《利用智能体人工智能简化 Amazon EKS 操作 [重复].pdf》由会员分享,可在线阅读,更多相关《利用智能体人工智能简化 Amazon EKS 操作 [重复].pdf(17页珍藏版)》请在三个皮匠报告上搜索。
1、 2025,Amazon Web Services,Inc.or its affiliates.All rights reserved.2025,Amazon Web Services,Inc.or its affiliates.All rights reserved.2025,Amazon Web Services,Inc.or its affiliates.All rights reserved.Sai VennamPrincipal Solutions ArchitectAWSLucas Soriano Alves DuartePrincipal Solutions ArchitectA
2、WSStreamline Amazon EKS operations with Agentic AIC N S 4 2 1-R 2025,Amazon Web Services,Inc.or its affiliates.All rights reserved.2025,Amazon Web Services,Inc.or its affiliates.All rights reserved.2025,Amazon Web Services,Inc.or its affiliates.All rights reserved.Meet the Newest Member of Your Team
3、 2025,Amazon Web Services,Inc.or its affiliates.All rights reserved.2025,Amazon Web Services,Inc.or its affiliates.All rights reserved.2025,Amazon Web Services,Inc.or its affiliates.All rights reserved.2025,Amazon Web Services,Inc.or its affiliates.All rights reserved.2025,Amazon Web Services,Inc.or
4、 its affiliates.All rights reserved.This isnt a chat bot its a teammate 2025,Amazon Web Services,Inc.or its affiliates.All rights reserved.2025,Amazon Web Services,Inc.or its affiliates.All rights reserved.Large language modelPrompt augmentationResponseEmbeddings modelData sourceVector storeEmbeddin
5、gs modelEmbeddingUserUser InputContext-0.020.89-0.38-0.530.950.17Text generation workflowSemantic searchDocument chunks2.User asks a question:“Why is my app response time high?”1.Kubernetes logs are chunked and stored in vector storage3.Context is built from users question and semantic search of sou
6、rce material4.Context+original user input is fed to FM on Amazon BedrockRAG-last years approach 2025,Amazon Web Services,Inc.or its affiliates.All rights reserved.2025,Amazon Web Services,Inc.or its affiliates.All rights reserved.S L A C K I N T E R F A C EK 8 S O R C H E S T R A T O R A G E N TUses