A Pipecat example demonstrating how to use WebsocketTransport

examples/websocket/server/bot_fast_api.py

@@ -0,0 +1,112 @@
+#
+# Copyright (c) 2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+import os
+import sys
+
+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.processors.frameworks.rtvi import RTVIConfig, RTVIObserver, RTVIProcessor
+from pipecat.serializers.protobuf import ProtobufFrameSerializer
+from pipecat.services.gemini_multimodal_live import GeminiMultimodalLiveLLMService
+from pipecat.transports.network.fastapi_websocket import (
+    FastAPIWebsocketParams,
+    FastAPIWebsocketTransport,
+)
+
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+SYSTEM_INSTRUCTION = f"""
+"You are Gemini Chatbot, a friendly, helpful robot.
+
+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. Keep your responses brief. One or two sentences at most.
+"""
+
+
+async def run_bot(websocket_client):
+    ws_transport = FastAPIWebsocketTransport(
+        websocket=websocket_client,
+        params=FastAPIWebsocketParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            add_wav_header=False,
+            vad_analyzer=SileroVADAnalyzer(),
+            serializer=ProtobufFrameSerializer(),
+        ),
+    )
+
+    llm = GeminiMultimodalLiveLLMService(
+        api_key=os.getenv("GOOGLE_API_KEY"),
+        voice_id="Puck",  # Aoede, Charon, Fenrir, Kore, Puck
+        transcribe_user_audio=True,
+        transcribe_model_audio=True,
+        system_instruction=SYSTEM_INSTRUCTION,
+    )
+
+    context = OpenAILLMContext(
+        [
+            {
+                "role": "user",
+                "content": "Start by greeting the user warmly and introducing yourself.",
+            }
+        ],
+    )
+    context_aggregator = llm.create_context_aggregator(context)
+
+    # RTVI events for Pipecat client UI
+    rtvi = RTVIProcessor(config=RTVIConfig(config=[]))
+
+    pipeline = Pipeline(
+        [
+            ws_transport.input(),
+            context_aggregator.user(),
+            rtvi,
+            llm,  # LLM
+            ws_transport.output(),
+            context_aggregator.assistant(),
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            observers=[RTVIObserver(rtvi)],
+        ),
+    )
+
+    @rtvi.event_handler("on_client_ready")
+    async def on_client_ready(rtvi):
+        logger.info("Pipecat client ready.")
+
+    @ws_transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info("Pipecat Client connected")
+        await rtvi.set_bot_ready()
+        # Kick off the conversation.
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+    @ws_transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info("Pipecat Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=False)
+
+    await runner.run(task)

examples/websocket/server/bot_websocket_server.py

@@ -0,0 +1,110 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import os
+
+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.processors.frameworks.rtvi import RTVIConfig, RTVIObserver, RTVIProcessor
+from pipecat.serializers.protobuf import ProtobufFrameSerializer
+from pipecat.services.gemini_multimodal_live import GeminiMultimodalLiveLLMService
+from pipecat.transports.network.websocket_server import (
+    WebsocketServerParams,
+    WebsocketServerTransport,
+)
+
+SYSTEM_INSTRUCTION = f"""
+"You are Gemini Chatbot, a friendly, helpful robot.
+
+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. Keep your responses brief. One or two sentences at most.
+"""
+
+
+async def run_bot_websocket_server():
+    ws_transport = WebsocketServerTransport(
+        params=WebsocketServerParams(
+            serializer=ProtobufFrameSerializer(),
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            add_wav_header=False,
+            vad_analyzer=SileroVADAnalyzer(),
+            session_timeout=60 * 3,  # 3 minutes
+        )
+    )
+
+    llm = GeminiMultimodalLiveLLMService(
+        api_key=os.getenv("GOOGLE_API_KEY"),
+        voice_id="Puck",  # Aoede, Charon, Fenrir, Kore, Puck
+        transcribe_user_audio=True,
+        transcribe_model_audio=True,
+        system_instruction=SYSTEM_INSTRUCTION,
+    )
+
+    context = OpenAILLMContext(
+        [
+            {
+                "role": "user",
+                "content": "Start by greeting the user warmly and introducing yourself.",
+            }
+        ],
+    )
+    context_aggregator = llm.create_context_aggregator(context)
+
+    # RTVI events for Pipecat client UI
+    rtvi = RTVIProcessor(config=RTVIConfig(config=[]))
+
+    pipeline = Pipeline(
+        [
+            ws_transport.input(),
+            context_aggregator.user(),
+            rtvi,
+            llm,  # LLM
+            ws_transport.output(),
+            context_aggregator.assistant(),
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            observers=[RTVIObserver(rtvi)],
+        ),
+    )
+
+    @rtvi.event_handler("on_client_ready")
+    async def on_client_ready(rtvi):
+        logger.info("Pipecat client ready.")
+
+    @ws_transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info("Pipecat Client connected")
+        await rtvi.set_bot_ready()
+        # Kick off the conversation.
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+    @ws_transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info("Pipecat Client disconnected")
+        await task.cancel()
+
+    @ws_transport.event_handler("on_session_timeout")
+    async def on_session_timeout(transport, client):
+        logger.info(f"Entering in timeout for {client.remote_address}")
+        await task.cancel()
+
+    runner = PipelineRunner()
+
+    await runner.run(task)

examples/websocket/server/env.example

@@ -0,0 +1,2 @@
+GOOGLE_API_KEY=
+WEBSOCKET_SERVER= # Options: 'fast_api' or 'websocket_server'

examples/websocket/server/requirements.txt

@@ -0,0 +1,4 @@
+python-dotenv
+fastapi[all]
+uvicorn
+pipecat-ai[silero,websocket,google]

examples/websocket/server/server.py

@@ -0,0 +1,79 @@
+#
+# Copyright (c) 2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+import asyncio
+import os
+from contextlib import asynccontextmanager
+from typing import Any, Dict
+
+import uvicorn
+from dotenv import load_dotenv
+from fastapi import FastAPI, Request, WebSocket
+from fastapi.middleware.cors import CORSMiddleware
+
+# Load environment variables
+load_dotenv(override=True)
+
+from bot_fast_api import run_bot
+from bot_websocket_server import run_bot_websocket_server
+
+
+@asynccontextmanager
+async def lifespan(app: FastAPI):
+    """Handles FastAPI startup and shutdown."""
+    yield  # Run app
+
+
+# Initialize FastAPI app with lifespan manager
+app = FastAPI(lifespan=lifespan)
+
+# Configure CORS to allow requests from any origin
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+
+@app.websocket("/ws")
+async def websocket_endpoint(websocket: WebSocket):
+    await websocket.accept()
+    print("WebSocket connection accepted")
+    try:
+        await run_bot(websocket)
+    except Exception as e:
+        print(f"Exception in run_bot: {e}")
+
+
+@app.post("/connect")
+async def bot_connect(request: Request) -> Dict[Any, Any]:
+    server_mode = os.getenv("WEBSOCKET_SERVER", "fast_api")
+    if server_mode == "websocket_server":
+        ws_url = "ws://localhost:8765"
+    else:
+        ws_url = "ws://localhost:7860/ws"
+    return {"ws_url": ws_url}
+
+
+async def main():
+    server_mode = os.getenv("WEBSOCKET_SERVER", "fast_api")
+    tasks = []
+    try:
+        if server_mode == "websocket_server":
+            tasks.append(run_bot_websocket_server())
+
+        config = uvicorn.Config(app, host="0.0.0.0", port=7860)
+        server = uvicorn.Server(config)
+        tasks.append(server.serve())
+
+        await asyncio.gather(*tasks)
+    except asyncio.CancelledError:
+        print("Tasks cancelled (probably due to shutdown).")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())