Update app.py

app.py

@@ -1,15 +1,18 @@
 import gradio as gr
-from fastapi import FastAPI, Request
+from fastapi import FastAPI, Request, HTTPException
 from fastapi.responses import JSONResponse
 import datetime
 import requests
 import os
-import json
-import asyncio
+import logging
 
 # Initialize FastAPI
 app = FastAPI()
 
+# Configure logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
 # Configuration
 API_URL = "https://api-inference.huggingface.co/models/Qwen/Qwen2.5-Coder-32B"
 headers = {
@@ -39,29 +42,31 @@ def format_chat_response(response_text, prompt_tokens=0, completion_tokens=0):
     }
 
 async def query_model(payload):
-    response = requests.post(API_URL, headers=headers, json=payload)
-    return response.json()
+    try:
+        response = requests.post(API_URL, headers=headers, json=payload)
+        response.raise_for_status()
+        return response.json()
+    except requests.exceptions.RequestException as e:
+        logger.error(f"Request failed: {e}")
+        raise HTTPException(status_code=500, detail=str(e))
 
 @app.get("/status")
 async def status():
     try:
         response_text = "it's working"
-        
-        return JSONResponse(
-            content=format_chat_response(response_text)
-        )
+        return JSONResponse(content=format_chat_response(response_text))
     except Exception as e:
-        return JSONResponse(
-            status_code=500,
-            content={"error": str(e)}
-        )
-        
+        logger.error(f"Status check failed: {e}")
+        raise HTTPException(status_code=500, detail=str(e))
+
 @app.post("/v1/chat/completions")
 async def chat_completion(request: Request):
     try:
         data = await request.json()
         messages = data.get("messages", [])
-        
+        if not messages:
+            raise HTTPException(status_code=400, detail="Messages are required")
+
         payload = {
             "inputs": {
                 "messages": messages
@@ -77,21 +82,17 @@ async def chat_completion(request: Request):
         response = await query_model(payload)
         
         if isinstance(response, dict) and "error" in response:
-            return JSONResponse(
-                status_code=500,
-                content={"error": response["error"]}
-            )
+            raise HTTPException(status_code=500, detail=response["error"])
         
         response_text = response[0]["generated_text"]
         
-        return JSONResponse(
-            content=format_chat_response(response_text)
-        )
+        return JSONResponse(content=format_chat_response(response_text))
+    except HTTPException as e:
+        logger.error(f"Chat completion failed: {e.detail}")
+        raise e
     except Exception as e:
-        return JSONResponse(
-            status_code=500,
-            content={"error": str(e)}
-        )
+        logger.error(f"Unexpected error: {e}")
+        raise HTTPException(status_code=500, detail=str(e))
 
 def generate_response(messages):
     payload = {
@@ -106,13 +107,18 @@ def generate_response(messages):
         }
     }
     
-    response = requests.post(API_URL, headers=headers, json=payload)
-    result = response.json()
-    
-    if isinstance(result, dict) and "error" in result:
-        return f"Error: {result['error']}"
-    
-    return result[0]["generated_text"]
+    try:
+        response = requests.post(API_URL, headers=headers, json=payload)
+        response.raise_for_status()
+        result = response.json()
+        
+        if isinstance(result, dict) and "error" in result:
+            return f"Error: {result['error']}"
+        
+        return result[0]["generated_text"]
+    except requests.exceptions.RequestException as e:
+        logger.error(f"Request failed: {e}")
+        return f"Error: {e}"
 
 def chat_interface(messages):
     chat_history = []
@@ -128,7 +134,6 @@ def chat_interface(messages):
 
 # Create Gradio interface
 def gradio_app():
-    #return gr.chat_interface(gr.Chatbot(placeholder="placeholder"), type="messages", value=[])
     return gr.ChatInterface(chat_interface, type="messages")
 
 # Mount both FastAPI and Gradio