site-logo

JAWS PANKRATION 2024

site-logo
HomeNewsTimetableCfPCommitteePromotionFollow UpPrivacy Policy

Building an AI Chat Assistant with Amazon Bedrock Agent

Lv200

Lv200

2024/8/25 03:40 (JST)
セッション情報

During the session, you will discover the potential of AWS's groundbreaking announcement from last year—the Bedrock agent.

Focused on building a smart assistant, this session will provide insights into how the Bedrock agent leverages the reasoning capability of foundation models (FMs) to support workflow orchestration and automation.

　

Explore the capabilities of the Bedrock agent through a captivating example project, where you will witness its ability to monitor updates on messaging platforms like Telegram, seamlessly translate messages, summarize content, and extract actionable insights.

　

By the end of this talk, every attendee will gain a deeper understanding of the possibilities that the Bedrock agent holds for optimizing productivity and facilitating smart assistance.

Join me as we embark on this exploration of the Bedrock agent's potential.

Darya Petrashka

Darya Petrashka

- AWS Community Builders -

- AWS Authorized Instructors(APN) -

セッションカテゴリ
Machine learning
関連AWSサービス
Bedrock
Lambda
S3
DynamoDB
セッション資料
    セッションアーカイブ
    セッションサマリ（by Amazon Bedrock）
      The speaker, an AWS Community Builder and authorized instructor, discusses building an AI chat assistant using Amazon Bedrock Agent. Amazon Bedrock is a managed service providing access to various foundation models like Llama, Mistral, and Titan through a single API. Bedrock Agents are orchestrational software that guide workflows between user requests, foundation models, external data sources, and applications. They often use the REACT (Reasoning and Action) framework, which combines chain-of-thought reasoning with action planning. The speaker introduces their project, an assistant agent designed to automate and speed up the processing of Telegram chats. This agent can pull messages from chats, summarize them, translate if necessary, and answer custom questions. The project involves creating a Telegram bot, setting up a DynamoDB table for chat IDs, and developing a Lambda function containing the required tools (APIs) for the agent to use. The agent is then built using the Amazon Bedrock console, where instructions and action groups are defined. Key steps in building the agent include: 1. Creating a Telegram bot and obtaining a token 2. Setting up a DynamoDB table 3. Creating a Lambda function with necessary tools 4. Building the agent in the Amazon Bedrock console 5. Providing instructions and connecting tools The speaker emphasizes considerations such as secure access to APIs, input validation, and careful permission management. They also mention limitations, including reliance on Telegram APIs and support for limited input modalities. In conclusion, Amazon Bedrock Agents are presented as a powerful tool for building AI assistants that require reasoning capabilities, with the speaker encouraging listeners to try building their own agents.

    戻る

    ©JAWS-UG (AWS User Group - Japan). All rights reserved.