feat: support local ai embedding, local ai search, local document content search#7839
Merged
feat: support local ai embedding, local ai search, local document content search#7839
Conversation
Contributor
Reviewer's Guide by SourceryThis pull request introduces local embedding generation and storage using Ollama and a SQLite-based vector database. The implementation includes setting up a new vector database, integrating Ollama for embedding generation, creating an asynchronous scheduler to process content for embedding, and updating the core application flow to trigger indexing for supported collaboration objects like documents. No diagrams generated as the changes look simple and do not need a visual representation. File-Level Changes
Tips and commandsInteracting with Sourcery
Customizing Your ExperienceAccess your dashboard to:
Getting Help
|
Contributor
There was a problem hiding this comment.
Hey @appflowy - I've reviewed your changes - here's some feedback:
Overall Comments:
- The migration down script
migrations/.../down.sqlappears to contain unresolved merge conflict markers. - Consider moving unrelated refactorings (e.g., filter logic, sorting signatures, AST changes) to separate PRs to focus this one on embeddings.
- The extensive conditional compilation for the desktop-only embedding feature significantly increases complexity across multiple crates.
Here's what I looked at during the review
- 🟡 General issues: 1 issue found
- 🟢 Security: all looks good
- 🟡 Testing: 2 issues found
- 🟡 Complexity: 2 issues found
- 🟢 Documentation: all looks good
Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
• Remove the obsolete Supabase test that’s no longer used.
• Add support for generating and using local embeddings.
• Introduce local AI-powered search functionality.
• Enable full-text search over document content (previously we only indexed files that existed on disk).
• Refactor folder-view search so that each workspace maintains its own Tantivy index directory.
• Reindex a document automatically whenever its content hash changes.
• Add end-to-end integration tests to verify search functionality.