MinerU Parser

Overview

Parse PDF, DOC, DOCX, PPT, PPTX, and image files into markdown format using the MinerU API. Extract text, tables, formulas, and structured content with support for OCR and VLM models.

Token Setup

REQUIRED: MinerU API requires authentication via API token.

Getting Your Token

1. Visit the MinerU website and register/login
2. Navigate to your account settings or API section
3. Generate or copy your API token

Recommended: Environment Variable

Set the token as an environment variable before starting work: