将多模型 AI 智能体迁移至 Amazon Bedrock AgentCore runtime
原标题：Migrating multi-model AI agents to Amazon Bedrock AgentCore runtime
AI 摘要
AWS 博客介绍如何将基于 Hugging Face smolagents 构建的多模型医疗 AI 智能体从自管理的 Amazon ECS/Fargate 迁移到 Amazon Bedrock AgentCore runtime。迁移后由 AgentCore 托管容器生命周期、扩缩容、身份与可观测性，同时保留三模型编排（SageMaker 上的 BioM-ELECTRA、Bedrock 上的 Llama 3.1 70B Instruct 及容器化模型服务）和基于 OpenSearch 的向量知识检索能力。文章强调 AgentCore 支持任意智能体框架与模型，可减少基础设施运维负担。
正文节选
Migrating multi-model AI agents to Amazon Bedrock AgentCore runtime Organizations building multi-model agentic AI applications face growing infrastructure complexity. Managing container orchestration, scaling policies, identity, and observability for multiple model types adds operational overhead. Teams often spend more time on infrastructure than on agent logic development. Developers running agentic frameworks on self-managed infrastructure such as Amazon Elastic Container Service (Amazon ECS)