Documentation Index
Fetch the complete documentation index at: https://mintlify.com/docling-project/docling/llms.txt
Use this file to discover all available pages before exploring further.
Docling provides a powerful command-line interface for document conversion and model management.
Main Commands
docling convert
Convert documents from various formats to different output formats.
docling convert [OPTIONS] SOURCE...
Arguments
| Argument | Description |
|---|
SOURCE | PDF files to convert. Can be local file paths, directory paths, or URLs. Multiple sources can be specified. |
Basic Examples
Convert a single PDF to Markdown:
docling convert document.pdf
docling convert doc1.pdf doc2.docx doc3.pptx
docling convert /path/to/documents/
docling convert https://example.com/document.pdf
docling convert document.pdf --to json --to html --to markdown
| Option | Description |
|---|
--from | Specify input formats to convert from. Defaults to all formats. |
--to | Specify output formats. Available: json, yaml, html, html_split_page, markdown, text, doctags, vtt. Defaults to markdown. |
--output | Output directory where results are saved. Default: current directory (.) |
--image-export-mode | Image export mode. Options: placeholder, embedded, referenced. Default: embedded |
--show-layout | If enabled, page images will show bounding boxes of items. |
Pipeline Options
| Option | Description |
|---|
--pipeline | Choose the processing pipeline. Options: standard, vlm. Default: standard |
--vlm-model | Choose the VLM preset to use (when using VLM pipeline). Default: granite_docling. Available presets include: granite_docling, smol_docling, etc. |
--asr-model | Choose the ASR model for audio/video files. Options include: whisper_tiny, whisper_base, whisper_small, whisper_medium, whisper_large, whisper_turbo, and MLX/native variants. Default: whisper_tiny |
Processing Options
| Option | Description |
|---|
--ocr / --no-ocr | Enable/disable OCR for bitmap content. Default: enabled |
--force-ocr | Replace any existing text with OCR generated text over the full content. |
--ocr-engine | The OCR engine to use. Default: auto (available: auto, tesseract_cli, tesseract, easyocr, rapidocr) |
--ocr-lang | Comma-separated list of languages for OCR engine. |
--psm | Page Segmentation Mode for OCR engine (0-13). |
--tables / --no-tables | Enable/disable table structure extraction. Default: enabled |
--table-mode | Table structure model mode. Options: fast, accurate. Default: accurate |
Enrichment Options
| Option | Description |
|---|
--enrich-code | Enable code enrichment model in the pipeline. |
--enrich-formula | Enable formula enrichment model in the pipeline. |
--enrich-picture-classes | Enable picture classification enrichment model. |
--enrich-picture-description | Enable picture description model. |
--enrich-chart-extraction | Enable chart extraction to convert bar, pie, and line charts to tabular format. |
PDF Backend Options
| Option | Description |
|---|
--pdf-backend | The PDF backend to use. Options: docling_parse, pypdfium2. Default: docling_parse |
--pdf-password | Password for protected PDF documents. |
| Option | Description |
|---|
--num-threads | Number of threads. Default: 4 |
--device | Accelerator device. Options: auto, cpu, cuda, mps. Default: auto |
--page-batch-size | Number of pages processed in one batch. |
--document-timeout | Timeout for processing each document, in seconds. |
Model and Plugin Options
| Option | Description |
|---|
--artifacts-path | Location of the model artifacts (for offline use). |
--enable-remote-services | Must be enabled when using models connecting to remote services. |
--allow-external-plugins | Must be enabled for loading modules from third-party plugins. |
--show-external-plugins | List third-party plugins available with --allow-external-plugins. |
Debug Options
| Option | Description |
|---|
--debug-visualize-cells | Enable debug output which visualizes PDF cells. |
--debug-visualize-ocr | Enable debug output which visualizes OCR cells. |
--debug-visualize-layout | Enable debug output which visualizes layout clusters. |
--debug-visualize-tables | Enable debug output which visualizes table cells. |
Profiling Options
| Option | Description |
|---|
--profiling | Summarize profiling details for all conversion stages. |
--save-profiling | Save profiling summaries to JSON. |
Other Options
| Option | Description |
|---|
--headers | Specify HTTP request headers for URL sources (JSON string). |
--abort-on-error / --no-abort-on-error | If enabled, processing aborts on first error. Default: disabled |
-v, --verbose | Set verbosity level. Use -v for info logging, -vv for debug logging. |
--version | Show version information. |
--logo | Display Docling ASCII art logo. |
Advanced Examples
Convert with OCR and table extraction:
docling convert document.pdf --ocr --tables --ocr-engine easyocr
docling convert document.pdf --to json --to markdown --to html --output ./output
docling convert document.pdf --pipeline vlm --vlm-model granite_docling
docling convert document.pdf \
--enrich-formula \
--enrich-code \
--enrich-picture-description \
--enrich-chart-extraction
docling convert protected.pdf --pdf-password "mypassword"
docling convert ./documents --profiling --save-profiling --output ./results
docling convert https://example.com/doc.pdf \
--headers '{"Authorization": "Bearer token123", "User-Agent": "Docling"}'
Docling provides helper commands for managing models and other utilities.
Download Docling models for offline use.
docling tools models download [OPTIONS] [MODELS]...
Arguments
| Argument | Description |
|---|
MODELS | Specific models to download. Available options: layout, tableformer, code_formula, picture_classifier, smolvlm, granitedocling, granitedocling_mlx, smoldocling, smoldocling_mlx, granite_vision, granite_chart_extraction, rapidocr, easyocr. |
Options
| Option | Description |
|---|
-o, --output-dir | Directory where models will be downloaded. Default: system cache directory |
--force | Force download even if models already exist. |
--all | Download all available models (mutually exclusive with specifying models). |
-q, --quiet | Minimal output, prints only the output directory. |
Examples
Download default models:
docling tools models download
layout, tableformer, code_formula, picture_classifier, and rapidocr.
Download specific models:
docling tools models download layout tableformer easyocr
docling tools models download --all
docling tools models download --output-dir /path/to/models
docling tools models download layout --force
MODEL_DIR=$(docling tools models download --quiet)
echo "Models are in: $MODEL_DIR"
# First download models
docling tools models download --output-dir ./my-models
# Then use them with convert
docling convert document.pdf --artifacts-path ./my-models
Download specific models from HuggingFace by repository ID.
docling tools models download-hf-repo [OPTIONS] MODELS...
Arguments
| Argument | Description |
|---|
MODELS | HuggingFace repository IDs to download (e.g., docling-project/docling-models). |
Options
| Option | Description |
|---|
-o, --output-dir | Directory where models will be downloaded. Default: system cache directory |
--force | Force download even if model already exists. |
-q, --quiet | Minimal output, prints only the output directory. |
Examples
Download a HuggingFace model:
docling tools models download-hf-repo docling-project/docling-models
docling tools models download-hf-repo \
docling-project/docling-models \
some-org/custom-model
docling tools models download-hf-repo docling-project/docling-models \
--output-dir /path/to/models
docling tools models download-hf-repo docling-project/docling-models --force