fix: embedding search for non-openai models #660
Merged
Conversation
This file contains 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Relates to:
Embedding search was broken when not using OpenAI models because our default zero embeddings are length 1536 (which is the length generated from remote embedding processing), but our locally generated embeddings are of length 384.
Risks
Low
Background
What does this PR do?
Fixes the embedding mismatch issue by generating a zero embedding vector based on the given model being used.
What kind of change is this?
Bug fix
Documentation changes needed?
My changes require a change to the project documentation.
Testing
Where should a reviewer start?
Run locally against OpenAI model and non-openai models
Detailed testing steps