Vector Search Python Packages

weaviate-client

A python native client for easy interaction with a Weaviate instance.

qdrant-client

Python client for Qdrant vector search engine

fastembed

Fast, Accurate, Lightweight Python library to make State of the Art Embedding

simsimd

SIMD-accelerated distances, dot products, matrix ops, geospatial & geometric kernels for 16 numeric types — from 6-bit floats to 64-bit complex — across x86, Arm, RISC-V, and WASM, with bindings for Python, Rust, C, C++, Swift, JS, and Go 📐

redisvl

Redis Vector Library (RedisVL) -- the AI-native Python client for Redis.

flashrank

Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cross-encoders and more. Created by Prithivi Da, open for PRs & Collaborations.

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.

numkong

SIMD-accelerated distances, dot products, matrix ops, geospatial & geometric kernels for 16 numeric types — from 6-bit floats to 64-bit complex — across x86, Arm, RISC-V, and WASM, with bindings for Python, Rust, C, C++, Swift, JS, and Go 📐

nucliadb-telemetry

NucliaDB, The AI Search database for RAG

pylibraft-cu12

RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing high performance applications.

libraft-cu12

RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing high performance applications.

onyx-devtools

Open Source AI Platform - AI Chat with advanced features that works with every LLM

fiftyone-db

Refine high-quality datasets and visual AI models

raft-dask-cu12

RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing high performance applications.

fiftyone

Refine high-quality datasets and visual AI models

cuvs-cu12

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

libcuvs-cu12

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

nucliadb-models

NucliaDB, The AI Search database for RAG

nucliadb-utils

NucliaDB, The AI Search database for RAG

nucliadb-sdk

NucliaDB, The AI Search database for RAG

nucliadb-protos

NucliaDB, The AI Search database for RAG

topk-sdk

High-quality search for AI-native applications.

turbovec

A vector index built on TurboQuant, written in Rust with Python bindings