| name | 0.4.4-understand-dense_passage_retriever |
| description | [0.4.4] Bi-encoder model trained on query-passage pairs to produce jointly learned dense embeddings for retrieval |
understand-dense_passage_retriever
CALL NUMBER: retrieval_augmented_generation_architecture_patt.dense_passage_retriever
DEFINITION: Bi-encoder model trained on query-passage pairs to produce jointly learned dense embeddings for retrieval
Invoke this skill to understand dense_passage_retriever down to its primitives. The RELATIVE ROOT below is the least-fixed-point closure of everything it bundles from — the full import cone, grouped by the lib each prim comes from. Projected from a prover-typed KB (MAP/SWI-Prolog consistency gate): every reference below resolves.
THE RELATIVE ROOT (the import cone, by lib)
CONSUMERS (what needs this)
ance_retrieval, colbert_biencoder_comparison, colbert_contrastive_training, dense_retrieval, knowledge_distillation_rag, rocketqa_retrieval
Projected from the retrieval augmented generation architecture patterns KB (207 concepts / 225 relations) — consistency-typed by MAP; the facet list after the colon IS the cross-lib dependency web.
(leaf — this is an actual skill.)
