Skip to main content

​
Installation

​
NuGet package

Or via the Visual Studio Package Manager Console:
Or by adding the package reference directly to your .csproj:

​
Dependencies

PDF4LLM depends on MuPDF.NET and lists it as a NuGet dependency. It is installed automatically — you do not need to add MuPDF.NET separately. After installation, two native DLLs are required at runtime: The NuGet package copies these to your project’s output directory on build. If your deployment environment does not allow automatic DLL placement, both files must be present in the same directory as your application executable, or on a path accessible via the PATH environment variable.

​
Supported targets

PDF4LLM targets .NET Standard 2.0, making it compatible with any framework that implements that standard.

​
Verify the installation

Add a using directive and call ToMarkdown on any PDF to confirm everything is wired up:

​
Resolving the assembly conflict

If you see this error at build or runtime:
Your installed version of MuPDF.NET already bundles PDF4LLM internally. Having both packages referenced simultaneously causes the conflict. Fix: Remove the explicit PDF4LLM package reference and rely on the bundled version:
Or remove the line from your .csproj manually:
The API is identical either way — using PDF4LLM; and PdfExtractor.* work regardless of which package supplies the assembly.
A future release of MuPDF.NET will stop bundling PDF4LLM, allowing both packages to coexist without conflict. Until then, use one or the other.

​
Optional: OCR support

OCR is not required for most PDFs. Enable it only when working with scanned documents or pages that contain no selectable text. OCR requires Tesseract to be installed on the host system and available on the PATH. PDF4LLM does not bundle Tesseract. Windows — Download the installer from UB Mannheim Tesseract builds and add the install directory to your PATH. macOS
Linux (Debian / Ubuntu)
Verify Tesseract is reachable:
See the OCR guide for language pack installation and usage.