diff --git a/.github/workflows/generate_docs.yaml b/.github/workflows/generate_docs.yaml new file mode 100644 index 000000000..242984d8a --- /dev/null +++ b/.github/workflows/generate_docs.yaml @@ -0,0 +1,47 @@ +name: Generate API Documentation + +on: + release: + types: [published] # Run on new release + workflow_dispatch: # Manual trigger + +jobs: + update-docs: + runs-on: ubuntu-latest + permissions: + contents: write + pull-requests: write + + steps: + - uses: actions/checkout@v4 + + - name: Set up Python + uses: actions/setup-python@v5 + with: + python-version: '3.12' + + - name: Install dependencies + run: | + python -m pip install --upgrade pip + pip install -r docs/api/requirements.txt + pip install . + + - name: Generate API documentation + run: | + cd docs/api + python generate_docs.py + + - name: Create Pull Request + uses: peter-evans/create-pull-request@v5 + with: + commit-message: 'docs: Update API documentation' + title: 'docs: Update API documentation' + body: | + Automated PR to update API documentation. + + - Generated using `docs/api/generate_docs.py` + - Triggered by: ${{ github.event_name }} + branch: update-api-docs + delete-branch: true + labels: | + documentation diff --git a/.gitignore b/.gitignore index 50eae09a2..50944a3a8 100644 --- a/.gitignore +++ b/.gitignore @@ -32,3 +32,7 @@ fly.toml # Example files pipecat/examples/twilio-chatbot/templates/streams.xml + +# Documentation +docs/api/_build/ +docs/api/api \ No newline at end of file diff --git a/.readthedocs.yaml b/.readthedocs.yaml new file mode 100644 index 000000000..667e789d9 --- /dev/null +++ b/.readthedocs.yaml @@ -0,0 +1,15 @@ +version: 2 + +build: + os: ubuntu-22.04 + tools: + python: '3.12' + +sphinx: + configuration: docs/api/conf.py + +python: + install: + - requirements: docs/api/requirements.txt + - method: pip + path: . diff --git a/docs/api/Makefile b/docs/api/Makefile new file mode 100644 index 000000000..d4bb2cbb9 --- /dev/null +++ b/docs/api/Makefile @@ -0,0 +1,20 @@ +# Minimal makefile for Sphinx documentation +# + +# You can set these variables from the command line, and also +# from the environment for the first two. +SPHINXOPTS ?= +SPHINXBUILD ?= sphinx-build +SOURCEDIR = . +BUILDDIR = _build + +# Put it first so that "make" without argument is like "make help". +help: + @$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O) + +.PHONY: help Makefile + +# Catch-all target: route all unknown targets to Sphinx using the new +# "make mode" option. $(O) is meant as a shortcut for $(SPHINXOPTS). +%: Makefile + @$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O) diff --git a/docs/api/conf.py b/docs/api/conf.py new file mode 100644 index 000000000..eab14f7e8 --- /dev/null +++ b/docs/api/conf.py @@ -0,0 +1,41 @@ +import sys +from pathlib import Path + +# Add source directory to path +docs_dir = Path(__file__).parent +project_root = docs_dir.parent +sys.path.insert(0, str(project_root / "src")) + +# Project information +project = "pipecat-ai" +copyright = "2024, Daily" +author = "Daily" + +# General configuration +extensions = [ + "sphinx.ext.autodoc", + "sphinx.ext.napoleon", + "sphinx.ext.viewcode", + "sphinx.ext.intersphinx", +] + +# 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", + "special-members": "__init__", + "undoc-members": True, + "exclude-members": "__weakref__", + "no-index": True, +} + +# HTML output settings +html_theme = "sphinx_rtd_theme" +html_static_path = ["_static"] +autodoc_typehints = "description" +html_show_sphinx = False # Remove "Built with Sphinx" diff --git a/docs/api/generate_docs.py b/docs/api/generate_docs.py new file mode 100644 index 000000000..972ea3c89 --- /dev/null +++ b/docs/api/generate_docs.py @@ -0,0 +1,104 @@ +#!/usr/bin/env python3 + +import shutil +import subprocess +from pathlib import Path + + +def run_command(command: list[str]) -> None: + """Run a command and exit if it fails.""" + print(f"Running: {' '.join(command)}") + try: + subprocess.run(command, check=True) + except subprocess.CalledProcessError as e: + print(f"Warning: Command failed: {' '.join(command)}") + print(f"Error: {e}") + + +def main(): + docs_dir = Path(__file__).parent + project_root = docs_dir.parent.parent + + # Install documentation requirements + requirements_file = docs_dir / "requirements.txt" + run_command(["pip", "install", "-r", str(requirements_file)]) + + # Install from project root, not docs directory + run_command(["pip", "install", "-e", str(project_root)]) + + # Install all service dependencies + services = [ + "anthropic", + "assemblyai", + "aws", + "azure", + "canonical", + "cartesia", + # "daily", + "deepgram", + "elevenlabs", + "fal", + "fireworks", + "gladia", + "google", + "grok", + "groq", + "langchain", + # "livekit", + "lmnt", + "moondream", + "nim", + "noisereduce", + "openai", + "openpipe", + "playht", + "silero", + "soundfile", + "websocket", + "whisper", + ] + + extras = ",".join(services) + try: + run_command(["pip", "install", "-e", f"{str(project_root)}[{extras}]"]) + except Exception as e: + print(f"Warning: Some dependencies failed to install: {e}") + + # Clean old files + api_dir = docs_dir / "api" + build_dir = docs_dir / "_build" + for dir in [api_dir, build_dir]: + if dir.exists(): + shutil.rmtree(dir) + + # Generate API documentation + run_command( + [ + "sphinx-apidoc", + "-f", # Force overwrite + "-e", # Put each module on its own page + "-M", # Put module documentation before submodule + "--no-toc", # Don't generate modules.rst (cleaner structure) + "-o", + str(api_dir), # Output directory + str(project_root / "src/pipecat"), + # Exclude problematic files and directories + str(project_root / "src/pipecat/processors/gstreamer"), # Optional gstreamer + str(project_root / "src/pipecat/transports/network"), # Pydantic issues + str(project_root / "src/pipecat/transports/services"), # Pydantic issues + str(project_root / "src/pipecat/transports/local"), # Optional dependencies + str(project_root / "src/pipecat/services/to_be_updated"), # Exclude to_be_updated + "**/test_*.py", # Test files + "**/tests/*.py", # Test files + ] + ) + + # Build HTML documentation + run_command(["sphinx-build", "-b", "html", str(docs_dir), str(build_dir / "html")]) + + print("\nDocumentation generated successfully!") + print(f"HTML docs: {build_dir}/html/index.html") + + +if __name__ == "__main__": + main() diff --git a/docs/api/index.rst b/docs/api/index.rst new file mode 100644 index 000000000..68afcb980 --- /dev/null +++ b/docs/api/index.rst @@ -0,0 +1,77 @@ +Pipecat API Reference Docs +========================== + +Welcome to Pipecat's API reference documentation! + +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 `_ +* `Website `_ + + +API Reference +------------- + +Core Components +~~~~~~~~~~~~~~~ + +* :mod:`pipecat.frames` +* :mod:`pipecat.processors` +* :mod:`pipecat.pipeline` + +Audio Processing +~~~~~~~~~~~~~~~~ + +* :mod:`pipecat.audio` +* :mod:`pipecat.vad` + +Services +~~~~~~~~ + +* :mod:`pipecat.services` + +Transport & Serialization +~~~~~~~~~~~~~~~~~~~~~~~~~ + +* :mod:`pipecat.transports` +* :mod:`pipecat.serializers` + +Utilities +~~~~~~~~~ + +* :mod:`pipecat.clocks` +* :mod:`pipecat.metrics` +* :mod:`pipecat.sync` +* :mod:`pipecat.transcriptions` +* :mod:`pipecat.utils` + +.. toctree:: + :maxdepth: 2 + :caption: API Reference + :hidden: + + api/pipecat.audio + api/pipecat.clocks + api/pipecat.frames + api/pipecat.metrics + api/pipecat.pipeline + api/pipecat.processors + api/pipecat.serializers + api/pipecat.services + api/pipecat.sync + api/pipecat.transcriptions + api/pipecat.transports + api/pipecat.utils + api/pipecat.vad + +Indices and tables +================== + +* :ref:`genindex` +* :ref:`modindex` +* :ref:`search` \ No newline at end of file diff --git a/docs/api/make.bat b/docs/api/make.bat new file mode 100644 index 000000000..32bb24529 --- /dev/null +++ b/docs/api/make.bat @@ -0,0 +1,35 @@ +@ECHO OFF + +pushd %~dp0 + +REM Command file for Sphinx documentation + +if "%SPHINXBUILD%" == "" ( + set SPHINXBUILD=sphinx-build +) +set SOURCEDIR=. +set BUILDDIR=_build + +%SPHINXBUILD% >NUL 2>NUL +if errorlevel 9009 ( + echo. + echo.The 'sphinx-build' command was not found. Make sure you have Sphinx + echo.installed, then set the SPHINXBUILD environment variable to point + echo.to the full path of the 'sphinx-build' executable. Alternatively you + echo.may add the Sphinx directory to PATH. + echo. + echo.If you don't have Sphinx installed, grab it from + echo.https://www.sphinx-doc.org/ + exit /b 1 +) + +if "%1" == "" goto help + +%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O% +goto end + +:help +%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O% + +:end +popd diff --git a/docs/api/requirements.txt b/docs/api/requirements.txt new file mode 100644 index 000000000..c1b9addb5 --- /dev/null +++ b/docs/api/requirements.txt @@ -0,0 +1,5 @@ +sphinx>=8.1.3 +sphinx-rtd-theme +sphinx-markdown-builder +sphinx-autodoc-typehints +toml \ No newline at end of file diff --git a/pyproject.toml b/pyproject.toml index 79026ddab..081c68c5f 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -62,7 +62,7 @@ moondream = [ "einops~=0.8.0", "timm~=1.0.8", "transformers~=4.44.0" ] nim = [ "openai~=1.50.2" ] noisereduce = [ "noisereduce~=3.0.3" ] openai = [ "openai~=1.50.2", "websockets~=13.1", "python-deepcompare~=1.0.1" ] -openpipe = [ "openpipe~=4.24.0" ] +openpipe = [ "openpipe~=4.38.0" ] playht = [ "pyht~=0.1.4", "websockets~=13.1" ] silero = [ "onnxruntime~=1.19.2" ] soundfile = [ "soundfile~=0.12.1" ] @@ -84,3 +84,10 @@ fallback_version = "0.0.0-dev" [tool.ruff] exclude = ["*_pb2.py"] line-length = 100 + +select = [ + "D", # Docstring rules +] + +[tool.ruff.pydocstyle] +convention = "google" \ No newline at end of file diff --git a/src/pipecat/audio/vad/vad_analyzer.py b/src/pipecat/audio/vad/vad_analyzer.py index 17bce6543..c291db7f3 100644 --- a/src/pipecat/audio/vad/vad_analyzer.py +++ b/src/pipecat/audio/vad/vad_analyzer.py @@ -8,7 +8,7 @@ from enum import Enum from loguru import logger -from pydantic.main import BaseModel +from pydantic import BaseModel from pipecat.audio.utils import calculate_audio_volume, exp_smoothing diff --git a/src/pipecat/services/cartesia.py b/src/pipecat/services/cartesia.py index a526d7333..8683fd29a 100644 --- a/src/pipecat/services/cartesia.py +++ b/src/pipecat/services/cartesia.py @@ -11,7 +11,7 @@ from typing import AsyncGenerator, List, Optional, Union from loguru import logger -from pydantic.main import BaseModel +from pydantic import BaseModel from pipecat.frames.frames import ( BotStoppedSpeakingFrame, diff --git a/src/pipecat/services/gladia.py b/src/pipecat/services/gladia.py index c659a20ac..8909c4bb2 100644 --- a/src/pipecat/services/gladia.py +++ b/src/pipecat/services/gladia.py @@ -10,7 +10,7 @@ import aiohttp from loguru import logger -from pydantic.main import BaseModel +from pydantic import BaseModel from pipecat.frames.frames import ( CancelFrame, diff --git a/src/pipecat/services/nim.py b/src/pipecat/services/nim.py index 0ce0171c9..2b57a5047 100644 --- a/src/pipecat/services/nim.py +++ b/src/pipecat/services/nim.py @@ -22,14 +22,6 @@ class NimLLMService(OpenAILLMService): base_url (str, optional): The base URL for NIM API. Defaults to "https://integrate.api.nvidia.com/v1" model (str, optional): The model identifier to use. Defaults to "nvidia/llama-3.1-nemotron-70b-instruct" **kwargs: Additional keyword arguments passed to OpenAILLMService - - Example: - ```python - service = NimLLMService( - api_key="your-api-key", - model="nvidia/llama-3.1-nemotron-70b-instruct" - ) - ``` """ def __init__( diff --git a/src/pipecat/services/openai.py b/src/pipecat/services/openai.py index b6927e8dc..4e11edc22 100644 --- a/src/pipecat/services/openai.py +++ b/src/pipecat/services/openai.py @@ -379,14 +379,25 @@ async def run_image_gen(self, prompt: str) -> AsyncGenerator[Frame, None]: class OpenAITTSService(TTSService): - """This service uses the OpenAI TTS API to generate audio from text. - The returned audio is PCM encoded at 24kHz. When using the DailyTransport, set the sample rate in the DailyParams accordingly: - ``` + """OpenAI Text-to-Speech service that generates audio from text. + + This service uses the OpenAI TTS API to generate PCM-encoded audio at 24kHz. + When using with DailyTransport, configure the sample rate in DailyParams + as shown below: + DailyParams( audio_out_enabled=True, audio_out_sample_rate=24_000, ) - ``` + + Args: + api_key: OpenAI API key. Defaults to None. + voice: Voice ID to use. Defaults to "alloy". + model: TTS model to use ("tts-1" or "tts-1-hd"). Defaults to "tts-1". + sample_rate: Output audio sample rate in Hz. Defaults to 24000. + **kwargs: Additional keyword arguments passed to TTSService. + + The service returns PCM-encoded audio at the specified sample rate. """ def __init__( diff --git a/src/pipecat/services/playht.py b/src/pipecat/services/playht.py index d272ee361..78be924af 100644 --- a/src/pipecat/services/playht.py +++ b/src/pipecat/services/playht.py @@ -14,7 +14,7 @@ import aiohttp import websockets from loguru import logger -from pydantic.main import BaseModel +from pydantic import BaseModel from pipecat.frames.frames import ( BotStoppedSpeakingFrame, diff --git a/src/pipecat/transports/base_transport.py b/src/pipecat/transports/base_transport.py index 3eac820f2..91f95fbbc 100644 --- a/src/pipecat/transports/base_transport.py +++ b/src/pipecat/transports/base_transport.py @@ -11,7 +11,7 @@ from typing import Optional from pydantic import ConfigDict -from pydantic.main import BaseModel +from pydantic import BaseModel from pipecat.audio.filters.base_audio_filter import BaseAudioFilter from pipecat.audio.mixers.base_audio_mixer import BaseAudioMixer diff --git a/src/pipecat/transports/network/fastapi_websocket.py b/src/pipecat/transports/network/fastapi_websocket.py index de1cf531e..cd21fbe0d 100644 --- a/src/pipecat/transports/network/fastapi_websocket.py +++ b/src/pipecat/transports/network/fastapi_websocket.py @@ -12,7 +12,7 @@ import wave from typing import Awaitable, Callable -from pydantic.main import BaseModel +from pydantic import BaseModel from pipecat.frames.frames import ( Frame, diff --git a/src/pipecat/transports/network/websocket_server.py b/src/pipecat/transports/network/websocket_server.py index 567dbac7d..711bc7596 100644 --- a/src/pipecat/transports/network/websocket_server.py +++ b/src/pipecat/transports/network/websocket_server.py @@ -10,7 +10,7 @@ import wave from typing import Awaitable, Callable -from pydantic.main import BaseModel +from pydantic import BaseModel from pipecat.frames.frames import ( CancelFrame,