Merge pull request #1766 from pipecat-ai/aleix/daily-fix-multiple-audio-video-sources

fix multiple audio video sources

CHANGELOG.md

@@ -9,6 +9,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Added
 
+- `UserImageRequestFrame.video_source` field has been added to request an image
+  from the desired video source.
+
 - Added support for the AWS Nova Sonic speech-to-speech model with the new
   `AWSNovaSonicLLMService`.
   See https://docs.aws.amazon.com/nova/latest/userguide/speech.html.
@@ -39,6 +42,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Fixed
 
+- Fixed a `DailyTransport` issue that was causing issues when multiple audio or
+  video sources where being captured.
+
 - Fixed a `UltravoxSTTService` issue that would cause the service to generate
   all tokens as one word.
 

src/pipecat/frames/frames.py

@@ -715,9 +715,10 @@ class UserImageRequestFrame(SystemFrame):
     context: Optional[Any] = None
     function_name: Optional[str] = None
     tool_call_id: Optional[str] = None
+    video_source: Optional[str] = None
 
     def __str__(self):
-        return f"{self.name}(user: {self.user_id}, function: {self.function_name}, request: {self.tool_call_id})"
+        return f"{self.name}(user: {self.user_id}, video_source: {self.video_source}, function: {self.function_name}, request: {self.tool_call_id})"
 
 
 @dataclass

src/pipecat/services/llm_service.py

@@ -190,6 +190,7 @@ class LLMService(AIService):
         function_name: Optional[str] = None,
         tool_call_id: Optional[str] = None,
         text_content: Optional[str] = None,
+        video_source: Optional[str] = None,
     ):
         await self.push_frame(
             UserImageRequestFrame(
@@ -197,6 +198,7 @@ class LLMService(AIService):
                 function_name=function_name,
                 tool_call_id=tool_call_id,
                 context=text_content,
+                video_source=video_source,
             ),
             FrameDirection.UPSTREAM,
         )

src/pipecat/transports/services/daily.py

@@ -700,7 +700,7 @@ class DailyTransportClient(EventHandler):
 
         await self.update_subscriptions(participant_settings={participant_id: media})
 
-        self._audio_renderers[participant_id] = {audio_source: callback}
+        self._audio_renderers.setdefault(participant_id, {})[audio_source] = callback
 
         self._client.set_audio_renderer(
             participant_id,
@@ -724,7 +724,7 @@ class DailyTransportClient(EventHandler):
 
         await self.update_subscriptions(participant_settings={participant_id: media})
 
-        self._video_renderers[participant_id] = {video_source: callback}
+        self._video_renderers.setdefault(participant_id, {})[video_source] = callback
 
         self._client.set_video_renderer(
             participant_id,
@@ -1061,13 +1061,14 @@ class DailyInputTransport(BaseInputTransport):
         video_source: str = "camera",
         color_format: str = "RGB",
     ):
-        self._video_renderers[participant_id] = {
+        if participant_id not in self._video_renderers:
-            video_source: {
+            self._video_renderers[participant_id] = {}
+
+        self._video_renderers[participant_id][video_source] = {
             "framerate": framerate,
             "timestamp": 0,
             "render_next_frame": [],
         }
-        }
 
         await self._client.capture_participant_video(
             participant_id, self._on_participant_video_frame, framerate, video_source, color_format
@@ -1075,7 +1076,8 @@ class DailyInputTransport(BaseInputTransport):
 
     async def request_participant_image(self, frame: UserImageRequestFrame):
         if frame.user_id in self._video_renderers:
-            self._video_renderers[frame.user_id]["render_next_frame"].append(frame)
+            video_source = frame.video_source if frame.video_source else "camera"
+            self._video_renderers[frame.user_id][video_source]["render_next_frame"].append(frame)
 
     async def _on_participant_video_frame(
         self, participant_id: str, video_frame: VideoFrame, video_source: str