Step-by-Step Guide: Setting Up RAG for Gen AI Agents Using IRIS Vector DB in Python

How to set up RAG for OpenAI agents using IRIS Vector DB in Python In this article, I’ll walk you through an example of using InterSystems IRIS Vector DB to store embeddings and integrate them with an OpenAI agent. To demonstrate this, we’ll create an OpenAI agent with knowledge of InterSystems technology. We’ll achieve this by storing embeddings of some InterSystems documentation in IRIS and then using IRIS vector search to retrieve relevant content—enabling a Retrieval-Augmented Generation (RAG) workflow. Note:  Section 1 details how process text into embeddings. If you are only interested in IRIS vector search you can skip ahead to Section 2. Section 1: Embedding Data Your embeddings are only as good as your data! To get the best results, you should prepare your data carefully. This may include: Cleaning the text (removing special characters or excess whitespace) Chunking the data into smaller pieces Other preprocessing techniques For this example, the documentation is stored in sim