Amazon Bedrock Managed Knowledge Base 推出单次检索与 Agentic 检索模式
Single-shot and agentic retrieval with Amazon Bedrock Managed Knowledge Base
AWS 给 Bedrock 知识库加了个很实用的开关：简单问题走单次 RAG，复杂问题才让智能体多轮检索，用 maxAgentIteration 控制。做企业知识库问答的工程师可以照着文中的银行政策助手示例改，能明显省延迟和调用成本。
AWS 在 Amazon Bedrock Managed Knowledge Base 中新增 single-shot RAG 与纯检索请求支持，通过 AgenticRetrieveStream 接口调用，可与原有的 agentic retrieval 并存使用。文章以 maxAgentIteration 参数为核心，说明如何控制智能体检索的迭代次数，把检索开销与请求复杂度匹配起来。
文中用了一个银行内部政策问答助手作为示例场景，展示不同查询该走单次检索还是多轮 agentic 检索：简单事实型问题一次召回即可返回答案，复杂问题才让智能体多次迭代检索。
对企业开发者来说，这意味着在同一套 Bedrock 知识库上可以按请求粒度调节 RAG 策略，而不必为简单查询付出 agentic 检索的额外延迟和 token 成本。
Single-shot and agentic retrieval with Amazon Bedrock Managed Knowledge Base
Amazon Bedrock Managed Knowledge Base now supports single-shot RAG and retrieval-only requests through AgenticRetrieveStream, alongside agentic retrieval. This post explains how the maxAgentIteration parameter matches retrieval effort to each request, using an illustrative internal banking policy assistant.
This report is categorized under AITOP's "How-to" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Amazon Bedrock, RAG, AWS, 智能体.
Primary source verification: published directly by AWS Machine Learning Blog with first-party authority.