Lesson 1: Where Hollin's documents come from, and how to read them
23 min read·13 Oct 2026
Module 2 · Lesson 1 · About 50 minutes · Needs: Module 1 (what retrieval does with documents), basic Python dictionaries and sets
The situation
Kwame hands you the raw files. His August prototype read Hollin's documents from wherever he could reach them, once, and never looked again. Three of its failures started here, before any search ran. It indexed the finance share without its permissions, so a support query pulled in internal cost prices. It never removed bulletin SB-114, withdrawn on 8 October 2026. And it indexed web pages whole, menus and cookie banners included.
Grace wants ingestion done properly. This lesson is the first step: where the documents live, how to read them politely, how to keep their permissions and changes, and how to turn plain text, Markdown and HTML into clean text.