MuPDF4LLM.NET
1.28.0.3-rc.1
dotnet add package MuPDF4LLM.NET --version 1.28.0.3-rc.1
NuGet\Install-Package MuPDF4LLM.NET -Version 1.28.0.3-rc.1
<PackageReference Include="MuPDF4LLM.NET" Version="1.28.0.3-rc.1" />
<PackageVersion Include="MuPDF4LLM.NET" Version="1.28.0.3-rc.1" />
<PackageReference Include="MuPDF4LLM.NET" />
paket add MuPDF4LLM.NET --version 1.28.0.3-rc.1
#r "nuget: MuPDF4LLM.NET, 1.28.0.3-rc.1"
#:package MuPDF4LLM.NET@1.28.0.3-rc.1
#addin nuget:?package=MuPDF4LLM.NET&version=1.28.0.3-rc.1&prerelease
#tool nuget:?package=MuPDF4LLM.NET&version=1.28.0.3-rc.1&prerelease
About
MuPDF4LLM.NET provides LLM/RAG helpers for MuPDF.NET: PDF-to-Markdown conversion, layout parsing, and document structure analysis. It is designed for use with RAG (Retrieval-Augmented Generation) pipelines and integration with LLMs.
Documentation: docs.pdf4llm.com · .NET installation
This package extends MuPDF.NET with:
- PDF-to-Markdown — Convert PDF pages to Markdown with layout awareness (tables, headers, images)
- Layout parsing — Extract document structure (pages, boxes, tables, images) as JSON or structured objects
- LlamaIndex integration —
PDFMarkdownReaderfor compatibility with LlamaIndex document loading - OCR support — Optional OCR for scanned or image-heavy pages
- Form fields — Extract key/value pairs from interactive PDF forms
Install with dotnet add package MuPDF4LLM.NET. MuPDF.NET is installed automatically as a dependency.
For Office/HWP documents (DOC/DOCX, XLS/XLSX, PPT/PPTX, HWP/HWPX), also install
MuPDFOffice.NET, call MuPDFOffice.Unlock(...),
then pass those paths to MuPDF4LLM.ToMarkdown / MuPDF4LLM.ToJson / MuPDF4LLM.ToText.
PyMuPDF Layout (optional)
AI-based page layout uses the Python package pymupdf-layout via an external worker. Install it once per machine:
dotnet msbuild -t:MuPDF4LLMNetSetupLayoutPython
This creates a per-user Python venv (Windows: %LOCALAPPDATA%\MuPDF4LLM.NET\.venv-layout, Linux/macOS: ~/.local/share/mupdf4llm.net/.venv-layout) and installs pinned pymupdf / pymupdf-layout wheels. MuPDF4LLM.NET discovers that venv automatically.
On Debian/Ubuntu, install system packages first:
sudo apt install python3-venv python3-pip
Alternatively, install pymupdf-layout into any Python 3.10+ environment and set MuPDF4LLM_NET_PYTHON to that interpreter. If layout is unavailable, MuPDF4LLM.NET falls back to classic text extraction.
Project-local venv: run python path/to/setup_layout_python.py --venv .mupdf4llm-net-venv in your project directory (also auto-discovered).
License and Copyright
MuPDF4LLM.NET is part of MuPDF.NET and is available under the Artifex Community License and commercial license agreements. If you determine you cannot meet the requirements of the Artifex Community License, please contact Artifex for more information regarding a commercial license.
| Product | Versions Compatible and additional computed target framework versions. |
|---|---|
| .NET | net5.0 is compatible. net5.0-windows was computed. net6.0 is compatible. net6.0-android was computed. net6.0-ios was computed. net6.0-maccatalyst was computed. net6.0-macos was computed. net6.0-tvos was computed. net6.0-windows was computed. net7.0 is compatible. net7.0-android was computed. net7.0-ios was computed. net7.0-maccatalyst was computed. net7.0-macos was computed. net7.0-tvos was computed. net7.0-windows was computed. net8.0 is compatible. net8.0-android was computed. net8.0-browser was computed. net8.0-ios was computed. net8.0-maccatalyst was computed. net8.0-macos was computed. net8.0-tvos was computed. net8.0-windows was computed. net9.0 was computed. net9.0-android was computed. net9.0-browser was computed. net9.0-ios was computed. net9.0-maccatalyst was computed. net9.0-macos was computed. net9.0-tvos was computed. net9.0-windows was computed. net10.0 was computed. net10.0-android was computed. net10.0-browser was computed. net10.0-ios was computed. net10.0-maccatalyst was computed. net10.0-macos was computed. net10.0-tvos was computed. net10.0-windows was computed. |
| .NET Core | netcoreapp2.0 was computed. netcoreapp2.1 was computed. netcoreapp2.2 was computed. netcoreapp3.0 was computed. netcoreapp3.1 was computed. |
| .NET Standard | netstandard2.0 is compatible. netstandard2.1 was computed. |
| .NET Framework | net461 is compatible. net462 was computed. net463 was computed. net47 was computed. net471 was computed. net472 is compatible. net48 is compatible. net481 was computed. |
| MonoAndroid | monoandroid was computed. |
| MonoMac | monomac was computed. |
| MonoTouch | monotouch was computed. |
| Tizen | tizen40 was computed. tizen60 was computed. |
| Xamarin.iOS | xamarinios was computed. |
| Xamarin.Mac | xamarinmac was computed. |
| Xamarin.TVOS | xamarintvos was computed. |
| Xamarin.WatchOS | xamarinwatchos was computed. |
-
.NETFramework 4.6.1
- Markdig (>= 0.38.0)
- Microsoft.ML.OnnxRuntime (>= 1.20.1)
- MuPDF.NET (>= 3.28.1.6)
-
.NETFramework 4.7.2
- Markdig (>= 0.38.0)
- Microsoft.ML.OnnxRuntime (>= 1.20.1)
- MuPDF.NET (>= 3.28.1.6)
-
.NETFramework 4.8
- Markdig (>= 0.38.0)
- Microsoft.ML.OnnxRuntime (>= 1.20.1)
- MuPDF.NET (>= 3.28.1.6)
-
.NETStandard 2.0
- Markdig (>= 0.38.0)
- Microsoft.ML.OnnxRuntime (>= 1.20.1)
- MuPDF.NET (>= 3.28.1.6)
-
net5.0
- Markdig (>= 0.38.0)
- Microsoft.ML.OnnxRuntime (>= 1.20.1)
- MuPDF.NET (>= 3.28.1.6)
-
net6.0
- Markdig (>= 0.38.0)
- Microsoft.ML.OnnxRuntime (>= 1.20.1)
- MuPDF.NET (>= 3.28.1.6)
-
net7.0
- Markdig (>= 0.38.0)
- Microsoft.ML.OnnxRuntime (>= 1.20.1)
- MuPDF.NET (>= 3.28.1.6)
-
net8.0
- Azure.AI.OpenAI (>= 2.1.0)
- Azure.Search.Documents (>= 11.6.0)
- Markdig (>= 0.38.0)
- Microsoft.Extensions.AI (>= 10.3.0)
- Microsoft.Extensions.AI.OpenAI (>= 10.3.0)
- Microsoft.ML.OnnxRuntime (>= 1.24.3)
- MuPDF.NET (>= 3.28.1.6)
- RapidOcrNet (>= 2.0.0)
NuGet packages
This package is not used by any NuGet packages.
GitHub repositories
This package is not used by any popular GitHub repositories.
| Version | Downloads | Last Updated |
|---|---|---|
| 1.28.0.3-rc.1 | 0 | 8/6/2026 |
LLM/RAG helpers for PDF processing: Markdown conversion, layout analysis, multi-column detection.