Vector Store Python Packages

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.

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.

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

libraft-cu13

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.

pylibraft-cu13

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.

raft-dask-cu13

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.

flaxkv

🗲 A high-performance on-disk dictionary.

pylibraft-cu11

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.

raft-dask-cu11

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.

cuvs-cu13

cuVS: Vector Search on the GPU

libcuvs-cu13

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

longprobe

Sub-second RAG regression testing. Define golden questions, detect lost chunks in CI. pytest for your RAG pipeline.

cuvs-cu11

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

libraft-cu11

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.

libcuvs-cu11

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

cogito-ergo

Memory retrieval for AI agents — integer-pointer fidelity guarantee, 93.4% R@1 on LongMemEval_S (hybrid tier). By Hermes Labs.

langchain-cratedb

CrateDB provider for LangChain.

flaxfile

🗲 A high-performance on-disk dictionary.

langchain-turboquant

LangChain VectorStore with TurboQuant compression (ICLR 2026) - 6x memory reduction, training-free, no GPU required. The first LangChain integration for Google Research's TurboQuant algorithm.

contexttape

File-based RAG storage: Zero-infrastructure vector database alternative for LLMs. Store embeddings in .is files, no Docker needed.

duckdb-haystack

Haystack document store and retriever for DuckDB VSS