Compare commits
3 Commits
vp-fix/mcp
...
mb/dependa
| Author | SHA1 | Date | |
|---|---|---|---|
|
336954f83f | ||
|
|
e1756688bc | ||
|
|
f1bb34c910 |
@@ -144,7 +144,7 @@ class InputParams(BaseModel):
|
||||
|
||||
#### Examples
|
||||
|
||||
Validated against `examples/07-interruptible.py`:
|
||||
Validated against `examples/foundational/07-interruptible.py`:
|
||||
|
||||
- Proper `create_transport()` usage
|
||||
- Correct pipeline structure
|
||||
|
||||
4
.github/workflows/python-compatibility.yaml
vendored
4
.github/workflows/python-compatibility.yaml
vendored
@@ -14,7 +14,7 @@ jobs:
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
python-version: ['3.11.15', '3.12.13', '3.13.12', '3.14.3']
|
||||
python-version: ['3.10.19', '3.11.14', '3.12.12', '3.13.12']
|
||||
|
||||
name: Python ${{ matrix.python-version }}
|
||||
steps:
|
||||
@@ -42,7 +42,7 @@ jobs:
|
||||
|
||||
- name: Test uv sync with all extras
|
||||
run: |
|
||||
uv sync --group dev --all-extras
|
||||
uv sync --group dev --all-extras --no-extra krisp
|
||||
|
||||
- name: Verify installation
|
||||
run: |
|
||||
|
||||
51
.github/workflows/sync-quickstart.yaml
vendored
Normal file
51
.github/workflows/sync-quickstart.yaml
vendored
Normal file
@@ -0,0 +1,51 @@
|
||||
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: ${{ github.sha }}
|
||||
"
|
||||
git push
|
||||
else
|
||||
echo "No changes to sync"
|
||||
fi
|
||||
@@ -1,13 +1,8 @@
|
||||
repos:
|
||||
- repo: local
|
||||
- repo: https://github.com/astral-sh/ruff-pre-commit
|
||||
rev: v0.12.1
|
||||
hooks:
|
||||
- id: ruff
|
||||
name: ruff
|
||||
entry: uv run ruff check --fix
|
||||
language: system
|
||||
types: [python]
|
||||
language_version: python3
|
||||
args: [--fix]
|
||||
- id: ruff-format
|
||||
name: ruff-format
|
||||
entry: uv run ruff format
|
||||
language: system
|
||||
types: [python]
|
||||
|
||||
@@ -11,7 +11,7 @@ build:
|
||||
jobs:
|
||||
post_install:
|
||||
- pip install uv
|
||||
- UV_PROJECT_ENVIRONMENT=$READTHEDOCS_VIRTUALENV_PATH uv sync --group docs --all-extras --no-extra gstreamer --no-extra local_smart_turn --no-extra moondream --no-extra riva --no-extra mlx-whisper
|
||||
- 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
|
||||
|
||||
sphinx:
|
||||
configuration: docs/api/conf.py
|
||||
|
||||
@@ -10,7 +10,7 @@ Pipecat is an open-source Python framework for building real-time voice and mult
|
||||
|
||||
```bash
|
||||
# Setup development environment
|
||||
uv sync --group dev --all-extras --no-extra gstreamer
|
||||
uv sync --group dev --all-extras --no-extra gstreamer --no-extra krisp
|
||||
|
||||
# Install pre-commit hooks
|
||||
uv run pre-commit install
|
||||
|
||||
@@ -23,7 +23,7 @@ Create your integration following the patterns and examples shown in the "Integr
|
||||
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 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
|
||||
@@ -225,17 +225,6 @@ Vision services process images and provide analysis such as descriptions, object
|
||||
|
||||
### Naming Conventions
|
||||
|
||||
#### Package and Repository Naming
|
||||
|
||||
Use the `pipecat-{vendor}` naming convention for your PyPI package and repository:
|
||||
|
||||
- `pipecat-{vendor}` — for single-service integrations (e.g., `pipecat-deepdub`)
|
||||
- `pipecat-{vendor}-{type}` — when a vendor offers multiple service types (e.g., `pipecat-upliftai-stt`, `pipecat-upliftai-tts`)
|
||||
|
||||
This convention makes community packages easily discoverable via PyPI search and clearly identifies them as part of the Pipecat ecosystem.
|
||||
|
||||
#### Class Naming
|
||||
|
||||
- **STT:** `VendorSTTService`
|
||||
- **LLM:** `VendorLLMService`
|
||||
- **TTS:**
|
||||
@@ -417,9 +406,8 @@ Use Pipecat's tracing decorators:
|
||||
|
||||
### Packaging and Distribution
|
||||
|
||||
- Name your package `pipecat-{vendor}` (see [Naming Conventions](#naming-conventions))
|
||||
- Use [uv](https://docs.astral.sh/uv/) for packaging (encouraged)
|
||||
- Publish to PyPI for easier installation
|
||||
- Consider releasing to PyPI for easier installation
|
||||
- Follow semantic versioning principles
|
||||
- Maintain a changelog
|
||||
|
||||
|
||||
37
README.md
37
README.md
@@ -8,7 +8,7 @@
|
||||
|
||||
**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? Run `pipecat init quickstart` or follow the [quickstart guide](https://docs.pipecat.ai/getting-started/quickstart).
|
||||
> Want to dive right in? Try the [quickstart](https://docs.pipecat.ai/getting-started/quickstart).
|
||||
|
||||
## 🚀 What You Can Build
|
||||
|
||||
@@ -80,25 +80,25 @@ Catch new features, interviews, and how-tos on our [Pipecat TV](https://www.yout
|
||||
<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>
|
||||
<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/vision/vision-moondream.py"><img src="https://github.com/pipecat-ai/pipecat/blob/main/examples/assets/moondream.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>
|
||||
</p>
|
||||
|
||||
## 🧩 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), [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) |
|
||||
| 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), [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), [Nebius](https://docs.pipecat.ai/server/services/llm/nebius), [Novita](https://docs.pipecat.ai/server/services/llm/novita), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nvidia), [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), [Sarvam](https://docs.pipecat.ai/server/services/llm/sarvam), [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), [Camb AI](https://docs.pipecat.ai/server/services/tts/camb), [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), [Kokoro](https://docs.pipecat.ai/server/services/tts/kokoro), [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), [Resemble](https://docs.pipecat.ai/server/services/tts/resemble), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [Sarvam](https://docs.pipecat.ai/server/services/tts/sarvam), [Smallest](https://docs.pipecat.ai/server/services/tts/smallest), [Speechmatics](https://docs.pipecat.ai/server/services/tts/speechmatics), [xAI](https://docs.pipecat.ai/server/services/tts/xai), [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), [LiveKit (WebRTC)](https://docs.pipecat.ai/server/services/transport/livekit), [SmallWebRTCTransport](https://docs.pipecat.ai/server/services/transport/small-webrtc), [WebSocket Server](https://docs.pipecat.ai/server/services/transport/websocket-server), [WhatsApp](https://docs.pipecat.ai/server/services/transport/whatsapp), Local |
|
||||
| Serializers | [Exotel](https://docs.pipecat.ai/server/services/serializers/exotel), [Genesys](https://docs.pipecat.ai/server/services/serializers/genesys), [Plivo](https://docs.pipecat.ai/server/services/serializers/plivo), [Twilio](https://docs.pipecat.ai/server/services/serializers/twilio), [Telnyx](https://docs.pipecat.ai/server/services/serializers/telnyx), [Vonage](https://docs.pipecat.ai/server/services/serializers/vonage) |
|
||||
| Video | [HeyGen](https://docs.pipecat.ai/server/services/video/heygen), [LemonSlice](https://docs.pipecat.ai/server/services/transport/lemonslice), [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/google-imagen), [Moondream](https://docs.pipecat.ai/server/services/vision/moondream) |
|
||||
| Audio Processing | [Silero VAD](https://docs.pipecat.ai/server/utilities/audio/silero-vad-analyzer), [Krisp Viva](https://docs.pipecat.ai/guides/features/krisp-viva), [Koala](https://docs.pipecat.ai/server/utilities/audio/koala-filter), [ai-coustics](https://docs.pipecat.ai/server/utilities/audio/aic-filter), [RNNoise](https://docs.pipecat.ai/server/utilities/audio/rnnoise-filter) |
|
||||
| Analytics & Metrics | [OpenTelemetry](https://docs.pipecat.ai/server/utilities/opentelemetry), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry) |
|
||||
| Community | [Browse community integrations →](https://docs.pipecat.ai/server/services/community-integrations) |
|
||||
| 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), [Camb AI](https://docs.pipecat.ai/server/services/tts/camb), [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), [Resemble](https://docs.pipecat.ai/server/services/tts/resemble), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [Sarvam](https://docs.pipecat.ai/server/services/tts/sarvam), [Smallest](https://docs.pipecat.ai/server/services/tts/smallest), [Speechmatics](https://docs.pipecat.ai/server/services/tts/speechmatics), [xAI](https://docs.pipecat.ai/server/services/tts/xai), [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 | [Exotel](https://docs.pipecat.ai/server/utilities/serializers/exotel), [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), [Vonage](https://docs.pipecat.ai/server/utilities/serializers/vonage) |
|
||||
| Video | [HeyGen](https://docs.pipecat.ai/server/services/video/heygen), [LemonSlice](https://docs.pipecat.ai/server/services/video/lemonslice), [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/google-imagen), [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) |
|
||||
| Community | [Browse community integrations →](https://docs.pipecat.ai/server/services/community-integrations) |
|
||||
|
||||
📚 [View full services documentation →](https://docs.pipecat.ai/server/services/supported-services)
|
||||
|
||||
@@ -142,15 +142,15 @@ You can get started with Pipecat running on your local machine, then move your a
|
||||
|
||||
## 🧪 Code examples
|
||||
|
||||
- [Foundational](https://github.com/pipecat-ai/pipecat/tree/main/examples) — small snippets that build on each other, introducing one or two concepts at a time
|
||||
- [Foundational](https://github.com/pipecat-ai/pipecat/tree/main/examples/foundational) — small snippets that build on each other, introducing one or two concepts at a time
|
||||
- [Example apps](https://github.com/pipecat-ai/pipecat-examples) — complete applications that you can use as starting points for development
|
||||
|
||||
## 🛠️ Contributing to the framework
|
||||
|
||||
### Prerequisites
|
||||
|
||||
**Minimum Python Version:** 3.11
|
||||
**Recommended Python Version:** >= 3.12
|
||||
**Minimum Python Version:** 3.10
|
||||
**Recommended Python Version:** 3.12
|
||||
|
||||
### Setup Steps
|
||||
|
||||
@@ -166,6 +166,7 @@ You can get started with Pipecat running on your local machine, then move your a
|
||||
```bash
|
||||
uv sync --group dev --all-extras \
|
||||
--no-extra gstreamer \
|
||||
--no-extra krisp \
|
||||
--no-extra local \
|
||||
```
|
||||
|
||||
|
||||
@@ -1 +0,0 @@
|
||||
- Updated `onnxruntime` from 1.23.2 to 1.24.3, adding support for Python 3.14.
|
||||
@@ -1 +0,0 @@
|
||||
- MCPClient now requires async with MCPClient(...) as mcp: or explicit start()/close() calls to manage the connection lifecycle.
|
||||
@@ -1 +0,0 @@
|
||||
- Fixed MCPClient opening a new connection for every tool call instead of reusing the session.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Added WebSocket-based `OpenAIResponsesLLMService` as the new default for the OpenAI Responses API. It maintains a persistent connection to `wss://api.openai.com/v1/responses` and automatically uses `previous_response_id` to send only incremental context, falling back to full context on reconnection or cache miss. The previous HTTP-based implementation is now available as `OpenAIResponsesHttpLLMService`.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed `OpenPipeLLMService` and the `openpipe` extra. OpenPipe was acquired by CoreWeave and the package is no longer maintained. If you were using `openpipe` as an LLM provider, switch to the underlying provider directly (e.g. `openai`). The OpenPipe interface can still be used with `OpenAILLMService` by specifying a `base_url`.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Updated `langchain` extra to require langchain 1.x (from 0.3.x), langchain-community 0.4.x (from 0.3.x), and langchain-openai 1.x (from 0.3.x). If you pin these packages in your project, update your pins accordingly.
|
||||
@@ -1 +0,0 @@
|
||||
- Fixed `InworldHttpTTSService` streaming responses crashing with `UnicodeDecodeError` when multi-byte UTF-8 characters were split across chunk boundaries. This caused TTS audio to cut off mid-sentence intermittently.
|
||||
@@ -1 +0,0 @@
|
||||
- Fixed a crash (`JSONDecodeError`) when a user interruption occurs while the LLM is streaming function call arguments. Previously, the incomplete JSON arguments were passed directly to `json.loads()`, causing an unhandled exception. Affected services: OpenAI, Google (OpenAI-compatible), and SambaNova.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed deprecated `observers` field from `PipelineParams`. Pass observers directly to `PipelineTask` constructor instead.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed deprecated `on_pipeline_ended`, `on_pipeline_cancelled`, and `on_pipeline_stopped` events from `PipelineTask`. Use `on_pipeline_finished` instead.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed `AudioBufferProcessor.user_continuous_stream` parameter. Use `user_audio_passthrough` instead.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed deprecated `camera_in_enabled`, `camera_in_is_live`, `camera_in_width`, `camera_in_height`, `camera_out_enabled`, `camera_out_is_live`, `camera_out_width`, `camera_out_height`, and `camera_out_color` transport params. Use the `video_in_*` and `video_out_*` equivalents instead.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed `RTVIObserver.errors_enabled` parameter.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed deprecated `vad_enabled` and `vad_audio_passthrough` transport params.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed `TTSService.say()`. Push a `TTSSpeakFrame` into the pipeline instead.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed `DailyRunner.configure_with_args()`. Use `PipelineRunner` with `RunnerArguments` instead.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed deprecated RTVI models, frames, and processor methods including `RTVIConfig`, `RTVIServiceConfig`, `RTVIServiceOptionConfig`, various `RTVI*Data` models, `RTVIActionFrame`, and `RTVIProcessor.handle_function_call`/`handle_function_call_start`. Use the updated RTVI processor API instead.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed `FrameProcessor.wait_for_task()`. Use `create_task()` and manage tasks with the built-in `TaskManager` instead.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed `KrispFilter`. The `krisp` extra has been removed from `pyproject.toml`.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed `LLMService.request_image_frame()`. Push a `UserImageRequestFrame` instead.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed `create_default_resampler()` from `pipecat.audio.utils`.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed `FalSmartTurnAnalyzer` and `LocalSmartTurnAnalyzer`.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed deprecated transport frames: `TransportMessageFrame`, `TransportMessageUrgentFrame`, `InputTransportMessageUrgentFrame`, `DailyTransportMessageFrame`, and `DailyTransportMessageUrgentFrame`. Use `OutputTransportMessageFrame`, `OutputTransportMessageUrgentFrame`, `InputTransportMessageFrame`, `DailyOutputTransportMessageFrame`, and `DailyOutputTransportMessageUrgentFrame` instead.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed deprecated `KeypadEntryFrame` alias.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed deprecated interruption frames: `StartInterruptionFrame` and `BotInterruptionFrame`. Use `InterruptionFrame` and `InterruptionTaskFrame` instead.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed `LLMService.start_callback` parameter. Register an `on_llm_response_start` event handler instead.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed single-argument function call support from `LLMService`. Functions must use named parameters instead of a single `arguments` parameter.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed `NoisereduceFilter`. Use system-level noise reduction or a service-based alternative instead.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed deprecated `pipecat.services.riva` package. Use `pipecat.services.nvidia.stt` and `pipecat.services.nvidia.tts` instead (`RivaSTTService` → `NvidiaSTTService`, `RivaTTSService` → `NvidiaTTSService`).
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed deprecated `pipecat.services.nim` package. Use `pipecat.services.nvidia.llm` instead (`NimLLMService` → `NvidiaLLMService`).
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed deprecated `pipecat.services.gemini_multimodal_live` package. Use `pipecat.services.google.gemini_live` instead. Note that class names no longer include "Multimodal" (e.g. `GeminiMultimodalLiveLLMService` → `GeminiLiveLLMService`).
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed deprecated `pipecat.services.aws_nova_sonic` package. Use `pipecat.services.aws.nova_sonic` instead.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed deprecated `pipecat.services.openai_realtime` package. Use `pipecat.services.openai.realtime` instead.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed deprecated `OpenAIRealtimeBetaLLMService` and `AzureRealtimeBetaLLMService`. Use `OpenAIRealtimeLLMService` and `AzureRealtimeLLMService` from `pipecat.services.openai.realtime` and `pipecat.services.azure.realtime` instead.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed deprecated `pipecat.services.deepgram.stt_sagemaker` and `pipecat.services.deepgram.tts_sagemaker` modules. Use `pipecat.services.deepgram.sagemaker.stt` and `pipecat.services.deepgram.sagemaker.tts` instead.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed deprecated `GoogleLLMOpenAIBetaService` from `pipecat.services.google.openai`. Use `GoogleLLMService` from `pipecat.services.google.llm` instead.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed deprecated `pipecat.services.google.llm_vertex` module. Use `pipecat.services.google.vertex.llm` instead.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed deprecated `pipecat.services.google.gemini_live.llm_vertex` module. Use `pipecat.services.google.gemini_live.vertex.llm` instead.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed deprecated `pipecat.services.ai_services` module. Import from `pipecat.services.ai_service`, `pipecat.services.llm_service`, `pipecat.services.stt_service`, `pipecat.services.tts_service`, etc. instead.
|
||||
@@ -1 +0,0 @@
|
||||
- Changed `GrokLLMService` default model from `grok-3-beta` to `grok-3`, now that the model is generally available.
|
||||
@@ -1 +0,0 @@
|
||||
- `GoogleImageGenService` now defaults to `imagen-4.0-generate-001` (previously `imagen-3.0-generate-002`).
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ `BaseOpenAILLMService.get_chat_completions()` now accepts an `LLMContext` instead of `OpenAILLMInvocationParams`. If you override this method, update your signature accordingly.
|
||||
@@ -1,22 +0,0 @@
|
||||
- ⚠️ Removed deprecated service-specific context and aggregator machinery, which was superseded by the universal `LLMContext` system.
|
||||
|
||||
Service-specific classes removed: `AnthropicLLMContext`, `AnthropicContextAggregatorPair`, `AWSBedrockLLMContext`, `AWSBedrockContextAggregatorPair`, `OpenAIContextAggregatorPair`, and their user/assistant aggregators. Also removed `create_context_aggregator()` from `LLMService`, `OpenAILLMService`, `AnthropicLLMService`, and `AWSBedrockLLMService`.
|
||||
|
||||
Base aggregator classes removed (from `pipecat.processors.aggregators.llm_response`): `BaseLLMResponseAggregator`, `LLMContextResponseAggregator`, `LLMUserContextAggregator`, `LLMAssistantContextAggregator`, `LLMUserResponseAggregator`, `LLMAssistantResponseAggregator`.
|
||||
|
||||
From the developer's point of view, migrating will usually be a matter of going from this:
|
||||
|
||||
```python
|
||||
context = OpenAILLMContext(messages, tools)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
```
|
||||
|
||||
To this:
|
||||
|
||||
```python
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
|
||||
context = LLMContext(messages, tools)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
```
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed deprecated frame types `LLMMessagesFrame` and `OpenAILLMContextAssistantTimestampFrame` from `pipecat.frames.frames`. Instead of `LLMMessagesFrame`, use `LLMContextFrame` with the new messages, or `LLMMessagesUpdateFrame` with `run_llm=True`.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed `GatedOpenAILLMContextAggregator` (from `pipecat.processors.aggregators.gated_open_ai_llm_context`). Use `GatedLLMContextAggregator` (from `pipecat.processors.aggregators.gated_llm_context`) instead.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed `VisionImageFrameAggregator` (from `pipecat.processors.aggregators.vision_image_frame`). Vision/image handling is now built into `LLMContext` (from `pipecat.processors.aggregators.llm_context`). See the `12*` examples for the recommended replacement pattern.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed deprecated compatibility modules: `pipecat.services.openai_realtime_beta` (use `pipecat.services.openai.realtime`), `pipecat.services.openai_realtime.context`, `pipecat.services.openai_realtime.frames`, `pipecat.services.openai.realtime.context`, `pipecat.services.openai.realtime.frames`, `pipecat.services.gemini_multimodal_live` (use `pipecat.services.google.gemini_live`), `pipecat.services.aws_nova_sonic.context` (use `pipecat.services.aws.nova_sonic`), `pipecat.services.google.openai` and `pipecat.services.google.llm_openai` (use `pipecat.services.google.llm`).
|
||||
@@ -1,18 +0,0 @@
|
||||
- ⚠️ Removed `OpenAILLMContext`, `OpenAILLMContextFrame`, and `OpenAILLMContext.from_messages()`. Use `LLMContext` (from `pipecat.processors.aggregators.llm_context`) and `LLMContextFrame` (from `pipecat.frames.frames`) instead. All services now exclusively use the universal `LLMContext`.
|
||||
|
||||
From the developer's point of view, migrating will usually be a matter of going from this:
|
||||
|
||||
```python
|
||||
context = OpenAILLMContext(messages, tools)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
```
|
||||
|
||||
To this:
|
||||
|
||||
```python
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
|
||||
context = LLMContext(messages, tools)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
```
|
||||
@@ -1 +0,0 @@
|
||||
- Added `enable_prompt_caching` setting to `AWSBedrockLLMService` for Bedrock ConverseStream prompt caching.
|
||||
@@ -1 +0,0 @@
|
||||
- Fixed `CartesiaTTSService` failing with "Context has closed" errors when switching voice, model, or language via `TTSUpdateSettingsFrame`. The service now automatically flushes the current audio context and opens a fresh one when these settings change.
|
||||
@@ -1,13 +0,0 @@
|
||||
- ⚠️ Removed deprecated service parameters and shims that have been replaced by the `settings=Service.Settings(...)` pattern or direct `__init__` parameters:
|
||||
- `PollyTTSService` alias (use `AWSTTSService`)
|
||||
- `TTSService`: `text_aggregator`, `text_filter` init params
|
||||
- `AWSNovaSonicLLMService`: `send_transcription_frames` init param
|
||||
- `DeepgramSTTService`: `url` init param (use `base_url`)
|
||||
- `FishAudioTTSService`: `model` init param (use `reference_id` or `settings`)
|
||||
- `GladiaSTTService`: `language` and `confidence` from `GladiaInputParams`, `InputParams` class alias
|
||||
- `GeminiTTSService`: `api_key` init param
|
||||
- `GeminiLiveLLMService`: `base_url` init param (use `http_options`)
|
||||
- `GoogleVertexLLMService`: `InputParams` class with `location`/`project_id` fields (use direct init params); `project_id` is now required, `location` defaults to `"us-east4"`
|
||||
- `MiniMaxHttpTTSService`: `english_normalization` from `InputParams` (use `text_normalization`)
|
||||
- `SimliVideoService`: `simli_config` init param (use `api_key`/`face_id`), `use_turn_server` init param; `api_key` and `face_id` are now required
|
||||
- `AnthropicLLMService`: `enable_prompt_caching_beta` from `InputParams` (use `enable_prompt_caching`)
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ `LLMService.function_call_timeout_secs` now defaults to `None` instead of `10.0`. Deferred function calls will run indefinitely unless a timeout is explicitly set at the service level or per-call. If you relied on the previous 10-second default, pass `function_call_timeout_secs=10.0` explicitly.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed deprecated `pipecat.sync` package. Use `pipecat.utils.sync` instead.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed deprecated `pipecat.transports.services` and `pipecat.transports.network` module aliases. Update imports to use `pipecat.transports.daily.transport`, `pipecat.transports.livekit.transport`, `pipecat.transports.websocket.*`, `pipecat.transports.webrtc.*`, and `pipecat.transports.daily.utils` respectively.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed deprecated `add_pattern_pair` method from `PatternPairAggregator`. Use `add_pattern` instead.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed deprecated `interruption_strategies` parameter from `PipelineParams`, `StartFrame`, and `FrameProcessor`. Use `LLMUserAggregator`'s `user_turn_strategies` parameter instead.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed deprecated `EmulateUserStartedSpeakingFrame` and `EmulateUserStoppedSpeakingFrame` frames, and the `emulated` field from `UserStartedSpeakingFrame` / `UserStoppedSpeakingFrame`.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed deprecated `pipecat.audio.interruptions` module (`BaseInterruptionStrategy`, `MinWordsInterruptionStrategy`). Use `pipecat.turns.user_start.MinWordsUserTurnStartStrategy` with `LLMUserAggregator`'s `user_turn_strategies` parameter instead.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed deprecated `pipecat.processors.transcript_processor` module (`TranscriptProcessor`, `TranscriptProcessorConfig`). Use pipeline observers instead.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed deprecated `TranscriptionMessage`, `ThoughtTranscriptionMessage`, and `TranscriptionUpdateFrame` from `pipecat.frames.frames`.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed deprecated `STTMuteFilter`, `STTMuteConfig`, and `STTMuteStrategy` from `pipecat.processors.filters.stt_mute_filter`. Use `pipecat.turns.user_mute` strategies with `LLMUserAggregator`'s `user_mute_strategies` parameter instead.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed deprecated `UserResponseAggregator` class from `pipecat.processors.aggregators.user_response`. Use `LLMUserAggregator` instead.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed deprecated `pipecat.utils.tracing.class_decorators` module. Use `pipecat.utils.tracing.service_decorators` instead.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed deprecated `allow_interruptions` parameter from `PipelineParams`, `StartFrame`, and `FrameProcessor`. Interruptions are now always allowed by default. Use `LLMUserAggregator`'s `user_turn_strategies` / `user_mute_strategies` parameters to control interruption behavior.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed `ExternalUserTurnStrategies` and the automatic fallback to it in `LLMUserAggregator` when a `SpeechControlParamsFrame` was received from the transport.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ Removed `vad_analyzer` and `turn_analyzer` parameters from `TransportParams` and all transport input classes, along with all deprecated VAD/turn analysis logic in `BaseInputTransport`. VAD and turn detection are now handled entirely by `LLMUserAggregator`.
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
# Build docs using uv
|
||||
echo "Installing dependencies with uv..."
|
||||
uv sync --group docs --all-extras --no-extra gstreamer --no-extra local_smart_turn --no-extra moondream --no-extra riva --no-extra mlx-whisper
|
||||
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
|
||||
|
||||
@@ -48,6 +48,8 @@ autodoc_default_options = {
|
||||
# Mock imports for optional dependencies
|
||||
autodoc_mock_imports = [
|
||||
# Krisp - has build issues on some platforms
|
||||
"pipecat_ai_krisp",
|
||||
"krisp",
|
||||
"krisp_audio",
|
||||
# System-specific GUI libraries
|
||||
"_tkinter",
|
||||
@@ -96,6 +98,7 @@ autodoc_mock_imports = [
|
||||
"cartesia",
|
||||
"camb",
|
||||
"sarvamai",
|
||||
"openpipe",
|
||||
"openai.types.beta.realtime",
|
||||
"langchain_core",
|
||||
"langchain_core.messages",
|
||||
|
||||
@@ -136,6 +136,9 @@ NVIDIA_API_KEY=...
|
||||
# OpenAI
|
||||
OPENAI_API_KEY=...
|
||||
|
||||
# OpenPipe
|
||||
OPENPIPE_API_KEY=...
|
||||
|
||||
# OpenRouter
|
||||
OPENROUTER_API_KEY=...
|
||||
|
||||
|
||||
@@ -1,150 +1,31 @@
|
||||
# Pipecat Examples
|
||||
|
||||
This directory contains examples showing how to build voice and multimodal agents with Pipecat.
|
||||
This directory contains examples to help you learn how to build with Pipecat.
|
||||
|
||||
## Setup
|
||||
## Getting Started
|
||||
|
||||
1. Follow the [README](https://github.com/pipecat-ai/pipecat/blob/main/README.md#%EF%B8%8F-contributing-to-the-framework) steps to get your local environment configured.
|
||||
New to Pipecat? Start here:
|
||||
|
||||
> **Run from root directory**: Make sure you are running the steps from the root directory.
|
||||
- **[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)_
|
||||
|
||||
> **Using local audio?**: The `LocalAudioTransport` requires a system dependency for `portaudio`. Install the dependency to use the transport.
|
||||
## Foundational Examples
|
||||
|
||||
2. Copy the [`env.example`](../env.example) file and add API keys for services you plan to use:
|
||||
Single-file examples that introduce core Pipecat concepts one at a time. These examples:
|
||||
|
||||
```bash
|
||||
cp env.example .env
|
||||
# Edit .env with your API keys
|
||||
```
|
||||
- Build on each other progressively
|
||||
- Focus on specific features or integrations
|
||||
- Are used for testing with every Pipecat release
|
||||
|
||||
3. Run any example:
|
||||
See the **[Foundational Examples README](foundational/)** for the complete list.
|
||||
|
||||
```bash
|
||||
uv run python getting-started/01-say-one-thing.py
|
||||
```
|
||||
## More Advanced Examples
|
||||
|
||||
4. Open the web interface at http://localhost:7860/client/ and click "Connect"
|
||||
Ready to explore complex use cases? Visit **[pipecat-examples](https://github.com/pipecat-ai/pipecat-examples)** for:
|
||||
|
||||
## Running examples with other transports
|
||||
|
||||
Most examples support running with other transports, like Twilio or Daily.
|
||||
|
||||
### Daily
|
||||
|
||||
You need to create a Daily account at https://dashboard.daily.co/u/signup. Once signed up, you can create your own room from the dashboard and set the environment variables `DAILY_ROOM_URL` and `DAILY_API_KEY`. Alternatively, you can let the example create a room for you (still needs `DAILY_API_KEY` environment variable). Then, start any example with `-t daily`:
|
||||
|
||||
```bash
|
||||
uv run getting-started/06-voice-agent.py -t daily
|
||||
```
|
||||
|
||||
### Twilio
|
||||
|
||||
It is also possible to run the example through a Twilio phone number. You will need to setup a few things:
|
||||
|
||||
1. Install and run [ngrok](https://ngrok.com/download).
|
||||
|
||||
```bash
|
||||
ngrok http 7860
|
||||
```
|
||||
|
||||
2. Configure your Twilio phone number. One way is to setup a TwiML app and set the request URL to the ngrok URL from step (1). Then, set your phone number to use the new TwiML app.
|
||||
|
||||
Then, run the example with:
|
||||
|
||||
```bash
|
||||
uv run getting-started/06-voice-agent.py -t twilio -x NGROK_HOST_NAME
|
||||
```
|
||||
|
||||
## Directory Structure
|
||||
|
||||
### [`getting-started/`](./getting-started/)
|
||||
|
||||
Progressive introduction to Pipecat, from minimal TTS to a full voice agent with function calling.
|
||||
|
||||
### [`voice/`](./voice/)
|
||||
|
||||
Full STT + LLM + TTS voice agent pipelines showcasing different speech service providers (Deepgram, ElevenLabs, Cartesia, etc.)
|
||||
|
||||
### [`function-calling/`](./function-calling/)
|
||||
|
||||
Function calling with different LLM providers (OpenAI, Anthropic, Google, etc.)
|
||||
|
||||
### [`transcription/`](./transcription/)
|
||||
|
||||
Speech-to-text examples with various STT providers.
|
||||
|
||||
### [`vision/`](./vision/)
|
||||
|
||||
Image description and vision capabilities with different multimodal LLMs.
|
||||
|
||||
### [`realtime/`](./realtime/)
|
||||
|
||||
Realtime and multimodal live APIs (OpenAI Realtime, Gemini Live, AWS Nova Sonic, Ultravox, Grok).
|
||||
|
||||
### [`persistent-context/`](./persistent-context/)
|
||||
|
||||
Maintaining conversation context across sessions with different providers.
|
||||
|
||||
### [`context-summarization/`](./context-summarization/)
|
||||
|
||||
Summarizing conversation context to manage token limits.
|
||||
|
||||
### [`update-settings/`](./update-settings/)
|
||||
|
||||
Changing service settings at runtime, organized by service type:
|
||||
|
||||
- **[`stt/`](./update-settings/stt/)** — Speech-to-text settings
|
||||
- **[`tts/`](./update-settings/tts/)** — Text-to-speech settings
|
||||
- **[`llm/`](./update-settings/llm/)** — LLM settings
|
||||
|
||||
### [`turn-management/`](./turn-management/)
|
||||
|
||||
Turn detection, interruption handling, and user input management.
|
||||
|
||||
### [`thinking-and-mcp/`](./thinking-and-mcp/)
|
||||
|
||||
LLM thinking/reasoning modes and MCP (Model Context Protocol) tool server integration.
|
||||
|
||||
### [`transports/`](./transports/)
|
||||
|
||||
Transport layer examples (WebRTC, Daily, LiveKit).
|
||||
|
||||
### [`video-avatar/`](./video-avatar/)
|
||||
|
||||
Video avatar integrations (Tavus, HeyGen, Simli, LemonSlice).
|
||||
|
||||
### [`video-processing/`](./video-processing/)
|
||||
|
||||
Video processing, mirroring, GStreamer, and custom video tracks.
|
||||
|
||||
### [`audio/`](./audio/)
|
||||
|
||||
Audio recording, background sounds, and sound effects.
|
||||
|
||||
### [`observability/`](./observability/)
|
||||
|
||||
Pipeline monitoring: observers, heartbeats, and Sentry metrics.
|
||||
|
||||
### [`rag/`](./rag/)
|
||||
|
||||
Retrieval-augmented generation, grounding, and long-term memory (Mem0, Gemini).
|
||||
|
||||
### [`features/`](./features/)
|
||||
|
||||
Miscellaneous features: wake phrases, live translation, service switching, voice switching, and more.
|
||||
|
||||
## Advanced Usage
|
||||
|
||||
### Customizing Network Settings
|
||||
|
||||
```bash
|
||||
uv run python <example-name> --host 0.0.0.0 --port 8080
|
||||
```
|
||||
|
||||
### Troubleshooting
|
||||
|
||||
- **No audio/video**: Check browser permissions for microphone and camera
|
||||
- **Connection errors**: Verify API keys in `.env` file
|
||||
- **Port conflicts**: Use `--port` to change the port
|
||||
|
||||
For more examples, visit the [pipecat-examples repository](https://github.com/pipecat-ai/pipecat-examples).
|
||||
- Production-ready applications
|
||||
- Multi-platform client implementations
|
||||
- Telephony integrations
|
||||
- Multimodal and creative applications
|
||||
- Deployment and monitoring examples
|
||||
|
||||
71
examples/foundational/01-say-one-thing-piper.py
Normal file
71
examples/foundational/01-say-one-thing-piper.py
Normal file
@@ -0,0 +1,71 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import os
|
||||
|
||||
import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.frames.frames import EndFrame, TTSSpeakFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.piper.tts import PiperHttpTTSService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
# We use lambdas to defer transport parameter creation until the transport
|
||||
# type is selected at runtime.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(audio_out_enabled=True),
|
||||
"twilio": lambda: FastAPIWebsocketParams(audio_out_enabled=True),
|
||||
"webrtc": lambda: TransportParams(audio_out_enabled=True),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
# Create an HTTP session
|
||||
async with aiohttp.ClientSession() as session:
|
||||
tts = PiperHttpTTSService(
|
||||
base_url=os.getenv("PIPER_BASE_URL"),
|
||||
aiohttp_session=session,
|
||||
sample_rate=24000,
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
Pipeline([tts, transport.output()]),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
# Register an event handler so we can play the audio when the client joins
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
await task.queue_frames([TTSSpeakFrame(f"Hello there!"), EndFrame()])
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
72
examples/foundational/01-say-one-thing-rime.py
Normal file
72
examples/foundational/01-say-one-thing-rime.py
Normal file
@@ -0,0 +1,72 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import os
|
||||
|
||||
import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.frames.frames import EndFrame, TTSSpeakFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.rime.tts import RimeHttpTTSService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
# We use lambdas to defer transport parameter creation until the transport
|
||||
# type is selected at runtime.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(audio_out_enabled=True),
|
||||
"twilio": lambda: FastAPIWebsocketParams(audio_out_enabled=True),
|
||||
"webrtc": lambda: TransportParams(audio_out_enabled=True),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
# Create an HTTP session
|
||||
async with aiohttp.ClientSession() as session:
|
||||
tts = RimeHttpTTSService(
|
||||
api_key=os.getenv("RIME_API_KEY", ""),
|
||||
aiohttp_session=session,
|
||||
settings=RimeHttpTTSService.Settings(
|
||||
voice="rex",
|
||||
),
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
Pipeline([tts, transport.output()]),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
# Register an event handler so we can play the audio when the client joins
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
await task.queue_frames([TTSSpeakFrame(f"Hello there!"), EndFrame()])
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
64
examples/foundational/01b-livekit-audio.py
Normal file
64
examples/foundational/01b-livekit-audio.py
Normal file
@@ -0,0 +1,64 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import asyncio
|
||||
import os
|
||||
import sys
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.frames.frames import TTSSpeakFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.runner.livekit import configure
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.transports.livekit.transport import LiveKitParams, LiveKitTransport
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
logger.remove(0)
|
||||
logger.add(sys.stderr, level="DEBUG")
|
||||
|
||||
|
||||
async def main():
|
||||
(url, token, room_name) = await configure()
|
||||
|
||||
transport = LiveKitTransport(
|
||||
url=url,
|
||||
token=token,
|
||||
room_name=room_name,
|
||||
params=LiveKitParams(audio_out_enabled=True),
|
||||
)
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
),
|
||||
)
|
||||
|
||||
runner = PipelineRunner()
|
||||
|
||||
task = PipelineTask(Pipeline([tts, transport.output()]))
|
||||
|
||||
# Register an event handler so we can play the audio when the
|
||||
# participant joins.
|
||||
@transport.event_handler("on_first_participant_joined")
|
||||
async def on_first_participant_joined(transport, participant_id):
|
||||
await asyncio.sleep(1)
|
||||
await task.queue_frame(
|
||||
TTSSpeakFrame(
|
||||
"Hello there! How are you doing today? Would you like to talk about the weather?"
|
||||
)
|
||||
)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(main())
|
||||
64
examples/foundational/01c-nvidia-riva-tts.py
Normal file
64
examples/foundational/01c-nvidia-riva-tts.py
Normal file
@@ -0,0 +1,64 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.frames.frames import EndFrame, TTSSpeakFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.nvidia.tts import NvidiaTTSService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
# We use lambdas to defer transport parameter creation until the transport
|
||||
# type is selected at runtime.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(audio_out_enabled=True),
|
||||
"twilio": lambda: FastAPIWebsocketParams(audio_out_enabled=True),
|
||||
"webrtc": lambda: TransportParams(audio_out_enabled=True),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
tts = NvidiaTTSService(api_key=os.getenv("NVIDIA_API_KEY"))
|
||||
|
||||
task = PipelineTask(
|
||||
Pipeline([tts, transport.output()]),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
# Register an event handler so we can play the audio when the client joins
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
await task.queue_frames([TTSSpeakFrame(f"Hello there!"), EndFrame()])
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
84
examples/foundational/03-still-frame.py
Normal file
84
examples/foundational/03-still-frame.py
Normal file
@@ -0,0 +1,84 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import os
|
||||
|
||||
import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.frames.frames import TextFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.fal.image import FalImageGenService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
# We use lambdas to defer transport parameter creation until the transport
|
||||
# type is selected at runtime.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
video_out_enabled=True,
|
||||
video_out_width=1024,
|
||||
video_out_height=1024,
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
video_out_enabled=True,
|
||||
video_out_width=1024,
|
||||
video_out_height=1024,
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
# Create an HTTP session
|
||||
async with aiohttp.ClientSession() as session:
|
||||
imagegen = FalImageGenService(
|
||||
settings=FalImageGenService.Settings(
|
||||
image_size="square_hd",
|
||||
),
|
||||
aiohttp_session=session,
|
||||
key=os.getenv("FAL_KEY"),
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
Pipeline([imagegen, transport.output()]),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
# Register an event handler so we can play the audio when the client joins
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
await task.queue_frame(TextFrame("a cat in the style of picasso"))
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
155
examples/foundational/06-listen-and-respond.py
Normal file
155
examples/foundational/06-listen-and-respond.py
Normal file
@@ -0,0 +1,155 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.frames.frames import Frame, LLMRunFrame, MetricsFrame
|
||||
from pipecat.metrics.metrics import (
|
||||
LLMUsageMetricsData,
|
||||
ProcessingMetricsData,
|
||||
TTFBMetricsData,
|
||||
TTSUsageMetricsData,
|
||||
)
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import (
|
||||
LLMContextAggregatorPair,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
class MetricsLogger(FrameProcessor):
|
||||
async def process_frame(self, frame: Frame, direction: FrameDirection):
|
||||
await super().process_frame(frame, direction)
|
||||
|
||||
if isinstance(frame, MetricsFrame):
|
||||
for d in frame.data:
|
||||
if isinstance(d, TTFBMetricsData):
|
||||
print(f"!!! MetricsFrame: {frame}, ttfb: {d.value}")
|
||||
elif isinstance(d, ProcessingMetricsData):
|
||||
print(f"!!! MetricsFrame: {frame}, processing: {d.value}")
|
||||
elif isinstance(d, LLMUsageMetricsData):
|
||||
tokens = d.value
|
||||
print(
|
||||
f"!!! MetricsFrame: {frame}, tokens: {tokens.prompt_tokens}, characters: {tokens.completion_tokens}"
|
||||
)
|
||||
elif isinstance(d, TTSUsageMetricsData):
|
||||
print(f"!!! MetricsFrame: {frame}, characters: {d.value}")
|
||||
await self.push_frame(frame, direction)
|
||||
|
||||
|
||||
# We use lambdas to defer transport parameter creation until the transport
|
||||
# type is selected at runtime.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
),
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
settings=OpenAILLMService.Settings(
|
||||
system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
|
||||
),
|
||||
)
|
||||
|
||||
ml = MetricsLogger()
|
||||
|
||||
context = LLMContext()
|
||||
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(),
|
||||
stt,
|
||||
user_aggregator,
|
||||
llm,
|
||||
tts,
|
||||
ml,
|
||||
transport.output(),
|
||||
assistant_aggregator,
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
params=PipelineParams(
|
||||
enable_metrics=True,
|
||||
enable_usage_metrics=True,
|
||||
),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
logger.info(f"Client connected")
|
||||
# Kick off the conversation.
|
||||
context.add_message(
|
||||
{"role": "developer", "content": "Please introduce yourself to the user."}
|
||||
)
|
||||
await task.queue_frames([LLMRunFrame()])
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
@@ -119,8 +119,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
)
|
||||
|
||||
image_sync_aggregator = ImageSyncAggregator(
|
||||
os.path.join(os.path.dirname(__file__), "..", "assets", "speaking.png"),
|
||||
os.path.join(os.path.dirname(__file__), "..", "assets", "waiting.png"),
|
||||
os.path.join(os.path.dirname(__file__), "assets", "speaking.png"),
|
||||
os.path.join(os.path.dirname(__file__), "assets", "waiting.png"),
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
@@ -8,9 +8,9 @@
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder
|
||||
from langchain_community.chat_message_histories import ChatMessageHistory
|
||||
from langchain_core.chat_history import BaseChatMessageHistory
|
||||
from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
|
||||
from langchain_core.runnables.history import RunnableWithMessageHistory
|
||||
from langchain_openai import ChatOpenAI
|
||||
from loguru import logger
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user