Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

Something went wrong. Please try again later. #1091

wangnanwy started this conversation in General
Discussion options

QQ截图20240823161258
I want to use the glm-4 model, but it doesn't work. The following prompt appears:
""
QQ截图20240823160905

You must be logged in to vote

Replies: 2 comments

Comment options

Hi I think I you case you have set api url to what looks like a openai compatable endpoint.
My suggestion would be:
Set LLLM_NAME=openai
Then inside application/llm/openai.py

self.client = OpenAI(
 api_key=api_key,
 base_url="http://open.bigmodel.cn/api/paas/v4", 
 )

Alse in your env variables set MODEL_NAME to glm-4

API_URL should point to docsgpt backend.
Configuration of LLM endpoint is separate

Hope this helps

You must be logged in to vote
0 replies
Comment options

已经收到您的来件!!
You must be logged in to vote
0 replies
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet

AltStyle によって変換されたページ (->オリジナル) /