Document Retrieval Python Packages

kb-arena

Benchmark 7 retrieval strategies on your own docs — naive vector, contextual, QnA pairs, knowledge graph, RAPTOR, PageIndex, and hybrid. Find which KB architecture fits your data.

langchain-rag-wiki

RAG meets wiki-style provenance. Surfaces documents, learns from usage, and lets users build personal knowledge bases on top of shared vector stores.

vearch

Distributed vector search for AI-native applications

pyvearch

A library for efficient similarity search and storage of deep learning vectors.

longprobe

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

iotadb

a minimal local embedding database.

vearch-cluster

Distributed vector search for AI-native applications