Skip to content

Add local embeddings for semantic search #1

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.

Sign up for GitHub

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

Jump to bottom
Merged
ojowwalker77 merged 1 commit into from
Jan 11, 2026
Merged

Add local embeddings for semantic search #1

ojowwalker77 merged 1 commit into from
Jan 11, 2026

Conversation

@ojowwalker77
Copy link
Owner

@ojowwalker77 ojowwalker77 commented Jan 11, 2026 •
edited
Loading

Summary

  • Add semantic search using local AI embeddings (no API keys needed)
  • Uses @xenova/transformers with all-MiniLM-L6-v2 model (384-dimensional vectors)
  • Store embeddings as BLOB in SQLite with auto-migration for existing databases
  • Model downloads once (~23MB) to ~/.get-papers/models/

New API

// Embed papers
yield* engine.embed("paper-id")
yield* engine.embedAll(100)

// Semantic search
yield* engine.similar("machine learning for climate")
yield* engine.similarTo("paper-id")

@ojowwalker77
Add local embeddings for semantic search
461bceb 
- Add @xenova/transformers with all-MiniLM-L6-v2 model (384-dim vectors)
- Store embeddings as BLOB in SQLite, auto-migrate existing DBs
- New engine methods: embed, embedAll, similar, similarTo
- Pure Effect.js API with EmbeddingError type
- Model downloads on first use (~23MB) to ~/.get-papers/models/
@ojowwalker77 ojowwalker77 merged commit f4f0623 into main Jan 11, 2026
2 checks passed
@ojowwalker77 ojowwalker77 deleted the add-local-embeddings branch January 11, 2026 10:46
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@ojowwalker77