feat: retrieve embeddings from database only when necessary#119
Open
Fangyi Zhou (fangyi-zhou) wants to merge 2 commits intolangchain-ai:mainfrom
Open
feat: retrieve embeddings from database only when necessary#119Fangyi Zhou (fangyi-zhou) wants to merge 2 commits intolangchain-ai:mainfrom
Fangyi Zhou (fangyi-zhou) wants to merge 2 commits intolangchain-ai:mainfrom
Conversation
Fangyi Zhou (fangyi-zhou)
force-pushed
the
select-columns-to-query
branch
from
3faed2b to
c1f5956
Compare
Fangyi Zhou (fangyi-zhou)
changed the title
Fangyi Zhou (fangyi-zhou)
force-pushed
the
select-columns-to-query
branch
from
c1f5956 to
712a40c
Compare
Author
|
Hello can I get a review of this PR? Eugene Yurtsev (@eyurtsev) |
Collaborator
|
Looks reasonable could you add unit tests? |
Author
|
I'm not sure how to add unit test for this performance patch, any ideas? |
When performing a similarity search without using maximal marginal relevance, the database query includes the embeddings by default, whereas the retrived embeddings are discarded without use. This can be very suboptimal when retrieve a large number of documents due to communication overhead.
Fangyi Zhou (fangyi-zhou)
force-pushed
the
select-columns-to-query
branch
from
712a40c to
cc40106
Compare
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
When performing a similarity search without using maximal marginal relevance, the database query includes the embeddings by default, whereas the retrived embeddings are discarded without use.
This can be very suboptimal when retrieve a large number of documents due to communication overhead.