html-extraction
Module for automatic summarization of text documents and HTML pages.
Reworked https://www.readability.com/ parsing library (now https://mercury.postlight.com/ is living alternative)
Domain-specific language for extracting structured data from HTML documents
Pareto-optimal models for cleaning the web — fast, encoder-based main-content extraction from HTML.
Auditable AI content ingestion: safe fetch, extraction, evidence gates, provenance ledgers, RAG datasets, and configurable provider/API exports.
