8000 [Feature Request]: Hope to add rerank models to the project · Issue #724 · infiniflow/ragflow · GitHub
[go: up one dir, main page]

Skip to content

[Feature Request]: Hope to add rerank models to the project #724

Closed

Description

@xxxl123

Is there an existing issue for the same feature request?

  • I have checked the existing issues.

Is your feature request related to a problem?

No response

Describe the feature you'd like

I think RAG+re-rank is a great combination that can improve recall accuracy.

Describe implementation you've considered

No response

Documentation, adoption, use case

No response

Additional information

No response

Activity

  1. Nuclear6 commented on May 13, 2024

    @Nuclear6

    I see that there is a rerank module in the project architecture diagram. Does the module they provide fail to meet the requirements? Or some other problem?
    image
    image

  2. xxxl123 commented on May 13, 2024

    @xxxl123
    Author

    I see that there is a rerank module in the project architecture diagram. Does the module they provide fail to meet the requirements? Or some other problem? image image

    I asked the developers, and they haven't added the rerank model yet.

  3. Nuclear6 commented on May 13, 2024

    @Nuclear6

    What you mean is that the rerank here is only based on some strategies to achieve the effect of rerank, and does not involve reranking LLM, right?

  4. xxxl123 commented on May 13, 2024

    @xxxl123
    Author

    image
    There should be a rearranging strategy, but the rerank model was not used.

  5. Nuclear6 commented on May 13, 2024

    @Nuclear6

    So I have a question, what rerank models are available here? Have you ever compared the results?

  6. KevinHuSh commented on May 13, 2024

    @KevinHuSh
    Contributor

    Weighted keywords and embedding similarity is RAGFlow's reranking model right now.
    And we're working on replacing the embedding similarity with other so called rerank models like BGE reranker and others.

  7. added
    💞 featureFeature request, pull request that fullfill a new feature.
    on May 13, 2024
  8. xxxl123 commented on May 13, 2024

    @xxxl123
    Author

    I think the accuracy of the recall is already very accurate now, and I hope it can be further improved. It shouldn't be worse after adding it.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    💞 featureFeature request, pull request that fullfill a new feature.

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions

      0