Update main.py

main.py

@@ -367,7 +367,6 @@ class Blackbox:
                                     except json.JSONDecodeError as je:
                                         logger.error("Failed to parse search results JSON.")
                                         raise je
-                break  # Exit the retry loop if successful
             except ClientError as ce:
                 logger.error(f"Client error occurred: {ce}. Retrying attempt {attempt + 1}/{retry_attempts}")
                 if attempt == retry_attempts - 1:
@@ -426,35 +425,35 @@ def create_response(content: str, model: str, finish_reason: Optional[str] = Non
 @app.post("/v1/chat/completions", response_model=ChatCompletionResponse)
 @limiter.limit("60/minute")  # Example: 60 requests per minute per IP
 async def chat_completions(
-    request: ChatRequest,
-    req: Request,
+    chat_request: ChatRequest,            # Renamed from 'request' to 'chat_request'
+    request: Request,                     # Added 'request: Request' parameter
     api_key: str = Depends(get_api_key)
 ):
-    logger.info(f"Received chat completions request: {request}")
+    logger.info(f"Received chat completions request: {chat_request}")
     try:
-        messages = [{"role": msg.role, "content": msg.content} for msg in request.messages]
-        prompt_tokens = count_tokens(messages, request.model)
+        messages = [{"role": msg.role, "content": msg.content} for msg in chat_request.messages]
+        prompt_tokens = count_tokens(messages, chat_request.model)
 
         async_generator = Blackbox.create_async_generator(
-            model=request.model,
+            model=chat_request.model,
             messages=messages,
             image=None,  # Adjust if image handling is required
             image_name=None,
-            webSearchMode=request.webSearchMode
+            webSearchMode=chat_request.webSearchMode
         )
 
-        if request.stream:
+        if chat_request.stream:
             async def generate():
                 try:
                     completion_tokens = 0
                     async for chunk in async_generator:
                         if isinstance(chunk, ImageResponse):
                             image_markdown = f"![image]({chunk.url})"
-                            response_chunk = create_response(image_markdown, request.model)
+                            response_chunk = create_response(image_markdown, chat_request.model)
                             yield f"data: {json.dumps(response_chunk)}\n\n"
                             completion_tokens += len(image_markdown.split())
                         else:
-                            response_chunk = create_response(chunk, request.model)
+                            response_chunk = create_response(chunk, chat_request.model)
                             yield f"data: {json.dumps(response_chunk)}\n\n"
                             completion_tokens += len(chunk.split())
                     
@@ -487,7 +486,7 @@ async def chat_completions(
                 id=f"chatcmpl-{uuid.uuid4()}",
                 object="chat.completion",
                 created=int(datetime.now().timestamp()),
-                model=request.model,
+                model=chat_request.model,
                 choices=[
                     ChatCompletionChoice(
                         index=0,
@@ -515,7 +514,7 @@ async def chat_completions(
 @app.get("/v1/models", response_model=Dict[str, List[Dict[str, str]]])
 @limiter.limit("60/minute")
 async def get_models(
-    request: Request,
+    request: Request,                      # Ensure 'request: Request' parameter is present
     api_key: str = Depends(get_api_key)
 ):
     logger.info("Fetching available models.")
@@ -526,7 +525,7 @@ async def get_models(
 @limiter.limit("60/minute")
 async def model_status(
     model: str,
-    request: Request,
+    request: Request,                      # Ensure 'request: Request' parameter is present
     api_key: str = Depends(get_api_key)
 ):
     """Check if a specific model is available."""
@@ -541,7 +540,9 @@ async def model_status(
 # Endpoint: Health Check
 @app.get("/v1/health", response_model=Dict[str, str])
 @limiter.limit("60/minute")
-async def health_check(request: Request):
+async def health_check(
+    request: Request                       # Ensure 'request: Request' parameter is present
+):
     """Health check endpoint to verify the service is running."""
     return {"status": "ok"}