Merge pull request #117 from daily-co/llm-use-aggregator-pass-through-fix

aggregators: fix LLMUserResponseAggregator passs-through

examples/foundational/06-listen-and-respond.py

@@ -10,8 +10,8 @@ from dailyai.services.elevenlabs_ai_service import ElevenLabsTTSService
 from dailyai.services.open_ai_services import OpenAILLMService
 from dailyai.services.ai_services import FrameLogger
 from dailyai.pipeline.aggregators import (
-    LLMAssistantContextAggregator,
-    LLMUserContextAggregator,
+    LLMAssistantResponseAggregator,
+    LLMUserResponseAggregator,
 )
 from runner import configure
 
@@ -55,11 +55,9 @@ async def main(room_url: str, token):
             },
         ]
 
-        tma_in = LLMUserContextAggregator(
-            messages, transport._my_participant_id)
-        tma_out = LLMAssistantContextAggregator(
-            messages, transport._my_participant_id
-        )
+        tma_in = LLMUserResponseAggregator(messages)
+        tma_out = LLMAssistantResponseAggregator(messages)
+
         pipeline = Pipeline(
             processors=[
                 fl,
@@ -78,8 +76,6 @@ async def main(room_url: str, token):
                 {"role": "system", "content": "Please introduce yourself to the user."})
             await pipeline.queue_frames([LLMMessagesFrame(messages)])
 
-        transport.transcription_settings["extra"]["endpointing"] = True
-        transport.transcription_settings["extra"]["punctuate"] = True
         await transport.run(pipeline)
 
 

examples/foundational/06a-image-sync.py

@@ -47,13 +47,12 @@ async def main(room_url: str, token):
             token,
             "Respond bot",
             5,
+            camera_enabled=True,
+            camera_width=1024,
+            camera_height=1024,
+            mic_enabled=True,
+            mic_sample_rate=16000,
         )
-        transport._camera_enabled = True
-        transport._camera_width = 1024
-        transport._camera_height = 1024
-        transport._mic_enabled = True
-        transport._mic_sample_rate = 16000
-        transport.transcription_settings["extra"]["punctuate"] = True
 
         tts = ElevenLabsTTSService(
             aiohttp_session=session,

examples/foundational/07-interruptible.py

@@ -67,7 +67,6 @@ async def main(room_url: str, token):
                 pre_processor=LLMUserResponseAggregator(messages),
             )
 
-        transport.transcription_settings["extra"]["punctuate"] = False
         await asyncio.gather(transport.run(), run_conversation())
 
 

examples/foundational/10-wake-word.py

@@ -129,12 +129,6 @@ async def main(room_url: str, token):
             camera_width=720,
             camera_height=1280,
         )
-        transport._mic_enabled = True
-        transport._mic_sample_rate = 16000
-        transport._camera_enabled = True
-        transport._camera_width = 720
-        transport._camera_height = 1280
-        transport.transcription_settings["extra"]["punctuate"] = True
 
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),

examples/foundational/11-sound-effects.py

@@ -82,7 +82,6 @@ async def main(room_url: str, token):
             mic_sample_rate=16000,
             camera_enabled=False,
         )
-        transport.transcription_settings["extra"]["punctuate"] = True
 
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),

examples/image-gen.py

@@ -77,8 +77,6 @@ async def main(room_url: str, token):
             async for audio in audio_generator:
                 transport.output_queue.put(Frame(FrameType.AUDIO_FRAME, audio))
 
-    transport.transcription_settings["extra"]["punctuate"] = False
-    transport.transcription_settings["extra"]["endpointing"] = False
     await asyncio.gather(transport.run(), handle_transcriptions())
 
 

examples/internal/11a-dial-out.py

@@ -127,8 +127,6 @@ async def main(room_url: str, token, phone):
                     transport.start_recording()
                     transport.dialout(phone)
 
-        transport.transcription_settings["extra"]["punctuate"] = True
-
         await asyncio.gather(transport.run(), handle_transcriptions())
 
 

examples/starter-apps/chatbot.py

@@ -139,8 +139,6 @@ async def main(room_url: str, token):
                 pre_processor=LLMUserResponseAggregator(messages),
             )
 
-        transport.transcription_settings["extra"]["endpointing"] = True
-        transport.transcription_settings["extra"]["punctuate"] = True
         await asyncio.gather(transport.run(), run_conversation())
 
 

examples/starter-apps/patient-intake.py

@@ -340,8 +340,6 @@ async def main(room_url: str, token):
                 pre_processor=OpenAIUserContextAggregator(context),
             )
 
-        transport.transcription_settings["extra"]["endpointing"] = True
-        transport.transcription_settings["extra"]["punctuate"] = True
         try:
             await asyncio.gather(transport.run(), handle_intake())
         except (asyncio.CancelledError, KeyboardInterrupt):

examples/starter-apps/storybot.py

@@ -278,8 +278,6 @@ async def main(room_url: str, token):
                 pipeline,
             )
 
-        transport.transcription_settings["extra"]["endpointing"] = True
-        transport.transcription_settings["extra"]["punctuate"] = True
         try:
             await asyncio.gather(transport.run(), storytime())
         except (asyncio.CancelledError, KeyboardInterrupt):

examples/starter-apps/translator.py

@@ -99,8 +99,6 @@ async def main(room_url: str, token):
         ts = TranslationSubtitles("spanish")
         pipeline = Pipeline([sa, tp, llm, lfra, ts, tts])
 
-        transport.transcription_settings["extra"]["endpointing"] = True
-        transport.transcription_settings["extra"]["punctuate"] = True
         await transport.run(pipeline)