doclingExtract and parse content from web pages, PDFs, documents (docx, pptx), and images using the docling CLI with GPU acceleration. Use INSTEAD of web_fetch for extracting content from specific URLs when you need clean, structured text. Use Brave (web_search) for searching/discovering pages. Use docling when you HAVE a URL and need its content parsed.
Install via ClawdBot CLI:
clawdbot install Er3mit4/doclingCLI tool for parsing documents and web pages into clean, structured text. Uses GPU acceleration for OCR and ML models.
docling CLI must be installed (e.g., via pipx install docling)docling "<URL>" --from html --to mdOutput: creates a .md file in current directory (or use --output)
docling "<URL>" --from html --to text --output /tmp/docling_outdocling "/path/to/file.pdf" --ocr --device cuda --output /tmp/docling_out| Option | Values | Description |
|--------|--------|-------------|
| --from | html, pdf, docx, pptx, image, md, csv, xlsx | Input format |
| --to | md, text, json, yaml, html | Output format |
| --device | auto, cuda, cpu | Accelerator (default: auto) |
| --output | path | Output directory (recommended: use controlled temp dir) |
| --ocr | flag | Enable OCR for images/scanned PDFs |
| --tables | flag | Extract tables (default: on) |
ā ļø Avoid these flags unless you trust the source:
--enable-remote-services - can send data to remote endpoints--allow-external-plugins - loads third-party code--headers with untrusted values - can redirect requestsdocling "" --from html --to text --output /tmp/docling_out Docling supports GPU acceleration via CUDA (NVIDIA). Verify CUDA is available:
python -c "import torch; print(torch.cuda.is_available())"See references/cli-reference.md for complete option list.
Generated Mar 1, 2026
Law firms use docling to extract structured text from legal PDFs, contracts, and court documents for case preparation and review. It enables quick OCR of scanned documents and conversion to searchable formats, improving efficiency in legal research and compliance checks.
Researchers and universities employ docling to parse academic papers, web articles, and presentation slides into clean text for literature reviews and data analysis. It supports various formats like PDF and PPTX, facilitating content extraction from diverse sources without manual copying.
Companies utilize docling to extract data from financial reports, PDFs, and web pages for generating insights and automated reports. It helps in converting documents to JSON or text formats, enabling integration with analytics tools for market analysis and decision-making.
Media agencies and publishers use docling to scrape and parse content from news websites and documents into markdown or plain text for content curation and republishing. It ensures clean extraction while avoiding security risks with untrusted sources.
Healthcare providers apply docling with OCR to convert scanned medical records, images, and PDFs into structured text for electronic health records (EHR) systems. This accelerates data entry and improves accessibility for patient management and analysis.
Offer docling as a cloud-based service with tiered pricing for different usage levels, targeting businesses needing regular document parsing. Revenue is generated through monthly or annual subscriptions, with add-ons for advanced features like GPU acceleration.
Sell custom licenses to large organizations for on-premise deployment, including support and integration services. This model provides tailored solutions for industries like legal or healthcare, with revenue from one-time fees and ongoing maintenance contracts.
Provide a free basic version of docling for individual users, while charging for API access and advanced features like high-volume processing or GPU support. Revenue comes from API usage fees and premium upgrades for developers and companies.
š¬ Integration Tip
Install docling via pipx and use temporary output directories to manage extracted files efficiently, ensuring cleanup after processing to maintain system security and performance.
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
Command-line tool to manage Google Workspace services including Gmail, Calendar, Drive, Sheets, Docs, Slides, Contacts, Tasks, People, Groups, and Keep.
Runs shell commands inside a dedicated tmux session named claw, captures, and returns the output, with safety checks for destructive commands.
A modern text-based browser. Renders web pages in the terminal using headless Firefox.
Write robust, portable shell scripts. Use when parsing arguments, handling errors properly, writing POSIX-compatible scripts, managing temp files, running commands in parallel, managing background processes, or adding --help to scripts.
NotebookLM CLI wrapper via `node {baseDir}/scripts/notebooklm.mjs`. Use for auth, notebooks, chat, sources, notes, sharing, research, and artifact generation/download.