I use httpx to make request to my LLM. Here is the code. import httpx import logging import json from httpx import TimeoutException try: content = '' logging.info(f"request payload:{payload}") async with httpx.AsyncClient(timeout=LLM_TIMEOUT) as client: async with client.stream("POST", MODEL_URL, headers=HEADERS, json=payload, timeout=LLM_TIMEOUT) as response: if response.status_code != 200: ans = await response.aread() logging.error(f"response.aread() error") raise Exception(f"Failed to generate completion stream: {ans}") async for line in response.aiter_lines(): if line.startswith("data:"): data_str = line[5:] if data_str.strip() == "[DONE]": break try: chunk_data = json.loads(data_str) if chunk_data['choices']: content += chunk_data["choices"][0]["delta"].get("content") except json.JSONDecodeError: logging.error("json parse error:", data_str) logging.info(f"request response:{content}") except TimeoutException as te: logging.warning("request timeout") Here the LLM_TIMEOUT is 60. However, I can see from my log that there exists some requests that costs more than 60 seconds. Anyone can help me solve this? Thanks in advance. Continue reading...