Merge pull request #3470 from pipecat-ai/mb/fix-docs-0.0.99

Docs fixes after 0.0.99

docs/api/conf.py

@@ -91,6 +91,25 @@ autodoc_mock_imports = [
     # MLX dependencies (Apple Silicon specific)
     "mlx",
     "mlx_whisper",  # Note: might need underscore format too
+    # Pydantic v2 compatibility issues in third-party SDKs
+    "hume",
+    "hume.tts",
+    "hume.tts.types",
+    "cartesia",
+    "camb",
+    "sarvamai",
+    "openpipe",
+    "openai.types.beta.realtime",
+    "langchain_core",
+    "langchain_core.messages",
+    # FastAPI - Pydantic v2 compatibility issues during Sphinx autodoc
+    "fastapi",
+    "fastapi.applications",
+    "fastapi.routing",
+    "fastapi.params",
+    "fastapi.middleware",
+    "fastapi.responses",
+    "uvicorn",
 ]
 
 # HTML output settings

pyproject.toml

@@ -97,7 +97,7 @@ qwen = []
 remote-smart-turn = []
 rime = [ "pipecat-ai[websockets-base]" ]
 riva = [ "pipecat-ai[nvidia]" ]
-runner = [ "python-dotenv>=1.0.0,<2.0.0", "uvicorn>=0.32.0,<1.0.0", "fastapi>=0.115.6,<0.122.0", "pipecat-ai-small-webrtc-prebuilt>=2.0.4"]
+runner = [ "python-dotenv>=1.0.0,<2.0.0", "uvicorn>=0.32.0,<1.0.0", "fastapi>=0.115.6,<0.128.0", "pipecat-ai-small-webrtc-prebuilt>=2.0.4"]
 sagemaker = ["aws_sdk_sagemaker_runtime_http2; python_version>='3.12'"]
 sambanova = []
 sarvam = [ "sarvamai==0.1.21", "pipecat-ai[websockets-base]" ]
@@ -113,7 +113,7 @@ together = []
 tracing = [ "opentelemetry-sdk>=1.33.0", "opentelemetry-api>=1.33.0", "opentelemetry-instrumentation>=0.54b0" ]
 ultravox = [ "pipecat-ai[websockets-base]" ]
 webrtc = [ "aiortc>=1.14.0,<2", "opencv-python>=4.11.0.86,<5" ]
-websocket = [ "pipecat-ai[websockets-base]", "fastapi>=0.115.6,<0.122.0" ]
+websocket = [ "pipecat-ai[websockets-base]", "fastapi>=0.115.6,<0.128.0" ]
 websockets-base = [ "websockets>=13.1,<16.0" ]
 whisper = [ "faster-whisper~=1.1.1" ]
 

src/pipecat/audio/filters/krisp_filter.py

@@ -61,6 +61,7 @@ class KrispFilter(BaseAudioFilter):
     Provides real-time noise reduction for audio streams using Krisp's
     proprietary noise suppression algorithms. Requires a Krisp model file
     for operation.
+
     .. deprecated:: 0.0.94
         The KrispFilter is deprecated and will be removed in a future version.
         Use KrispVivaFilter instead.

src/pipecat/serializers/vonage.py

@@ -34,8 +34,7 @@ class VonageFrameSerializer(FrameSerializer):
     WebSocket streaming protocol.
 
     Note:
-    Ref docs:
+        Ref docs: https://developer.vonage.com/en/video/guides/audio-connector
-        https://developer.vonage.com/en/video/guides/audio-connector
     """
 
     class InputParams(BaseModel):

src/pipecat/services/openai/realtime/events.py

@@ -1002,17 +1002,15 @@ class TokenDetails(BaseModel):
         image_tokens: Number of image tokens used (for input only).
     """
 
+    model_config = ConfigDict(extra="allow")
+    __pydantic_extra__: dict[str, Any]
+
     cached_tokens: Optional[int] = 0
     text_tokens: Optional[int] = 0
     audio_tokens: Optional[int] = 0
     cached_tokens_details: Optional[CachedTokensDetails] = None
     image_tokens: Optional[int] = 0
 
-    class Config:
-        """Pydantic configuration for TokenDetails."""
-
-        extra = "allow"
-
 
 class Usage(BaseModel):
     """Token usage statistics for a response.

src/pipecat/services/openai_realtime_beta/events.py

@@ -877,15 +877,13 @@ class TokenDetails(BaseModel):
         audio_tokens: Number of audio tokens used. Defaults to 0.
     """
 
+    model_config = ConfigDict(extra="allow")
+    __pydantic_extra__: dict[str, Any]
+
     cached_tokens: Optional[int] = 0
     text_tokens: Optional[int] = 0
     audio_tokens: Optional[int] = 0
 
-    class Config:
-        """Pydantic configuration for TokenDetails."""
-
-        extra = "allow"
-
 
 class Usage(BaseModel):
     """Token usage statistics for a response.

src/pipecat/transports/daily/utils.py

@@ -10,11 +10,11 @@ Methods that wrap the Daily API to create rooms, check room URLs, and get meetin
 """
 
 import time
-from typing import Dict, List, Literal, Optional
+from typing import Any, Dict, List, Literal, Optional
 from urllib.parse import urlparse
 
 import aiohttp
-from pydantic import BaseModel, Field, ValidationError
+from pydantic import BaseModel, ConfigDict, Field, ValidationError
 
 
 class DailyRoomSipParams(BaseModel):
@@ -77,7 +77,7 @@ class TranscriptionBucketConfig(BaseModel):
     allow_api_access: bool = False
 
 
-class DailyRoomProperties(BaseModel, extra="allow"):
+class DailyRoomProperties(BaseModel):
     """Properties for configuring a Daily room.
 
     Reference: https://docs.daily.co/reference/rest-api/rooms/create-room#properties
@@ -100,6 +100,11 @@ class DailyRoomProperties(BaseModel, extra="allow"):
         start_video_off: Whether video is off by default.
     """
 
+    model_config = ConfigDict(extra="allow")
+
+    # Pydantic v2.12+ requires explicit annotation for extra fields
+    __pydantic_extra__: dict[str, Any]
+
     exp: Optional[float] = None
     enable_chat: bool = False
     enable_prejoin_ui: bool = False
@@ -113,7 +118,7 @@ class DailyRoomProperties(BaseModel, extra="allow"):
     recordings_bucket: Optional[RecordingsBucketConfig] = None
     transcription_bucket: Optional[TranscriptionBucketConfig] = None
     sip: Optional[DailyRoomSipParams] = None
-    sip_uri: Optional[dict] = None
+    sip_uri: Optional[Dict[str, Any]] = None
     start_video_off: bool = False
 
     @property
@@ -203,7 +208,7 @@ class DailyMeetingTokenProperties(BaseModel):
     enable_recording: Optional[Literal["cloud", "local", "raw-tracks"]] = None
     enable_prejoin_ui: Optional[bool] = None
     start_cloud_recording: Optional[bool] = None
-    permissions: Optional[dict] = None
+    permissions: Optional[Dict[str, Any]] = None
 
 
 class DailyMeetingTokenParams(BaseModel):

uv.lock

@@ -1446,7 +1446,7 @@ wheels = [
 
 [[package]]
 name = "fastapi"
-version = "0.121.3"
+version = "0.127.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "annotated-doc" },
@@ -1454,9 +1454,9 @@ dependencies = [
     { name = "starlette" },
     { name = "typing-extensions" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/80/f0/086c442c6516195786131b8ca70488c6ef11d2f2e33c9a893576b2b0d3f7/fastapi-0.121.3.tar.gz", hash = "sha256:0055bc24fe53e56a40e9e0ad1ae2baa81622c406e548e501e717634e2dfbc40b", size = 344501, upload-time = "2025-11-19T16:53:39.243Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/96/8a/6b9ba6eb8ff3817caae83120495965d9e70afb4d6348cb120e464ee199f4/fastapi-0.127.1.tar.gz", hash = "sha256:946a87ee5d931883b562b6bada787d6c8178becee2683cb3f9b980d593206359", size = 391876, upload-time = "2025-12-26T13:04:47.075Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/98/b6/4f620d7720fc0a754c8c1b7501d73777f6ba43b57c8ab99671f4d7441eb8/fastapi-0.121.3-py3-none-any.whl", hash = "sha256:0c78fc87587fcd910ca1bbf5bc8ba37b80e119b388a7206b39f0ecc95ebf53e9", size = 109801, upload-time = "2025-11-19T16:53:37.918Z" },
+    { url = "https://files.pythonhosted.org/packages/d2/f3/a6858d147ed2645c095d11dc2440f94a5f1cd8f4df888e3377e6b5281a0f/fastapi-0.127.1-py3-none-any.whl", hash = "sha256:31d670a4f9373cc6d7994420f98e4dc46ea693145207abc39696746c83a44430", size = 112332, upload-time = "2025-12-26T13:04:45.329Z" },
 ]
 
 [package.optional-dependencies]
@@ -4513,8 +4513,8 @@ requires-dist = [
     { name = "docstring-parser", specifier = "~=0.16" },
     { name = "einops", marker = "extra == 'moondream'", specifier = "~=0.8.0" },
     { name = "fal-client", marker = "extra == 'fal'", specifier = "~=0.5.9" },
-    { name = "fastapi", marker = "extra == 'runner'", specifier = ">=0.115.6,<0.122.0" },
+    { name = "fastapi", marker = "extra == 'runner'", specifier = ">=0.115.6,<0.128.0" },
-    { name = "fastapi", marker = "extra == 'websocket'", specifier = ">=0.115.6,<0.122.0" },
+    { name = "fastapi", marker = "extra == 'websocket'", specifier = ">=0.115.6,<0.128.0" },
     { name = "faster-whisper", marker = "extra == 'whisper'", specifier = "~=1.1.1" },
     { name = "google-cloud-speech", marker = "extra == 'google'", specifier = ">=2.33.0,<3" },
     { name = "google-cloud-texttospeech", marker = "extra == 'google'", specifier = ">=2.31.0,<3" },