yusufhilmi/client-vector-search

A client side vector search library that can embed, store, search, and cache vectors. Works on the browser and node. It outperforms OpenAI's text-embedding-ada-002 and is way faster than Pinecone and other VectorDBs.

54
/ 100
Established

Leverages the Xenova transformers library (gte-small model) for client-side embeddings without server dependencies, and performs vector search via cosine similarity with optional persistence to IndexedDB for caching. Supports both browser and Node.js environments with a straightforward API for indexing, CRUD operations, and similarity search across hundreds to thousands of vectors. Designed for sub-100ms performance on typical use cases with planned HNSW indexing for improved scalability.

229 stars and 2,270 monthly downloads. No commits in the last 6 months. Available on npm.

Stale 6m
Maintenance 0 / 25
Adoption 18 / 25
Maturity 25 / 25
Community 11 / 25

How are scores calculated?

Stars

229

Forks

15

Language

TypeScript

License

MIT

Last pushed

May 29, 2024

Monthly downloads

2,270

Commits (30d)

0

Dependencies

3

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/yusufhilmi/client-vector-search"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.