# Document parsing

> Document parsing turns a file, such as a PDF or a page, into text and structure you can chunk.

Turning a file, such as a PDF or a page, into text and structure you can chunk.

Track: Retrieval & Grounding
Access: free
Card: https://buildsparkai.com/document-parsing
Plain text: https://buildsparkai.com/document-parsing.md
Last checked: 2026-10-18

## What it is

Azure Document Intelligence's layout model, v4.0 (API version 2024-11-30, generally available), takes a PDF, an image, or an Office file and returns text, tables, selection marks, and structure. The layout guide separates a geometric role, such as a table, from a logical role, such as a heading. Microsoft's version table lists v4.0 with no announced end of support. It lists v2.1 end of support as September 15, 2027, so this card cites v4.0. LlamaParse's current docs say Parse converts PDFs, scans, and Office files to markdown or JSON, and that the older llama-parse package is deprecated. This card cites the current docs. The picture is one page, two ways. It does not call either API.

## Why it matters

**Cost.** Azure's layout guide says the paid tier accepts a file up to 500 MB, and the free tier up to 4 MB. PDFs and TIFFs can run to 2,000 pages, and the free tier processes the first two pages. Those are limits on that API, not a price. LlamaParse's current docs show a parse call and do not state a page rate on the page this card cites. This card does not add one.

**Quality.** A table that comes back as one line can be split through the middle of a row. Azure's layout response can keep a table as a table, and a heading as a heading. LlamaParse's docs show markdown with a heading and a table.

**Risk.** Azure's layout guide says a password-locked PDF must be unlocked before you submit it. A parse can still drop a footer or a scanned line. The chunk you search is only as complete as the text you kept.

## Try today

Take one PDF you would put in the support bot. Read the text you would chunk. If a table row no longer names its column, parse for structure before you split.

## Common mistake

Chunking a plain-text export of the PDF and treating a broken table row as a fact.

## Self-check

A parsed row says "14." The heading "Refund window, days" was on the line above, and the export dropped it. What is wrong?

Retrieval can return "14" without the heading

## Practice and deep

Coming soon. One support PDF, with the heading and the table row written as the text you would chunk.

Coming soon. How Azure's v4.0 layout response labels a table and a heading, and how LlamaParse returns markdown for the same kind of file.

## Sources

- [Azure Document Intelligence, Layout v4.0](https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/prebuilt/layout?view=doc-intel-4.0.0)
- [Azure Document Intelligence, Version support](https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/overview?view=doc-intel-4.0.0)
- [LlamaParse, Documentation](https://developers.llamaindex.ai/llamaparse/)

Opened 2026-10-18. The layout page is v4.0, which Microsoft lists with no announced end of support. v2.1 is listed with an end of support on September 15, 2027, so this card does not cite it. The deprecated llama-parse package is not a source. This card does not add a page rate.