PyRank
docling-project

docling-slim

Get your documents ready for gen AI
PyPI GitHub
More links
Download Stats changelog issues
Verified repo
Monthly downloads
2.9M
Weekly downloads
767.1K
GitHub stars *
69.0K

Downloads in the 30 and 7 days to October 10, 2026. Refreshed weekly.

Package Information

Latest Version
2.140.0
Requires Python
<4.0,>=3.10
Licence
MIT
Last Release
8 hr ago
First Release
April 29, 2026
Total Releases
53
Python Versions
3 3.10 3.11 3.12 3.13 3.14
No reported malware or high/critical advisories · Details

The current version has no OSV.dev malware reports and no critical or high-severity vulnerabilities.

Package Insights

What's this?
Score breakdown - each component scores 0-100, weighted by percentage
Maintenance
100
Popularity
97
Adoption
90
Community
70
Provenance
100
How the maintenance status was determined
Last commit
0 days ago
Monthly downloads
2,903,557
• Active
Activity within 30 days
Stable
Activity within 31-180 days
Minimal
Activity within 181-365 days, or no activity data
At Risk
No activity for > 365 days, but > 10,000 monthly downloads
Archived
Repository flagged as archived on GitHub
How the popularity category was determined
Monthly downloads
2,903,557
Stars
68,962
Stars per 1k downloads
23.75
Industry Standard
> 10,000,000 monthly downloads
Hidden Gem
< 0.5 stars per 1k downloads and > 100,000 monthly downloads
• Community Favorite
> 5 stars per 1k downloads
Rising Star
Balanced ratio of stars to downloads
Unknown
Fewer than 1,000 monthly downloads, or no star data
How download momentum is calculated
Week daily avg
109,588
Month daily avg
96,785
Momentum
+13.2%
((week_daily_avg - month_daily_avg) / month_daily_avg) * 100
More insights and metrics
Python version support tiers
requires_python
<4.0,>=3.10
Cutting Edge
Minimum supported version is 3.14 or newer
Modern
Minimum supported version is 3.11 to 3.13
• Legacy
Supports 3.10 or older (or Python 2)
Unknown
No requires_python specified or unparseable
License categories
License
MIT
• Permissive
MIT, Apache, BSD, ISC, Unlicense, CC0, etc.
Copyleft
GPL, LGPL, AGPL, MPL, EPL, etc.
Proprietary
Commercial, all rights reserved, custom EULAs
Unknown
No license specified, or none of the above match
How the release cadence was determined
Last release
0 days ago
Total releases
53
Releases/year
113.8
• Rapid
Last release within 365 days and > 12 releases/year
Regular
Last release within 365 days
Slow
Last release 366-730 days ago
Stalled
Last release > 730 days ago, or no releases
Unknown
No usable release date available
How contributor risk was determined
Contributors
380
Monthly downloads
2,903,557
High Load
≤ 2 contributors and ≥ 50,000 monthly downloads
Moderate Load
< 10 contributors and ≥ 500,000 monthly downloads
Low Load
< 25 contributors and ≥ 5,000,000 monthly downloads, or sole maintainer with ≥ 10,000 monthly downloads
• Balanced
Enough contributors for the package's popularity
Unknown
No contributor data available
Engagement
82
 
Issue Burden
10.1
per 1k stars
Discussions
6.9
per 1k stars
Fork Ratio
7.5%
contrib / forks
Stale Release
No
 
PR Velocity
Quiet
 
Not all downloads include detailed metadata. Breakdowns reflect the subset that does.

Downloads by OS

Linux 60.2K
Windows 1.6K
macOS 1.4K

Python Versions

3.12
66.3% 41.5K
3.13
17.0% 10.7K
3.11
10.1% 6.3K
3.14
5.7% 3.6K
3.10
0.9% 582

Top Countries

1. US US
54.9K
2. DE DE
2.2K
3. CA CA
807
4. FR FR
706
5. BE BE
553
6. IN IN
540
7. NL NL
485
8. GB GB
396
9. SG SG
346
10. JP JP
329

Weekly Downloads

GitHub Stars *

Dependencies

9
162 optional dependencies
  • accelerate<2,>=1.0.0[models-local]
    extra == "models-local"
  • accelerate<2,>=1.0.0[all]
    extra == "all"
  • accelerate<2,>=1.0.0[standard]
    extra == "standard"
  • accelerate<2.0.0,>=1.2.1[models-vlm-inline]
    extra == "models-vlm-inline"
  • arelle-release<3.0.0,>=2.38.17[all]
    extra == "all"
  • arelle-release<3.0.0,>=2.38.17[format-xml-xbrl]
    extra == "format-xml-xbrl"
  • beautifulsoup4<5.0.0,>=4.12.3[standard]
    extra == "standard"
  • beautifulsoup4<5.0.0,>=4.12.3[all]
    extra == "all"
  • beautifulsoup4<5.0.0,>=4.12.3[format-email]
    extra == "format-email"
  • beautifulsoup4<5.0.0,>=4.12.3[format-html]
    extra == "format-html"
  • beautifulsoup4<5.0.0,>=4.12.3[format-web]
    extra == "format-web"
  • beautifulsoup4<5.0.0,>=4.12.3[format-xml-jats]
    extra == "format-xml-jats"
  • beautifulsoup4<5.0.0,>=4.12.3[format-xml-uspto]
    extra == "format-xml-uspto"
  • defusedxml<0.8.0,>=0.7.1[standard]
    extra == "standard"
  • defusedxml<0.8.0,>=0.7.1[all]
    extra == "all"
  • defusedxml<0.8.0,>=0.7.1[format-iwork]
    extra == "format-iwork"
  • defusedxml<0.8.0,>=0.7.1[format-xml-uspto]
    extra == "format-xml-uspto"
  • defusedxml<0.8.0,>=0.7.1[models-local]
    extra == "models-local"
  • docling-core<3.0.0,>=2.98.0[standard]
    extra == "standard"
  • docling-core<3.0.0,>=2.98.0[feat-chunking]
    extra == "feat-chunking"
  • docling-core<3.0.0,>=2.98.0[all]
    extra == "all"
  • docling-ibm-models<5,>=4.0.2[models-local]
    extra == "models-local"
  • docling-ibm-models<5,>=4.0.2[standard]
    extra == "standard"
  • docling-ibm-models<5,>=4.0.2[all]
    extra == "all"
  • docling-parse<8.0.0,>=7.22.1[all]
    extra == "all"
  • docling-parse<8.0.0,>=7.22.1[format-pdf-docling]
    extra == "format-pdf-docling"
  • docling-parse<8.0.0,>=7.22.1[standard]
    extra == "standard"
  • docling-parse<8.0.0,>=7.22.1[format-pdf]
    extra == "format-pdf"
  • easyocr<2.0,>=1.7[all]
    extra == "all"
  • easyocr<2.0,>=1.7[feat-ocr-easyocr]
    extra == "feat-ocr-easyocr"
  • einops<1.0.0,>=0.8.1[models-vlm-inline]
    extra == "models-vlm-inline"
  • einops<1.0.0,>=0.8.1[all]
    extra == "all"
  • httpx<1.0.0,>=0.28[standard]
    extra == "standard"
  • httpx<1.0.0,>=0.28[service-client]
    extra == "service-client"
  • httpx<1.0.0,>=0.28[all]
    extra == "all"
  • huggingface-hub<2,>=0.23[all]
    extra == "all"
  • huggingface-hub<2,>=0.23[standard]
    extra == "standard"
  • huggingface-hub<2,>=0.23[models-local]
    extra == "models-local"
  • librosa<1.0.0,>=0.10.0[format-video]
    extra == "format-video"
  • lxml<7.0.0,>=4.0.0[format-xml-jats]
    extra == "format-xml-jats"
  • lxml<7.0.0,>=4.0.0[all]
    extra == "all"
  • mail-parser<5.0.0,>=4.1.4[format-email]
    extra == "format-email"
  • mail-parser<5.0.0,>=4.1.4[standard]
    extra == "standard"
  • mail-parser<5.0.0,>=4.1.4[all]
    extra == "all"
  • marko<3.0.0,>=2.1.2[format-web]
    extra == "format-web"
  • marko<3.0.0,>=2.1.2[standard]
    extra == "standard"
  • marko<3.0.0,>=2.1.2[format-markdown]
    extra == "format-markdown"
  • marko<3.0.0,>=2.1.2[all]
    extra == "all"
  • mlx-vlm<1.0.0,>=0.7.0[models-vlm-inline]
    (python_version >= "3.10" and sys_platform == "darwin" and platform_machine == "arm64") and extra == "models-vlm-inline"
  • mlx-vlm<1.0.0,>=0.7.0[all]
    (python_version >= "3.10" and sys_platform == "darwin" and platform_machine == "arm64") and extra == "all"
  • mlx-whisper>=0.4.3[format-video]
    (python_version >= "3.10" and sys_platform == "darwin" and platform_machine == "arm64") and extra == "format-video"
  • mlx-whisper>=0.4.3[format-audio]
    (python_version >= "3.10" and sys_platform == "darwin" and platform_machine == "arm64") and extra == "format-audio"
  • mlx-whisper>=0.4.3[all]
    (python_version >= "3.10" and sys_platform == "darwin" and platform_machine == "arm64") and extra == "all"
  • nemotron-ocr>=2.0.0[feat-ocr-nemotron]
    (python_version == "3.12" and sys_platform == "linux" and platform_machine == "x86_64") and extra == "feat-ocr-nemotron"
  • numba>=0.63.0[format-audio]
    extra == "format-audio"
  • numba>=0.63.0[format-video]
    extra == "format-video"
  • numba>=0.63.0[all]
    extra == "all"
  • numpy<3.0.0,>=1.24.0[extract-core]
    extra == "extract-core"
  • numpy<3.0.0,>=1.24.0[standard]
    extra == "standard"
  • numpy<3.0.0,>=1.24.0[convert-core]
    extra == "convert-core"
  • numpy<3.0.0,>=1.24.0[all]
    extra == "all"
  • ocrmac<2.0.0,>=1.0.0[feat-ocr-mac]
    sys_platform == "darwin" and extra == "feat-ocr-mac"
  • ocrmac<2.0.0,>=1.0.0[all]
    sys_platform == "darwin" and extra == "all"
  • odfdo<4.0.0,>=3.22.0[format-opendocument]
    extra == "format-opendocument"
  • onnxruntime<1.24[models-onnxruntime]
    (python_version < "3.11" and sys_platform == "darwin") and extra == "models-onnxruntime"
  • onnxruntime<1.24[all]
    (python_version < "3.11" and sys_platform == "darwin") and extra == "all"
  • onnxruntime<1.24,>=1.7.0[feat-ocr-rapidocr-onnx]
    python_version < "3.11" and extra == "feat-ocr-rapidocr-onnx"
  • onnxruntime-gpu<1.24[models-onnxruntime]
    (python_version < "3.11" and (sys_platform == "linux" or sys_platform == "win32")) and extra == "models-onnxruntime"
  • onnxruntime-gpu<1.24[all]
    (python_version < "3.11" and (sys_platform == "linux" or sys_platform == "win32")) and extra == "all"
  • open-clip-torch<4.0.0,>=3.2.0[all]
    extra == "all"
  • open-clip-torch<4.0.0,>=3.2.0[models-vlm-inline]
    extra == "models-vlm-inline"
  • openai-whisper>=20250625[format-audio]
    extra == "format-audio"
  • openai-whisper>=20250625[format-video]
    extra == "format-video"
  • openai-whisper>=20250625[all]
    extra == "all"
  • openpyxl<4.0.0,>=3.1.5[standard]
    extra == "standard"
  • openpyxl<4.0.0,>=3.1.5[format-xlsx]
    extra == "format-xlsx"
  • openpyxl<4.0.0,>=3.1.5[format-office]
    extra == "format-office"
  • openpyxl<4.0.0,>=3.1.5[all]
    extra == "all"
  • pandas<4.0.0,>=2.1.4[feat-ocr-tesserocr]
    extra == "feat-ocr-tesserocr"
  • pandas<4.0.0,>=2.1.4[all]
    extra == "all"
  • peft>=0.18.1[models-vlm-inline]
    extra == "models-vlm-inline"
  • peft>=0.18.1[all]
    extra == "all"
  • pillow<13.0.0,>=10.0.0[standard]
    extra == "standard"
  • pillow<13.0.0,>=10.0.0[convert-core]
    extra == "convert-core"
  • pillow<13.0.0,>=10.0.0[extract-core]
    extra == "extract-core"
  • pillow<13.0.0,>=10.0.0[all]
    extra == "all"
  • playwright>=1.58.0[format-html-render]
    extra == "format-html-render"
  • playwright>=1.58.0[all]
    extra == "all"
  • polyfactory>=2.22.2[extract-core]
    extra == "extract-core"
  • polyfactory>=2.22.2[all]
    extra == "all"
  • polyfactory>=2.22.2[standard]
    extra == "standard"
  • pylatexenc<3.0,>=2.10[format-office]
    extra == "format-office"
  • pylatexenc<3.0,>=2.10[format-pptx]
    extra == "format-pptx"
  • pylatexenc<3.0,>=2.10[standard]
    extra == "standard"
  • pylatexenc<3.0,>=2.10[all]
    extra == "all"
  • pylatexenc<3.0,>=2.10[format-latex]
    extra == "format-latex"
  • pypdfium2!=4.30.1,<6.0.0,>=4.30.0[format-pdf-pypdfium2]
    extra == "format-pdf-pypdfium2"
  • pypdfium2!=4.30.1,<6.0.0,>=4.30.0[standard]
    extra == "standard"
  • pypdfium2!=4.30.1,<6.0.0,>=4.30.0[all]
    extra == "all"
  • pypdfium2!=4.30.1,<6.0.0,>=4.30.0[format-pdf]
    extra == "format-pdf"
  • python-docx<2.0.0,>=1.2.0[format-office]
    extra == "format-office"
  • python-docx<2.0.0,>=1.2.0[standard]
    extra == "standard"
  • python-docx<2.0.0,>=1.2.0[all]
    extra == "all"
  • python-docx<2.0.0,>=1.2.0[format-docx]
    extra == "format-docx"
  • python-dotenv~=1.0[service-client]
    extra == "service-client"
  • python-dotenv~=1.0[standard]
    extra == "standard"
  • python-dotenv~=1.0[all]
    extra == "all"
  • python-dotenv~=1.0[cli]
    extra == "cli"
  • python-oxmsg<0.1.0,>=0.0.2[standard]
    extra == "standard"
  • python-oxmsg<0.1.0,>=0.0.2[all]
    extra == "all"
  • python-oxmsg<0.1.0,>=0.0.2[format-email]
    extra == "format-email"
  • python-pptx<2.0.0,>=1.0.2[format-pptx]
    extra == "format-pptx"
  • python-pptx<2.0.0,>=1.0.2[standard]
    extra == "standard"
  • python-pptx<2.0.0,>=1.0.2[all]
    extra == "all"
  • python-pptx<2.0.0,>=1.0.2[format-office]
    extra == "format-office"
  • qwen-vl-utils>=0.0.11[models-vlm-inline]
    extra == "models-vlm-inline"
  • qwen-vl-utils>=0.0.11[all]
    extra == "all"
  • rapidocr<4.0.0,>=3.9.1[feat-ocr-rapidocr-onnx]
    extra == "feat-ocr-rapidocr-onnx"
  • rapidocr<4.0.0,>=3.9.1[all]
    extra == "all"
  • rapidocr<4.0.0,>=3.9.1[standard]
    extra == "standard"
  • rapidocr<4.0.0,>=3.9.1[feat-ocr-rapidocr]
    extra == "feat-ocr-rapidocr"
  • resemblyzer<0.2.0,>=0.1.4[format-video]
    extra == "format-video"
  • rich>=13.0.0[cli]
    extra == "cli"
  • rich>=13.0.0[all]
    extra == "all"
  • rich>=13.0.0[service-client]
    extra == "service-client"
  • rich>=13.0.0[standard]
    extra == "standard"
  • rtree<2.0.0,>=1.3.0[extract-core]
    extra == "extract-core"
  • rtree<2.0.0,>=1.3.0[standard]
    extra == "standard"
  • rtree<2.0.0,>=1.3.0[all]
    extra == "all"
  • rtree<2.0.0,>=1.3.0[convert-core]
    extra == "convert-core"
  • scikit-image>=0.19[feat-ocr-easyocr]
    extra == "feat-ocr-easyocr"
  • scikit-image>=0.19[all]
    extra == "all"
  • scikit-learn<2.0.0,>=1.3.0[format-video]
    extra == "format-video"
  • scipy<2.0.0,>=1.6.0[convert-core]
    extra == "convert-core"
  • scipy<2.0.0,>=1.6.0[extract-core]
    extra == "extract-core"
  • scipy<2.0.0,>=1.6.0[standard]
    extra == "standard"
  • scipy<2.0.0,>=1.6.0[all]
    extra == "all"
  • soundfile<1.0.0,>=0.12.1[format-video]
    extra == "format-video"
  • tesserocr<3.0.0,>=2.7.1[feat-ocr-tesserocr]
    extra == "feat-ocr-tesserocr"
  • tesserocr<3.0.0,>=2.7.1[all]
    extra == "all"
  • timm<2.0.0,>=1.0.22[models-vlm-inline]
    extra == "models-vlm-inline"
  • timm<2.0.0,>=1.0.22[all]
    extra == "all"
  • torch<3.0.0,>=2.2.2[all]
    extra == "all"
  • torch<3.0.0,>=2.2.2[models-local]
    extra == "models-local"
  • torch<3.0.0,>=2.2.2[standard]
    extra == "standard"
  • torchvision<1,>=0[all]
    extra == "all"
  • torchvision<1,>=0[models-local]
    extra == "models-local"
  • torchvision<1,>=0[standard]
    extra == "standard"
  • transformers!=5.0.*,!=5.1.*,!=5.10.*,!=5.11.*,!=5.12.*,!=5.13.*,!=5.14.*,!=5.15.*,!=5.2.*,!=5.3.*,!=5.9.*,<6.0.0,>=4.42.0[all]
    sys_platform == "darwin" and extra == "all"
  • transformers!=5.0.*,!=5.1.*,!=5.10.*,!=5.11.*,!=5.12.*,!=5.13.*,!=5.14.*,!=5.15.*,!=5.2.*,!=5.3.*,!=5.9.*,<6.0.0,>=4.42.0[models-vlm-inline]
    sys_platform == "darwin" and extra == "models-vlm-inline"
  • tritonclient<3.0.0,>=2.65.0[all]
    extra == "all"
  • tritonclient<3.0.0,>=2.65.0[models-remote]
    extra == "models-remote"
  • typer<0.27.0,>=0.19.0[all]
    extra == "all"
  • typer<0.27.0,>=0.19.0[cli]
    extra == "cli"
  • typer<0.27.0,>=0.19.0[service-client]
    extra == "service-client"
  • typer<0.27.0,>=0.19.0[standard]
    extra == "standard"
  • websockets<17.0,>=14.0[all]
    extra == "all"
  • websockets<17.0,>=14.0[service-client]
    extra == "service-client"
  • websockets<17.0,>=14.0[standard]
    extra == "standard"
  • whisper-s2t-reborn<2.0.0,>=1.7.1[all]
    (sys_platform != "darwin" or platform_machine != "arm64") and extra == "all"
  • whisper-s2t-reborn<2.0.0,>=1.7.1[format-audio]
    (sys_platform != "darwin" or platform_machine != "arm64") and extra == "format-audio"
  • whisper-s2t-reborn<2.0.0,>=1.7.1[format-video]
    (sys_platform != "darwin" or platform_machine != "arm64") and extra == "format-video"

Used By

17
View all 17 dependents

Repository details

Forks
5.1K
Issues
694
Last Commit
13 hr ago
Contributors
380
Open PRs
188
Archived
No

Data and sources

Tracking Since
September 26, 2026
Data Updated
October 11, 2026
Data Freshness
Fresh
Keywords
convert docling document docx html layout model markdown pdf segmentation
Sources and methodology