AI Knowledge and AI Answer Microservices for RAG

Project

Artificial Intelligence

Intermediate

Use Template

This is a 'Project' template which means that it contains a group of workflows that work together to achieve a particular aim

Overview

Copy

When you are ready to scale your AI applications, services, and automations this project helps you by creating discrete micro-services for the various RAG components using Tray's API Management features. These can be deployed in other automations for AI Agents or triggered from outside the Tray application as Managed APIs.

If you need help reach out in the community in the #ai-help channel!

Set-up

Copy

1. Import the Project

2. Update the authentications for Bedrock (or replace with your preferred AI vendor)

3. Create a vector table (dimensions need to match your embedding model of choice)

   1. Update the vector table steps to point to this table

4. Create the API Operations for your API triggered workflows

5. Create a client within the project access control menu (save the api_key)

6. Update the HTTP client in the Answer Service to point to the Knowledge service workflow

7. Call either API from other automations or from code outside of Tray.

Next Steps

Copy

Use one of our Knowledge indexing templates or our Getting started with RAG template to populate your knowledge base in vector storage. Pair this with our Slackbot and other AI Agent templates to compose your first enterprise Agent.

If you need help reach out in the community in the #ai-help channel!