pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-08 20:42:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

Feat: MinerU supports VLM-Transfomers backend (#10809)

Browse Source 
### What problem does this PR solve?

MinerU supports VLM-Transfomers backend.

Set `MINERU_BACKEND="pipeline"` to choose the backend. (Options:
pipeline | vlm-transformers, default is pipeline)

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

---------

Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
This commit is contained in:
Yongteng Lei
2025-10-27 17:04:13 +08:00
committed by GitHub
parent 16ec6ad346
commit 5acc407240
3 changed files with 33 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
docs/faq.mdx
View File

@ -536,5 +536,16 @@ uv pip install -U "mineru[core]" -i https://mirrors.aliyun.com/pypi/simple
4. In the web UI, navigate to the **Configuration** page of your dataset. Click **Built-in** in the **Ingestion pipeline** section, select a chunking method from the **Built-in** dropdown, which supports PDF parsing, and slect **MinerU** in **PDF parser**.
5. If you use a custom ingestion pipeline instead, you must also complete the first three steps before selecting **MinerU** in the **Parsing method** section of the **Parser** component.
---
### How to specify the settings of MinerU?
Set `MINERU_EXECUTABLE` to the path of the MinerU executable. (Default: mineru)
Set `MINERU_DELETE_OUTPUT=0` to keep MinerU's output. (Default: 1, which deletes temporary output)
Set `MINERU_OUTPUT_DIR` to specify the output directory. (Uses a temporary directory if unset)
Set `MINERU_BACKEND="pipeline"` to choose the backend. (Options: pipeline | vlm-transformers, default is pipeline)
Other environment variables listed [here](https://opendatalab.github.io/MinerU/usage/cli_tools/#environment-variables-description) are supported automatically by MinerU.