TechThiran

Building robust AI systems for information retrieval presents a recurring challenge: balancing precision and recall. Retrieval-Augmented Generation (RAG) frameworks have emerged as a powerful solution, allowing language models to generate responses grounded in real-world data. However, traditional retrieval methods often struggle with messy, mixed-type data or exact keyword queries. This is where Hybrid Search and Agentic RAG come into play, transforming our approach to dat

I've been contemplating this blog since 2024, and here I am, finally putting pen to paper in 2026. Remarkably, my understanding of Retrieval-Augmented Generation (RAG) has remained consistent over the past two years. This reflects the depth of research I've conducted since 2023. RAG has fundamentally reshaped our perception of Large Language Models (LLMs) and their limitations. It’s time to share my journey, insights, and practical experiences with this powerful architecture.

When I first started working with LangGraph, I was struck by its unique approach to state management, which deviates from the typical global state mutation model found in many frameworks. Instead of directly modifying a shared state variable, LangGraph nodes return explicit updates that are applied to a central state. This design fundamentally alters how state evolves during graph execution, and it took me some time to fully grasp its nuances. In this post, I’ll break down L

I often find myself diving headfirst into coding, driven by excitement and curiosity, sometimes neglecting to fully grasp the underlying mechanics of the tools I use. This approach has led to both triumphs and frustrations. Recently, while delving deeper into LangGraph, I encountered another one of those "WHAT THE HELL" moments that compelled me to step back, learn the fundamentals, and gain insights that I believe can help others avoid similar pitfalls. In this post, I’ll s