LlamaIndex proposes a shared Document Parsing Protocol for parser output rules

AILlamaIndex has introduced the Document Parsing Protocol (DPP), a shared set of rules for how document parsers handle text, tables, forms, charts, and diagrams. The protocol addresses differences in how parsers decide whether a region is a table or text and how to handle multi-row table headers.

LlamaIndex 🦙Official

@llama_index

View on X

Is that a table, or just text that happens to line up?
If a table has two header rows, should the output preserve both?

Parsers make these judgment calls differently. Those differences shape what your agent understands about a document.

We built the Document Parsing Protocol (DPP) to give those decisions a shared rulebook.

DPP covers text, tables, forms, charts, and diagrams, and even includes chemical structures and music notation. Each rule comes with example pages and expected outputs to make it concrete.

The working draft is live, and we’d love your feedback :) Get the Claude skill or ChatGPT reference file, try it on your messiest page, and let us know what comes back.

Try it here: https://www.parseprotocol.com/#adopt

Source details

LlamaIndex 🦙 · x.comPublished Oct 28, 11:31 AM ET · added here 11:55 AM ET

Original title: Is that a table, or just text that happens to line up?

LlamaIndex proposes a shared Document Parsing Protocol for parser output rules

Topics