||||
- Are used for testing with every Pipecat release
|
||||
Each project has its own set of dependencies and configuration variables. They intentionally avoids shared code across projects — you can grab whichever demo folder you want to work with as a starting point.
|
||||
|
||||
See the **[Foundational Examples README](foundational/)** for the complete list.
|
||||
We recommend you start with a virtual environment:
|
||||
|
||||
## More Advanced Examples
|
||||
```shell
|
||||
cd pipecat-ai/examples/simple-chatbot
|
||||
|
||||
Ready to explore complex use cases? Visit **[pipecat-examples](https://github.com/pipecat-ai/pipecat-examples)** for:
|
||||
python -m venv venv
|
||||
|
||||
- Production-ready applications
|
||||
- Multi-platform client implementations
|
||||
- Telephony integrations
|
||||
- Multimodal and creative applications
|
||||
- Deployment and monitoring examples
|
||||
source venv/bin/activate
|
||||
|
||||
pip install -r requirements.txt
|
||||
```
|
||||
|
||||
Next, follow the steps in the README for each demo.
|
||||
|
||||
ℹ️ Make sure you `pip install -r requirements.txt` for each demo project, so you can be sure to have the necessary service dependencies that extend the functionality of Pipecat. You can read more about the framework architecture [here](https://github.com/pipecat-ai/pipecat/tree/main/docs).
|
||||
|
||||
## Projects:
|
||||
|
||||
| Project | Description | Services |
|
||||
|----------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------|
|
||||
| [Simple Chatbot](simple-chatbot) | Basic voice-driven conversational bot. A good starting point for learning the flow of the framework. | Deepgram, ElevenLabs, OpenAI, Daily, Daily Prebuilt UI |
|
||||
| [Storytelling Chatbot](storytelling-chatbot) | Stitches together multiple third-party services to create a collaborative storytime experience. | Deepgram, ElevenLabs, OpenAI, Fal, Daily, Custom UI |
|
||||
| [Translation Chatbot](translation-chatbot) | Listens for user speech, then translates that speech to Spanish and speaks the translation back. Demonstrates multi-participant use-cases. | Deepgram, Azure, OpenAI, Daily, Daily Prebuilt UI |
|
||||
| [Moondream Chatbot](moondream-chatbot) | Demonstrates how to add vision capabilities to GPT4. **Note: works best with a GPU** | Deepgram, ElevenLabs, OpenAI, Moondream, Daily, Daily Prebuilt UI |
|
||||
| [Patient intake](patient-intake) | A chatbot that can call functions in response to user input. | Deepgram, ElevenLabs, OpenAI, Daily, Daily Prebuilt UI |
|
||||
| [Phone Chatbot](phone-chatbot) | A chatbot that connects to PSTN/SIP phone calls, powered by Daily or Twilio. | Deepgram, ElevenLabs, OpenAI, Daily, Twilio |
|
||||
| [Twilio Chatbot](twilio-chatbot) | A chatbot that connects to an incoming phone call from Twilio. | Deepgram, ElevenLabs, OpenAI, Daily, Twilio |
|
||||
| [studypal](studypal) | A chatbot to have a conversation about any article on the web | |
|
||||
| [WebSocket Chatbot Server](websocket-server) | A real-time websocket server that handles audio streaming and bot interactions with speech-to-text and text-to-speech capabilities. | Cartesia, Deepgram, OpenAI, Websockets |
|
||||
|
||||
> [!IMPORTANT]
|
||||
> These example projects use Daily as a WebRTC transport and can be joined using their hosted Prebuilt UI.
|
||||
> It provides a quick way to join a real-time session with your bot and test your ideas without building any frontend code. If you'd like to see an example of a custom UI, try Storybot.
|
||||
|
||||
|
||||
## FAQ
|
||||
|
||||
### Deployment
|
||||
|
||||
For each of these demos we've included a `Dockerfile`. Out of the box, this should provide everything needed to get the respective demo running on a VM:
|
||||
|
||||
```shell
|
||||
docker build username/app:tag .
|
||||
|
||||
docker run -p 7860:7860 --env-file ./.env username/app:tag
|
||||
|
||||
docker push ...
|
||||
```
|
||||
|
||||
### SSL
|
||||
|
||||
If you're working with a custom UI (such as with the Storytelling Chatbot), it's important to ensure your deployment platform supports HTTPS, as accessing user devices such as mics and webcams requires SSL.
|
||||
|
||||
If you try to run a custom UI without SSL, you may see an error in the console telling you that `navigator` is undefined, or no devices are available.
|
||||
|
||||
### Are these examples production ready?
|
||||
|
||||
Yes, kind of.
|
||||
|
||||
These demos attempt to keep things simple and are unopinionated regarding environment or scalability.
|
||||
|
||||
We're using FastAPI to spawn a subprocess for the bots / agents — useful for small tests, but not so great for production grade apps with many concurrent users. You can see how this works in each project's `start` endpoint in `server.py`.
|
||||
|
||||
Creating virtualized worker pools and on-demand instances is out of scope for these examples, but we hope to add some examples to this repo soon!
|
||||
|
||||
For projects that have CUDA as a requirement, such as Moondream Chatbot, be sure to deploy to a GPU-powered platform (such as [fly.io](https://fly.io) or [Runpod](https://runpod.io).)
|
||||
|
||||
## Getting help
|
||||
|
||||
➡️ [Join our Discord](https://discord.gg/pipecat)
|
||||
|
||||
➡️ [Reach us on Twitter](https://x.com/pipecat_ai)
|
||||
|
||||
45
examples/bot-ready-signalling/README.md
Normal file
45
examples/bot-ready-signalling/README.md
Normal file
@@ -0,0 +1,45 @@
|
||||
# Bot ready signaling
|
||||
|
||||
A simple Pipecat example demonstrating how to handle signaling between the client and the bot,
|
||||
ensuring that the bot starts sending audio only when the client is available,
|
||||
thereby avoiding the risk of cutting off the beginning of the audio.
|
||||
|
||||
## Quick Start
|
||||
|
||||
### First, start the bot server:
|
||||
|
||||
1. Navigate to the server directory:
|
||||
```bash
|
||||
cd server
|
||||
```
|
||||
2. Create and activate a virtual environment:
|
||||
```bash
|
||||
python3 -m venv venv
|
||||
source venv/bin/activate # On Windows: venv\Scripts\activate
|
||||
```
|
||||
3. Install requirements:
|
||||
```bash
|
||||
pip install -r requirements.txt
|
||||
```
|
||||
4. Copy env.example to .env and configure:
|
||||
- Add your API keys
|
||||
5. Start the server:
|
||||
```bash
|
||||
python server.py
|
||||
```
|
||||
|
||||
### Next, connect using the client app:
|
||||
|
||||
For client-side setup, refer to the [JavaScript Guide](client/javascript/README.md).
|
||||
|
||||
## Important Note
|
||||
|
||||
Ensure the bot server is running before using any client implementations.
|
||||
|
||||
## Requirements
|
||||
|
||||
- Python 3.10+
|
||||
- Node.js 16+ (for JavaScript)
|
||||
- Daily API key
|
||||
- Cartesia API key
|
||||
- Modern web browser with WebRTC support
|
||||
27
examples/bot-ready-signalling/client/javascript/README.md
Normal file
27
examples/bot-ready-signalling/client/javascript/README.md
Normal file
@@ -0,0 +1,27 @@
|
||||
# JavaScript Implementation
|
||||
|
||||
Basic implementation using the [Pipecat JavaScript SDK](https://docs.pipecat.ai/client/js/introduction).
|
||||
|
||||
## Setup
|
||||
|
||||
1. Run the bot server. See the [server README](../../README).
|
||||
|
||||
2. Navigate to the `client/javascript` directory:
|
||||
|
||||
```bash
|
||||
cd client/javascript
|
||||
```
|
||||
|
||||
3. Install dependencies:
|
||||
|
||||
```bash
|
||||
npm install
|
||||
```
|
||||
|
||||
4. Run the client app:
|
||||
|
||||
```
|
||||
npm run dev
|
||||
```
|
||||
|
||||
5. Visit http://localhost:5173 in your browser.
|
||||
34
examples/bot-ready-signalling/client/javascript/index.html
Normal file
34
examples/bot-ready-signalling/client/javascript/index.html
Normal file
@@ -0,0 +1,34 @@
|
||||
<!DOCTYPE html>
|
||||
<html lang="en">
|
||||
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
<title>AI Chatbot</title>
|
||||
</head>
|
||||
|
||||
<body>
|
||||
<div class="container">
|
||||
<div class="status-bar">
|
||||
<div class="status">
|
||||
Status: <span id="connection-status">Disconnected</span>
|
||||
</div>
|
||||
<div class="controls">
|
||||
<button id="connect-btn">Connect</button>
|
||||
<button id="disconnect-btn" disabled>Disconnect</button>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<audio id="bot-audio" autoplay></audio>
|
||||
|
||||
<div class="debug-panel">
|
||||
<h3>Debug Info</h3>
|
||||
<div id="debug-log"></div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<script type="module" src="/src/app.js"></script>
|
||||
<link rel="stylesheet" href="/src/style.css">
|
||||
</body>
|
||||
|
||||
</html>
|
||||
1081
examples/bot-ready-signalling/client/javascript/package-lock.json
generated
Normal file
1081
examples/bot-ready-signalling/client/javascript/package-lock.json
generated
Normal file
File diff suppressed because it is too large
Load Diff
20
examples/bot-ready-signalling/client/javascript/package.json
Normal file
20
examples/bot-ready-signalling/client/javascript/package.json
Normal file
@@ -0,0 +1,20 @@
|
||||
{
|
||||
"name": "client",
|
||||
"version": "1.0.0",
|
||||
"main": "index.js",
|
||||
"scripts": {
|
||||
"dev": "vite",
|
||||
"build": "vite build",
|
||||
"preview": "vite preview"
|
||||
},
|
||||
"keywords": [],
|
||||
"author": "",
|
||||
"license": "ISC",
|
||||
"description": "",
|
||||
"devDependencies": {
|
||||
"vite": "^6.0.9"
|
||||
},
|
||||
"dependencies": {
|
||||
"@daily-co/daily-js": "0.74.0"
|
||||
}
|
||||
}
|
||||
216
examples/bot-ready-signalling/client/javascript/src/app.js
Normal file
216
examples/bot-ready-signalling/client/javascript/src/app.js
Normal file
@@ -0,0 +1,216 @@
|
||||
/**
|
||||
* Copyright (c) 2024–2025, Daily
|
||||
*
|
||||
* SPDX-License-Identifier: BSD 2-Clause License
|
||||
*/
|
||||
|
||||
import Daily from "@daily-co/daily-js";
|
||||
|
||||
/**
|
||||
* ChatbotClient handles the connection and media management for a real-time
|
||||
* voice interaction with an AI bot.
|
||||
*/
|
||||
class ChatbotClient {
|
||||
constructor() {
|
||||
// Initialize client state
|
||||
this.dailyCallObject = null;
|
||||
this.setupDOMElements();
|
||||
this.setupEventListeners();
|
||||
}
|
||||
|
||||
/**
|
||||
* Set up references to DOM elements and create necessary media elements
|
||||
*/
|
||||
setupDOMElements() {
|
||||
// Get references to UI control elements
|
||||
this.connectBtn = document.getElementById('connect-btn');
|
||||
this.disconnectBtn = document.getElementById('disconnect-btn');
|
||||
this.statusSpan = document.getElementById('connection-status');
|
||||
this.debugLog = document.getElementById('debug-log');
|
||||
|
||||
// Create an audio element for bot's voice output
|
||||
this.botAudio = document.createElement('audio');
|
||||
this.botAudio.autoplay = true;
|
||||
this.botAudio.playsInline = true;
|
||||
document.body.appendChild(this.botAudio);
|
||||
}
|
||||
|
||||
/**
|
||||
* Set up event listeners for connect/disconnect buttons
|
||||
*/
|
||||
setupEventListeners() {
|
||||
this.connectBtn.addEventListener('click', () => this.connect());
|
||||
this.disconnectBtn.addEventListener('click', () => this.disconnect());
|
||||
}
|
||||
|
||||
/**
|
||||
* Add a timestamped message to the debug log
|
||||
*/
|
||||
log(message) {
|
||||
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
|
||||
}
|
||||
|
||||
this.debugLog.appendChild(entry);
|
||||
this.debugLog.scrollTop = this.debugLog.scrollHeight;
|
||||
console.log(message);
|
||||
}
|
||||
|
||||
/**
|
||||
* Update the connection status display
|
||||
*/
|
||||
updateStatus(status) {
|
||||
this.statusSpan.textContent = status;
|
||||
this.log(`Status: ${status}`);
|
||||
}
|
||||
|
||||
handleEventToConsole (evt) {
|
||||
this.log(`Received event: ${evt.action}`);
|
||||
};
|
||||
|
||||
/**
|
||||
* Set up listeners for track events (start/stop)
|
||||
* This handles new tracks being added during the session
|
||||
*/
|
||||
setupTrackListeners() {
|
||||
if (!this.dailyCallObject) return;
|
||||
|
||||
this.dailyCallObject.on("joined-meeting", () => {
|
||||
this.updateStatus('Connected');
|
||||
this.connectBtn.disabled = true;
|
||||
this.disconnectBtn.disabled = false;
|
||||
this.log('Client connected');
|
||||
});
|
||||
this.dailyCallObject.on("track-started", (evt) => {
|
||||
if (evt.track.kind === "audio" && evt.participant.local === false) {
|
||||
this.log("Audio track started.")
|
||||
this.setupAudioTrack(evt.track);
|
||||
}
|
||||
});
|
||||
this.dailyCallObject.on("track-stopped", this.handleEventToConsole.bind(this));
|
||||
this.dailyCallObject.on("participant-joined", this.handleEventToConsole.bind(this));
|
||||
this.dailyCallObject.on("participant-updated", this.handleEventToConsole.bind(this));
|
||||
this.dailyCallObject.on("participant-left", () => {
|
||||
// When the bot leaves, we are also disconnecting from the call
|
||||
this.disconnect()
|
||||
});
|
||||
this.dailyCallObject.on("left-meeting", () => {
|
||||
this.updateStatus('Disconnected');
|
||||
this.connectBtn.disabled = false;
|
||||
this.disconnectBtn.disabled = true;
|
||||
this.log('Client disconnected');
|
||||
});
|
||||
this.dailyCallObject.on("error", this.handleEventToConsole.bind(this));
|
||||
}
|
||||
|
||||
/**
|
||||
* Set up an audio track for playback
|
||||
* Handles both initial setup and track updates
|
||||
*/
|
||||
setupAudioTrack(track) {
|
||||
this.log(`Setting up audio track, track state: ${track.readyState}, muted: ${track.muted}`);
|
||||
|
||||
// Check if we're already playing this track
|
||||
if (this.botAudio.srcObject) {
|
||||
const oldTrack = this.botAudio.srcObject.getAudioTracks()[0];
|
||||
if (oldTrack?.id === track.id) return;
|
||||
}
|
||||
// Create a new MediaStream with the track and set it as the audio source
|
||||
this.botAudio.srcObject = new MediaStream([track]);
|
||||
this.botAudio.onplaying = async (event) => {
|
||||
this.log("onplaying")
|
||||
this.log("Will send the audio message to play the audio at the next tick")
|
||||
this.dailyCallObject.sendAppMessage("playable")
|
||||
}
|
||||
}
|
||||
|
||||
async fetchRoomInfo() {
|
||||
let connectUrl = '/connect'
|
||||
let res = await fetch(connectUrl, {
|
||||
method: "POST",
|
||||
mode: "cors",
|
||||
headers: new Headers({
|
||||
"Content-Type": "application/json"
|
||||
}),
|
||||
})
|
||||
if (res.ok) {
|
||||
return res.json();
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Initialize and connect to the bot
|
||||
* This sets up the RTVI client, initializes devices, and establishes the connection
|
||||
*/
|
||||
async connect() {
|
||||
try {
|
||||
// Initialize the client
|
||||
this.dailyCallObject = Daily.createCallObject({
|
||||
subscribeToTracksAutomatically: true,
|
||||
});
|
||||
|
||||
// Set up listeners for media track events
|
||||
this.setupTrackListeners();
|
||||
|
||||
this.log('Creating the bot...');
|
||||
let roomInfo = await this.fetchRoomInfo()
|
||||
|
||||
// Connect to the bot
|
||||
this.log('Connecting to bot...');
|
||||
// Only for making debugger easier
|
||||
window.callObject = this.dailyCallObject;
|
||||
await this.dailyCallObject.join({
|
||||
url: roomInfo.room_url,
|
||||
});
|
||||
|
||||
this.log('Connection complete');
|
||||
} catch (error) {
|
||||
// Handle any errors during connection
|
||||
this.log(`Error connecting: ${error.message}`);
|
||||
this.log(`Error stack: ${error.stack}`);
|
||||
this.updateStatus('Error');
|
||||
|
||||
// Clean up if there's an error
|
||||
if (this.dailyCallObject) {
|
||||
try {
|
||||
await this.dailyCallObject.leave();
|
||||
} catch (disconnectError) {
|
||||
this.log(`Error during disconnect: ${disconnectError.message}`);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Disconnect from the bot and clean up media resources
|
||||
*/
|
||||
async disconnect() {
|
||||
if (this.dailyCallObject) {
|
||||
try {
|
||||
// Disconnect the RTVI client
|
||||
await this.dailyCallObject.leave();
|
||||
await this.dailyCallObject.destroy();
|
||||
this.dailyCallObject = null;
|
||||
|
||||
// Clean up audio
|
||||
if (this.botAudio.srcObject) {
|
||||
this.botAudio.srcObject.getTracks().forEach((track) => track.stop());
|
||||
this.botAudio.srcObject = null;
|
||||
}
|
||||
} catch (error) {
|
||||
this.log(`Error disconnecting: ${error.message}`);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Initialize the client when the page loads
|
||||
window.addEventListener('DOMContentLoaded', () => {
|
||||
new ChatbotClient();
|
||||
});
|
||||
@@ -0,0 +1,98 @@
|
||||
body {
|
||||
margin: 0;
|
||||
padding: 20px;
|
||||
font-family: Arial, sans-serif;
|
||||
background-color: #f0f0f0;
|
||||
}
|
||||
|
||||
.container {
|
||||
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;
|
||||
}
|
||||
|
||||
#connect-btn {
|
||||
background-color: #4caf50;
|
||||
color: white;
|
||||
}
|
||||
|
||||
#disconnect-btn {
|
||||
background-color: #f44336;
|
||||
color: white;
|
||||
}
|
||||
|
||||
button:disabled {
|
||||
opacity: 0.5;
|
||||
cursor: not-allowed;
|
||||
}
|
||||
|
||||
.main-content {
|
||||
background-color: #fff;
|
||||
border-radius: 8px;
|
||||
padding: 20px;
|
||||
margin-bottom: 20px;
|
||||
}
|
||||
|
||||
.bot-container {
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
align-items: center;
|
||||
}
|
||||
|
||||
#bot-video-container {
|
||||
width: 640px;
|
||||
height: 360px;
|
||||
background-color: #e0e0e0;
|
||||
border-radius: 8px;
|
||||
margin: 20px auto;
|
||||
overflow: hidden;
|
||||
display: flex;
|
||||
align-items: center;
|
||||
justify-content: center;
|
||||
}
|
||||
|
||||
#bot-video-container video {
|
||||
width: 100%;
|
||||
height: 100%;
|
||||
object-fit: cover;
|
||||
}
|
||||
|
||||
.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;
|
||||
}
|
||||
@@ -0,0 +1,13 @@
|
||||
import { defineConfig } from 'vite';
|
||||
|
||||
export default defineConfig({
|
||||
server: {
|
||||
proxy: {
|
||||
// Proxy /api requests to the backend server
|
||||
'/connect': {
|
||||
target: 'http://0.0.0.0:7860', // Replace with your backend URL
|
||||
changeOrigin: true,
|
||||
},
|
||||
},
|
||||
},
|
||||
});
|
||||
1
examples/bot-ready-signalling/client/react-native/.nvmrc
Normal file
1
examples/bot-ready-signalling/client/react-native/.nvmrc
Normal file
@@ -0,0 +1 @@
|
||||
22.14
|
||||
60
examples/bot-ready-signalling/client/react-native/README.md
Normal file
60
examples/bot-ready-signalling/client/react-native/README.md
Normal file
@@ -0,0 +1,60 @@
|
||||
# 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.
|
||||
75
examples/bot-ready-signalling/client/react-native/app.json
Normal file
75
examples/bot-ready-signalling/client/react-native/app.json
Normal file
@@ -0,0 +1,75 @@
|
||||
{
|
||||
"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.
|
After Width: | Height: | Size: 17 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 1.4 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 22 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 46 KiB |
@@ -0,0 +1,7 @@
|
||||
module.exports = function(api) {
|
||||
api.cache(true);
|
||||
return {
|
||||
presets: ['babel-preset-expo'],
|
||||
plugins: [["module:react-native-dotenv"]],
|
||||
};
|
||||
};
|
||||
@@ -0,0 +1 @@
|
||||
API_BASE_URL=http://YOUR_LOCAL_IP:7860
|
||||
7
examples/bot-ready-signalling/client/react-native/index.js
vendored
Normal file
7
examples/bot-ready-signalling/client/react-native/index.js
vendored
Normal file
@@ -0,0 +1,7 @@
|
||||
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);
|
||||
@@ -0,0 +1,4 @@
|
||||
// Learn more https://docs.expo.io/guides/customizing-metro
|
||||
const { getDefaultConfig } = require('expo/metro-config');
|
||||
|
||||
module.exports = getDefaultConfig(__dirname);
|
||||
10983
examples/bot-ready-signalling/client/react-native/package-lock.json
generated
Normal file
10983
examples/bot-ready-signalling/client/react-native/package-lock.json
generated
Normal file
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"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
|
||||
}
|
||||
121
examples/bot-ready-signalling/client/react-native/src/App.js
vendored
Normal file
121
examples/bot-ready-signalling/client/react-native/src/App.js
vendored
Normal file
@@ -0,0 +1,121 @@
|
||||
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;
|
||||
50
examples/bot-ready-signalling/server/README.md
Normal file
50
examples/bot-ready-signalling/server/README.md
Normal file
@@ -0,0 +1,50 @@
|
||||
# Bot ready signaling Server
|
||||
|
||||
A FastAPI server that manages bot instances and provide endpoint for Pipecat client connections.
|
||||
|
||||
## Endpoints
|
||||
|
||||
- `POST /connect` - Pipecat client connection endpoint
|
||||
|
||||
## Environment Variables
|
||||
|
||||
Copy `env.example` to `.env` and configure:
|
||||
|
||||
```ini
|
||||
# Required API Keys
|
||||
DAILY_API_KEY= # Your Daily API key
|
||||
CARTESIA_API_KEY= # Your Cartesia API key
|
||||
|
||||
# Optional Configuration
|
||||
DAILY_API_URL= # Optional: Daily API URL (defaults to https://api.daily.co/v1)
|
||||
DAILY_SAMPLE_ROOM_URL= # Optional: Fixed room URL for development
|
||||
HOST= # Optional: Host address (defaults to 0.0.0.0)
|
||||
FAST_API_PORT= # Optional: Port number (defaults to 7860)
|
||||
```
|
||||
|
||||
## Running the Server
|
||||
|
||||
Set up and activate your virtual environment:
|
||||
|
||||
```bash
|
||||
python3 -m venv venv
|
||||
source venv/bin/activate # On Windows: venv\Scripts\activate
|
||||
```
|
||||
|
||||
Install dependencies:
|
||||
|
||||
```bash
|
||||
pip install -r requirements.txt
|
||||
```
|
||||
|
||||
If you want to use the local version of `pipecat` in this repo rather than the last published version, also run:
|
||||
|
||||
```bash
|
||||
pip install --editable "../../../[daily,cartesia,openai]"
|
||||
```
|
||||
|
||||
Run the server:
|
||||
|
||||
```bash
|
||||
python server.py
|
||||
```
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user