01 / Blog · Aug 13, 2026
Converting PDF to Markdown for an LLM is useful only when reading order, headings, lists, tables, and page context survive the transformation. Keep a structured companion record beside Markdown so chunks and citations remain traceable to source pages and parser evidence.
Read post →
02 / Blog · Sep 29, 2026
PDF to JSON is useful when the JSON names pages, ordered blocks, and the route that produced them. DocParse returns that record as docir.v1 alongside Markdown. The Markdown is for reading. The JSON is for citations, tables, and reprocessing.
Read post →
03 / Blog · Sep 29, 2026
A scanned PDF is a set of page images. Parsing it means recognizing the text, keeping page numbers, and recording that the route was OCR or layout analysis. A digital text layer and a scan should not share one silent default.
Read post →
04 / Blog · Sep 29, 2026
A PDF table is a grid, not a paragraph. Extraction has to keep headers, row order, and the page the grid came from. Markdown is a readable view of a small table. The structured record is what an application should trust for a cell.
Read post →
05 / Blog · Sep 29, 2026
A multi-column PDF stores glyphs with positions, not paragraphs. Sorting every line from top to bottom mixes the columns. Detect the regions, read each column from top to bottom, then move to the next column.
Read post →
06 / Blog · Sep 29, 2026
In a PDF, a heading is often just larger or bolder text at a position. Markdown needs that line marked as a heading, with a level that matches the outline. Later chunks should break on those headings instead of on an arbitrary token count.
Read post →
07 / Blog · Sep 29, 2026
A Word file already stores paragraphs, styles, lists, and tables. Parsing it means carrying that structure into Markdown and into DocIR, including heading levels and list grouping. Flattening the document to a single string throws away the outline the author wrote.
Read post →
08 / Blog · Sep 29, 2026
A PowerPoint file is a sequence of slides, and each slide is a page. Parsing should keep the slide number, the title, and the body text in that order. Text boxes sorted only by coordinates scramble the slide the way columns scramble a PDF.
Read post →
09 / Blog · Sep 29, 2026
An Excel file is a set of sheets. Each sheet has a name, a header row, and records under those headers. Parsing should keep that shape. A single paragraph of cell values drops the header that makes a number mean something.
Read post →
10 / Blog · Sep 29, 2026
PNG, JPEG, and WebP files have no text layer. Any words you index come from OCR or a vision route. DocParse enables image parsing only for an approved paid workspace, and the job should record that route and its warnings.
Read post →
11 / Blog · Sep 29, 2026
HTML already has headings, lists, and tables. CSV already has a header and rows. Parsing them means keeping that structure in Markdown and DocIR. Stripping an HTML page to a text blob, or joining a CSV into one paragraph, drops the only labels the file had.
Read post →