Upload folder using huggingface_hub

app.py

@@ -7,6 +7,7 @@ import gradio as gr
 import numpy as np
 from dotenv import load_dotenv
 from elevenlabs import ElevenLabs
+from fastapi import FastAPI
 from fastapi.responses import HTMLResponse, StreamingResponse
 from fastrtc import (
     AdditionalOutputs,
@@ -15,7 +16,7 @@ from fastrtc import (
     get_tts_model,
     get_twilio_turn_credentials,
 )
-from fastrtc.utils import aggregate_bytes_to_16bit, audio_to_bytes
+from fastrtc.utils import audio_to_bytes
 from gradio.utils import get_space
 from groq import Groq
 from pydantic import BaseModel
@@ -44,6 +45,7 @@ def response(
     ).text
     print("prompt", prompt)
     chatbot.append({"role": "user", "content": prompt})
+    yield AdditionalOutputs(chatbot)
     messages.append({"role": "user", "content": prompt})
     response = claude_client.messages.create(
         model="claude-3-5-haiku-20241022",
@@ -56,7 +58,6 @@ def response(
         if getattr(block, "type", None) == "text"
     )
     chatbot.append({"role": "assistant", "content": response_text})
-    yield AdditionalOutputs(chatbot)
     import time
 
     start = time.time()
@@ -66,6 +67,7 @@ def response(
         print("chunk", i, time.time() - start)
         yield chunk
     print("finished tts", time.time() - start)
+    yield AdditionalOutputs(chatbot)
 
 
 chatbot = gr.Chatbot(type="messages")
@@ -91,7 +93,11 @@ class InputData(BaseModel):
     chatbot: list[Message]
 
 
-@stream.get("/")
+app = FastAPI()
+stream.mount(app)
+
+
+@app.get("/")
 async def _():
     rtc_config = get_twilio_turn_credentials() if get_space() else None
     html_content = (curr_dir / "index.html").read_text()
@@ -99,19 +105,20 @@ async def _():
     return HTMLResponse(content=html_content, status_code=200)
 
 
-@stream.post("/input_hook")
+@app.post("/input_hook")
 async def _(body: InputData):
     stream.set_input(body.webrtc_id, body.model_dump()["chatbot"])
     return {"status": "ok"}
 
 
-@stream.get("/outputs")
+@app.get("/outputs")
 def _(webrtc_id: str):
     async def output_stream():
         async for output in stream.output_stream(webrtc_id):
             chatbot = output.args[0]
-            yield f"event: output\ndata: {json.dumps(chatbot[-2])}\n\n"
-            yield f"event: output\ndata: {json.dumps(chatbot[-1])}\n\n"
+            if len(chatbot) > 1:
+                yield f"event: output\ndata: {json.dumps(chatbot[-2])}\n\n"
+                yield f"event: output\ndata: {json.dumps(chatbot[-1])}\n\n"
 
     return StreamingResponse(output_stream(), media_type="text/event-stream")
 
@@ -119,9 +126,11 @@ def _(webrtc_id: str):
 if __name__ == "__main__":
     import os
 
-    if not os.getenv("PHONE"):
+    if (mode := os.getenv("MODE")) == "UI":
+        stream.ui.launch(server_port=7860)
+    elif mode == "PHONE":
+        stream.fastphone(host="0.0.0.0", port=7860)
+    else:
         import uvicorn
 
-        s = uvicorn.run(stream, host="0.0.0.0", port=7860)
-    else:
-        stream.fastphone(host="0.0.0.0", port=7860)
+        uvicorn.run(app, host="0.0.0.0", port=7860)