Update app.py

app.py

@@ -1,4 +1,4 @@
-from fastapi import FastAPI, HTTPException
+from fastapi import FastAPI, HTTPException, Request
 from pydantic import BaseModel
 from llama_cpp import Llama
 from concurrent.futures import ThreadPoolExecutor, as_completed
@@ -116,23 +116,23 @@ def generate_chat_response(request, model_data):
     try:
         user_input = normalize_input(request.message)
         response = model(user_input, top_k=request.top_k, top_p=request.top_p, temperature=request.temperature)
-        return {"model": model_data['name'], "response": response}
+        return response
     except Exception:
         pass
 
+@app.post("/generate")
 @spaces.GPU(duration=0)
 async def generate(request: ChatRequest):
     try:
         responses = []
-        with ThreadPoolExecutor() as executor:
-            futures = [executor.submit(generate_chat_response, request, model_data) for model_data in global_data['models']]
-            for future in as_completed(futures):
-                try:
-                    response = future.result()
-                    if response:
-                        responses.append(response)
-                except Exception:
-                    pass
+        models = global_data['models']
+        for model_data in models:
+            response = generate_chat_response(request, model_data)
+            if response:
+                responses.append({
+                    "model": model_data['name'],
+                    "response": response
+                })
         
         if not responses:
             raise HTTPException(status_code=500, detail="Error: No responses generated.")
@@ -147,11 +147,12 @@ async def generate(request: ChatRequest):
         pass
 
 @app.api_route("/{method_name:path}", methods=["GET", "POST", "PUT", "DELETE", "PATCH"])
-async def handle_request(method_name: str):
+async def handle_request(method_name: str, request: Request):
     try:
-        return {"message": "Request handled successfully"}
+        body = await request.json()
+        return {"message": "Request handled successfully", "body": body}
     except Exception:
-        raise HTTPException(status_code=500, detail="Error: Internal Server Error")
+        pass
 
 if __name__ == "__main__":
     uvicorn.run(app, host="0.0.0.0", port=7860)