Update main.py

main.py

@@ -328,56 +328,56 @@ class ChatRequest(BaseModel):
     user: Optional[str] = None
 
 @app.post("/v1/chat/completions", dependencies=[Depends(rate_limiter_per_ip)])
-async def chat_completions(request: ChatRequest, req: Request, api_key: str = Depends(get_api_key)):
+async def chat_completions(request: ChatRequest, req: Request, api_key: str = Depends(get_api_key)):  # Make sure this function is async
     client_ip = req.client.host
     # Redact user messages only for logging purposes
     redacted_messages = [{"role": msg.role, "content": "[redacted]"} for msg in request.messages]
 
     logger.info(f"Received chat completions request from API key: {api_key} | IP: {client_ip} | Model: {request.model} | Messages: {redacted_messages}")
 
-try:
-    # Validate that the requested model is available
-    if request.model not in Blackbox.models and request.model not in Blackbox.model_aliases:
-        logger.warning(f"Attempt to use unavailable model: {request.model} from IP: {client_ip}")
-        raise HTTPException(status_code=400, detail="Requested model is not available.")
-
-    # Process the request with actual message content, but don't log it
-    response_content = await Blackbox.create_completion(
-        model=request.model,
-        messages=[{"role": msg.role, "content": msg.content} for msg in request.messages],  # Actual message content used here
-    )
-
-    logger.info(f"Completed response generation for API key: {api_key} | IP: {client_ip}")
-    return {
-        "id": f"chatcmpl-{uuid.uuid4()}",
-        "object": "chat.completion",
-        "created": int(datetime.now().timestamp()),
-        "model": request.model,
-        "choices": [
-            {
-                "message": {
-                    "role": "assistant",
-                    "content": response_content
-                },
-                "finish_reason": "stop",
-                "index": 0
+    try:
+        # Validate that the requested model is available
+        if request.model not in Blackbox.models and request.model not in Blackbox.model_aliases:
+            logger.warning(f"Attempt to use unavailable model: {request.model} from IP: {client_ip}")
+            raise HTTPException(status_code=400, detail="Requested model is not available.")
+
+        # Process the request with actual message content, but don't log it
+        response_content = await Blackbox.create_completion(  # Correct usage of await inside async function
+            model=request.model,
+            messages=[{"role": msg.role, "content": msg.content} for msg in request.messages],  # Actual message content used here
+        )
+
+        logger.info(f"Completed response generation for API key: {api_key} | IP: {client_ip}")
+        return {
+            "id": f"chatcmpl-{uuid.uuid4()}",
+            "object": "chat.completion",
+            "created": int(datetime.now().timestamp()),
+            "model": request.model,
+            "choices": [
+                {
+                    "message": {
+                        "role": "assistant",
+                        "content": response_content
+                    },
+                    "finish_reason": "stop",
+                    "index": 0
+                }
+            ],
+            "usage": {
+                "prompt_tokens": sum(len(msg.content.split()) for msg in request.messages),
+                "completion_tokens": len(response_content.split()),
+                "total_tokens": sum(len(msg.content.split()) for msg in request.messages) + len(response_content.split())
             }
-        ],
-        "usage": {
-            "prompt_tokens": sum(len(msg.content.split()) for msg in request.messages),
-            "completion_tokens": len(response_content.split()),
-            "total_tokens": sum(len(msg.content.split()) for msg in request.messages) + len(response_content.split())
         }
-    }  # Closing the dictionary here
-except ModelNotWorkingException as e:
-    logger.warning(f"Model not working: {e} | IP: {client_ip}")
-    raise HTTPException(status_code=503, detail=str(e))
-except HTTPException as he:
-    logger.warning(f"HTTPException: {he.detail} | IP: {client_ip}")
-    raise he
-except Exception as e:
-    logger.exception(f"An unexpected error occurred while processing the chat completions request from IP: {client_ip}.")
-    raise HTTPException(status_code=500, detail=str(e))
+    except ModelNotWorkingException as e:
+        logger.warning(f"Model not working: {e} | IP: {client_ip}")
+        raise HTTPException(status_code=503, detail=str(e))
+    except HTTPException as he:
+        logger.warning(f"HTTPException: {he.detail} | IP: {client_ip}")
+        raise he
+    except Exception as e:
+        logger.exception(f"An unexpected error occurred while processing the chat completions request from IP: {client_ip}.")
+        raise HTTPException(status_code=500, detail=str(e))
 
 
 # Endpoint: GET /v1/models