Easily Build a RAG Solution

Introduction

Retrieval-augmented generation (RAG) is an innovative technology that’s particularly useful for applications that require enterprise data to correctly respond to a prompt. It has many practical uses, including real-time information discovery and customer support automation.

In this solution, we’ve packaged everything you need to easily set up a working RAG application using Oracle Autonomous Database and Oracle Cloud Infrastructure (OCI) Generative AI. We’ve included a Terraform script for deployment and a front-end built with Oracle APEX to alter settings and enter prompts. Upload your own data samples, either structured or unstructured data types—Oracle AI Vector Search will make them accessible.

This solution also lets you tweak the vector parameters, such as chunking and vector indexing, before embedding, providing hands-on experience with tuning how AI generates responses. Get started with this simple but powerful “RAG-in-a-box” solution.

Demo

Prerequisites and setup

1. Oracle Cloud account—sign-up page
2. OCI Generative AI—documentation
3. Oracle Autonomous Database—documentation
4. Oracle Database 23ai—documentation

Getting started

• Detailed steps and sample code on GitHub

Additional resources

• Blog: Accelerate your RAG implementation with “RAG-in-a-Box” packages