Member-only story

One of These Will Be Your Favorite Chunking Technique For RAGs.

Document splitting and RAGs beyond the basics.

Thuwarakesh Murallie
AI Advances
Photo by Jason Abdilla on Unsplash

A RAG is only as good as its chunks. — Thuwarakesh (me)

If your RAG app is not performing to your expectations, perhaps it’s time to change your chunking strategy. Better chunks mean better retrieval, which means high-quality responses.

However, no chunking technique is better than the others. You need to choose based on several factors, including your project budget.

How does better chunking lead to high-quality responses?

If you’re reading this, I can assume you know what chunking and RAG are. Nonetheless, here is what it is, in short.

LLMs are trained on massive public datasets. Yet, they aren’t updated afterward. Therefore, LLMs don’t know anything after the pretraining cutoff date. Also, your use of LLM can be about your organization’s private data, which the LLM had no way of knowing.

Therefore, a beautiful solution called RAG has emerged. RAG asks the LLM to answer questions based on the context provided in the prompt itself. We even ask it not to answer even if the LLM knows the answer, but the provided context is insufficient.

Create an account to read the full story.

The author made this story available to Medium members only.
If you’re new to Medium, create a new account to read this story on us.

Or, continue in mobile web

Already have an account? Sign in

Written by Thuwarakesh Murallie

Data Science Journalist & Independent Consultant

Responses (6)

What are your thoughts?