Ask your WhatsApp: build a private RAG with LlamaIndex

Fri, 05 Sep 2025 13:09:00 -0400

Why build a WhatsApp RAG?

I have a very active group chat with my friends on WhatsApp. At the time of writing, it is a bit over half a million messages. Since LLMs became a thing, I always wondered how I could use this data for something useful—or at the very least, prank my friends.

Last year I tried a few different approaches to fine tune a model using the chat data, but it didn’t work all that well. Fine‑tuning a model on commodity hardware is a challenge in itself and the results were underwhelming. So I dropped that idea for a while. While going through the material for the HuggingFace Agents Course though, it became very clear that RAG (Retrieval Augmented Generation) would be a perfect fit for what I was trying to do.

Hugging face agents

Mon, 25 Aug 2025 10:40:48 -0400

I’ve been working through the Hugging Face agents course, and I’m enjoying it quite a bit. Highly recommended! First, it’s rounding out my knowledge of LLMs, transformers, and AI in general. Second, it paints a very clear picture of what agentic AI is all about—while staying away from the hype. I’ll try to summarize here, but I really recommend checking out the full course.

This is not a formal definition, but I think the crucial feature of agents is the ability to use tools to interact with the environment. Instead of relying solely on the knowledge of the model itself, agents can search the web, access web pages, and use Unix commands like find, ls, and grep to help answer your questions. Another key characteristic is that this all happens in a loop, giving the agent the ability to course correct in case things don’t go as planned in order to achieve its goal.

AI on The Learning Loop

Ask your WhatsApp: build a private RAG with LlamaIndex

Why build a WhatsApp RAG?

Hugging face agents