Parse complex documents without losing tables, layout, or uncertainty

“feat: optional HTML field on RAG chunk records Motivation Docling already converts to a structured DoclingDocument and exports retrieval chunks as JSONL via --to chunks. Each ChunkedDocumentResultItem carries text, raw_text, headings, captions, doc_items, page_numbers, and metadata (including origin). It does not carry the HTML of the items in that chunk. Marker's --output_format chunks puts full HTML on each…”

“Hi Malte and team; Teams building enterprise RAG on Haystack need high throughput in document-loading components. AnyDoc converts heavy PDFs and tables to clean Markdown in seconds, boosting pipeline efficiency. Founder's Lock: the first 100 get lifetime 50% off ($14.50/mo instead of $29) plus 5,000 free pages in month one. Details: https://www.ostlertech.com/anydoc Best, OstlerTech Team”

“### Problem In the `pypdfium2` PDF backend, `PyPdfiumPageBackend._object_rects` / `has_content_in` re-enumerate every object on the page on each call. `has_content_in` is invoked per layout cluster (2-3 times each), so on a page with many objects the cost is O(clusters × objects), and text extraction via `get_text_bounded` is O(rects × chars). A page with a large number of path/text objects makes conversion…”

“### Bug When the table structure model returns a grid that leaves a PDF word outside every row band and every column band, `MatchingPostProcessor._pick_orphan_cells` in docling-ibm-models drops that word, and because the layout stage already assigned it to the table cluster, docling never emits it as text either. The word is absent from the `DoclingDocument`, the Markdown and the JSON export. On a dense public…”

“## Question / proposal Is Docling interested in a vendor-neutral profile for embedding a versioned `DoclingDocument` JSON representation in the source PDF, so later consumers can load it instead of repeating PDF parsing, layout inference, and OCR? PDF 2.0 Associated Files and PDF/A-4f already provide a plausible container. A minimal interoperability profile could define: - the embedded file media type and…”

“**Is your feature request related to a problem? Please describe.** When processing PDFs with `DocumentCleaner(remove_repeated_substrings=True)`, documents that are effectively empty after cleaning still pass through downstream. For example: - A scanned-image page → extracted text is `" "` (whitespace only) - A footer-only page → after `remove_repeated_substrings=True`, content becomes `""` - A chapter-title page…”

“## Bug Since v2.116.0 (the layout-driven OCR pipeline refactor in #3710), table extraction can misalign row labels and numeric values on PDFs where the embedded native PDF text layer is only partially reliable — common for auto-generated Chinese/Japanese/Korean regulatory filings, where some table cells carry real native PDF text and others are effectively garbled or image-backed and need OCR. ## What we observed…”

“## Feature request: extract embedded MathML / native structured equations before formula reconstruction ### Description Does Docling currently detect and extract a structured mathematical representation that is already embedded in the source document, instead of reconstructing the formula visually using the formula enrichment model? In particular, modern accessible/tagged PDFs can contain a MathML representation…”

“This is a docling-core schema proposal (that repo has discussions disabled, so posting here). Follow-up to #301 and companion to docling PR #4055, which extracts the AcroForm widget layer and is the concrete producer that wants to write these attributes. 1. Motivation DoclingDocument's form model (FormItem + GraphData, the field_* labels) represents visible page content: every GraphCell documents its text/orig as…”

“### Bug When parsing arXiv HTML generated by LaTeXML, Docling preserves the surrounding text but completely loses the contents of HTML ` ` elements. The source HTML contains valid ` ` elements with standard ` `, ` `, ` `, ` `, ` `, and ` ` elements. However, after conversion with `DocumentConverter`, the resulting DoclingDocument JSON does not contain the table cell contents, and `export_to_markdown()`…”

“The PR #3934 drafted a first declarative backend, `IWorkPagesDocumentBackend`, to parse Apple's iWork Pages documents. The backend needs some improvements to pair the capabilities of similar backend parsers like `MsWordDocumentBackend` for Word documents. Just drop a line if you're interested in resolving this issue. Make sure to follow the…”

“From: YRA Tech (document-accessibility tooling; Docling is the structural backbone of our conversion pipeline). Prior upstream work: docling#3803 (supersample), docling-parse#299/#300/#301/#314, the MLX conversion kit for docling#3943. Summary. We convert documents into tagged, PDF/UA-conformant PDFs using DoclingDocument as our canonical model. Docling's layout, table, and reading-order components are the…”