Updating foundation examples to use SmallWebRTCTransport and pipecat-ai-small-webrtc-prebuilt (#1534)

Co-authored-by: Filipi Fuchter <filipi@daily.co>

examples/foundational/14e-function-calling-gemini.py

@@ -6,12 +6,9 @@
 
 import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.adapters.schemas.function_schema import FunctionSchema
 from pipecat.adapters.schemas.tools_schema import ToolsSchema
@@ -22,15 +19,17 @@ from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.cartesia.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.google.llm import GoogleLLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
-video_participant_id = None
+# Global variable to store the peer connection ID
+webrtc_peer_id = None
 
 
 async def get_weather(function_name, tool_call_id, arguments, llm, context, result_callback):
@@ -40,71 +39,85 @@ async def get_weather(function_name, tool_call_id, arguments, llm, context, resu
 
 
 async def get_image(function_name, tool_call_id, arguments, llm, context, result_callback):
-    logger.debug(f"!!! IN get_image {video_participant_id}, {arguments}")
     question = arguments["question"]
+    logger.debug(f"Requesting image with user_id={webrtc_peer_id}, question={question}")
+
+    # Request the image frame
     await llm.request_image_frame(
-        user_id=video_participant_id,
+        user_id=webrtc_peer_id,
         function_name=function_name,
         tool_call_id=tool_call_id,
         text_content=question,
     )
 
+    # Wait a short time for the frame to be processed
+    await asyncio.sleep(0.5)
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+    # Return a result to complete the function call
+    await result_callback(
+        f"I've captured an image from your camera and I'm analyzing what you asked about: {question}"
+    )
 
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                transcription_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-            ),
-        )
 
-        tts = CartesiaTTSService(
-            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        )
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    global webrtc_peer_id
+    webrtc_peer_id = webrtc_connection.pc_id
 
-        llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"), model="gemini-2.0-flash-001")
-        llm.register_function("get_weather", get_weather)
-        llm.register_function("get_image", get_image)
+    logger.info(f"Starting bot with peer_id: {webrtc_peer_id}")
 
-        weather_function = FunctionSchema(
-            name="get_weather",
-            description="Get the current weather",
-            properties={
-                "location": {
-                    "type": "string",
-                    "description": "The city and state, e.g. San Francisco, CA",
-                },
-                "format": {
-                    "type": "string",
-                    "enum": ["celsius", "fahrenheit"],
-                    "description": "The temperature unit to use. Infer this from the user's location.",
-                },
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            camera_in_enabled=True,  # Make sure camera input is enabled
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
+
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
+
+    llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"), model="gemini-2.0-flash-001")
+    llm.register_function("get_weather", get_weather)
+    llm.register_function("get_image", get_image)
+
+    weather_function = FunctionSchema(
+        name="get_weather",
+        description="Get the current weather",
+        properties={
+            "location": {
+                "type": "string",
+                "description": "The city and state, e.g. San Francisco, CA",
             },
-            required=["location", "format"],
-        )
-        get_image_function = FunctionSchema(
-            name="get_image",
-            description="Get an image from the video stream.",
-            properties={
-                "question": {
-                    "type": "string",
-                    "description": "The question that the user is asking about the image.",
-                }
+            "format": {
+                "type": "string",
+                "enum": ["celsius", "fahrenheit"],
+                "description": "The temperature unit to use. Infer this from the user's location.",
             },
-            required=["question"],
-        )
-        tools = ToolsSchema(standard_tools=[weather_function, get_image_function])
+        },
+        required=["location", "format"],
+    )
+    get_image_function = FunctionSchema(
+        name="get_image",
+        description="Get an image from the video stream.",
+        properties={
+            "question": {
+                "type": "string",
+                "description": "The question that the user is asking about the image.",
+            }
+        },
+        required=["question"],
+    )
+    tools = ToolsSchema(standard_tools=[weather_function, get_image_function])
 
-        system_prompt = """\
+    system_prompt = """\
 You are a helpful assistant who converses with a user and answers questions. Respond concisely to general questions.
 
 Your response will be turned into speech so use only simple words and punctuation.
@@ -115,54 +128,63 @@ You can respond to questions about the weather using the get_weather tool.
 
 You can answer questions about the user's video stream using the get_image tool. Some examples of phrases that \
 indicate you should use the get_image tool are:
-  - What do you see?
-  - What's in the video?
-  - Can you describe the video?
-  - Tell me about what you see.
-  - Tell me something interesting about what you see.
-  - What's happening in the video?
+- What do you see?
+- What's in the video?
+- Can you describe the video?
+- Tell me about what you see.
+- Tell me something interesting about what you see.
+- What's happening in the video?
 """
-        messages = [
-            {"role": "system", "content": system_prompt},
-            {"role": "user", "content": "Say hello."},
+    messages = [
+        {"role": "system", "content": system_prompt},
+        {"role": "user", "content": "Say hello."},
+    ]
+
+    context = OpenAILLMContext(messages, tools)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),
+            stt,
+            context_aggregator.user(),
+            llm,
+            tts,
+            transport.output(),
+            context_aggregator.assistant(),
         ]
+    )
 
-        context = OpenAILLMContext(messages, tools)
-        context_aggregator = llm.create_context_aggregator(context)
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+    )
 
-        pipeline = Pipeline(
-            [
-                transport.input(),
-                context_aggregator.user(),
-                llm,
-                tts,
-                transport.output(),
-                context_aggregator.assistant(),
-            ]
-        )
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected: {client}")
+        # Kick off the conversation.
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-            ),
-        )
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            global video_participant_id
-            video_participant_id = participant["id"]
-            await transport.capture_participant_transcription(participant["id"])
-            await transport.capture_participant_video(video_participant_id, framerate=0)
-            # Kick off the conversation.
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        runner = PipelineRunner()
+    runner = PipelineRunner(handle_sigint=False)
 
-        await runner.run(task)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()