Skip to content

Support for Milvus Full Text Search in Dify #11370

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

Closed
5 tasks done
kgpp34 opened this issue Dec 5, 2024 · 1 comment · Fixed by #11430
Closed
5 tasks done

Support for Milvus Full Text Search in Dify #11370

kgpp34 opened this issue Dec 5, 2024 · 1 comment · Fixed by #11430
Labels
💪 enhancement New feature or request 👻 feat:rag Embedding related issue, like qdrant, weaviate, milvus, vector database. stale Issue has not had recent activity or appears to be solved. Stale issues will be automatically closed

Comments

@kgpp34
Copy link
Contributor

kgpp34 commented Dec 5, 2024

Self Checks

  • I have searched for existing issues search for existing issues, including closed ones.
  • I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
  • [FOR CHINESE USERS] 请务必使用英文提交 Issue,否则会被关闭。谢谢!:)
  • Please do not modify this template :) and fill in all the required fields.

1. Is this request related to a challenge you're experiencing? Tell me about your story.

Yes, currently Dify defaults to using Weaviate vector database. However, in China, many companies use Milvus. Before version 2.5.0-beta, we had to support BM25 ourselves. Now, Milvus 2.5.0 supports this algorithm, so we can use Milvus for hybrid search in Dify.

  • What is the feature you'd like to see?

I'd like to see Dify support the new text to sparse vector functionality provided by Milvus 2.5.0-beta and pymilvus2.5.0. When we insert a text field, Milvus should automatically execute text to sparse vector using a custom pymilvus Function.

  • How will this feature improve your workflow / experience?

This feature will bring full text search when the user uses Milvus vector database in Dify. It will promote and upgrade the
hybrid search ability, and it will increase robustness for Dify's RAG.

2. Additional context or comments

I'd like to see Dify support the new text to sparse vector functionality provided by Milvus 2.5.0-beta and pymilvus2.5.0. When we insert a text field, Milvus should automatically execute text to sparse vector using a custom pymilvus Function.

3. Can you help us with this feature?

  • I am interested in contributing to this feature.
@dosubot dosubot bot added 👻 feat:rag Embedding related issue, like qdrant, weaviate, milvus, vector database. 💪 enhancement New feature or request labels Dec 5, 2024
Copy link

dosubot bot commented Jan 5, 2025

Hi, @kgpp34. I'm Dosu, and I'm helping the Dify team manage their backlog. I'm marking this issue as stale.

Issue Summary:

  • You requested the integration of Milvus full-text search into Dify.
  • Milvus is noted for its widespread use in China as an alternative to Weaviate.
  • Milvus 2.5.0-beta supports the BM25 algorithm, which could enhance Dify's hybrid search.
  • You expressed interest in contributing to this feature's development.
  • No further comments or activities have been made on this issue.

Next Steps:

  • Please let us know if this issue is still relevant to the latest version of Dify by commenting here to keep the discussion open.
  • If there is no further activity, this issue will be automatically closed in 15 days.

Thank you for your understanding and contribution!

@dosubot dosubot bot added the stale Issue has not had recent activity or appears to be solved. Stale issues will be automatically closed label Jan 5, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
💪 enhancement New feature or request 👻 feat:rag Embedding related issue, like qdrant, weaviate, milvus, vector database. stale Issue has not had recent activity or appears to be solved. Stale issues will be automatically closed
Projects
None yet
Development

Successfully merging a pull request may close this issue.

1 participant