AWS Machine Learning Blog · Rajesh Nagpal · 4 小时前模型评分54
如何用 EDB Postgres 人工智能（AI，Artificial Intelligence） 与 Amazon Bedrock AgentCore 为智能体搭建语义层
Build a semantic layer for agentic AI with EDB Postgres AI and Amazon Bedrock AgentCore
导读
文章演示如何用 EDB Postgres 人工智能（AI，Artificial Intelligence） 在 Postgres 数据库内构建语义层，并让运行在 Amazon Bedrock AgentCore 上的 Strands Agents 智能体通过 模型上下文协议（MCP，Model Context Protocol） 端点查询该层回答客户 360 问题。
分类置信度
高
- 官方或准官方来源，且无冲突类别。
- 正文、可信日期、主分类和证据摘录完整。
来源级别：官方一手
事件类型：分析与教程
证据摘录
- “In this post, we show how to build a semantic layer for agentic AI using EDB Postgres AI .”
- “The model layer in this post is Anthropic Claude on Amazon Bedrock , the same as prior posts (model availability varies by AWS Region ).”
- “The AIDB AMI ships with a default SemKB named semkb over public , so creating c360_kb leaves two SemKBs on the instance.”
- “When more than one SemKB exists, every aidb.semantic_kb_search call must pass kb_name explicitly.”
- “For production, use an internal ALB with AgentCore Gateway VPC egress to keep connectivity between Gateway and the ALB private.”
来源：AWS Machine Learning Blog · aws.amazon.com