Merge pull request #800 from pipecat-ai/mb/autogen-docs

Auto-generate API reference docs

src/pipecat/audio/vad/vad_analyzer.py

@@ -8,7 +8,7 @@ from abc import abstractmethod
 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
 

src/pipecat/services/cartesia.py

@@ -11,7 +11,7 @@ import uuid
 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,

src/pipecat/services/gladia.py

@@ -10,7 +10,7 @@ from typing import AsyncGenerator, Optional
 
 import aiohttp
 from loguru import logger
-from pydantic.main import BaseModel
+from pydantic import BaseModel
 
 from pipecat.frames.frames import (
     CancelFrame,

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__(

src/pipecat/services/openai.py

@@ -379,14 +379,25 @@ class OpenAIImageGenService(ImageGenService):
 
 
 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__(

src/pipecat/services/playht.py

@@ -14,7 +14,7 @@ from typing import AsyncGenerator, Optional
 import aiohttp
 import websockets
 from loguru import logger
-from pydantic.main import BaseModel
+from pydantic import BaseModel
 
 from pipecat.frames.frames import (
     BotStoppedSpeakingFrame,

src/pipecat/transports/base_transport.py

@@ -11,7 +11,7 @@ from abc import ABC, abstractmethod
 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

src/pipecat/transports/network/fastapi_websocket.py

@@ -12,7 +12,7 @@ import typing
 import wave
 
 from typing import Awaitable, Callable
-from pydantic.main import BaseModel
+from pydantic import BaseModel
 
 from pipecat.frames.frames import (
     Frame,

src/pipecat/transports/network/websocket_server.py

@@ -10,7 +10,7 @@ import time
 import wave
 
 from typing import Awaitable, Callable
-from pydantic.main import BaseModel
+from pydantic import BaseModel
 
 from pipecat.frames.frames import (
     CancelFrame,