RAPTOR

Recursively embeds, clusters, and summarises chunks into a tree of abstractions. Retrieval traverses the tree at query time. ICLR 2024.

At a glance

Optimised for: retrieval quality / accuracy on long-context QA

Anti-fit: most are research papers; production fitness varies by maintainer

Hierarchical clustering retrieval — multi-resolution recall over long documents; widely adopted in 2024 RAG stacks.

Indexing cost grows with corpus; cluster quality depends on embedding choice.

+20% absolute accuracy on QuALITY benchmark with GPT-4. Multi-step-reasoning state of the art on QA tasks at publication.

Other retrieval-as-memory hybrids in the catalog, ranked by inbound references.

GraphRAG (Microsoft) T1
Modular graph-based RAG. Leiden community detection over knowledge graph; community summaries at multiple levels. DRIFT Search hybrid (Oct 2024).
RETRO T3
DeepMind. Retrieval-Enhanced Transformer with chunked cross-attention over a 2T-token retrieval database. Frozen BERT retriever + differentiable encoder.
Atlas T3
Meta AI. Jointly fine-tunes retriever + LM for few-shot tasks.
RAPTOR T3
Stanford recursive-summarisation tree over the corpus — clusters and summarises documents into a hierarchical index; retrieves at multiple levels. ICLR 2024.
Self-RAG T4
Trains an LLM end-to-end to emit reflection tokens that decide whether to retrieve, assess passage relevance, and critique output quality — all within a single model.
HippoRAG / HippoRAG2 T3
Hippocampus-inspired RAG. LLMs + knowledge graphs + Personalized PageRank to mimic neocortex/hippocampus roles. NeurIPS 2024.