Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fix: moves caching of vector store to LCModelComponent level #3435

Merged
merged 3 commits into from
Aug 21, 2024

Conversation

jordanrfrazier
Copy link
Collaborator

@jordanrfrazier jordanrfrazier commented Aug 19, 2024

Prevents multiple build_vector_store calls from embedding the input multiple times.

Closes #3376

@dosubot dosubot bot added the size:L This PR changes 100-499 lines, ignoring generated files. label Aug 19, 2024
Copy link
Contributor

Pull Request Validation Report

This comment is automatically generated by Conventional PR

Whitelist Report

Whitelist Active Result
Pull request is a draft and should be ignored
Pull request is made by a whitelisted user and should be ignored
Pull request is submitted by a bot and should be ignored
Pull request is submitted by administrators and should be ignored

Result

Pull request does not satisfy any enabled whitelist criteria. Pull request will be validated.

Validation Report

Validation Active Result
All commits in this pull request has valid messages
Pull request does not introduce too many changes
Pull request has a valid title
Pull request has mentioned issues
Pull request has valid branch name
Pull request should have a non-empty body

Result

Pull request satisfies all enabled pull request rules.

Last Modified at 19 Aug 24 19:44 UTC

@github-actions github-actions bot added the bug Something isn't working label Aug 19, 2024
Copy link

This pull request is automatically being deployed by Amplify Hosting (learn more).

Access this pull request here: https://pr-3435.dmtpw4p5recq1.amplifyapp.com

@github-actions github-actions bot added bug Something isn't working and removed bug Something isn't working labels Aug 19, 2024
Copy link
Contributor

@ogabrielluiz ogabrielluiz left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hey @jordanrfrazier

Very nice implementation.

Is this focused on making sure the document is never added more than once in a single build?

@jordanrfrazier
Copy link
Collaborator Author

Hey @jordanrfrazier

Very nice implementation.

Is this focused on making sure the document is never added more than once in a single build?

@ogabrielluiz that's correct, yes.

Though I also think we should give users the option to generate deterministic ID's from the content, but that can be implemented after.

@dosubot dosubot bot added the lgtm This PR has been approved by a maintainer label Aug 21, 2024
@jordanrfrazier jordanrfrazier merged commit 96ca71d into main Aug 21, 2024
28 checks passed
@jordanrfrazier jordanrfrazier deleted the cache-vector-stores branch August 21, 2024 21:38
anovazzi1 pushed a commit that referenced this pull request Aug 26, 2024
* refactor LCModelComponent to use a cached vector store to prevent multiple embeddings
ogabrielluiz pushed a commit that referenced this pull request Aug 27, 2024
* refactor LCModelComponent to use a cached vector store to prevent multiple embeddings
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working lgtm This PR has been approved by a maintainer size:L This PR changes 100-499 lines, ignoring generated files.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

One chuck record would be embedded 3 times and inserted 3 records in milvus db
2 participants