Ac RAG Systems

Building the whole retrieval-augmented answering loop as one system: the query transform stage before retrieval, multi-hop decomposition when one query cannot reach the answer, chunk-level citation so every claim traces to a source, grounding verification that catches unsupported answers, refusal behaviour when the corpus is silent, and the written RAG record. It explains how the loop components compose; it never recommends an embedding model and never promises an accuracy. Use when asking "RAG", "retrieval augmented generation", "query rewriting", "multi-hop retrieval", "citation extraction", "grounding check", "hallucination guard", "answer verification", "corpus is silent", "RAG evaluation", "RAG pipeline design". Not for vector index and hybrid search mechanics (ac-retrieval-and-vector-systems), not for the grounding prompt itself (ac-prompt-engineer), not for model evaluation suites (ac-model-evaluation).

jiayaoqijia Updated 81 repo stars

File contents

jiayaoqijia/cryptoskill commit 3ebf35ac16

Frequently asked questions

npx get-skill add jiayaoqijia/ac-rag-systems