{
 "schema_version": 1,
 "generated": "2026-10-31",
 "id": "docling-project-docling--convert-a-research-pdf-with-tables-to-markdown",
 "repo": "docling-project/docling",
 "repo_url": "https://github.com/docling-project/docling",
 "repo_slug": "docling-project-docling",
 "title": "Convert a complex PDF with tables into clean Markdown",
 "page_title": "How to convert a complex PDF with tables into clean Markdown with Docling",
 "summary": "Install Docling and convert a paper or report, keeping layout, reading order and tables intact.",
 "who": "A researcher who keeps getting jumbled columns and broken tables when extracting text from PDFs.",
 "problem": "Two-column layouts, tables and formulas come out scrambled with simple PDF text extraction.",
 "outcome": "A Markdown file in the current directory with the document's structure, tables and reading order preserved.",
 "steps": [
  "Install with `pip install docling`",
  "Convert a document from a URL or a local path with `docling https://arxiv.org/pdf/2206.01062`",
  "Open the generated .md file in the current directory",
  "Try the visual language model pipeline with `docling --pipeline vlm --vlm-model granite_docling https://arxiv.org/pdf/2206.01062` and compare"
 ],
 "agent_prompt": "Install docling-project/docling and convert <pdf path or URL> to Markdown with the docling CLI. Then run it again with the granite_docling VLM pipeline and tell me which version handled the tables better.",
 "agents": [
  "claude-code",
  "codex",
  "cursor"
 ],
 "difficulty": "Beginner",
 "time": "15 minutes",
 "basis": "readme",
 "caveat": "The first run downloads models, and the VLM pipeline is much slower without a GPU.",
 "category": "Research",
 "tags": [
  "Research"
 ],
 "lang": "python",
 "requirements": [
  "Python 3.10 or higher",
  "macOS, Linux or Windows on x86_64 or arm64",
  "Optional: a GPU for faster VLM pipelines such as GraniteDocling"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": true,
 "score": 1.0,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/docling-project-docling/convert-a-research-pdf-with-tables-to-markdown/",
 "md": "https://dedupedai.com/use-cases/docling-project-docling/convert-a-research-pdf-with-tables-to-markdown/index.md",
 "disclaimer": "Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked \"Seen in the wild\", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email hello@dedupedai.com and we will look at it promptly.",
 "api": "https://dedupedai.com/api/v1/usecases/docling-project-docling--convert-a-research-pdf-with-tables-to-markdown.json",
 "api_version": "v1"
}