DEDUPEDWho it is forA researcher who keeps getting jumbled columns and broken tables when extracting text from PDFs.
The problemTwo-column layouts, tables and formulas come out scrambled with simple PDF text extraction.
The outcomeA Markdown file in the current directory with the document's structure, tables and reading order preserved.
What you need first
- Python 3.10 or higher
- macOS, Linux or Windows on x86_64 or arm64
- Optional: a GPU for faster VLM pipelines such as GraniteDocling
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/2206.01062and compare
Prompt for your agent
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.
Caveat. The first run downloads models, and the VLM pipeline is much slower without a GPU.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for docling-project/docling and "Convert a complex PDF with tables into clean Markdown"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer