Update app.py

app.py

@@ -1,10 +1,15 @@
 # app.py
 import os
+import logging
 from fastapi import FastAPI, HTTPException
 from pydantic import BaseModel
 from huggingface_hub import InferenceClient
 from typing import Optional
 
+# Set up logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
 # Initialize FastAPI app
 app = FastAPI(
     title="LLM Chat API",
@@ -17,26 +22,32 @@ class ChatRequest(BaseModel):
 
 class ChatResponse(BaseModel):
     response: str
+    status: str
 
 def llm_chat_response(text: str) -> str:
     try:
         HF_TOKEN = os.getenv("HF_TOKEN")
+        logger.info("Checking HF_TOKEN...")
         if not HF_TOKEN:
+            logger.error("HF_TOKEN not found in environment variables")
             raise HTTPException(status_code=500, detail="HF_TOKEN not configured")
         
+        logger.info("Initializing InferenceClient...")
         client = InferenceClient(api_key=HF_TOKEN)
+        
         messages = [
             {
                 "role": "user",
                 "content": [
                     {
                         "type": "text",
-                        "text": text + str('describe in one line only')
+                        "text": text + str(' describe in one line only')
                     }
                 ]
             }
         ]
         
+        logger.info("Sending request to model...")
         response_from_llama = client.chat.completions.create(
             model="meta-llama/Llama-3.2-11B-Vision-Instruct",
             messages=messages,
@@ -44,18 +55,31 @@ def llm_chat_response(text: str) -> str:
         )
         return response_from_llama.choices[0].message['content']
     except Exception as e:
+        logger.error(f"Error in llm_chat_response: {str(e)}")
         raise HTTPException(status_code=500, detail=str(e))
 
 @app.post("/chat", response_model=ChatResponse)
 async def chat(request: ChatRequest):
     try:
+        logger.info(f"Received chat request with text: {request.text}")
         response = llm_chat_response(request.text)
-        return ChatResponse(response=response)
+        return ChatResponse(response=response, status="success")
     except HTTPException as he:
+        logger.error(f"HTTP Exception in chat endpoint: {str(he)}")
         raise he
     except Exception as e:
+        logger.error(f"Unexpected error in chat endpoint: {str(e)}")
         raise HTTPException(status_code=500, detail=str(e))
 
 @app.get("/")
 async def root():
-    return {"message": "Welcome to the LLM Chat API. Use POST /chat endpoint to get responses."}
+    return {"message": "Welcome to the LLM Chat API. Use POST /chat endpoint to get responses."}
+
+# Add error handling for 404 and 405 errors
+@app.exception_handler(404)
+async def not_found_handler(request, exc):
+    return {"error": "Endpoint not found. Please use POST /chat for queries."}, 404
+
+@app.exception_handler(405)
+async def method_not_allowed_handler(request, exc):
+    return {"error": "Method not allowed. Please check the API documentation."}, 405