Currently, it defaults to "pipeline", which has substantially worse performance. It attempts to support using the vlm backend, but the value is not supported. MinerU logs this:
Exception: vlm-vllm-engine backend is not supported in async mode, please use vlm-vllm-async-engine backend
Passing the backend parameter vlm-vllm-async-engine works as expected and produces more accurate markdown files.
Fixed
Change the backend parameter passed to MinerU from vlm-vllm-engine to vlm-vllm-async-engine
Contributor License Agreement
By submitting this pull request, I confirm that I have read and fully agree to the Contributor License Agreement (CLA), and I am providing my contributions under its terms.
Note
Deleting the CLA section will lead to immediate closure of your PR and it will not be merged in.
🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.
## 📋 Pull Request Information
**Original PR:** https://github.com/open-webui/open-webui/pull/19105
**Author:** [@1over137](https://github.com/1over137)
**Created:** 11/11/2025
**Status:** ❌ Closed
**Base:** `dev` ← **Head:** `patch-1`
---
### 📝 Commits (2)
- [`e0d5de1`](https://github.com/open-webui/open-webui/commit/e0d5de16978786b8a7538adf1efcde5258f38faf) Merge pull request #18978 from open-webui/dev
- [`efa5665`](https://github.com/open-webui/open-webui/commit/efa5665828ff21e42cfca4f82fd3e84c12a59639) Update mineru.py
### 📊 Changes
**1 file changed** (+1 additions, -1 deletions)
<details>
<summary>View changed files</summary>
📝 `backend/open_webui/retrieval/loaders/mineru.py` (+1 -1)
</details>
### 📄 Description
### Description
(discussion https://github.com/open-webui/open-webui/discussions/18446)
Currently, it defaults to "pipeline", which has substantially worse performance. It attempts to support using the `vlm` backend, but the value is not supported. MinerU logs this:
```
Exception: vlm-vllm-engine backend is not supported in async mode, please use vlm-vllm-async-engine backend
```
Passing the backend parameter `vlm-vllm-async-engine` works as expected and produces more accurate markdown files.
### Fixed
- Change the `backend` parameter passed to MinerU from `vlm-vllm-engine` to `vlm-vllm-async-engine`
### Contributor License Agreement
By submitting this pull request, I confirm that I have read and fully agree to the [Contributor License Agreement (CLA)](https://github.com/open-webui/open-webui/blob/main/CONTRIBUTOR_LICENSE_AGREEMENT), and I am providing my contributions under its terms.
> [!NOTE]
> Deleting the CLA section will lead to immediate closure of your PR and it will not be merged in.
---
<sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
📋 Pull Request Information
Original PR: https://github.com/open-webui/open-webui/pull/19105
Author: @1over137
Created: 11/11/2025
Status: ❌ Closed
Base:
dev← Head:patch-1📝 Commits (2)
e0d5de1Merge pull request #18978 from open-webui/devefa5665Update mineru.py📊 Changes
1 file changed (+1 additions, -1 deletions)
View changed files
📝
backend/open_webui/retrieval/loaders/mineru.py(+1 -1)📄 Description
Description
(discussion https://github.com/open-webui/open-webui/discussions/18446)
Currently, it defaults to "pipeline", which has substantially worse performance. It attempts to support using the
vlmbackend, but the value is not supported. MinerU logs this:Passing the backend parameter
vlm-vllm-async-engineworks as expected and produces more accurate markdown files.Fixed
backendparameter passed to MinerU fromvlm-vllm-enginetovlm-vllm-async-engineContributor License Agreement
By submitting this pull request, I confirm that I have read and fully agree to the Contributor License Agreement (CLA), and I am providing my contributions under its terms.
🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.