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.

46
/ 100
Emerging

This library helps web and server-side developers embed, store, search, and cache text vectors directly within their applications, rather than relying on external vector databases. It takes text input, converts it into numerical embeddings, and allows for rapid similarity searches, returning the most relevant items. Developers building front-end or serverless applications who need fast, localized search capabilities would find this useful.

229 stars. No commits in the last 6 months. Available on npm.

Use this if you are a developer building an application that needs to perform fast, client-side or serverless semantic search on small to medium datasets (hundreds to thousands of items) without external database dependencies.

Not ideal if your application requires searching massive datasets (millions of vectors) or needs advanced vector database features like distributed indexing and real-time updates across multiple servers.

web-development application-development semantic-search client-side-processing serverless-architecture
Stale 6m
Maintenance 0 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 11 / 25

How are scores calculated?

Stars

229

Forks

15

Language

TypeScript

License

MIT

Last pushed

May 29, 2024

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.