LlamaIndex on The Learning Loop https://blog.juzam.pro/tags/llamaindex/ Recent content in LlamaIndex on The Learning Loop Hugo -- 0.147.7 en-us Fri, 05 Sep 2025 13:09:00 -0400 Ask your WhatsApp: build a private RAG with LlamaIndex https://blog.juzam.pro/posts/2025-09-05/zaprag/ Fri, 05 Sep 2025 13:09:00 -0400 https://blog.juzam.pro/posts/2025-09-05/zaprag/ <h2 id="why-build-a-whatsapp-rag">Why build a WhatsApp RAG?</h2> <p>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.</p> <p>Last year I tried a few different approaches to fine tune a model using the chat data, but it didn&rsquo;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 <a href="https://huggingface.co/learn/agents-course/unit2/llama-index/components">HuggingFace Agents Course</a> though, it became very clear that RAG (Retrieval Augmented Generation) would be a perfect fit for what I was trying to do.</p>