Update main.py

main.py

@@ -229,10 +229,10 @@ class Blackbox:
         cleaned_text = re.sub(pattern, '', text)
         try:
             response_json = json.loads(cleaned_text)
-            # Assuming the response is in {"response": "Your answer here."} format
-            return response_json.get("response", cleaned_text)
+            # Adjust based on actual response structure
+            return response_json.get("response", response_json.get("data", cleaned_text))
         except json.JSONDecodeError:
-            return cleaned_text
+            return cleaned_text.strip()
 
     @classmethod
     async def generate_response(
@@ -252,6 +252,7 @@ class Blackbox:
 
         prefix = cls.model_prefixes.get(model, "")
         
+        # Construct the prompt
         formatted_prompt = ""
         for message in messages:
             role = message.get('role', '').capitalize()
@@ -297,30 +298,12 @@ class Blackbox:
                     "role": "user"
                 }
             ],
-            "id": chat_id,
-            "previewToken": None,
-            "userId": None,
-            "codeModelMode": True,
-            "agentMode": agent_mode,
-            "trendingAgentMode": trending_agent_mode,
-            "isMicMode": False,
-            "userSystemPrompt": None,
-            "maxTokens": 1024,
-            "playgroundTopP": 0.9,
-            "playgroundTemperature": 0.5,
-            "isChromeExt": False,
-            "githubToken": None,
-            "clickedAnswer2": False,
-            "clickedAnswer3": False,
-            "clickedForceWebSearch": False,
-            "visitFromDelta": False,
-            "mobileClient": False,
-            "webSearchMode": False,
-            "userSelectedModel": cls.userSelectedModel.get(model, model)
+            "model": model  # Simplified payload for testing
         }
 
         async with ClientSession(headers=common_headers) as session:
             try:
+                logger.debug(f"Payload sent to Blackbox API: {json.dumps(payload_api_chat)}")
                 async with session.post(
                     cls.api_endpoint,
                     headers=headers_api_chat_combined,
@@ -347,411 +330,214 @@ class Blackbox:
                 logger.exception(f"Unexpected error during /api/chat request: {str(e)}")
                 return f"Unexpected error during /api/chat request: {str(e)}"
 
-    @classmethod
-    async def create_async_generator(
-        cls,
-        model: str,
-        messages: List[Dict[str, str]],
-        proxy: Optional[str] = None,
-        websearch: bool = False,
-        **kwargs
-    ) -> AsyncGenerator[Union[str, ImageResponseModel], None]:
-        """
-        Creates an asynchronous generator for streaming responses from Blackbox AI.
-
-        Parameters:
-            model (str): Model to use for generating responses.
-            messages (List[Dict[str, str]]): Message history.
-            proxy (Optional[str]): Proxy URL, if needed.
-            websearch (bool): Enables or disables web search mode.
-            **kwargs: Additional keyword arguments.
+    # ===============================
+    # 7. Initialize FastAPI App
+    # ===============================
+    app = FastAPI()
+
+    # ====================================
+    # 8. Define Middleware and Dependencies
+    # ====================================
+    @app.middleware("http")
+    async def security_middleware(request: Request, call_next):
+        client_ip = request.client.host
+        # Enforce that POST requests to /v1/chat/completions must have Content-Type: application/json
+        if request.method == "POST" and request.url.path == "/v1/chat/completions":
+            content_type = request.headers.get("Content-Type")
+            if content_type != "application/json":
+                logger.warning(f"Invalid Content-Type from IP: {client_ip} for path: {request.url.path}")
+                return JSONResponse(
+                    status_code=400,
+                    content={
+                        "error": {
+                            "message": "Content-Type must be application/json",
+                            "type": "invalid_request_error",
+                            "param": None,
+                            "code": None
+                        }
+                    },
+                )
+        response = await call_next(request)
+        return response
 
-        Yields:
-            Union[str, ImageResponseModel]: Segments of the generated response or ImageResponseModel objects.
+    async def cleanup_rate_limit_stores():
         """
-        model = cls.get_model(model)
-
-        chat_id = cls.generate_random_string()
-        next_action = cls.generate_next_action()
-        next_router_state_tree = cls.generate_next_router_state_tree()
-
-        agent_mode = cls.agentMode.get(model, {})
-        trending_agent_mode = cls.trendingAgentMode.get(model, {})
-
-        prefix = cls.model_prefixes.get(model, "")
-        
-        formatted_prompt = ""
-        for message in messages:
-            role = message.get('role', '').capitalize()
-            content = message.get('content', '')
-            if role and content:
-                formatted_prompt += f"{role}: {content}\n"
-        
-        if prefix:
-            formatted_prompt = f"{prefix} {formatted_prompt}".strip()
-
-        referer_path = cls.model_referers.get(model, f"/?model={model}")
-        referer_url = f"{cls.url}{referer_path}"
-
-        common_headers = {
-            'accept': '*/*',
-            'accept-language': 'en-US,en;q=0.9',
-            'cache-control': 'no-cache',
-            'origin': cls.url,
-            'pragma': 'no-cache',
-            'priority': 'u=1, i',
-            'sec-ch-ua': '"Chromium";v="129", "Not=A?Brand";v="8"',
-            'sec-ch-ua-mobile': '?0',
-            'sec-ch-ua-platform': '"Linux"',
-            'sec-fetch-dest': 'empty',
-            'sec-fetch-mode': 'cors',
-            'sec-fetch-site': 'same-origin',
-            'user-agent': 'Mozilla/5.0 (X11; Linux x86_64) '
-                          'AppleWebKit/537.36 (KHTML, like Gecko) '
-                          'Chrome/129.0.0.0 Safari/537.36'
-        }
-
-        headers_api_chat = {
-            'Content-Type': 'application/json',
-            'Referer': referer_url
-        }
-        headers_api_chat_combined = {**common_headers, **headers_api_chat}
-
-        payload_api_chat = {
-            "messages": [
-                {
-                    "id": chat_id,
-                    "content": formatted_prompt,
-                    "role": "user"
-                }
-            ],
-            "id": chat_id,
-            "previewToken": None,
-            "userId": None,
-            "codeModelMode": True,
-            "agentMode": agent_mode,
-            "trendingAgentMode": trending_agent_mode,
-            "isMicMode": False,
-            "userSystemPrompt": None,
-            "maxTokens": 1024,
-            "playgroundTopP": 0.9,
-            "playgroundTemperature": 0.5,
-            "isChromeExt": False,
-            "githubToken": None,
-            "clickedAnswer2": False,
-            "clickedAnswer3": False,
-            "clickedForceWebSearch": False,
-            "visitFromDelta": False,
-            "mobileClient": False,
-            "webSearchMode": websearch,
-            "userSelectedModel": cls.userSelectedModel.get(model, model)
-        }
-
-        headers_chat = {
-            'Accept': 'text/x-component',
-            'Content-Type': 'text/plain;charset=UTF-8',
-            'Referer': f'{cls.url}/chat/{chat_id}?model={model}',
-            'next-action': next_action,
-            'next-router-state-tree': next_router_state_tree,
-            'next-url': '/'
-        }
-        headers_chat_combined = {**common_headers, **headers_chat}
-
-        data_chat = '[]'
-
-        async with ClientSession(headers=common_headers) as session:
-            try:
-                async with session.post(
-                    cls.api_endpoint,
-                    headers=headers_api_chat_combined,
-                    json=payload_api_chat,
-                    proxy=proxy
-                ) as response_api_chat:
-                    response_api_chat.raise_for_status()
-                    text = await response_api_chat.text()
-                    logger.debug(f"Raw response from Blackbox API: {text}")  # Log raw response
-                    cleaned_response = cls.clean_response(text)
-                    logger.debug(f"Cleaned response: {cleaned_response}")  # Log cleaned response
-
-                    if model in cls.image_models:
-                        match = re.search(r'!\[.*?\]\((https?://[^\)]+)\)', cleaned_response)
-                        if match:
-                            image_url = match.group(1)
-                            image_response = ImageResponseModel(images=image_url, alt="Generated Image")
-                            yield image_response
-                        else:
-                            yield cleaned_response
-                    else:
-                        if websearch:
-                            match = re.search(r'\$~~~\$(.*?)\$~~~\$', cleaned_response, re.DOTALL)
-                            if match:
-                                source_part = match.group(1).strip()
-                                answer_part = cleaned_response[match.end():].strip()
-                                try:
-                                    sources = json.loads(source_part)
-                                    source_formatted = "**Source:**\n"
-                                    for item in sources:
-                                        title = item.get('title', 'No Title')
-                                        link = item.get('link', '#')
-                                        position = item.get('position', '')
-                                        source_formatted += f"{position}. [{title}]({link})\n"
-                                    final_response = f"{answer_part}\n\n{source_formatted}"
-                                except json.JSONDecodeError:
-                                    final_response = f"{answer_part}\n\nSource information is unavailable."
-                            else:
-                                final_response = cleaned_response
-                        else:
-                            if '$~~~$' in cleaned_response:
-                                final_response = cleaned_response.split('$~~~$')[0].strip()
-                            else:
-                                final_response = cleaned_response
-
-                        yield final_response
-            except ClientResponseError as e:
-                error_text = f"Error {e.status}: {e.message}"
-                try:
-                    error_response = await e.response.text()
-                    cleaned_error = cls.clean_response(error_response)
-                    error_text += f" - {cleaned_error}"
-                    logger.error(f"Blackbox API ClientResponseError: {error_text}")
-                except Exception:
-                    pass
-                yield error_text
-            except Exception as e:
-                yield f"Unexpected error during /api/chat request: {str(e)}"
+        Periodically cleans up stale entries in the rate_limit_store to prevent memory bloat.
+        """
+        while True:
+            current_time = time.time()
+            ips_to_delete = [ip for ip, value in rate_limit_store.items() if current_time - value["timestamp"] > RATE_LIMIT_WINDOW * 2]
+            for ip in ips_to_delete:
+                del rate_limit_store[ip]
+                logger.debug(f"Cleaned up rate_limit_store for IP: {ip}")
+            await asyncio.sleep(CLEANUP_INTERVAL)
+
+    async def rate_limiter_per_ip(request: Request):
+        """
+        Rate limiter that enforces a limit based on the client's IP address.
+        """
+        client_ip = request.client.host
+        current_time = time.time()
 
-            chat_url = f'{cls.url}/chat/{chat_id}?model={model}'
+        # Initialize or update the count and timestamp
+        if current_time - rate_limit_store[client_ip]["timestamp"] > RATE_LIMIT_WINDOW:
+            rate_limit_store[client_ip] = {"count": 1, "timestamp": current_time}
+        else:
+            if rate_limit_store[client_ip]["count"] >= RATE_LIMIT:
+                logger.warning(f"Rate limit exceeded for IP address: {client_ip}")
+                raise HTTPException(status_code=429, detail='Rate limit exceeded for IP address | NiansuhAI')
+            rate_limit_store[client_ip]["count"] += 1
 
-            try:
-                async with session.post(
-                    chat_url,
-                    headers=headers_chat_combined,
-                    data=data_chat,
-                    proxy=proxy
-                ) as response_chat:
-                    response_chat.raise_for_status()
-                    pass
-            except ClientResponseError as e:
-                error_text = f"Error {e.status}: {e.message}"
-                try:
-                    error_response = await e.response.text()
-                    cleaned_error = cls.clean_response(error_response)
-                    error_text += f" - {cleaned_error}"
-                    logger.error(f"Blackbox API ClientResponseError during chat URL request: {error_text}")
-                except Exception:
-                    pass
-                yield error_text
-            except Exception as e:
-                yield f"Unexpected error during /chat/{chat_id} request: {str(e)}"
+    async def get_api_key(request: Request, authorization: str = Header(None)) -> str:
+        """
+        Dependency to extract and validate the API key from the Authorization header.
+        """
+        client_ip = request.client.host
+        if authorization is None or not authorization.startswith('Bearer '):
+            logger.warning(f"Invalid or missing authorization header from IP: {client_ip}")
+            raise HTTPException(status_code=401, detail='Invalid authorization header format')
+        api_key = authorization[7:]
+        if api_key not in API_KEYS:
+            logger.warning(f"Invalid API key attempted: {api_key} from IP: {client_ip}")
+            raise HTTPException(status_code=401, detail='Invalid API key')
+        return api_key
+
+    # =====================================
+    # 9. Define FastAPI Event Handlers
+    # =====================================
+    @app.on_event("startup")
+    async def startup_event():
+        asyncio.create_task(cleanup_rate_limit_stores())
+        logger.info("Started rate limit store cleanup task.")
+
+    # ==========================================
+    # 10. Define FastAPI Endpoints
+    # ==========================================
+    @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)):
+        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}")
 
-# ============================
-# 7. Initialize FastAPI App
-# ============================
-app = FastAPI()
+        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.generate_response(
+                model=request.model,
+                messages=[{"role": msg.role, "content": msg.content} for msg in request.messages],
+                temperature=request.temperature,
+                max_tokens=request.max_tokens
+            )
 
-# ====================================
-# 8. Define Middleware and Dependencies
-# ====================================
-@app.middleware("http")
-async def security_middleware(request: Request, call_next):
-    client_ip = request.client.host
-    # Enforce that POST requests to /v1/chat/completions must have Content-Type: application/json
-    if request.method == "POST" and request.url.path == "/v1/chat/completions":
-        content_type = request.headers.get("Content-Type")
-        if content_type != "application/json":
-            logger.warning(f"Invalid Content-Type from IP: {client_ip} for path: {request.url.path}")
-            return JSONResponse(
-                status_code=400,
-                content={
-                    "error": {
-                        "message": "Content-Type must be application/json",
-                        "type": "invalid_request_error",
-                        "param": None,
-                        "code": None
+            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": [
+                    {
+                        "index": 0,
+                        "message": {
+                            "role": "assistant",
+                            "content": response_content
+                        },
+                        "finish_reason": "stop"
                     }
+                ],
+                "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())
                 },
-            )
-    response = await call_next(request)
-    return response
-
-async def cleanup_rate_limit_stores():
-    """
-    Periodically cleans up stale entries in the rate_limit_store to prevent memory bloat.
-    """
-    while True:
-        current_time = time.time()
-        ips_to_delete = [ip for ip, value in rate_limit_store.items() if current_time - value["timestamp"] > RATE_LIMIT_WINDOW * 2]
-        for ip in ips_to_delete:
-            del rate_limit_store[ip]
-            logger.debug(f"Cleaned up rate_limit_store for IP: {ip}")
-        await asyncio.sleep(CLEANUP_INTERVAL)
-
-async def rate_limiter_per_ip(request: Request):
-    """
-    Rate limiter that enforces a limit based on the client's IP address.
-    """
-    client_ip = request.client.host
-    current_time = time.time()
-
-    # Initialize or update the count and timestamp
-    if current_time - rate_limit_store[client_ip]["timestamp"] > RATE_LIMIT_WINDOW:
-        rate_limit_store[client_ip] = {"count": 1, "timestamp": current_time}
-    else:
-        if rate_limit_store[client_ip]["count"] >= RATE_LIMIT:
-            logger.warning(f"Rate limit exceeded for IP address: {client_ip}")
-            raise HTTPException(status_code=429, detail='Rate limit exceeded for IP address | NiansuhAI')
-        rate_limit_store[client_ip]["count"] += 1
-
-async def get_api_key(request: Request, authorization: str = Header(None)) -> str:
-    """
-    Dependency to extract and validate the API key from the Authorization header.
-    """
-    client_ip = request.client.host
-    if authorization is None or not authorization.startswith('Bearer '):
-        logger.warning(f"Invalid or missing authorization header from IP: {client_ip}")
-        raise HTTPException(status_code=401, detail='Invalid authorization header format')
-    api_key = authorization[7:]
-    if api_key not in API_KEYS:
-        logger.warning(f"Invalid API key attempted: {api_key} from IP: {client_ip}")
-        raise HTTPException(status_code=401, detail='Invalid API key')
-    return api_key
-
-# =====================================
-# 9. Define FastAPI Event Handlers
-# =====================================
-@app.on_event("startup")
-async def startup_event():
-    asyncio.create_task(cleanup_rate_limit_stores())
-    logger.info("Started rate limit store cleanup task.")
-
-# ==========================================
-# 10. Define FastAPI Endpoints
-# ==========================================
-@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)):
-    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.generate_response(
-            model=request.model,
-            messages=[{"role": msg.role, "content": msg.content} for msg in request.messages],
-            temperature=request.temperature,
-            max_tokens=request.max_tokens
-        )
-
-        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": [
-                {
-                    "index": 0,
-                    "message": {
-                        "role": "assistant",
-                        "content": response_content
-                    },
-                    "finish_reason": "stop"
+            }
+        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))
+
+    @app.get("/v1/models", dependencies=[Depends(rate_limiter_per_ip)])
+    async def get_models(req: Request):
+        client_ip = req.client.host
+        logger.info(f"Fetching available models from IP: {client_ip}")
+        return {"data": [{"id": model, "object": "model"} for model in Blackbox.models]}
+
+    @app.get("/v1/health", dependencies=[Depends(rate_limiter_per_ip)])
+    async def health_check(req: Request):
+        client_ip = req.client.host
+        logger.info(f"Health check requested from IP: {client_ip}")
+        return {"status": "ok"}
+
+    # ========================================
+    # 11. Define Custom Exception Handler
+    # ========================================
+    @app.exception_handler(HTTPException)
+    async def http_exception_handler(request: Request, exc: HTTPException):
+        client_ip = request.client.host
+        logger.error(f"HTTPException: {exc.detail} | Path: {request.url.path} | IP: {client_ip}")
+        return JSONResponse(
+            status_code=exc.status_code,
+            content={
+                "error": {
+                    "message": exc.detail,
+                    "type": "invalid_request_error",
+                    "param": None,
+                    "code": None
                 }
-            ],
-            "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())
             },
-        }
-    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))
-
-@app.get("/v1/models", dependencies=[Depends(rate_limiter_per_ip)])
-async def get_models(req: Request):
-    client_ip = req.client.host
-    logger.info(f"Fetching available models from IP: {client_ip}")
-    return {"data": [{"id": model, "object": "model"} for model in Blackbox.models]}
-
-@app.get("/v1/health", dependencies=[Depends(rate_limiter_per_ip)])
-async def health_check(req: Request):
-    client_ip = req.client.host
-    logger.info(f"Health check requested from IP: {client_ip}")
-    return {"status": "ok"}
+        )
 
-# ===============================
-# 11. Define Custom Exception Handler
-# ===============================
-@app.exception_handler(HTTPException)
-async def http_exception_handler(request: Request, exc: HTTPException):
-    client_ip = request.client.host
-    logger.error(f"HTTPException: {exc.detail} | Path: {request.url.path} | IP: {client_ip}")
-    return JSONResponse(
-        status_code=exc.status_code,
-        content={
-            "error": {
-                "message": exc.detail,
-                "type": "invalid_request_error",
-                "param": None,
-                "code": None
-            }
-        },
-    )
+    # ============================
+    # 12. Optional: Streaming Endpoint
+    # ============================
+    @app.post("/v1/chat/completions/stream", dependencies=[Depends(rate_limiter_per_ip)])
+    async def chat_completions_stream(request: ChatRequest, req: Request, api_key: str = Depends(get_api_key)):
+        client_ip = req.client.host
+        # Redact user messages only for logging purposes
+        redacted_messages = [{"role": msg.role, "content": "[redacted]"} for msg in request.messages]
 
-# ============================
-# 12. Optional: Streaming Endpoint
-# ============================
-@app.post("/v1/chat/completions/stream", dependencies=[Depends(rate_limiter_per_ip)])
-async def chat_completions_stream(request: ChatRequest, req: Request, api_key: str = Depends(get_api_key)):
-    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 streaming 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.")
-
-        # Create an asynchronous generator for the response
-        async_generator = Blackbox.create_async_generator(
-            model=request.model,
-            messages=[{"role": msg.role, "content": msg.content} for msg in request.messages],
-            temperature=request.temperature,
-            max_tokens=request.max_tokens
-        )
+        logger.info(f"Received streaming 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.")
+
+            # Create an asynchronous generator for the response
+            async_generator = Blackbox.create_async_generator(
+                model=request.model,
+                messages=[{"role": msg.role, "content": msg.content} for msg in request.messages],
+                temperature=request.temperature,
+                max_tokens=request.max_tokens
+            )
 
-        logger.info(f"Started streaming response for API key: {api_key} | IP: {client_ip}")
-        return StreamingResponse(async_generator, media_type="text/event-stream")
-    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 streaming chat completions request from IP: {client_ip}.")
-        raise HTTPException(status_code=500, detail=str(e))
-
-# ========================================
-# 13. Run the Application with Uvicorn
-# ========================================
-if __name__ == "__main__":
-    import uvicorn
-    uvicorn.run(app, host="0.0.0.0", port=8000)
+            logger.info(f"Started streaming response for API key: {api_key} | IP: {client_ip}")
+            return StreamingResponse(async_generator, media_type="text/event-stream")
+        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 streaming chat completions request from IP: {client_ip}.")
+            raise HTTPException(status_code=500, detail=str(e))
+
+    # ========================================
+    # 13. Run the Application with Uvicorn
+    # ========================================
+    if __name__ == "__main__":
+        import uvicorn
+        uvicorn.run(app, host="0.0.0.0", port=8000)