Creating a Tavus example using the SmallWebRTCTransport.

2025-05-23 23:03:24 -03:00
parent 4a3404883f
commit 6346ca1a84
1 changed files with 125 additions and 0 deletions
--- a/examples/foundational/21a-tavus-layer-small-webrtc.py
+++ b/examples/foundational/21a-tavus-layer-small-webrtc.py
@@ -0,0 +1,125 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import argparse
+import os
+
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.pipeline.pipeline import Pipeline
+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.services.tavus.video import TavusVideoService
+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)
+
+
+async def run_bot(webrtc_connection: SmallWebRTCConnection, _: argparse.Namespace):
+    logger.info(f"Starting bot")
+    async with aiohttp.ClientSession() as session:
+        transport = SmallWebRTCTransport(
+            webrtc_connection=webrtc_connection,
+            params=TransportParams(
+                audio_in_enabled=True,
+                audio_out_enabled=True,
+                video_out_enabled=True,
+                video_out_is_live=True,
+                vad_analyzer=SileroVADAnalyzer(),
+                video_out_width=1280,
+                video_out_height=720,
+            ),
+        )
+
+        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+        tts = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="a167e0f3-df7e-4d52-a9c3-f949145efdab",
+        )
+
+        llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"))
+
+        tavus = TavusVideoService(
+            api_key=os.getenv("TAVUS_API_KEY"),
+            replica_id=os.getenv("TAVUS_REPLICA_ID"),
+            session=session,
+        )
+
+        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(),  # User responses
+                llm,  # LLM
+                tts,  # TTS
+                tavus,  # Tavus output layer
+                transport.output(),  # Transport bot output
+                context_aggregator.assistant(),  # Assistant spoken responses
+            ]
+        )
+
+        task = PipelineTask(
+            pipeline,
+            params=PipelineParams(
+                audio_in_sample_rate=16000,
+                audio_out_sample_rate=24000,
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=True,
+                report_only_initial_ttfb=True,
+            ),
+        )
+
+        @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": "Start by greeting the user and ask how you can help.",
+                }
+            )
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @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()
+
+        runner = PipelineRunner(handle_sigint=False)
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    from run import main
+
+    main()