Skip to main content

XLGEN

Plain-language guides for the xlgen monorepo, aimed at health-economics modelers, product owners, and reviewers who do not need to read Python. Each page ends with a short technical summary for engineers.

Start here

PageAudience focus
Overall approachTables-first pipeline, enriched knowledge graph, stage map
xl_ingestCOM vs openpyxl, workbook preparation

Pipeline stages (in order)

#PageOne-line summary
1xl_tableBlocking → filtering → framing: find tables
2xl_grammarChildren (hierarchy) + core, titles, headers, row names (annotate)
3xl_dagFormula dependency graph on core regions
4xl_ontologyBIM tags + QC repair/promote
5xl_summarizeOptional LLM overall + input tables

Conceptual flow

Tables (xl_table) → core + labels + children (xl_grammar) → dependencies (xl_dag) → semantics (xl_ontology) → enriched KG → optional LLM (xl_summarize / planned xl_structural).