Build an ecommerce product recommendation chatbot with Amazon Bedrock Agents
Machine Learning Blog
This article explains how to build an ecommerce product recommendation chatbot using Amazon Bedrock Agents and foundation models from Amazon Bedrock.
Specifically, the article covers:
- Solution overview: Creating an intelligent chatbot that can converse naturally with users, understand their gift preferences, query a product catalog API, and recommend relevant products
- Prerequisites: Required AWS services, IAM policies, and permissions
- Deploying solution resources: Using AWS CloudFormation to create a DynamoDB table for product data, a Lambda function for the product API, and a Lambda function to populate sample product data
- Creating the agent: Requesting model access, creating the agent and action group using CloudFormation, understanding the agent instructions and OpenAPI schema
- Testing the chatbot: Example conversations demonstrating how the chatbot gathers preferences and recommends products, along with rationale explanations
- Clean up: Deleting the CloudFormation stacks to remove resources
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
Related articles
Sep 10
2024
2024
Building a privacy preserving chatbot with Amazon Bedrock
Jul 25
2024
2024
Evaluate conversational AI agents with Amazon Bedrock
Nov 12
2024
2024
Deliver personalized marketing with Amazon Bedrock Agents
Jun 11
2026
2026
Building AI shopping agent using Amazon Bedrock AgentCore Runtime and Amazon OpenSearch Service
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.