配置model_format为internlm_silicon，报错：Invalid token

[L-Chris]

配置为internlm_silicon，请求后端时报错invalid token，硅基的API key已配置

报错信息如下：

python -m mindsearch.app --lang cn --model_format internlm_silicon --search_engine DuckDuckGoSearch --asy
INFO:     Started server process [10608]
INFO:     Waiting for application startup.
INFO:     Application startup complete.
INFO:     Uvicorn running on http://0.0.0.0:8002 (Press CTRL+C to quit)
C:\Users\MI\.pyenv\pyenv-win\versions\3.10.0\lib\site-packages\lagent\llms\openai.py:513: DeprecationWarning: `top_k` parameter is deprecated in OpenAI APIs.
  warnings.warn('`top_k` parameter is deprecated in OpenAI APIs.',
C:\Users\MI\.pyenv\pyenv-win\versions\3.10.0\lib\site-packages\lagent\agents\stream.py:212: UserWarning: Neither plugin nor interpreter executor is initialized. An exception will be thrown when the agent call a tool.
  warnings.warn(
INFO:     127.0.0.1:63318 - "POST /solve HTTP/1.1" 200 OK
"Invalid token"

[cleven1]

@L-Chris 大佬解决了吗? 突然间我也报这个错误, 打log调试, 压根没走到请求API就报Invalid token

[L-Chris]

@cleven1 没有，用docker compose跑起来倒是通了，不过体验很差。。。比官方demo差远了，好奇官方demo用的什么搜索api

[monteraro]

似乎是代码有些问题，在key=os.environ.get("SILICON_API_KEY", "YOUR SILICON API KEY")这一行直接赋值后跑起来了