Build a RAG-Based Chatbot to Retrieve Visualizations in 3 Steps
A step-by-step guide to creating a visualization discovery chatbot with OpenAI API, FAISS, and Streamlit
My Chatbot — Viz Retriever
Over the last six years, I’ve embarked on a journey of creating a new data visualization every week — over 300 of them, to be precise! (You can read more about my journey here). This vast collection is like a treasure trove, but the downside? Finding that one specific visualization I know I’ve created can feel like searching for a needle in a haystack, especially when my Tableau repository is overflowing.
That’s when the idea hit me: What if I could use LLMs to help me retrieve visualizations based on specific topics? This sounded like a perfect use case for RAG(Retrieval-Augmented Generation).
In this article, I’ll walk you through the three simple steps I took to build a RAG-based chatbot. You can check out the demo below and even play with my app on Streamlit 👀.
