Verified project record

opendatalab/MinerU

MinerU converts PDF, image, DOCX, PPTX, and XLSX files into Markdown and JSON for downstream retrieval and processing. It offers CLI, API, and WebUI interfaces with multiple parsing backends that support CPU execution, GPU acceleration, or remote inference.

Project overview

The project supports full-format native parsing across five input types and provides layout detection alongside formula-to-LaTeX and table-to-HTML conversion.

Project type: RAG · Document Processing · Data Processing
Use cases: Documents & Office · Knowledge Q&A
Deployment: Refer to project documentation
License: License pending

Best for

Developers and data teams building retrieval pipelines who need to convert PDF, image, DOCX, PPTX, and XLSX inputs into Markdown and JSON.
Users who require parsing of complex layouts with automatic removal of headers, footers, and page numbers.

Key capabilities

Supports PDF, image, DOCX, PPTX, and XLSX inputs for document conversion.
Removes headers, footers, footnotes, page numbers, and outputs text in human-readable order for single-column, multi-column, and complex layouts.
Automatically recognizes and converts formulas to LaTeX and tables to HTML format.
Automatically detects scanned PDFs and garbled PDFs to enable OCR functionality supporting detection and recognition of 109 languages.
Extracts images, image descriptions, tables, table titles, and footnotes from documents.
Provides built-in CLI, FastAPI, and Gradio WebUI for local orchestration and multi-service deployment.
Preserves the structure of the original document, including headings, paragraphs, and lists.

Limitations and risks

Document parsing is a complex task. In scenarios involving complex layouts, scanned pages, and handwritten content, parsing results may fall short of expectations.
Docker deployment is only supported on Linux and Windows environments with WSL2 support; macOS users should not use Docker deployment.
In non-mainline environments, 100% project availability cannot be guaranteed due to hardware and software diversity and third-party dependency compatibility issues.
The key dependency `ray` does not support Python 3.13 on Windows, restricting supported versions to 3.10 through 3.12.

Getting started

Setup requires command line interface proficiency due to multiple backend and hardware compatibility choices. The first success path involves upgrading pip, installing uv, running `uv pip install -U "mineru[all]"`, and executing `mineru -p <input_path> -o <output_path>`.

Alternatives and comparisons

Provides native code unstructured data extraction from PDFs, Word, and HTML without relying on external services.
Converts PDFs and Word documents into structured data within spaCy Doc objects, integrating with Docling.
Parses PDFs into metadata-rich chunks for RAG pipelines in pure Rust with zero C dependencies.

Project comparisons

Evidence and sources

GitHub project description: Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
README: MinerU is a document parsing tool that converts `PDF`, image, `DOCX`, `PPTX`, and `XLSX` inputs into machine-readable formats such as Markdown and JSON for downstream retrieval, e…
README: 2026/06/18 3.4 Released
README: The OCR model for the `pipeline` backend has been upgraded to `PP-OCRv6`, improving OCR accuracy by about `11%` on OmniDocBench v1.6.
README: VLM model upgraded to `MinerU2.5-Pro-2605-1.2B`

Reviewed at: 2026-07-17T05:28:44Z

Open original GitHub project