Marker

Marker converts documents to markdown, JSON, chunks, and HTML quickly and accurately.

Tool Features

Marker converts various document formats including:

• PDF files
• Image files
• PPTX, DOCX, XLSX files
• HTML files
• EPUB files
• Files in all languages

Formatting Capabilities

Marker handles various document elements:

• Formats tables, forms, equations, inline math
• Extracts links, references, and code blocks
• Extracts and saves images
• Removes headers/footers and other artifacts

Extensibility

Marker offers excellent extensibility:

• Extensible with your own formatting and logic
• Does structured extraction, given a JSON schema (beta)
• Optionally boost accuracy with LLMs (and your own prompt)
• Works on GPU, CPU, or MPS

Use Cases

Marker is suitable for scenarios that require converting various document formats to structured text, such as:

• Converting PDF documents to editable Markdown format
• Extracting structured data from documents
• Preparing training data for machine learning projects
• Document digitization and archiving
• Automating document processing workflows