跳到正文
每分钟自动更新
10月6日周二
  1. AWS Machine Learning Blog

    Introducing GLM 5.3 on Amazon Bedrock

    中文摘要

    Z.ai 的 GLM 5.3 现已在 Amazon Bedrock 上可用:这是一个用于编码和长周期代理任务的 753B 参数专家混合模型。了解如何通过 OpenAI 兼容的 API 调用它,通过提示缓存来降低成本和延迟,并使用开源的 Strix 代理进行授权安全测试。

    英文原文

    GLM 5.3 from Z.ai is now available on Amazon Bedrock: a 753B-parameter mixture-of-experts model built for coding and long-horizon agentic tasks. Learn how to invoke it with the OpenAI-compatible APIs, cut cost and latency with prompt caching, and run an authorized security test with the open-source Strix agent.

  2. AWS Machine Learning Blog

    Supercharge regulated workloads with Claude Code and Amazon Bedrock

    中文摘要

    Anthropic Claude Opus 5.5 和 Claude Sonnet 5.5 在 AWS GovCloud(美国)区域的 Amazon Bedrock 上可用。了解如何使用 Claude Code,Anthropic 的代理编码工具,以实现合规对齐的、人工智能辅助的开发,用于受监管和 ITAR 工作负载。

    英文原文

    Anthropic Claude Opus 5.5 and Claude Sonnet 5.5 are available on Amazon Bedrock in the AWS GovCloud (US) Regions. Learn how to use them with Claude Code, Anthropic's agentic coding tool, for compliance-aligned, AI-assisted development on regulated and ITAR workloads.

10月2日周五
  1. AWS Machine Learning Blog

    Add secure Web Search to Claude Desktop with Amazon Bedrock AgentCore

    中文摘要

    Amazon Bedrock 上的 Claude Desktop 仅限于该模型的知识截止日期,不支持网络搜索。在本文中,我们将逐步介绍如何使用 Amazon Bedrock AgentCore 网关将 Claude Desktop 连接到网络搜索,通过 AWS IAM Identity Center 和 Amazon Cognito 进行基于 JWT 的入站身份验证。

    英文原文

    Claude Desktop on Amazon Bedrock is limited to the model's knowledge cutoff without web search. In this post, we walk through connecting Claude Desktop to Web Search using Amazon Bedrock AgentCore Gateway, with JWT-based inbound authentication through AWS IAM Identity Center and Amazon Cognito.

  2. AWS Machine Learning Blog

    Building ambient agents with Amazon Bedrock AgentCore: From event-driven signals to human-in-the-loop workflows

    中文摘要

    环境代理会响应事件,例如 Amazon S3 上传、计划任务或警报,而不是等待聊天提示。本文将介绍如何使用 Amazon Bedrock AgentCore 在 Amazon SQS、AWS Lambda 和 Amazon DynamoDB 上构建与框架无关的环境代理,仅使用一个 ask_human 工具和一个用于人工审核的作业页面。

    英文原文

    Ambient agents respond to events such as an Amazon S3 upload, a schedule, or an alert instead of waiting for a chat prompt. This post walks through building framework-agnostic ambient agents on Amazon Bedrock AgentCore using Amazon SQS, AWS Lambda, and Amazon DynamoDB, with a single ask_human tool and a Jobs page for human-in-the-loop review.

9月30日周三
  1. AWS Machine Learning Blog

    Query claims in natural language with Amazon Bedrock Knowledge Bases

    中文摘要

    这个技术教程在 Amazon Bedrock 知识库上构建了一个对话式声明助手,该助手能够用引用的方式回答自然语言问题。本文档涵盖了从 Amazon S3 导入声明文档、使用 AgenticRetrieveStream API 进行查询、多轮跟进、元数据过滤以及上下文基础的防护措施。

    英文原文

    This technical how-to builds a conversational claims assistant on Amazon Bedrock Knowledge Bases that answers natural-language questions with citations. It covers ingesting claim documents from Amazon S3, querying with the AgenticRetrieveStream API, multi-turn follow-ups, metadata filters, and contextual grounding guardrails.

  2. AWS Machine Learning Blog

    Amazon Bedrock expands Claude model availability to in-country inferencing in India

    中文摘要

    Anthropic 的 Claude Opus 5、Claude Sonnet 5 和 Claude Haiku 4.5 现已通过 Amazon Bedrock 地理跨区域推理在印度推出。您可以在处理印度区域内的数据时访问这些模型,并可通过 Amazon Bedrock 控制台或使用 Messages、InvokeModel 和 Converse API 开始使用。

    英文原文

    Anthropic's Claude Opus 5, Claude Sonnet 5, and Claude Haiku 4.5 are now available in India through Amazon Bedrock geographic cross-Region inference. You can access these models while processing data within the India Regions, and get started from the Amazon Bedrock console or with the Messages, InvokeModel, and Converse APIs.

  3. AWS Machine Learning Blog

    Introducing Anthropic models on Amazon Bedrock for in-region inference in Seoul and Singapore

    中文摘要

    Amazon Bedrock 现在支持 Anthropic 的 Claude Opus 5 和 Claude Sonnet 5,并在首尔提供本地推理支持,同时在新加坡支持 Claude Sonnet 5。如果您在韩国或新加坡有本地数据处理需求,现在可以大规模使用这些 Anthropic 模型,推理过程将完全在您调用的区域内进行。

    英文原文

    Amazon Bedrock now supports Anthropic's Claude Opus 5 and Claude Sonnet 5 with in-region inference in Seoul, and Claude Sonnet 5 in Singapore. If you have local data processing requirements in South Korea or Singapore, you can now use these Anthropic models at scale, with inference processed entirely within the Region you call.