Enterprise Knowledge Q&A with RAG and OCI Generative AI

Introduction

It’s not enough to have answers—they have to be accessible and easy to retrieve by users. Large organizations with many moving parts face a particular challenge keeping up with Q&A systems over time. That’s where OCI Generative AI and retrieval-augmented generation (RAG) can step in to help create friendlier systems with more frequent updates based on new web pages.

In this demo, we’ll create a RAG model using OCI Generative AI, LlamaIndex, Qdrant vector database, and SentenceTransformerEmbeddings. This 21-line code will allow you to scrape web pages and use LlamaIndex for indexing, OCI Generative AI for question generation, and Qdrant for vector indexing.

Demo

Prerequisites and setup

1. Oracle Cloud account—sign-up page
2. Getting started with OCI Generative AI—documentation
3. LlamaIndex—documentation
4. LangChain—documentation
5. Qdrant vector similarity search engine—documentation
6. SentenceTransformers—documentation

Getting started

• Detailed steps and sample code on GitHub