add logging for llm output

main.py

@@ -365,9 +365,13 @@ async def search_assistant(query: SearchQueryModel, api_key: str = Depends(verif
         raise HTTPException(status_code=500, detail="Failed to fetch search data")
         
     def process_response():
+        logger.info(f"Generating response using LLM: {messages}")
+        full_response = ""
         for content in chat_with_llama_stream(messages, model=query.model_id):
+            full_response+=content
             yield content
         logger.info(f"Completed search assistant response for query: {query.query}")
+        logger.info(f"LLM Response: {full_response}")
 
     return StreamingResponse(process_response(), media_type="text/event-stream")