使用 Amazon Bedrock 实现向量提示文档分类
原标题：Implement vector-prompt document classification using Amazon Bedrock
AI 摘要
AWS 博客介绍了一种基于 Amazon Bedrock 的多智能体文档分类方案，用于保险行业对政策、宣誓书等文档进行准确分类。该方案使用 Strands Agents SDK 编排三个智能体：文档分析智能体（基于 Claude Haiku 4.5）、向量相似性搜索智能体（基于 Titan Multimodal Embeddings 和 FAISS）以及验证智能体，通过交叉验证提高分类准确性。文章提供了架构概述和实现指南。
正文节选
Implement vector-prompt document classification using Amazon Bedrock Vector-prompt classification on Amazon Bedrock helps insurance companies accurately classify thousands of daily documents: policies, affidavits, endorsements, and regulatory forms, for compliance, claims, and customer service. Manual classification is time-consuming and error-prone, while traditional automated approaches struggle with documents that look similar but serve different purposes. A policy endorsement and a regulator