T
traeai
Sign in

产品

Amazon SageMaker AI

别名:SageMaker AI

AWS提供的机器学习开发环境

已跟踪 6 条高相关材料

TraeAI 观察

相关材料

已收录 6 条与 Amazon SageMaker AI 相关的内容,按评分排序。

Build real-time voice applications with Amazon SageMaker AI and vLLM

Build Real-Time Voice Applications with Amazon SageMaker AI and vLLM

AWS Machine Learning Blog2911 字 (约 12 分钟)
87

AWS combines SageMaker AI with vLLM to enable bidirectional streaming speech-to-text inference, supporting real-time voice assistants, live captions, and more with significantly reduced latency.

入选理由:SageMaker AI提供原生HTTP/2双向流式传输(端口8443),自动处理HTTP/2事件流与WebSocket协议转换

FeaturedArticle#AWS#SageMaker#vLLM#Voice AI#Streaming Inference英文
Preventing data exfiltration in machine learning environments with Amazon SageMaker AI

Preventing data exfiltration in machine learning environments with Amazon SageMaker AI

AWS Architecture Blog1140 字 (约 5 分钟)
85

AWS通过三层安全架构实现机器学习环境数据防泄露,结合SageMaker AI与Secure Browser保障数据安全与开发效率。

入选理由:采用Amazon SageMaker Studio可减少80%的Jupyter环境维护成本

FeaturedArticle#AWS#机器学习#数据安全#SageMaker#VPC英文
Build a protein research copilot with Amazon Bedrock AgentCore

Build a protein research copilot with Amazon Bedrock AgentCore

AWS Machine Learning Blog3088 字 (约 13 分钟)
85

本文展示如何使用 Amazon Bedrock AgentCore 构建蛋白质研究助手,实现自然语言查询、向量相似性搜索和 AI 结果总结。

入选理由:使用 Strands Agents SDK 解析自然语言查询为结构化参数。

FeaturedArticle#Amazon Bedrock#AI#蛋白质研究#机器学习英文
Improve your agent’s tool-calling accuracy with SFT and DPO on Amazon SageMaker AI

By using Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) techniques, you can significantly improve the tool-calling accuracy of a small language model on Amazon SageMaker AI. These methods combine high-quality datasets and human feedback to optimize the model’s interactions with digital tools.

入选理由:使用SFT和DPO技术可以提高AI代理执行复杂任务时选择正确工具的能力。

FeaturedArticle#Supervised Fine-Tuning#Direct Preference Optimization#Amazon SageMaker AI英文
Build a custom portal with embedded Amazon SageMaker AI MLflow Apps

Build a custom portal with embedded Amazon SageMaker AI MLflow Apps

AWS Machine Learning Blog2483 字 (约 10 分钟)
85

This solution provides a custom portal with embedded Amazon SageMaker AI MLflow Apps, giving teams a persistent, bookmarkable URL to the full MLflow web UI without presigned URLs or AWS Management Console access. It simplifies access management and integrates with existing SSO infrastructure.

入选理由:The solution uses a custom portal with embedded MLflow UI for easy access management.

FeaturedArticle#ML#SageMaker#MLflow#Custom Portal# AuthenticationEnglish
Announcing OpenAI-compatible API support for Amazon SageMaker AI endpoints

Announcing OpenAI-Compatible API Support for Amazon SageMaker AI Endpoints

AWS Machine Learning Blog2798 字 (约 12 分钟)
85

AWS SageMaker AI now supports OpenAI-compatible API interfaces. Users can call models on SageMaker through OpenAI SDK, LangChain, or Strands Agents by only changing the endpoint URL, without needing custom clients or code rewrites.

入选理由:SageMaker AI 端点现在提供 /openai/v1 路径,支持 Chat Completions 请求和流式响应,Bearer Token 有效期最长12小时。

FeaturedArticle#Amazon SageMaker#OpenAI#Machine Learning#API Compatibility#AWS Services英文

跨材料问答 · Amazon SageMaker AI

回答基于:Amazon SageMaker AI 相关 6 条材料
    0 / 500

    AI may generate inaccurate information. Please verify important content.