Giskard provides open source evaluation and testing tools for LLM agents.
Open source
24 alternativesopendatalab/MinerU
MinerU converts complex PDF and Office documents into Markdown or JSON for AI workflows.
About opendatalab/MinerU
MinerU is a GitHub repository that converts complex PDF and Office documents into Markdown or JSON for use in AI and agent workflows. It accepts PDFs, scanned or captured images, Word, PowerPoint, and Excel files, OpenDocument files, EPUB, OFD, HTML, MHTML, RTF, and CSV or TSV files, among others.
Parsing is organized into four tiers. Flash is intended for fast previews and indexing, Basic adds OCR and model-based parsing, and Standard and Advanced are intended for more demanding layouts and quality requirements. PDFs and images support all four tiers, while Office, OpenDocument, EPUB, OFD, HTML, MHTML, and CSV/TSV files use only local Flash native parsing. Documents are not automatically uploaded to the official service, and remote parsing requires explicit configuration. The project requires Python 3.10 or later and below 3.15.
Key features
- Converts PDFs, scanned images, and Office files into Markdown or JSON
- Four parsing tiers, from Flash previews to Standard and Advanced
- Local document library that caches results and searches document content
- Continues reading by page or block with stable citation locators
- Configurable model backends including ONNX, Torch, llama.cpp, vLLM, and LMDeploy
- Renders a single document model to nine output targets, including DOCX and EPUB
Best for: Developers and teams building LLM or agent workflows that need text and structure extracted from PDFs and Office documents.
Good for
- Local document library caches results and supports content search
- Documents are not automatically uploaded to the official service
- Multiple parsing tiers let users choose between speed and layout quality
Watch out for
- Office, OpenDocument, EPUB, OFD, HTML, and CSV/TSV files use only Flash native parsing
- Remote parsing requires explicit configuration
- Requires Python 3.10 or later and below 3.15
opendatalab/MinerU at a glance
- Category
- AI & Machine Learning › AI Data & Analytics
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Not stated
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
opendatalab/MinerU alternatives
Tools and sites you could use instead, ranked by how closely they match.
Open-RAG-Eval evaluates retrieval-augmented generation without requiring golden answers.
Open source
24 alternatives
Vearch provides distributed vector search capabilities for applications built around artificial intelligence.
Open source
24 alternatives
DB-GPT is an open-source agentic data assistant for AI and data products.
Open source
24 alternatives
AutoRAG helps an agent search for information across files on a computer.
RagTune helps inspect, debug, benchmark, and tune retrieval for retrieval augmented generation systems.
Open source
24 alternativesPopular in AI Data & Analytics
Well-known listings from the same topic.
Dotgetdot.aiForvioforvio.comFluidAI Medicalfluidai.mdApache Zeppelinzeppelin.apache.orgSola Securitysola.securityQuadraticquadratichq.com
opendatalab/MinerU FAQ
Are documents sent to an external service when I parse them?
Documents are not automatically uploaded to the official service. Remote parsing requires explicit configuration.
Which parsing tiers are available for Office files?
PDFs and images support all four tiers. Office, OpenDocument, EPUB, OFD, HTML/MHTML, and CSV/TSV files use local Flash native parsing.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.