Document Retrieval Python Packages

optivision-rag

Visual-token compression for VLM document retrieval: 448 KB to 3.95 KB per page (113.5x) at 86.7% of baseline nDCG@5. ColPali/ColSmol, PyTorch, Qdrant.

kb-arena

Benchmark 19 retrieval architectures (vector, contextual, QnA, knowledge graph, LightRAG, hybrid, RAPTOR, PageIndex, BM25, metadata-filtered, temporal, rerank, HyDE, multi-query, late-interaction, SPLADE, agentic, plus two quantum-inspired rerankers) on your own docs. Citable evidence bundles, bootstrap CIs, significance tests.

vearch

Distributed vector search for AI-native applications

iotadb

a minimal local embedding database.

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-cluster

Distributed vector search for AI-native applications

pyvearch

Distributed vector search for AI-native applications

longprobe

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