jbarrow / tinyhnswLinks
build your own vector database -- the littlest hnsw
☆64Updated 9 months ago
Alternatives and similar repositories for tinyhnsw
Users that are interested in tinyhnsw are comparing it to the libraries listed below
Sorting:
- Official Rust Implementation of Model2Vec☆138Updated last week
- Extremely memory-efficient vector database☆75Updated last year
- Embeddable library or single binary for indexing and searching 1B vectors☆305Updated 3 months ago
- Generate BM25 sparse vector inside PostgreSQL☆87Updated 11 months ago
- Heirarchical Navigable Small Worlds☆101Updated 2 months ago
- XTR/WARP (SIGIR'25) is an extremely fast and accurate retrieval engine based on Stanford's ColBERTv2/PLAID and Google DeepMind's XTR.☆166Updated 5 months ago
- HNSW tutorial☆151Updated last year
- High-performance MinHash implementation in Rust with Python bindings for efficient similarity estimation and deduplication of large datas…☆204Updated last week
- Extracts structured data from unstructured input. Programming language agnostic. Uses llama.cpp☆44Updated last year
- ☆60Updated 6 months ago
- Vector Database with support for late interaction and token level embeddings.☆55Updated 3 months ago
- ☆61Updated last year
- ☆163Updated last year
- A GPU Accelerated Binary Vector Store☆47Updated 7 months ago
- Efficient vector database for hundred millions of embeddings.☆207Updated last year
- Lightweight Nearest Neighbors with Flexible Backends☆308Updated last week
- Rust framework for LLM orchestration☆203Updated last year
- Rust implementation of Surya☆60Updated 7 months ago
- Radient turns many data types (not just text) into vectors for similarity search, RAG, regression analysis, and more.☆280Updated last month
- Tree-based indexes for neural-search☆32Updated last year
- Pivotal Token Search☆127Updated 2 months ago
- ☆440Updated last month
- open source tooling for AI search and understanding☆51Updated 2 years ago
- Baguetter is a flexible, efficient, and hackable search engine library implemented in Python. It's designed for quickly benchmarking, imp…☆189Updated last year
- Fast, SQL powered, in-process vector search for any language with an SQLite driver☆322Updated 11 months ago
- Multi-model transactional embedded database☆68Updated 10 months ago
- Official Python API client library for turbopuffer☆78Updated this week
- Build data processing and data analysis pipelines that leverage the power of LLMs 🧠☆226Updated this week
- TensorRT-LLM server with Structured Outputs (JSON) built with Rust☆59Updated 5 months ago
- Data Encoding and Representation Analysis☆40Updated last year