Update app.py

app.py

@@ -1,23 +1,30 @@
 import os
+import logging
 from fastapi import FastAPI, HTTPException, Query
 from fastapi.responses import StreamingResponse
 from pydantic import BaseModel
 from openai import AsyncOpenAI
 from typing import Optional
 
+# Configure logging
+logging.basicConfig(level=logging.DEBUG)
+logger = logging.getLogger(__name__)
+
 app = FastAPI()
 
 class GenerateRequest(BaseModel):
     prompt: str
 
 async def generate_ai_response(prompt: str, model: str):
-    # Configuration for AI endpoint
+    logger.debug(f"Received prompt: {prompt}, model: {model}")
     token = os.getenv("GITHUB_TOKEN")
-    endpoint = os.getenv("AI_SERVER_URL", "https://models.github.ai/inference")  # Default fallback
+    endpoint = os.getenv("AI_SERVER_URL", "https://models.github.ai/inference")
     
     if not token:
+        logger.error("GitHub token not configured")
         raise HTTPException(status_code=500, detail="GitHub token not configured")
 
+    logger.debug(f"Using endpoint: {endpoint}")
     client = AsyncOpenAI(base_url=endpoint, api_key=token)
 
     try:
@@ -37,6 +44,7 @@ async def generate_ai_response(prompt: str, model: str):
                 yield chunk.choices[0].delta.content
 
     except Exception as err:
+        logger.error(f"AI generation failed: {str(err)}")
         yield f"Error: {str(err)}"
         raise HTTPException(status_code=500, detail=f"AI generation failed: {str(err)}")
 
@@ -46,19 +54,15 @@ async def generate_response(
     prompt: Optional[str] = Query(None, description="The input text prompt for the AI"),
     request: Optional[GenerateRequest] = None
 ):
-    """
-    Generate a streaming AI response based on the provided prompt and model.
-    
-    - **model**: The AI model to use (specified as a query parameter, defaults to default-model)
-    - **prompt**: The input text prompt for the AI (can be in query parameter or request body)
-    """
-    # Determine prompt source: query parameter or request body
+    logger.debug(f"Request received - model: {model}, prompt: {prompt}, body: {request}")
     final_prompt = prompt if prompt is not None else (request.prompt if request is not None else None)
     
     if not final_prompt or not final_prompt.strip():
+        logger.error("Prompt cannot be empty")
         raise HTTPException(status_code=400, detail="Prompt cannot be empty")
     
     if not model or not model.strip():
+        logger.error("Model cannot be empty")
         raise HTTPException(status_code=400, detail="Model cannot be empty")
     
     return StreamingResponse(
@@ -68,4 +72,3 @@ async def generate_response(
 
 def get_app():
     return app
-