Hierarchical Tree-Organized Retrieval (RAPTOR) in Production RAG: Recursive Summarization, Gaussian Mixture Clustering, and Cross-Scale Querying
Standard retrieval-augmented generation (RAG) architectures operate on flat document chunks. Corpora are split into fixed token windows (typically 256 to 1024 tokens), mapped into vector space via dense embedding models, and queried through approximate nearest neighbor (ANN) search. While this setup efficiently resolves localized factual lookups ("What is the termination clause in contract X?"), it systematically fails on thematic synthesis, cross-document comparison, and high-level aggregation
1 min