An AI-powered pipeline that reads 807 chapters (~12 million words) of The Wandering Inn web serial, extracts every geographical reference using Claude, and renders them as an interactive Leaflet map with a spoiler-free chapter slider. Single binary with all assets embedded via go:embed.

Features

  • Spoiler-free chapter slider — only see locations mentioned up to your current chapter
  • Multi-format navigation for web, audiobook, and ebook readers
  • Clickable relationship lines between connected locations
  • Ghost provenance lines showing extraction source
  • Searchable sidebar with location details
  • WCAG AA accessibility compliance
  • Single binary deployment — all assets embedded

Pipeline

The four-stage extraction pipeline:

  1. Scrape — Download chapters from the web serial
  2. Extract — Use Claude (Sonnet 4) to identify and extract geographical references with structured output
  3. Aggregate — Deduplicate, normalize, and cross-reference locations across all chapters
  4. Serve — Interactive Leaflet map with chapter-based filtering

By the Numbers

12M
Words Processed
600+
Locations Extracted
4,200
Lines of Code
100%
AI-Generated

Tech Stack

Go 1.25+, Cobra CLI, DuckDB for storage, Leaflet.js for mapping, Claude API for extraction. Requires an Anthropic API key for the extraction step.