Chunking Technique Research

June 9, 2026

AI   Python  

After building RAG systems for technical books, I kept asking which chunking strategy actually retrieves better. I built a research platform to answer that with real vector search, LLM-as-judge ground truth, and metrics such as NDCG, MAP, and MRR. I compare fixed-length and overlap splitters with heading-aware and linguistically scored approaches. Some of this is still a heuristic, not a settled result.

HAL - Highly Adaptable Learning AI

March 18, 2025

Python   AI  

HAL is a retrieval-augmented generation assistant for technical books, with a WarGames-style terminal UI. I built it to ingest compiler and systems texts, chunk and embed them, store them in Qdrant, and answer questions from that store. This article is the stack, the architecture, and what I learned. It is part nostalgia project and part a real attempt to make those books searchable.