Building Generative AI Agents: Amazon Bedrock, Amazon DynamoDB, Amazon Kendra, Amazon Lex, LangChain

This AWS sample solution creates a Generative AI-powered Financial Services Agent that can assist users with finding their account information, completing a loan application, or answering any natural language question while also sourcing links for the provided answers. Amazon Lex supplies the Natural Language Understanding (NLU) and Natural Language Processing (NLP) interface for the open-source LangChain Conversational Agent within an AWS Amplify website. The Agent is equipped with tools that include an Anthropic Claude LLM hosted on Amazon Bedrock and synthetic customer data stored on Amazon DynamoDB and Amazon Kendra.

This solution is intended to act as a launchpad for developers to create their own personalized conversational agents for various applications, such as chatbots, virtual assistants, and customer support systems.

Subscribe:

Do you have technical AWS questions?

ABOUT AWS
Amazon Web Services (AWS) is the world’s most comprehensive and broadly adopted cloud platform, offering over 200 fully featured services from data centers globally. Millions of customers — including the fastest-growing startups, largest enterprises, and leading government agencies — are using AWS to lower costs, become more agile, and innovate faster.

#AWS #AmazonWebServices #CloudComputing

[CurtisSavage]

Do the tools in amazon bedrock now replace this approach? E.g. Am I able to achieve this solution in more of a turnkey way using amazon bedrock agents? if so, pros and cons of each approach?

[jeffb]

Any suggestions on how to adapt this architecture to include some of the AWS Healthcare tools for a patient facing AI chatbot app?

[jochemtoma]

is there a video that goes in detail from scratch to import this solution and make it functional? With a new aws account. Very curious if this is already there or not.

[jeffb]

How did you equip the Lex Chatbot with ability to allow user to upload documents? Could the bot participate in Q&A based on the documents the user uploads ?

[dusanbosnjakovic]

How do you make sure to break out of the static flow when necessary? What controls if you will use Claude, llms general answering ability, or static flow, especially once the flow has started?

[SivaChidambaram]

So AWS suggesting to use a 3rd party "Kommunicate" to integrate the Lex into the website?

[dusanbosnjakovic]

You don't mean chain of thought, but ReAct.