Switch to BGE-M3 embedding model with lazy loading #1
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
- Replace DefaultEmbeddingFunction with BGEM3EmbeddingFunction - Add lazy loading for embedding model to improve startup time - Update vector dimension from 768 to 1024 for BGE-M3 compatibility
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
Switch to BGE-M3 embedding model with lazy loading.
Why
I needed better French support for my documents. The default model is optimized for English and wasn't giving good results in French. BGE-M3 handles multilingual content much better.
I also added lazy loading because the model takes ~2 min to load, which was slowing down server startup.
What do you think about making the embedding model configurable in the future?
Breaking change
Vector dimension changed from 768 to 1024, so existing indexes need to be rebuilt.