mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-05-30 04:27:30 +08:00
### What problem does this PR solve? Implement MinerU Provider **The following functionalities are now supported:** **MinerU** ---- - [x] Parse file - [x] Show task - [ ] ~~List tasks~~ **Verified examples from the CLI:** ```plaintext RAGFlow(user)> parse with 'vlm@test@mineru' file 'https://arxiv.org/pdf/2505.09358' +--------------------------------------+ | task_id | +--------------------------------------+ | 142ac8ea-d9d0-4a68-a2d1-d3af67635dc9 | +--------------------------------------+ RAGFlow(user)> show 'test@mineru' task '142ac8ea-d9d0-4a68-a2d1-d3af67635dc9' +--------------------------------------------+-------+ | content | index | +--------------------------------------------+-------+ | Task is running... Progress: 17 / 18 pages | 0 | +--------------------------------------------+-------+ RAGFlow(user)> show 'test@mineru' task '142ac8ea-d9d0-4a68-a2d1-d3af67635dc9' +--------------------------------------------------------------------------------------------+-------+ | content | index | +--------------------------------------------------------------------------------------------+-------+ | https://cdn-mineru.openxlab.org.cn/pdf/2026-05-18/142ac8ea-d9d0-4a68-a2d1-d3af67635dc9.zip | 0 | +--------------------------------------------------------------------------------------------+-------+ ``` ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue) - [x] New Feature (non-breaking change which adds functionality) - [x] Refactoring