Docling Slim
Lightweight SDK for parsing documents with minimal dependencies and opt-in extras
Docling Slim is a minimal-dependency version of Docling that allows you to install only the components you need. It provides the core document processing functionality with ~50MB of base dependencies, and you can add specific features through optional extras.
When to Use Docling Slim
- Use
docling(recommended): If you want the full-featured experience with all standard capabilities - Use
docling-slim: If you need fine-grained control over dependencies or want to minimize installation size
For Most Users: Use the Main Docling Package
We recommend most users install the full-featured docling package instead:
pip install docling
The docling package includes all standard features, the CLI tools, and is the easiest way to get started. Visit the main Docling documentation for complete guides and examples.
Installation
With Specific Features
# PDF support with local models
pip install docling-slim[format-pdf,models-local]
# Office formats only
pip install docling-slim[format-office]
# PDF + CLI
pip install docling-slim[format-pdf,cli]
# Docling service client for using the Docling Serve API
pip install docling-slim[service-client]
Available Extras
Convenience Bundles
| Extra | Description | Use Case |
|---|---|---|
standard |
All standard features (same as docling package) |
Full-featured usage |
all |
All available extras | Complete installation |
CLI
| Extra | Description | Use Case |
|---|---|---|
cli |
Command-line interface (typer, rich) | CLI tools (docling, docling-tools) |
Core Components
| Extra | Description | Use Case |
|---|---|---|
convert-core |
Core conversion components (numpy, pillow, scipy) | Basic document conversion |
extract-core |
Structured information extraction | Data extraction from documents |
Format Support
PDF Formats
| Extra | Description | Use Case |
|---|---|---|
format-pdf |
PDF parsing (pypdfium2 + docling-parse) | PDF documents |
format-pdf-pypdfium2 |
PDF rendering only | Lightweight PDF support |
format-pdf-docling |
Advanced PDF parsing with docling-parse (independent of pypdfium2) | Complex PDF layouts |
Office Formats (office = docx + pptx + xlsx)
| Extra | Description | Use Case |
|---|---|---|
format-office |
All Office formats | Microsoft Office documents |
format-docx |
Microsoft Word documents | .docx files |
format-pptx |
Microsoft PowerPoint | .pptx files |
format-xlsx |
Microsoft Excel | .xlsx files |
Web Formats (web = html + markdown)
| Extra | Description | Use Case |
|---|---|---|
format-web |
HTML and Markdown | Web content |
format-html |
HTML parsing | Web pages and HTML files |
format-markdown |
Markdown parsing | .md files |
Other Formats
| Extra | Description | Use Case |
|---|---|---|
format-latex |
LaTeX documents | .tex files |
format-xml-xbrl |
XBRL financial reports | Financial documents |
format-html-render |
HTML rendering with Playwright | Dynamic web content |
format-audio |
Audio transcription (Whisper) | .wav, .mp3 files |
OCR Engines
| Extra | Description | Use Case |
|---|---|---|
feat-ocr-rapidocr |
RapidOCR (lightweight) | Fast OCR |
feat-ocr-rapidocr-onnx |
RapidOCR with ONNX runtime | Optimized OCR |
feat-ocr-easyocr |
EasyOCR | Multi-language OCR |
feat-ocr-tesserocr |
Tesseract OCR | High-accuracy OCR |
feat-ocr-mac |
macOS native OCR | macOS only |
Models
| Extra | Description | Use Case |
|---|---|---|
models-local |
Local PyTorch models | GPU/CPU inference |
models-remote |
Remote model serving (Triton) | Production deployments |
models-onnxruntime |
ONNX Runtime acceleration | Optimized inference |
models-vlm-inline |
Vision Language Models | Image understanding, inline processing |
Other features
| Extra | Description | Use Case |
|---|---|---|
feat-chunking |
Document chunking | RAG applications |
service-client |
Docling service client | Remote processing |
License
MIT License - See LICENSE
Metadata
Release files for docling-slim 2.133.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| docling_slim-2.133.0.tar.gz | 775.3 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| docling_slim-2.133.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 1.7 MB
Release files / docling_slim-2.133.0.tar.gz
| Download URL | docling_slim-2.133.0.tar.gz |
|---|---|
| Size | 775.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
190e72946fd985a6ae3710916bc0012f40c35025910babcf463ebb75f0c797be
|
|
BLAKE2b-256 checksum How to use checksums |
289f44cc6414d775fd536789f012a17f032eba1316d5b129321bf2d07d02286b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 3, 2026.
Transparency logRelease files / docling_slim-2.133.0-py3-none-any.whl
| Download URL | docling_slim-2.133.0-py3-none-any.whl |
|---|---|
| Size | 950.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
419c26b89d65b113e9bea6293b128bb7503e3ef104d271525279e31423fe8153
|
|
BLAKE2b-256 checksum How to use checksums |
da7e650b15e2cbc6e78c62b408ae7f69b128c98c21952849586bf7055738d7a9
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 3, 2026.
Transparency log
