Blog
Writing
Life, tech, and everything in-between.
Semantic RAG
6 minAI
Semantic RAG is a fixed pipeline: chunk, embed, search, generate. Tuned well, it handles most production lookup workloads at a cost the alternatives cannot match. A short walkthrough of the pieces and the upgrades that matter.
The Augmented LLM: Retrieval, Tools, and Memory
6 minAI
A bare language model is a closed system. It cannot look up a fresh fact, cannot act in the world, cannot remember the last conversation. Every non-trivial agent is an attempt to lift one or more of those three constraints.