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

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

examples/foundational/26b-gemini-multimodal-live-function-calling.py

@@ -4,15 +4,11 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 from datetime import datetime
 
-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 AdapterType, ToolsSchema
@@ -23,13 +19,12 @@ 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.gemini_multimodal_live.gemini import GeminiMultimodalLiveLLMService
-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")
-
 
 async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
     temperature = 75 if args["format"] == "fahrenheit" else 24
@@ -51,87 +46,99 @@ for the weather, call this function.
 """
 
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                vad_enabled=True,
-                vad_audio_passthrough=True,
-                # set stop_secs to something roughly similar to the internal setting
-                # of the Multimodal Live api, just to align events. This doesn't really
-                # matter because we can only use the Multimodal Live API's phrase
-                # endpointing, for now.
-                vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
-            ),
-        )
+    # Initialize the SmallWebRTCTransport with the connection
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_enabled=True,
+            vad_audio_passthrough=True,
+            # set stop_secs to something roughly similar to the internal setting
+            # of the Multimodal Live api, just to align events. This doesn't really
+            # matter because we can only use the Multimodal Live API's phrase
+            # endpointing, for now.
+            vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
+        ),
+    )
 
-        weather_function = FunctionSchema(
-            name="get_current_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.",
-                },
+    weather_function = FunctionSchema(
+        name="get_current_weather",
+        description="Get the current weather",
+        properties={
+            "location": {
+                "type": "string",
+                "description": "The city and state, e.g. San Francisco, CA",
             },
-            required=["location", "format"],
-        )
-        search_tool = {"google_search": {}}
-        tools = ToolsSchema(
-            standard_tools=[weather_function], custom_tools={AdapterType.GEMINI: [search_tool]}
-        )
+            "format": {
+                "type": "string",
+                "enum": ["celsius", "fahrenheit"],
+                "description": "The temperature unit to use. Infer this from the user's location.",
+            },
+        },
+        required=["location", "format"],
+    )
+    search_tool = {"google_search": {}}
+    tools = ToolsSchema(
+        standard_tools=[weather_function], custom_tools={AdapterType.GEMINI: [search_tool]}
+    )
 
-        llm = GeminiMultimodalLiveLLMService(
-            api_key=os.getenv("GOOGLE_API_KEY"),
-            system_instruction=system_instruction,
-            tools=tools,
-        )
+    llm = GeminiMultimodalLiveLLMService(
+        api_key=os.getenv("GOOGLE_API_KEY"),
+        system_instruction=system_instruction,
+        tools=tools,
+    )
 
-        llm.register_function("get_current_weather", fetch_weather_from_api)
+    llm.register_function("get_current_weather", fetch_weather_from_api)
 
-        context = OpenAILLMContext(
-            [{"role": "user", "content": "Say hello."}],
-        )
-        context_aggregator = llm.create_context_aggregator(context)
+    context = OpenAILLMContext(
+        [{"role": "user", "content": "Say hello."}],
+    )
+    context_aggregator = llm.create_context_aggregator(context)
 
-        pipeline = Pipeline(
-            [
-                transport.input(),
-                context_aggregator.user(),
-                llm,
-                transport.output(),
-                context_aggregator.assistant(),
-            ]
-        )
+    pipeline = Pipeline(
+        [
+            transport.input(),
+            context_aggregator.user(),
+            llm,
+            transport.output(),
+            context_aggregator.assistant(),
+        ]
+    )
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-            ),
-        )
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+    )
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            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")
+        # Kick off the conversation.
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-        runner = PipelineRunner()
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        await runner.run(task)
+    @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)
+
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()