I have searched the existing issues and discussions.
I am using the latest version of Open WebUI.
Installation Method
Git Clone
Open WebUI Version
v0.6.13
Ollama Version (if applicable)
No response
Operating System
Windows 10
Browser (if applicable)
No response
Confirmation
I have read and followed all instructions in README.md.
I am using the latest version of both Open WebUI and Ollama.
I have included the browser console logs.
I have included the Docker container logs.
I have provided every relevant configuration, setting, and environment variable used in my setup.
I have clearly listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc).
I have documented step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation. My steps:
Start with the initial platform/version/OS and dependencies used,
Specify exact install/launch/configure commands,
List URLs visited, user input (incl. example values/emails/passwords if needed),
Describe all options and toggles enabled or changed,
Include any files or environmental changes,
Identify the expected and actual result at each stage,
Ensure any reasonably skilled user can follow and hit the same issue.
Expected Behavior
Can upload PDF files containing images normally when using docling
Actual Behavior
upload PDF files containing images failed.
Steps to Reproduce
Set the value of Content Extraction Engine to "docling" , "tesseract", "eng"
Go to chat page and upload a PDF file containing images, then failed.
Logs & Screenshots
Additional Information
No response
Originally created by @xiajianlin on GitHub (Jun 10, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/14821
### Check Existing Issues
- [x] I have searched the existing issues and discussions.
- [x] I am using the latest version of Open WebUI.
### Installation Method
Git Clone
### Open WebUI Version
v0.6.13
### Ollama Version (if applicable)
_No response_
### Operating System
Windows 10
### Browser (if applicable)
_No response_
### Confirmation
- [x] I have read and followed all instructions in `README.md`.
- [x] I am using the latest version of **both** Open WebUI and Ollama.
- [x] I have included the browser console logs.
- [x] I have included the Docker container logs.
- [x] I have **provided every relevant configuration, setting, and environment variable used in my setup.**
- [x] I have clearly **listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup** (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc).
- [x] I have documented **step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation**. My steps:
- Start with the initial platform/version/OS and dependencies used,
- Specify exact install/launch/configure commands,
- List URLs visited, user input (incl. example values/emails/passwords if needed),
- Describe all options and toggles enabled or changed,
- Include any files or environmental changes,
- Identify the expected and actual result at each stage,
- Ensure any reasonably skilled user can follow and hit the same issue.
### Expected Behavior
Can upload PDF files containing images normally when using docling
### Actual Behavior
upload PDF files containing images failed.
### Steps to Reproduce
1. Set the value of Content Extraction Engine to "docling" , "tesseract", "eng"
2. Go to chat page and upload a PDF file containing images, then failed.
### Logs & Screenshots
### Additional Information
_No response_
GiteaMirror
added the bug label 2026-04-19 23:06:57 -05:00
Seems like open-webui is incompatible with docling-serve v12 and v13. Last working version is v11.
<!-- gh-comment-id:2959054911 -->
@Expro commented on GitHub (Jun 10, 2025):
Seems like open-webui is incompatible with docling-serve v12 and v13. Last working version is v11.
I have the same issue. I did notice this error with ALL versions of docling though
ERROR:docling_serve.engines.async_local.worker:Worker 0 failed to process job 0b523f78-3735-4132-a971-36df5de69f62: 500: ({'eng'}, 'is not supported')
That is my setting for the OCR language. If i remove it then things start to work again. So it must be the API changed.
<!-- gh-comment-id:2963770570 -->
@geiseri commented on GitHub (Jun 11, 2025):
I have the same issue. I did notice this error with ALL versions of docling though
```
ERROR:docling_serve.engines.async_local.worker:Worker 0 failed to process job 0b523f78-3735-4132-a971-36df5de69f62: 500: ({'eng'}, 'is not supported')
```
That is my setting for the OCR language. If i remove it then things start to work again. So it must be the API changed.
@frenzybiscuit commented on GitHub (Jun 12, 2025):
Seems like open-webui is incompatible with docling-serve v12 and v13. Last working version is v11.
BINGO! This is correct.
In your docker compose file, set the image to: quay.io/docling-project/docling-serve:v0.11.0
<!-- gh-comment-id:2967874701 -->
@frenzybiscuit commented on GitHub (Jun 12, 2025):
> Seems like open-webui is incompatible with docling-serve v12 and v13. Last working version is v11.
BINGO! This is correct.
In your docker compose file, set the image to: quay.io/docling-project/docling-serve:v0.11.0
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.
Originally created by @xiajianlin on GitHub (Jun 10, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/14821
Check Existing Issues
Installation Method
Git Clone
Open WebUI Version
v0.6.13
Ollama Version (if applicable)
No response
Operating System
Windows 10
Browser (if applicable)
No response
Confirmation
README.md.Expected Behavior
Can upload PDF files containing images normally when using docling
Actual Behavior
upload PDF files containing images failed.
Steps to Reproduce
Logs & Screenshots
Additional Information
No response
@Expro commented on GitHub (Jun 10, 2025):
Seems like open-webui is incompatible with docling-serve v12 and v13. Last working version is v11.
@silentoplayz commented on GitHub (Jun 10, 2025):
Related - https://github.com/open-webui/open-webui/issues/14807
@geiseri commented on GitHub (Jun 11, 2025):
I have the same issue. I did notice this error with ALL versions of docling though
That is my setting for the OCR language. If i remove it then things start to work again. So it must be the API changed.
@frenzybiscuit commented on GitHub (Jun 12, 2025):
BINGO! This is correct.
In your docker compose file, set the image to: quay.io/docling-project/docling-serve:v0.11.0