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.

Sign up for GitHub

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

Jump to bottom

Add support for latest txtai indexing options #61

Closed
davidmezzetti opened this issue Dec 15, 2022 · 0 comments
Closed

Add support for latest txtai indexing options #61

davidmezzetti opened this issue Dec 15, 2022 · 0 comments
Assignees
@davidmezzetti
Milestone
v2.1.0

Comments

@davidmezzetti
Copy link
Member

Make the following improvements to better integrate with the latest txtai indexing options.

  • Only tokenize text if scoring is set. Transformers models don't need text tokenization and it can hurt performance.
  • Only filter sections when indexing if scoring is set. This isn't necessary for Transformers models.
  • Check the return type from embeddings.search and handle both dict content=true and tuple content=false return types.
@davidmezzetti davidmezzetti added this to the v2.1.0 milestone Dec 15, 2022
@davidmezzetti davidmezzetti self-assigned this Dec 15, 2022
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@davidmezzetti davidmezzetti

Labels
None yet
Projects
None yet
Milestone
v2.1.0
Development

No branches or pull requests
1 participant
@davidmezzetti