How-toOfficial

用 Amazon Bedrock 的 Agentic Retrieve 构建带长期记忆的多用户 Agent

Build memory-aware AI agents with Agentic Retrieve on Amazon Bedrock Managed Knowledge Base

Why we picked it

AWS 把记忆和文档检索合并成一次调用,多用户场景下每个用户的记忆和文档权限自动隔离。做企业内部助手或客服 bot 的开发者可以省掉自己拼 RAG 加 memory 层的功夫,用 Bedrock 的团队尤其值得试。

AWS 在 Amazon Bedrock Managed Knowledge Base 与 Bedrock AgentCore memory 之间打通了新能力:对话存储、事实抽取和长期记忆可以通过一次 AgenticRetrieveStream 调用完成,不再需要开发者自行编排检索与记忆模块。文章给出的方案是一个多用户助手架构:每个用户的记忆相互隔离,文档检索也按权限过滤,用户只能命中自己有权阅读的文档。实现层面,AgentCore memory 负责从历史对话中抽取事实并持久化,知识库检索则在查询时同时读取记忆上下文和权限范围内的文档。对需要构建企业内部助手、客服系统或多租户应用的开发者来说,这套组合把权限隔离和用户级记忆这两个常见难点收敛到了托管服务里,减少了自建向量库加记忆层的维护成本。

Image · AWS Machine Learning Blog
Body

与 LangChain、LlamaIndex 等框架里手动拼装 memory 加 RAG 的做法相比,AWS 的方案把记忆抽取和检索都放在服务端,代价是绑定 Bedrock 生态。已经在用 Bedrock 的团队可以直接在现有知识库上开启这项能力。

Original · AWS Machine Learning Blog

Build memory-aware AI agents with Agentic Retrieve on Amazon Bedrock Managed Knowledge Base

Amazon Bedrock Managed Knowledge Base and Amazon Bedrock AgentCore memory now store conversations, extract facts, and bring long-term memory into a single AgenticRetrieveStream call. This post shows how to build a memory-aware, multi-user assistant where each user sees only the documents they may read and each user's memory stays private.

Industry Coordinates & Source Verification

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, AgentCore, RAG, agents.

Primary source verification: published directly by AWS Machine Learning Blog with first-party authority.