RAG代理模式

RAG代理是一个将其答案基于检索文档的LLM代理，而不是依赖于基础模型记住的内容。这里的模式描述了如何以可靠的方式做到这一点：如何检索、如何重排序、如何验证、如何呈现用户可以检查的引用，以及当检索失败时如何回退。

简单RAG是入门点 — 嵌入查询，获取最近邻，粘贴到提示中 — 但生产RAG是围绕它的所有内容：在向量和词汇索引之间的混合搜索、交叉编码重排序、上下文分块、查询重写（HyDE）、纠正检索（CRAG）、对检索质量的自我反思（Self-RAG）、在检索形状任务上微调模型（RAFT）、图感知检索（GraphRAG），以及随着解析而流动的引用。

Field-tested patterns to start with

• Agentic RAG — Replace static retrieve-then-generate with autonomous agents that plan, choose sources, retrieve iteratively, reflect, and re-query.
• Naive RAG — Condition the generator on top-k chunks retrieved from an external dense index so knowledge lives outside parameters.
• Hybrid Search — Combine sparse lexical retrieval (BM25) with dense vector retrieval and fuse the results.
• Cross-Encoder Reranking — After cheap bi-encoder or BM25 retrieval, rescore top-N candidates with a cross-encoder that jointly attends over (query, candidate).
• Contextual Retrieval — Prepend a short LLM-generated description to each chunk before embedding so the chunk carries its situating context.
• HyDE — Have the LLM write a hypothetical answer document, embed it, and use it as the retrieval query.
• CRAG — Add a lightweight retrieval evaluator that grades each retrieved document and triggers corrective web search on poor retrievals.
• Self-RAG — Fine-tune the model to emit reflection tokens that decide when to retrieve, evaluate retrieved relevance, and assess generated support.
• RAFT — Train the model to ignore irrelevant retrieved documents (distractors) in a domain-specific RAG setting.
• GraphRAG — Build an LLM-extracted entity-and-relation knowledge graph plus hierarchical community summaries, then answer global queries via map-reduce over those summaries.
• Citation Streaming — Stream citations alongside generated text so the UI can render source links in place as content appears.
• Chain of Verification — Reduce hallucination by drafting an answer, generating independent verification questions, answering them in isolation, and revising.

Recommended reading

• Retrieval & RAG — 23 patterns
• Verification & Reflection — 32 patterns

Or open the full contents for all 564 patterns in 14 books.

Related guides

• AI Agents Patterns — AI agents patterns: named, reusable shapes for building AI agents that reason, use tools, coordinate, and stay safe — single-agent loops an…
• AI Agents Patterns Catalog — The AI agents patterns catalog: a complete, GoF-formal pattern language for AI agents across reasoning, planning, tool use, retrieval, memo…
• LLM Agent Design Patterns — A GoF-formal catalog of LLM agent design patterns: ReAct, tool use, plan-and-execute, reflection, step budget, and more. Each pattern decom…
• Agentic Design Patterns — A GoF-formal catalog of agentic design patterns — named, reusable shapes for building autonomous AI agents: agent loops, tool use, planning…
• Agentic AI Design Patterns — Agentic AI design patterns for systems already in production — what to ship, what to observe, what to budget, what to gate. Augmented LLM,…
• AI Agent Design Patterns — How to build an AI agent: the named shapes you reach for during design and implementation — reasoning (ReAct, plan-and-execute, reflection)…
• Agent Design Patterns — Agent design patterns treat the agent loop as a software-engineering primitive: an observe→reason→act cycle wrapped in tools, memory, super…
• Agentic Patterns — A complete pattern language for agentic systems, organised in Alexander-style books across reasoning, planning, tool use, retrieval, verifi…
• Agentic AI Architecture — How to structure agentic AI: the architectural patterns that hold an LLM-powered system together. Supervisor, orchestrator-workers, augment…
• Multi-Agent Patterns — Patterns for coordinating multiple LLM agents: supervisor, orchestrator-workers, handoff, debate, hierarchical agents, swarm, role assignme…
• AI Agent Safety Patterns — Safety patterns for LLM agents: step budget, kill switch, constitutional charter, approval queue, sandbox isolation, input/output guardrail…