issue: [api] page_no on upload file with docling, Picture Description Mode also got error #5962

New Issue

2025-11-11T16:40:14-06:00

GiteaMirror commented

2025-11-11 16:40:14 -06:00

Originally created by @parsue on GitHub (Aug 5, 2025).

Check Existing Issues

I have searched the existing issues and discussions.
I am using the latest version of Open WebUI.

Installation Method

Pip Install

Open WebUI Version

v0.6.18

Ollama Version (if applicable)

v0.10.1

Operating System

Windows 11

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

upload files with contents.

Actual Behavior

return 200 and add an file data without collection id and contents.
get missing positional argument: 'page_no' on using orc.
get unmarshal array in Go struct field when enable Picture Description Mode, tried to add the structure but failed.
confirmed model in Picture Description is download and can be run with given api.

Steps to Reproduce

my steps

download python 3.11.9 window installer 64-bit from official site
install python
install open-webui by pip (latest)
install docling by pip (latest)
install docling-serve[ui]==0.16.1 <-- for api v1alpha
start open-webui serve
start docling-serve
open open-webui, admin login
go to admin panel > settings > documents > save settings as additional information
restart open-webui serve
visit open-webui docs
upload pdf file by api/v1/files/ as additional information
watch docling and open-webui terminal for logs

reason without browser and docker logs

not using docker
use api only, not using web ui to test

Logs & Screenshots

error on orc:

ERROR:docling_serve.engines.async_local.worker:Worker 0 failed to process job 204b5473-2328-444c-ad2d-23f191122f9f: DoclingDocument._make_copy_with_refmode() missing 1 required positional argument: 'page_no'

error on Picture Description Mode:

ERROR:docling.utils.api_image_request:Error calling the API. Response was {"error":"json: cannot unmarshal array into Go struct field ChatRequest.messages.content of type string"}
ERROR:docling.utils.api_image_request:Error calling the API. Response was {"error":"json: cannot unmarshal array into Go struct field ChatRequest.messages.content of type string"}
ERROR:docling_serve.engines.async_local.worker:Worker 0 failed to process job fbdfa12b-0f70-403b-8140-90a77cff8cd4: 500: 400 Client Error: Bad Request for url: http://localhost:11434/api/chat

Additional Information

Docling version:

Docling Serve version: 0.16.1
Docling version: 2.43.0
Docling Core version: 2.44.1
Docling IBM Models version: 3.9.0
Docling Parse version: 4.1.0
Python: cpython-311 (3.11.9)
Platform: Windows-10-10.0.26100-SP0

Originally created by @parsue on GitHub (Aug 5, 2025). ### Check Existing Issues - [x] I have searched the existing issues and discussions. - [x] I am using the latest version of Open WebUI. ### Installation Method Pip Install ### Open WebUI Version v0.6.18 ### Ollama Version (if applicable) v0.10.1 ### Operating System Windows 11 ### 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 upload files with contents. ### Actual Behavior - return 200 and add an file data without collection id and contents. - get missing positional argument: 'page_no' on using orc. - get unmarshal array in Go struct field when enable Picture Description Mode, tried to add the structure but failed. - confirmed model in Picture Description is download and can be run with given api. ### Steps to Reproduce ### my steps 1. download python 3.11.9 window installer 64-bit from official site 2. install python 3. install open-webui by pip (latest) 4. install docling by pip (latest) 5. install docling-serve[ui]==0.16.1 <-- for api v1alpha 6. start open-webui serve 7. start docling-serve 8. open open-webui, admin login 9. go to admin panel > settings > documents > save settings as additional information 10. restart open-webui serve 11. visit open-webui docs 12. upload pdf file by api/v1/files/ as additional information 13. watch docling and open-webui terminal for logs ### reason without browser and docker logs - not using docker - use api only, not using web ui to test ### Logs & Screenshots <img width="1047" height="645" alt="Image" src="https://github.com/user-attachments/assets/ddb5617d-cb8b-4c4a-931c-adc38d23b8fc" /> <img width="1017" height="994" alt="Image" src="https://github.com/user-attachments/assets/5f48620e-9704-4cd1-ba54-6411a1fe9ab0" /> error on orc: ``` ERROR:docling_serve.engines.async_local.worker:Worker 0 failed to process job 204b5473-2328-444c-ad2d-23f191122f9f: DoclingDocument._make_copy_with_refmode() missing 1 required positional argument: 'page_no' ``` error on Picture Description Mode: ``` ERROR:docling.utils.api_image_request:Error calling the API. Response was {"error":"json: cannot unmarshal array into Go struct field ChatRequest.messages.content of type string"} ERROR:docling.utils.api_image_request:Error calling the API. Response was {"error":"json: cannot unmarshal array into Go struct field ChatRequest.messages.content of type string"} ERROR:docling_serve.engines.async_local.worker:Worker 0 failed to process job fbdfa12b-0f70-403b-8140-90a77cff8cd4: 500: 400 Client Error: Bad Request for url: http://localhost:11434/api/chat ``` ### Additional Information Docling version: ``` Docling Serve version: 0.16.1 Docling version: 2.43.0 Docling Core version: 2.44.1 Docling IBM Models version: 3.9.0 Docling Parse version: 4.1.0 Python: cpython-311 (3.11.9) Platform: Windows-10-10.0.26100-SP0 ```

GiteaMirror added the bug label 2025-11-11 16:40:14 -06:00

GiteaMirror closed this issue

2025-11-11 16:40:14 -06:00

GiteaMirror commented

2025-11-11 16:40:15 -06:00

@mballesterosc commented on GitHub (Aug 6, 2025):

I'm experiencing the same error. I'm waiting for the new release of OpenWebUI that will include compatibility with docling >1.0.0

@mballesterosc commented on GitHub (Aug 6, 2025): I'm experiencing the same error. I'm waiting for the new release of OpenWebUI that will include compatibility with docling >1.0.0

GiteaMirror commented

2025-11-11 16:40:15 -06:00

@parsue commented on GitHub (Aug 6, 2025):

I found that the problem may be on the docling side.
I tried on docling api or ui and met same issue. It should be the easyocr is updated and requesting the arguments but docling ocr loader is not handling this.

@parsue commented on GitHub (Aug 6, 2025): I found that the problem may be on the docling side. I tried on docling api or ui and met same issue. It should be the easyocr is updated and requesting the arguments but docling ocr loader is not handling this.