Merge branch 'main' into smart_turn

examples/foundational/02-llm-say-one-thing.py

@@ -38,7 +38,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/05-sync-speech-and-image.py

@@ -85,7 +85,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
 
     # Create an HTTP session for API calls
     async with aiohttp.ClientSession() as session:
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
         tts = CartesiaHttpTTSService(
             api_key=os.getenv("CARTESIA_API_KEY"),

examples/foundational/05a-local-sync-speech-and-image.py

@@ -93,7 +93,7 @@ async def main():
                         self.frame = frame
                     await self.push_frame(frame, direction)
 
-            llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+            llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
             tts = CartesiaHttpTTSService(
                 api_key=os.getenv("CARTESIA_API_KEY"),

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

@@ -73,7 +73,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     ml = MetricsLogger()
 

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

@@ -91,7 +91,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/07-interruptible.py

@@ -45,7 +45,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/07a-interruptible-vad.py

@@ -44,7 +44,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/07b-interruptible-langchain.py

@@ -74,7 +74,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
             ("human", "{input}"),
         ]
     )
-    chain = prompt | ChatOpenAI(model="gpt-4o", temperature=0.7)
+    chain = prompt | ChatOpenAI(model="gpt-4.1", temperature=0.7)
     history_chain = RunnableWithMessageHistory(
         chain,
         get_session_history,

examples/foundational/07c-interruptible-deepgram-vad.py

@@ -48,7 +48,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
 
     tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-helios-en")
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/07c-interruptible-deepgram.py

@@ -42,7 +42,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
 
     tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-helios-en")
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/07d-interruptible-elevenlabs-http.py

@@ -49,7 +49,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
             aiohttp_session=session,
         )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
         messages = [
             {

examples/foundational/07d-interruptible-elevenlabs.py

@@ -45,7 +45,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id=os.getenv("ELEVENLABS_VOICE_ID", ""),
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/07e-interruptible-playht-http.py

@@ -46,7 +46,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_url="s3://voice-cloning-zero-shot/d9ff78ba-d016-47f6-b0ef-dd630f59414e/female-cs/manifest.json",
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/07e-interruptible-playht.py

@@ -48,7 +48,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         params=PlayHTTTSService.InputParams(language=Language.EN),
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/07g-interruptible-openai.py

@@ -46,7 +46,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
 
     tts = OpenAITTSService(api_key=os.getenv("OPENAI_API_KEY"), voice="ballad")
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/07h-interruptible-openpipe.py

@@ -50,7 +50,6 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
     llm = OpenPipeLLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
         openpipe_api_key=os.getenv("OPENPIPE_API_KEY"),
-        model="gpt-4o",
         tags={"conversation_id": f"pipecat-{timestamp}"},
     )
 

examples/foundational/07i-interruptible-xtts.py

@@ -49,7 +49,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
             base_url="http://localhost:8000",
         )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
         messages = [
             {

examples/foundational/07j-interruptible-gladia.py

@@ -54,7 +54,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY", ""), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY", ""))
 
     messages = [
         {

examples/foundational/07k-interruptible-lmnt.py

@@ -42,7 +42,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
 
     tts = LmntTTSService(api_key=os.getenv("LMNT_API_KEY"), voice_id="morgan")
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/07m-interruptible-polly.py

@@ -48,7 +48,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         params=PollyTTSService.InputParams(engine="neural", language="en-GB", rate="1.05"),
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/07o-interruptible-assemblyai.py

@@ -47,7 +47,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/07p-interruptible-krisp.py

@@ -44,7 +44,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
 
     tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-helios-en")
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/07q-interruptible-rime-http.py

@@ -49,7 +49,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
             aiohttp_session=session,
         )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
         messages = [
             {

examples/foundational/07q-interruptible-rime.py

@@ -45,7 +45,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="rex",
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/07t-interruptible-fish.py

@@ -45,7 +45,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         model="4ce7e917cedd4bc2bb2e6ff3a46acaa1",  # Barack Obama
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/07v-interruptible-neuphonic-http.py

@@ -45,7 +45,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="fc854436-2dac-4d21-aa69-ae17b54e98eb",  # Emily
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/07v-interruptible-neuphonic.py

@@ -45,7 +45,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="fc854436-2dac-4d21-aa69-ae17b54e98eb",  # Emily
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/07w-interruptible-fal.py

@@ -47,7 +47,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/07x-interruptible-local.py

@@ -45,7 +45,7 @@ async def main():
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/10-wake-phrase.py

@@ -47,7 +47,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/11-sound-effects.py

@@ -93,7 +93,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
 
     stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),

examples/foundational/12b-describe-video-gpt-4o.py

@@ -74,7 +74,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
     stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
     # OpenAI GPT-4o for vision analysis
-    openai = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    openai = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),

examples/foundational/14-function-calling.py

@@ -53,7 +53,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     # You can also register a function_name of None to get all functions
     # sent to the same callback with an additional function_name parameter.

examples/foundational/14d-function-calling-video.py

@@ -82,7 +82,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
     llm.register_function("get_weather", get_weather)
     llm.register_function("get_image", get_image)
 

examples/foundational/15-switch-voices.py

@@ -83,7 +83,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="a0e99841-438c-4a64-b679-ae501e7d6091",  # Barbershop Man
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
     llm.register_function("switch_voice", switch_voice)
 
     tools = [

examples/foundational/15a-switch-languages.py

@@ -73,7 +73,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="d4db5fb9-f44b-4bd1-85fa-192e0f0d75f9",  # Spanish-speaking Lady
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
     llm.register_function("switch_language", switch_language)
 
     tools = [

examples/foundational/16-gpu-container-local-bot.py

@@ -6,7 +6,6 @@
 
 import os
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
 
@@ -40,105 +39,101 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         ),
     )
 
-    # Create an HTTP session
-    async with aiohttp.ClientSession() as session:
-        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-        tts = DeepgramTTSService(
-            aiohttp_session=session,
-            api_key=os.getenv("DEEPGRAM_API_KEY"),
-            voice="aura-asteria-en",
-            base_url="http://0.0.0.0:8080/v1/speak",
-        )
+    tts = DeepgramTTSService(
+        api_key=os.getenv("DEEPGRAM_API_KEY"),
+        voice="aura-asteria-en",
+        base_url="http://0.0.0.0:8080",
+    )
 
-        llm = OpenAILLMService(
-            # To use OpenAI
-            # api_key=os.getenv("OPENAI_API_KEY"),
-            # model="gpt-4o"
-            # Or, to use a local vLLM (or similar) api server
-            model="meta-llama/Meta-Llama-3-8B-Instruct",
-            base_url="http://0.0.0.0:8000/v1",
-        )
+    llm = OpenAILLMService(
+        # To use OpenAI
+        # api_key=os.getenv("OPENAI_API_KEY"),
+        # Or, to use a local vLLM (or similar) api server
+        model="meta-llama/Meta-Llama-3-8B-Instruct",
+        base_url="http://0.0.0.0:8000/v1",
+    )
 
-        messages = [
-            {
-                "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-            },
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            context_aggregator.user(),
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),
         ]
+    )
 
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+        ),
+    )
 
-        pipeline = Pipeline(
-            [
-                transport.input(),  # Transport user input
-                stt,  # STT
-                context_aggregator.user(),
-                llm,  # LLM
-                tts,  # TTS
-                transport.output(),  # Transport bot output
-                context_aggregator.assistant(),
-            ]
-        )
+    # When the first participant joins, the bot should introduce itself.
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-            ),
-        )
-
-        # When the first participant joins, the bot should introduce itself.
-        @transport.event_handler("on_client_connected")
-        async def on_client_connected(transport, client):
-            logger.info(f"Client connected")
-            # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
-
-        # Handle "latency-ping" messages. The client will send app messages that look like
-        # this:
-        #   { "latency-ping": { ts: <client-side timestamp> }}
-        #
-        # We want to send an immediate pong back to the client from this handler function.
-        # Also, we will push a frame into the top of the pipeline and send it after the
-        #
-        @transport.event_handler("on_app_message")
-        async def on_app_message(transport, message, sender):
-            try:
-                if "latency-ping" in message:
-                    logger.debug(f"Received latency ping app message: {message}")
-                    ts = message["latency-ping"]["ts"]
-                    # Send immediately
-                    transport.output().send_message(
-                        DailyTransportMessageFrame(
-                            message={"latency-pong-msg-handler": {"ts": ts}}, participant_id=sender
-                        )
+    # Handle "latency-ping" messages. The client will send app messages that look like
+    # this:
+    #   { "latency-ping": { ts: <client-side timestamp> }}
+    #
+    # We want to send an immediate pong back to the client from this handler function.
+    # Also, we will push a frame into the top of the pipeline and send it after the
+    #
+    @transport.event_handler("on_app_message")
+    async def on_app_message(transport, message, sender):
+        try:
+            if "latency-ping" in message:
+                logger.debug(f"Received latency ping app message: {message}")
+                ts = message["latency-ping"]["ts"]
+                # Send immediately
+                transport.output().send_message(
+                    DailyTransportMessageFrame(
+                        message={"latency-pong-msg-handler": {"ts": ts}}, participant_id=sender
                     )
-                    # And push to the pipeline for the Daily transport.output to send
-                    await task.queue_frame(
-                        DailyTransportMessageFrame(
-                            message={"latency-pong-pipeline-delivery": {"ts": ts}},
-                            participant_id=sender,
-                        )
+                )
+                # And push to the pipeline for the Daily transport.output to send
+                await task.queue_frame(
+                    DailyTransportMessageFrame(
+                        message={"latency-pong-pipeline-delivery": {"ts": ts}},
+                        participant_id=sender,
                     )
-            except Exception as e:
-                logger.debug(f"message handling error: {e} - {message}")
+                )
+        except Exception as e:
+            logger.debug(f"message handling error: {e} - {message}")
 
-        @transport.event_handler("on_client_disconnected")
-        async def on_client_disconnected(transport, client):
-            logger.info(f"Client disconnected")
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        @transport.event_handler("on_client_closed")
-        async def on_client_closed(transport, client):
-            logger.info(f"Client closed connection")
-            await task.cancel()
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        runner = PipelineRunner(handle_sigint=False)
+    runner = PipelineRunner(handle_sigint=False)
 
-        await runner.run(task)
+    await runner.run(task)
 
 
 if __name__ == "__main__":

examples/foundational/17-detect-user-idle.py

@@ -47,7 +47,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/20a-persistent-context-openai.py

@@ -185,7 +185,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     # you can either register a single function for all function calls, or specific functions
     # llm.register_function(None, fetch_weather_from_api)

examples/foundational/22-natural-conversation.py

@@ -56,7 +56,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
     # statement. This doesn't really need to be an LLM, we could use NLP
     # libraries for that, but it was easier as an example because we
     # leverage the context aggregators.
-    statement_llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    statement_llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     statement_messages = [
         {
@@ -69,7 +69,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
     statement_context_aggregator = statement_llm.create_context_aggregator(statement_context)
 
     # This is the regular LLM.
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/22b-natural-conversation-proposal.py

@@ -224,10 +224,10 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
     # This is the LLM that will be used to detect if the user has finished a
     # statement. This doesn't really need to be an LLM, we could use NLP
     # libraries for that, but we have the machinery to use an LLM, so we might as well!
-    statement_llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    statement_llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     # This is the regular LLM.
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
     # You can also register a function_name of None to get all functions
     # sent to the same callback with an additional function_name parameter.
     llm.register_function("get_current_weather", fetch_weather_from_api)

examples/foundational/22c-natural-conversation-mixed-llms.py

@@ -428,16 +428,10 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
     # This is the LLM that will be used to detect if the user has finished a
     # statement. This doesn't really need to be an LLM, we could use NLP
     # libraries for that, but we have the machinery to use an LLM, so we might as well!
-    statement_llm = AnthropicLLMService(
-        api_key=os.getenv("ANTHROPIC_API_KEY"),
-        model="claude-3-5-sonnet-20241022",
-    )
+    statement_llm = AnthropicLLMService(api_key=os.getenv("ANTHROPIC_API_KEY"))
 
     # This is the regular LLM.
-    llm = OpenAILLMService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        model="gpt-4o",
-    )
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
     # Register a function_name of None to get all functions
     # sent to the same callback with an additional function_name parameter.
     llm.register_function("get_current_weather", fetch_weather_from_api)

examples/foundational/22d-natural-conversation-gemini-audio.py

@@ -33,7 +33,10 @@ from pipecat.pipeline.parallel_pipeline import ParallelPipeline
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.llm_response import LLMAssistantResponseAggregator
+from pipecat.processors.aggregators.llm_response import (
+    LLMAssistantAggregatorParams,
+    LLMAssistantResponseAggregator,
+)
 from pipecat.processors.aggregators.openai_llm_context import (
     OpenAILLMContext,
     OpenAILLMContextFrame,
@@ -478,7 +481,7 @@ class LLMAggregatorBuffer(LLMAssistantResponseAggregator):
     """Buffers the output of the transcription LLM. Used by the bot output gate."""
 
     def __init__(self, **kwargs):
-        super().__init__(expect_stripped_words=False)
+        super().__init__(params=LLMAssistantAggregatorParams(expect_stripped_words=False))
         self._transcription = ""
 
     async def process_frame(self, frame: Frame, direction: FrameDirection):

examples/foundational/23-bot-background-sound-daily.py

@@ -62,7 +62,7 @@ async def main():
             voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
         )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
         messages = [
             {

examples/foundational/23-bot-background-sound-p2p.py

@@ -4,15 +4,13 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-"""
-Usage
+"""Usage
 -----
 Set the path to your background audio file using the `INPUT_AUDIO_PATH` environment variable, then run the bot using:
 
     INPUT_AUDIO_PATH=path/to/your_audio.mp3 python 23-bot-background-sound.py
 
 Example:
-
     INPUT_AUDIO_PATH=my_audio.mp3 python 23-bot-background-sound.py
 """
 
@@ -71,7 +69,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/24-stt-mute-filter.py

@@ -64,7 +64,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
 
     tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-helios-en")
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
     llm.register_function("get_current_weather", fetch_weather_from_api)
 
     weather_function = FunctionSchema(

examples/foundational/28-transcription-processor.py

@@ -109,10 +109,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        model="gpt-4o",
-    )
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/29-livekit-audio-chat.py

@@ -127,7 +127,7 @@ async def main():
             ),
         )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
         tts = CartesiaTTSService(
             api_key=os.getenv("CARTESIA_API_KEY"),

examples/foundational/30-observer.py

@@ -88,7 +88,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/35-pattern-pair-voice-switching.py

@@ -120,7 +120,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
     )
 
     # Initialize LLM
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     # System prompt for storytelling with voice switching
     system_prompt = """You are an engaging storyteller that uses different voices to bring stories to life.

examples/foundational/36-user-email-gathering.py

@@ -63,7 +63,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
     #     aiohttp_session=session,
     # )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
     # You can aslo register a function_name of None to get all functions
     # sent to the same callback with an additional function_name parameter.
     llm.register_function("store_user_emails", store_user_emails)

examples/foundational/37-mem0.py

@@ -210,10 +210,6 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
     @rtvi.event_handler("on_client_ready")
     async def on_client_ready(rtvi):
         await rtvi.set_bot_ready()
-
-    @transport.event_handler("on_client_connected")
-    async def on_client_connected(transport, client):
-        logger.info(f"Client connected")
         # Get personalized greeting based on user memories. Can pass agent_id and run_id as per requirement of the application to manage short term memory or agent specific memory.
         greeting = await get_initial_greeting(
             memory_client=memory.memory_client, user_id=USER_ID, agent_id=None, run_id=None
@@ -225,6 +221,10 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection):
         # Queue the context frame to start the conversation
         await task.queue_frames([context_aggregator.user().get_context_frame()])
 
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):
         logger.info(f"Client disconnected")