updated docker

Dockerfile

@@ -11,8 +11,10 @@ RUN pip install --no-cache-dir -r requirements.txt
 # Copy the backend code
 COPY . .
 
+RUN  chmod +x ./setup.sh && ./setup.sh
 # Expose the port the app runs on
 EXPOSE 7860
 
+
 # Run the application
 CMD ["uvicorn", "server:app", "--host", "0.0.0.0", "--port", "7860"] 

bot/bot_websocket_server.py

@@ -7,16 +7,21 @@ 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 opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
 
 from pipecat.services.ollama.llm import OLLamaLLMService
 
 # from pipecat.services.fish.tts import FishAudioTTSService
-from pipecat.services.xtts.tts import XTTSService
+# from pipecat.services.xtts.tts import XTTSService
 from pipecat.transcriptions.language import Language
-
+# from service.Dia.tts import DiaTTSService
 
 from pipecat.processors.frameworks.rtvi import RTVIConfig, RTVIObserver, RTVIProcessor
 from pipecat.serializers.protobuf import ProtobufFrameSerializer
+from pipecat.transports.network.fastapi_websocket import (
+    FastAPIWebsocketParams,
+    FastAPIWebsocketTransport,
+)
 from pipecat.services.whisper.stt import WhisperSTTService
 from pipecat.transports.network.websocket_server import (
     WebsocketServerParams,
@@ -24,10 +29,14 @@ from pipecat.transports.network.websocket_server import (
 )
 import aiohttp
 
+from dotenv import load_dotenv
 from service.Kokoro.tts import KokoroTTSService
-from service.orpheus.tts import OrpheusTTSService
+# from service.orpheus.tts import OrpheusTTSService
+
 # from service.chatterbot.tts import ChatterboxTTSService
 
+# from pipecat.utils.tracing.setup import setup_tracing
+
 SYSTEM_INSTRUCTION = f"""
 "You are Gemini Chatbot, a friendly, helpful robot.
 
@@ -38,17 +47,45 @@ Your output will be converted to audio so don't include special characters in yo
 Respond to what the user said in a creative and helpful way. Keep your responses brief. One or two sentences at most.
 """
 
+load_dotenv(override=True)
+
+# IS_TRACING_ENABLED = bool(os.getenv("ENABLE_TRACING"))
+
+# # Initialize tracing if enabled
+# if IS_TRACING_ENABLED:
+#     # Create the exporter
+#     otlp_exporter = OTLPSpanExporter()
+
+#     # Set up tracing with the exporter
+#     setup_tracing(
+#         service_name="pipecat-demo",
+#         exporter=otlp_exporter,
+#         console_export=bool(os.getenv("OTEL_CONSOLE_EXPORT")),
+#     )
+#     logger.info("OpenTelemetry tracing initialized")
+
+
+async def run_bot_websocket_server(websocket_client):
+    # 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
+    #     )
+    # )
 
-async def run_bot_websocket_server():
-    ws_transport = WebsocketServerTransport(
-        params=WebsocketServerParams(
-            serializer=ProtobufFrameSerializer(),
+    ws_transport = FastAPIWebsocketTransport(
+        websocket=websocket_client,
+        params=FastAPIWebsocketParams(
             audio_in_enabled=True,
             audio_out_enabled=True,
             add_wav_header=False,
             vad_analyzer=SileroVADAnalyzer(),
-            session_timeout=60 * 3,  # 3 minutes
-        )
+            serializer=ProtobufFrameSerializer(),
+        ),
     )
 
     stt = WhisperSTTService(
@@ -110,6 +147,11 @@ async def run_bot_websocket_server():
     #     model_name="",
     #     sample_rate=16000,
     # )
+
+    # TTS = DiaTTSService(
+    #     model_name="nari-labs/Dia-1.6B",
+    #     sample_rate=16000,
+    # )
     pipeline = Pipeline(
         [
             ws_transport.input(),
@@ -127,8 +169,12 @@ async def run_bot_websocket_server():
         pipeline,
         params=PipelineParams(
             enable_metrics=True,
+            allow_interruptions=True,
             enable_usage_metrics=True,
         ),
+        # enable_turn_tracking=True,
+        # enable_tracing=IS_TRACING_ENABLED,
+        conversation_id="test",
         observers=[RTVIObserver(rtvi)],
     )
 

server.py

@@ -1,25 +1,37 @@
-# main.py
+#
+# Copyright (c) 2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
 import asyncio
 import os
+import sys
 from contextlib import asynccontextmanager
 from typing import Any, Dict
 
 import uvicorn
 from dotenv import load_dotenv
-from fastapi import FastAPI, Request, WebSocket, WebSocketDisconnect
+from fastapi import FastAPI, Request, WebSocket
 from fastapi.middleware.cors import CORSMiddleware
-from fastapi.staticfiles import StaticFiles
 
-from bot.bot_websocket_server import run_bot_websocket_server  
+# from bot.bot_fast_api import run_bot
+from bot.bot_websocket_server import run_bot_websocket_server
 
+
+# Load environment variables
 load_dotenv(override=True)
 
+
 @asynccontextmanager
 async def lifespan(app: FastAPI):
-    yield  # Handle startup/shutdown
+    """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=["*"],
@@ -28,28 +40,43 @@ app.add_middleware(
     allow_headers=["*"],
 )
 
+
 @app.websocket("/ws")
 async def websocket_endpoint(websocket: WebSocket):
     await websocket.accept()
     print("WebSocket connection accepted")
     try:
-        await run_bot_websocket_server(websocket)  # Just the handler, not a server
-    except WebSocketDisconnect:
-        print("WebSocket disconnected")
+        await run_bot_websocket_server(websocket)
     except Exception as e:
-        print(f"Error in WebSocket handler: {e}")
+        print(f"Exception in run_bot: {e}")
+
 
 @app.post("/connect")
 async def bot_connect(request: Request) -> Dict[Any, Any]:
-    proto = "ws"
-    if "x-forwarded-proto" in request.headers and request.headers["x-forwarded-proto"] == "https":
-        proto = "wss"
-    
-    host = request.headers.get("host", "localhost:7860")
-    
-    return {"ws_url": f"{proto}://{host}/ws"}
+    return {"ws_url": "ws://localhost:7860/ws"}
+
+
+async def main():
+    config = uvicorn.Config(app, host="0.0.0.0", port=7860)
+    server = uvicorn.Server(config)
+    await server.serve()
 
-app.mount("/", StaticFiles(directory="static", html=True), name="static")
 
 if __name__ == "__main__":
-    uvicorn.run("server:app", host="0.0.0.0", port=7860, reload=False)
+    import signal
+
+    async def serve():
+        config = uvicorn.Config(app, host="0.0.0.0", port=7860)
+        server = uvicorn.Server(config)
+        await server.serve()
+
+    loop = asyncio.new_event_loop()
+    asyncio.set_event_loop(loop)
+
+    try:
+        loop.run_until_complete(serve())
+    except KeyboardInterrupt:
+        print("Received exit signal (Ctrl+C), shutting down...")
+    finally:
+        loop.run_until_complete(loop.shutdown_asyncgens())
+        loop.close()

setup.sh

@@ -0,0 +1,7 @@
+mkdir -p bot/assets
+wget https://github.com/thewh1teagle/kokoro-onnx/releases/download/model-files-v1.0/kokoro-v1.0.onnx -O bot/assets/kokoro-v1.0.int8.onnx
+wget https://github.com/thewh1teagle/kokoro-onnx/releases/download/model-files-v1.0/kokoro-v1.0.fp16-gpu.onnx -O bot/assets/kokoro-v1.0.fp16-gpu.onnx
+wget https://huggingface.co/NeuML/kokoro-base-onnx/resolve/main/voices.json -O bot/assets/voices.json
+curl -fsSL https://ollama.com/install.sh | sh 
+sleep 100
+ollama pull llama3.1