December 16, 2025
Welcome back to The RAG Learning Log. In our last two posts, we laid the groundwork with a Basic RAG pipeline and explored how LangChain acts as the glue. But recently, while working on a deeper RAG project, I hit the inevitable glass ceiling. I real...
December 10, 2025
Introduction: From Idea to Intelligent Application Hello, everyone! If you read my last blog post, you know I’ve been diving deep into the world of Retrieval-Augmented Generation (RAG). I’ve decided to commit to a blog series, documenting everything ...
August 6, 2025
Why RAG? Disclaimer: A lot of technical terms have been used in this blog. You can read them here. Think of a basic chat application. At its core, under the hood, it processes your input and generates a response based on the data it was trained on,...
July 31, 2025
What is Ollama? Your AI Lunchbox: Bringing LLMs Anywhere with Ollama Remember that lunchbox you used to take to school? Inside, you had delicious, home-cooked food from your mom. You carried it yourself, and you could eat it whenever you wanted, righ...
July 31, 2025
Prompting is the art and science of creating effective input tokens for the LLMs to generate the desired outputs. Its basically how we “talk” to the AI, and the way we phrase our inputs to determines the quality of the output of the response.Think of...
July 31, 2025
Tokenization Tokenization is the process of converting text into a sequence of tokens, which can be anything like words, sub-words, or characters. It may seem to us that LLMs understand Hindi, English, Numbers, practically everything in human existen...