{"library":"hnswsqlite","type":"library","category":null,"description":"A TypeScript library that combines HNSWlib approximate nearest neighbor vector search with SQLite persistence for lightweight semantic search. Current stable version is 0.2.1, released on [approx date]. It supports multiple embedding providers (OpenAI, HuggingFace, WebLLM, MediaPipe, TensorFlow.js) and provides a CLI tool. Key differentiators: no external dependencies beyond SQLite and HNSWlib, TypeScript-first with full type declarations, batch operations, and a plugin system for embedding generation. Suitable for building semantic search and recommendation systems.","language":"javascript","status":"active","version":"0.2.1","tags":["javascript","vector","search","sqlite","hnswlib","typescript","semantic","embeddings"],"last_verified":"Sun Jun 07","install":[{"cmd":"npm install hnswsqlite","imports":["import { VectorStore } from 'hnswsqlite'","import { OpenAIEmbedder } from 'hnswsqlite/plugins/openai'","import VectorStore from 'hnswsqlite'","import type { EmbeddingPlugin } from 'hnswsqlite'"]},{"cmd":"yarn add hnswsqlite","imports":[]},{"cmd":"pnpm add hnswsqlite","imports":[]}],"homepage":"https://github.com/praveencs87/hnswsqlite#readme","github":"https://github.com/praveencs87/hnswsqlite","docs":null,"changelog":null,"pypi":null,"npm":"hnswsqlite","openapi_spec":null,"status_page":null,"smithery":null,"compatibility":null}