Similarity Search Python Packages

lancedb

Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.

chonkie

🦛 CHONK docs with Chonkie ✨ — The lightweight ingestion library for fast, efficient and robust RAG pipelines

usearch

Fast Open-Source Search & Clustering engine × for Vectors & Arbitrary Objects × in C++, C, Python, JavaScript, Rust, Java, Objective-C, Swift, C#, GoLang, and Wolfram 🔍

gptcache

Semantic cache for LLMs. Fully integrated with LangChain and llama_index.

libcuvs-cu12

cuVS - a library for vector search and clustering on the GPU

cuvs-cu12

cuVS - a library for vector search and clustering on the GPU

zvec

A lightweight, lightning-fast, in-process vector database

libcuvs-cu13

cuVS - a library for vector search and clustering on the GPU

qann

Quantized Nearest Neighbors is a C++ vector search with Python bindings

elastiknn-client

Elasticsearch plugin for nearest neighbor search. Store vectors and run similarity search using exact and approximate algorithms.

cuvs-cu13

cuVS - a library for vector search and clustering on the GPU

fastembed-vectorstore

In-memory vector store with FastEmbed integration for Python applications.

fpsim2

Simple package for fast molecular similarity searches

wickra-genome

A vector database of the whole market: every asset as a live vector over the 497 O(1) streaming indicators the registry resolves. Similarity search, clustering, anomaly detection over microstructure DNA.

wickra-shazam

Shazam for markets — match an asset's current 514-dim microstructure fingerprint against its entire history to name the regime ("that's the May-2021 crash setup"), over the Wickra core, in ten languages.

lynsedb

Embedded-first vector database that grows into a self-hosted service and lightweight cluster.

torchdr

TorchDR - PyTorch Dimensionality Reduction

scann-core

ScaNN vector similarity search as a standalone library: fast approximate nearest-neighbor search for C++, Python and Rust, no TensorFlow needed. AVX2/AVX-512 and Arm Neon/SVE kernels, free-threaded Python, optional PyTorch and TensorFlow integration. Not an official Google product.

setsimilaritysearch

All-pair set similarity search on millions of sets in Python and on a laptop

oasysdb

In-memory vector store with efficient read and write performance for semantic caching and retrieval system. Redis for Semantic Caching.

usearch-iscc

Fast Open-Source Search & Clustering engine × for Vectors & Arbitrary Objects × in C++, C, Python, JavaScript, Rust, Java, Objective-C, Swift, C#, GoLang, and Wolfram 🔍

pynear

A python library for efficient KNN search within metric spaces using multiple distance functions.

relate-search

Code similarity search by compression - find near-duplicate files, clone families, and where a pasted snippet came from. No embeddings, no model, no vector database.

tfsim-nightly

TensorFlow Similarity is a python package focused on making similarity learning quick and easy.