Skip to content

Example solution to inference images and create images using Amazon Bedrock

License

Notifications You must be signed in to change notification settings

sfloresk/inventory-ai

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Inventory AI

This code provides an example of how to create an end-to-end solution to inference images of food products, detecting the name and brand. Additionally, it allows you to create a recipe from text, including images. It has been optimized to read images that contain a single product only

Architecture diagram

Infrastructure

The infrastructure is based on:

  1. Amazon API Gateway - Entry point to send images and text
  2. Amazon Lambda Function - Handle requests to detect images and generate recipes
  3. Amazon Cognito - Provides authentication for the API
  4. Amazon Bedrock - Used for inference requests to Anthropic Claude 3 sonnet and Amazon Titan image models
  5. Amazon S3 - Host the web application
  6. Amazon Cloudfront - Content delivery network for the web application

Most of the deployment of the infrastructure is automated using the Serverless Application Model. For detail instructions, follows the steps here

Web portal

Example single page application built in Vue JS - it is integrated with Cognito to provide a seamlessly experience, allowing users to sign up and sign in.

Inventory AI web user interface: image processing Inventory AI web user interface: recipe generation

Detail instructions to install the web app can be found here

Support

Please open an issue for any questions or issues

About

Example solution to inference images and create images using Amazon Bedrock

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published