Query Optimization and Retrieval Algorithms

Adaptive-RAG is a research implementation that routes questions among no-retrieval, single-step, and iterative retrieval strategies according to predicted complexity.

Contriever is Meta's unsupervised dense-retrieval model and training code for learning transferable query-passage representations without relevance labels.

Corrective-RAG is the reference implementation of CRAG, which evaluates retrieved documents and can trigger corrective web retrieval before generation.

DPR is Meta's Dense Passage Retrieval codebase for training dual encoders and retrieving passages with dense maximum-inner-product search.

FLARE is the reference implementation of Forward-Looking Active Retrieval, which retrieves during generation when forthcoming sentence confidence is low.

HyDE is the reference implementation of Hypothetical Document Embeddings, which generates a hypothetical answer document and embeds it to retrieve real passages without relevance labels.

RAFT is a training recipe and reference implementation for adapting models to answer from retrieved domain documents while distinguishing relevant context from distractors.

Rankify is a unified information-retrieval toolkit that exposes retrieval, reranking, query expansion, dataset, and evaluation components behind common interfaces.

RAPTOR is a retrieval approach and implementation that recursively clusters and summarizes text to build a tree queried at multiple abstraction levels.

Self-RAG is a research framework in which a model adaptively retrieves passages and emits reflection tokens to critique relevance, support, and response quality.

SPLADE is Naver's learned sparse-retrieval implementation that expands queries and documents into weighted vocabulary terms compatible with inverted indexes.