Skip to content

Conversation

@khoroshevskyi
Copy link
Member

Changes:

  • Added sparse search vector
  • Improved embedded string information (more concise and most relevant information)
  • Updated CLI
  • Added embedding tracking (if indexing failed, it can be recovered later)
  • Improved speed
  • Improved code quality and simplisity
  • Added tests and cron job

return sparse_model


def get_dense_model(dense_model: str) -> Union[None, TextEmbedding]:
Copy link
Member

Choose a reason for hiding this comment

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

Option to use gpu if available? Could be useful. This is easy in SentenceTransformer less sure about fastembed

@nleroy917
Copy link
Member

Some comments but it does look good as is! Feel free to pick and choose what comments you want to address 😄

@khoroshevskyi khoroshevskyi merged commit 5bcf001 into master Dec 12, 2025
3 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants