refactor: improve semantic embeddings performance #514
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
deathbeam
force-pushed
the
improve-embeddings
branch
from
65a0b39 to
14d4ce3
Compare
Previously the semantic embeddings were using older model and not using the query in most optimal way. Now it is using text-embedding-3-small model for reduced cost and better performance, embeddings are stored in 512 dimensions and the embedding process was refactored to be more straightforward and use less API calls by including the query in the initial embedding call. Also slightly improves the formatting of the embedding prompt to be more readable. Signed-off-by: Tomas Slusny <slusnucky@gmail.com>
deathbeam
force-pushed
the
improve-embeddings
branch
from
14d4ce3 to
de08a03
Compare
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Outdated suggestions cannot be applied.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.
Previously the semantic embeddings were using older model and not using the query in most optimal way. Now it is using text-embedding-3-small model for reduced cost and better performance, embeddings are stored in 512 dimensions and the embedding process was refactored to be more straightforward and use less API calls by including the query in the initial embedding call.
Also slightly improves the formatting of the embedding prompt to be more readable.