DS4SD/docling
A document parser that turns PDFs, Word and PowerPoint files, spreadsheets, HTML and XBRL financial reports into Markdown, JSON or other structured formats. It keeps tables, reading order and formulas intact, can use vision models for scanned pages, and ships with LangChain and LlamaIndex integrations plus an MCP server.
Idea adaptedKey files read, not run
I learnt this repo's idea and adapted it into my own workspace setup.
How we know
We read the README and key files, not every source file, and did not run it, so the most we can say is Idea adapted or Risky.
Good for
Anyone feeding PDFs or office files into an LLM or a retrieval pipeline who needs the tables and structure to survive.
Not for
Someone who only needs to read one PDF by eye; a full install with the vision-model options is heavier than a plain text extractor for simple jobs.
Repo
- Stars
- None
- License
- NoneNo license means the author keeps every right. You can read the code, but you have no right to copy or reuse it.
- Maturity
- None
- Last push
- Last checked
- 2026-11-14