Update api/utils.py

api/utils.py

@@ -53,6 +53,7 @@ def strip_model_prefix(content: str, model_prefix: Optional[str] = None) -> str:
         return content[len(model_prefix):].strip()
     return content
 
+# Process streaming response with headers from config.py
 async def process_streaming_response(request: ChatRequest):
     request_id = f"chatcmpl-{uuid.uuid4()}"
     logger.info(f"Processing request with ID: {request_id} - Model: {request.model}")
@@ -63,6 +64,7 @@ async def process_streaming_response(request: ChatRequest):
 
     headers_api_chat = get_headers_api_chat(BASE_URL)
 
+    # Delay for 'o1-preview' model if necessary
     if request.model == 'o1-preview':
         delay_seconds = random.randint(1, 60)
         logger.info(f"Introducing a delay of {delay_seconds} seconds for model 'o1-preview' (Request ID: {request_id})")
@@ -145,6 +147,7 @@ async def process_streaming_response(request: ChatRequest):
             logger.error(f"Request error occurred for Request ID {request_id}: {e}")
             raise HTTPException(status_code=500, detail=str(e))
 
+# Process non-streaming response with headers from config.py
 async def process_non_streaming_response(request: ChatRequest):
     request_id = f"chatcmpl-{uuid.uuid4()}"
     logger.info(f"Processing request with ID: {request_id} - Model: {request.model}")
@@ -155,6 +158,7 @@ async def process_non_streaming_response(request: ChatRequest):
 
     headers_api_chat = get_headers_api_chat(BASE_URL)
 
+    # Delay for 'o1-preview' model if necessary
     if request.model == 'o1-preview':
         delay_seconds = random.randint(20, 60)
         logger.info(f"Introducing a delay of {delay_seconds} seconds for model 'o1-preview' (Request ID: {request_id})")