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

Ensure consistent float type for cached embedding return values #10185

Merged

Conversation

kazuya-awano
Copy link
Contributor

@kazuya-awano kazuya-awano commented Nov 1, 2024

Checklist:

Important

Please review the checklist below before submitting your pull request.

  • Please open an issue before creating a PR or link to an existing issue
  • I have performed a self-review of my own code
  • I have commented my code, particularly in hard-to-understand areas
  • I ran dev/reformat(backend) and cd web && npx lint-staged(frontend) to appease the lint gods

Description

This PR ensures that the return values of embeddings retrieved from the cache are consistently in float type. This change prevents potential issues caused by type mismatches (float vs float64) during serialization, especially when using Chroma as the vector database.

Fixes #7213

Type of Change

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to not work as expected)
  • This change requires a documentation update, included: Dify Document
  • Improvement, including but not limited to code refactoring, performance optimization, and UI/UX improvement
  • Dependency upgrade

Testing Instructions

  • Test
    • Set up Chroma as the vector database
    • Run a Retrieval Testing
      • Results are retrieved successfully.
    • Run the same search again
      • Before Fix: Prior to this fix, running the search twice would result in an error: Type is not JSON serializable: numpy.float64.
      • After Fix: After applying this fix, the same search should succeed without errors, and the results should be retrieved consistently.

@dosubot dosubot bot added size:XS This PR changes 0-9 lines, ignoring generated files. 🐞 bug Something isn't working labels Nov 1, 2024
@crazywoola crazywoola requested a review from JohnJyong November 2, 2024 11:46
@dosubot dosubot bot added the lgtm This PR has been approved by a maintainer label Nov 29, 2024
@crazywoola crazywoola merged commit 2d6865d into langgenius:main Nov 29, 2024
6 checks passed
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:XS This PR changes 0-9 lines, ignoring generated files.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

The value of embedding is stored in Redis, and when it is retrieved, it becomes float64.
2 participants