Benchmark 9 retrieval architectures (vector, contextual, QnA, knowledge graph, hybrid, RAPTOR, PageIndex, BM25, rerank) on your own docs. Automated hyperparameter search with bootstrap CIs and significance tests.
python cli benchmark neo4j retrieval evaluation knowledge-graph hyperparameter-optimization document-retrieval ndcg statistical-significance rag bpref vector-search hybrid-search llm chromadb retrieval-augmented-generation rag-evaluation graphrag
-
Updated
May 21, 2026 - Python