mineru
A practical document parsing tool for converting PDF, images, DOCX, PPTX, and XLSX into Markdown and JSON
Decision gist · record as of 2026-08-14
Yes, with conditions. MinerU is actively maintained, has no known vulnerabilities, and offers broad multi-format support with strong accuracy on complex documents. However, the custom license treatment is unclear—verify the terms before commercial use. The 29 runtime dependencies are substantial; assess whether your environment can absorb them. Install if you need reliable document parsing for RAG, LLM workflows, or multi-format ingestion; skip if you need lightweight PDF-only extraction or have strict license requirements.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10–3.13.
- First run may download model files (size and time depend on chosen backend).
- Verify custom license terms before production use.
License · maintenance · safety
LicenseRef-MinerU-Open-Source-License (unclear) — Licensed under MinerU Open Source License (LicenseRef-MinerU-Open-Source-License), a custom Apache 2.0–based license. License treatment is marked unclear in the metadata; verify the exact terms at the repository before integrating into proprietary or commercial workflows.
last release 2026-08-14 (0 days) · last repo commit 2026-08-14 · 77,637 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 335,817 downloads/mo, #7,471 on PyPI
Alternatives
Verify before relying
pip install mineru
from mineru.api import MinerU
api = MinerU()
result = api.parse_pdf('document.pdf')
print(result.to_markdown())- Whether the custom MinerU Open Source License permits commercial use without restrictions or attribution requirements.
- Whether all 29 runtime dependencies are required for basic parsing or if subsets can be installed for lighter use cases.
- Performance characteristics (latency, throughput, memory) for typical document sizes and batch processing.
- Whether the VLM and OCR engines require model downloads on first run and how much disk space they consume.
What it is and what it does
MinerU is a document parsing engine that reads PDF, DOCX, PPTX, XLSX, images, and web pages and outputs them as structured Markdown or JSON. It uses a dual VLM (vision language model) and OCR engine to handle both text-based and scanned documents, supporting 109 languages and complex layouts like multi-column text, cross-page tables, and handwriting. The package includes native parsers for DOCX, PPTX, and XLSX (as of version 3.1.0), converts formulas to LaTeX and tables to HTML, and reconstructs layout in human reading order with automatic header/footer removal.
The package ships with multiple inference backends: a fast pipeline backend optimized for CPU/GPU, a VLM engine for high accuracy, and a hybrid engine balancing speed and precision. It integrates with LangChain, LlamaIndex, Dify, FastGPT, and other RAG frameworks, and offers CLI, REST API, Python SDK, and MCP Server interfaces. You can deploy it privately and fully offline, with support for domestic AI chips (Ascend, Cambricon, Enflame, and others). The 29 runtime dependencies include heavy libraries like opencv-python, huggingface-hub, and fastapi, so installation expands your environment substantially.
Use it for
- Ingest PDFs and documents into RAG pipelines by converting them to structured Markdown or JSON for embedding and retrieval.
- Parse scanned or handwritten documents with OCR to extract text and tables in human reading order.
- Convert DOCX, PPTX, and XLSX files to Markdown for version control, archival, or downstream processing.
- Build document understanding workflows for LLM agents that need to reason over complex layouts and multi-language content.
- Extract and reconstruct tables from PDFs as HTML or JSON for data analysis and database ingestion.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, with conditions.
MinerU is actively maintained, has no known vulnerabilities, and offers broad multi-format support with strong accuracy on complex documents. However, the custom license treatment is unclear—verify the terms before commercial use. The 29 runtime dependencies are substantial; assess whether your environment can absorb them. Install if you need reliable document parsing for RAG, LLM workflows, or multi-format ingestion; skip if you need lightweight PDF-only extraction or have strict license requirements.
Install
mineru on PyPI
Before you install
Low install friction with a pure-Python wheel. Brings 29 runtime dependencies including heavy libraries (opencv-python, huggingface-hub, modelscope, fastapi) that will expand your environment significantly. Active maintenance with recent releases and high repository engagement (77637 stars).
Requires Python 3.10–3.13. First run may download model files (size and time depend on chosen backend). Verify custom license terms before production use.
License in practice
Licensed under MinerU Open Source License (LicenseRef-MinerU-Open-Source-License), a custom Apache 2.0–based license. License treatment is marked unclear in the metadata; verify the exact terms at the repository before integrating into proprietary or commercial workflows.
Quickstart
pip install mineru
from mineru.api import MinerU
api = MinerU()
result = api.parse_pdf('document.pdf')
print(result.to_markdown())Verify before relying
- Whether the custom MinerU Open Source License permits commercial use without restrictions or attribution requirements.
- Whether all 29 runtime dependencies are required for basic parsing or if subsets can be installed for lighter use cases.
- Performance characteristics (latency, throughput, memory) for typical document sizes and batch processing.
- Whether the VLM and OCR engines require model downloads on first run and how much disk space they consume.
Package facts
| License | LicenseRef-MinerU-Open-Source-License unclear |
| Python support | Supports the current Python release <3.14,>=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 29 packagesclicklogurunumpytqdmrequestshttpxpillowpypdfium2pypdfreportlabpdftextmodelscopehuggingface-hubjson-repairopencv-pythonfast-langdetectopenaibeautifulsoup4magikamineru-vl-utilspython-docxpypptx-with-oxmlmammothpylatexenclxmlopenpyxlfastapipython-multipartuvicorn |
| Maintenance | Actively maintained 0 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 335,817 / month, #7,471 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13 |
Evidence: mineru-3.4.5-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “document parsing ocr vlm”
- mineruConverts PDF, DOCX, PPTX, XLSX, images, and web pages into structured…
- marker-pdfMarker converts PDFs, images, and other document formats (PPTX, DOCX,…
- vlmrunPython SDK for the VLM Run API platform, providing access to…
Give your agent the search over MCP, or paste the wish link into any chat.
More Text Processing packages
A drop-in replacement for Python's standard `re` module that adds advanced regex features like nested sets, fuzzy matching, lookaround in conditionals, and full Unicode case-folding while maintaining backward compatibility.
pyparsing provides a library for building text parsers directly in Python code using composable grammar classes, handling quoted strings, whitespace variation, and embedded comments without regex or lex/yacc.
Install it if you need to parse text or define grammars programmatically.
fonttools manipulates font files in multiple formats (TrueType, OpenType, AFM, Type 1, Mac-specific) and includes TTX, a tool to convert fonts to and from XML text format.
Install it if you need to read, write, or manipulate fonts programmatically or via the TTX command-line tool.
Docutils converts plaintext documentation in reStructuredText format into multiple output formats including HTML, XML, and LaTeX using a modular processing system.
RapidFuzz provides fast fuzzy string matching using Levenshtein Distance and related metrics, implemented mostly in C++ with Python bindings for rapid similarity scoring and approximate string matching.
Install it if you need fuzzy string matching; it's a solid replacement for FuzzyWuzzy with better licensing and performance.
tinycss2 parses CSS strings into token and block objects, and generates CSS strings from those objects, following the CSS Syntax Level 3 specification without enforcing specific properties or values.
Install it if your project requires CSS tokenization or syntax manipulation.
See also marker-pdf · mineru-vl-utils · paddleocr · docling · pymupdf4llm · docling-slim · liteparse · ocrmypdf · llama-parse · pymupdfpro