Skip to content
Discussion options

You must be logged in to vote

Hi There! It's not suggested to use the bge-large-zh-v1.5 as embedding model, because it can only handle 512 tokens in one text chunk. Could you try another embedding model (like jina-embedding-v3, bge-m3, text-embedding-v3)? If the problem presists, could you share the logs in container data-process?

Replies: 1 comment

Comment options

You must be logged in to vote
0 replies
Answer selected by Phinease
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
None yet
2 participants