As a companion specification to the Docling project, DocLang defines a structured, machine-readable format for documents of any type. Not a converter. Not an API. A standard — like JSON for data, like HTML for the web — that any tool can implement and any pipeline can consume.
Every component carries a semantic tag, bounding box coordinates, and reading order — natively encoded in a format LLM tokenizers can parse without translation overhead. A table encodes its full grid structure via OTSL. A heading carries its level and page position.
Your model doesn’t have to guess. Governance metadata — PII flags, RAG permissions, training constraints — lives inside <head>, not in a sidecar file. The same standard extends beyond text documents. Audio transcripts, images, and video segments encode as first-class elements — speakers, timestamps, and scenes using the same primitives as headings and tables.
DocLang was created by the Docling team and launched as a standard in June 2026.
