commit 00000022

app.py

@@ -2,16 +2,15 @@ import os
 import time
 import torch
 import re
-import uvicorn
-import gradio as gr
-from fastapi import FastAPI
+from fastapi import FastAPI, Request
 from fastapi.responses import StreamingResponse
 from pydantic import BaseModel
 from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
 from huggingface_hub import login
 from langchain_community.tools import DuckDuckGoSearchRun
 from fastapi.middleware.cors import CORSMiddleware
-from fastapi.staticfiles import StaticFiles
+import os
+import uvicorn
 
 # ✅ Safe GPU decorator
 try:
@@ -28,7 +27,7 @@ app = FastAPI(
     redoc_url="/redoc"    # ReDoc at /redoc
 )
 
-# Enable CORS
+# Enable CORS (important for browser clients)
 app.add_middleware(
     CORSMiddleware,
     allow_origins=["*"],
@@ -104,29 +103,6 @@ async def chat_stream(body: ChatRequest):
 
     return StreamingResponse(generate(), media_type="text/plain")
 
-# ---------------- Gradio UI ----------------
-def gradio_chat(message, history):
-    # Convert Gradio format to your API format
-    formatted_history = [{"role": "user" if i % 2 == 0 else "assistant", "content": msg}
-                         for i, (msg, _) in enumerate(history)]
-    reply = generate_full_reply(message, formatted_history)
-    history.append((message, reply))
-    return history, ""
-
-with gr.Blocks() as gradio_app:
-    gr.Markdown("# 🤖 ChatMate - Real-Time AI Assistant")
-    chatbot = gr.Chatbot()
-    msg = gr.Textbox(placeholder="Type your message here...")
-    clear = gr.Button("Clear Chat")
-
-    msg.submit(gradio_chat, [msg, chatbot], [chatbot, msg])
-    clear.click(lambda: None, None, chatbot, queue=False)
-
-# Mount Gradio inside FastAPI
-#from fastapi.middleware.wsgi import WSGIMiddleware
-##app.mount("/", gr.mount_gradio_app(app, gradio_app, path="/"))
-app = gr.mount_gradio_app(app, gradio_app, path="/gradio")
-
 # ---------------- Startup warm-up ----------------
 @app.on_event("startup")
 async def warmup_model():
@@ -134,6 +110,10 @@ async def warmup_model():
     _ = generate_full_reply("Hello", [])
 
 # ---------------- Run with Uvicorn ----------------
+# In Hugging Face Spaces, just run: uvicorn app:app --host 0.0.0.0 --port 7860
 if __name__ == "__main__":
+    # Hugging Face Spaces usually expects port 7860
     port = int(os.environ.get("PORT", 7860))
-    uvicorn.run("app:app", host="0.0.0.0", port=port, reload=False)
+
+    # Run using uvicorn for FastAPI/Flask with ASGI wrapper
+    uvicorn.run("app:app", host="0.0.0.0", port=port, reload=False)