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.
☆177Updated 7 months ago
Alternatives and similar repositories for client-vector-search:
Users that are interested in client-vector-search are comparing it to the libraries listed below
- ☆136Updated this week
- SemanticFinder - frontend-only live semantic search with transformers.js☆247Updated 3 weeks ago
- Library to generate vector embeddings in NodeJS☆96Updated 2 months ago
- JavaScript implementation of LiteLLM.☆103Updated last year
- Web-optimized vector database (written in Rust).☆198Updated this week
- Fully typed & consistent chat APIs for OpenAI, Anthropic, Groq, and Azure's chat models for browser, edge, and node environments.☆156Updated 7 months ago
- A simple vector database built on idb☆74Updated last year
- Vector Storage is a vector database that enables semantic similarity searches on text documents in the browser's local storage. It uses O…☆209Updated last month
- LLM tools used in production at Dexa☆87Updated last week
- AI functions for Typescript☆79Updated last year
- Full in-browser Semantic Search with Huggingface Transformers.js and ElectricSQL's PGlite!☆94Updated 5 months ago
- A Markdown-like syntax for writing prompts. Includes an in-editor playground.☆106Updated last year
- rerank library for easy reranking of results☆34Updated 4 months ago
- hnswlib-node provides Node.js bindings for Hnswlib☆106Updated this week
- OpenAI Whisper API based on Node.js / Bun.sh in a Docker Container + Google Cloud Run Example☆111Updated last year
- Turn a stream of token into a parsable JSON object as soon as possible. Enable Streaming UI for AI app based on LLM.☆93Updated 7 months ago
- Safely deploy OpenAI's Realtime APIs in less than 5 minutes!☆153Updated 3 months ago
- TypeScript generator for llama.cpp Grammar directly from TypeScript interfaces☆131Updated 6 months ago
- A blazing-fast semantic search React component. Match by meaning, not just by letters. Search as you type without waiting (no debounce ne…☆212Updated 4 months ago
- Vectra is a local vector database for Node.js with features similar to pinecone but built using local files.☆425Updated 2 months ago
- Smithery connects language models to Model Context Protocols, allowing you to build agents that use resources and tools without being ove…☆40Updated this week
- ☆139Updated last year
- Framework to evaluate LLM generated ReactJS code.☆53Updated 9 months ago
- A UI library to animate and style streaming LLM output☆118Updated 3 weeks ago
- WebAssembly (Wasm) Build and Bindings for llama.cpp☆225Updated 5 months ago
- Vercel and web-llm template to run wasm models directly in the browser.☆133Updated last year
- Node.js bindings for faiss☆117Updated last year
- A relay server for OpenAI's realtime API, for Cloudflare Workers☆121Updated 2 months ago
- A JavaScript implementation of Llama 3 using node-mlx.☆70Updated 6 months ago
- ☆166Updated last year