I have searched for any existing and/or related issues.
I have searched for any existing and/or related discussions.
I have also searched in the CLOSED issues AND CLOSED discussions and found no related items (your issue might already be addressed on the development branch!).
I am using the latest version of Open WebUI.
Installation Method
Docker
Open WebUI Version
0.7.2
Ollama Version (if applicable)
No response
Operating System
Ubuntu 24.04
Browser (if applicable)
147.0.2
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
Type "Tell me five countries with his capitals and put it into a pdf-file!" (or xlsx/csv) in the chat and get a pdf/xlsx/csv-file (like on chatgpt.com).
Actual Behavior
I got the answer:
I can’t create the XLSX directly with pandas here because the openpyxl library isn’t available in this environment, but I can still give you a ready‑to-use Excel file by constructing it manually.
or
I can’t use the reportlab library here, so I’ll generate the PDF using a simpler approach with a built‑in library. I’ll create the PDF now and then give it to you to download.
Steps to Reproduce
use open-webui with docker (in my case with LiteLLM as proxy)
use a model like GPT-5.1
use in the settings the default pyodide as engine of code execution
check if the model can handle uploaded files
if the model can handle uploaded file, ask the model to generate a file from input like "Tell me five countries with his capitals and put it into a pdf-file!"
Originally created by @Sebastian-SWP on GitHub (Feb 3, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/21125
### Check Existing Issues
- [x] I have searched for any existing and/or related issues.
- [x] I have searched for any existing and/or related discussions.
- [x] I have also searched in the CLOSED issues AND CLOSED discussions and found no related items (your issue might already be addressed on the development branch!).
- [x] I am using the latest version of Open WebUI.
### Installation Method
Docker
### Open WebUI Version
0.7.2
### Ollama Version (if applicable)
_No response_
### Operating System
Ubuntu 24.04
### Browser (if applicable)
147.0.2
### 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
Type "Tell me five countries with his capitals and put it into a pdf-file!" (or xlsx/csv) in the chat and get a pdf/xlsx/csv-file (like on chatgpt.com).
### Actual Behavior
I got the answer:
> I can’t create the XLSX directly with pandas here because the openpyxl library isn’t available in this environment, but I can still give you a ready‑to-use Excel file by constructing it manually.
or
> I can’t use the reportlab library here, so I’ll generate the PDF using a simpler approach with a built‑in library. I’ll create the PDF now and then give it to you to download.
### Steps to Reproduce
1. use open-webui with docker (in my case with LiteLLM as proxy)
2. use a model like GPT-5.1
3. use in the settings the default pyodide as engine of code execution
4. check if the model can handle uploaded files
5. if the model can handle uploaded file, ask the model to generate a file from input like "Tell me five countries with his capitals and put it into a pdf-file!"
### Logs & Screenshots
<img width="1313" height="793" alt="Image" src="https://github.com/user-attachments/assets/fd4ed190-4b11-4b6a-8a20-db9d5650db44" />
### Additional Information
[console-export-2026-2-3_14-26-17.log](https://github.com/user-attachments/files/25046929/console-export-2026-2-3_14-26-17.log)
[docker logs openwebui.log](https://github.com/user-attachments/files/25047153/docker.logs.openwebui.log)
GiteaMirror
added the bug label 2026-05-25 12:25:19 -05:00
#19496issue: 500 internal server error appears in v0.6.40 by cloudtuotuo • Nov 26, 2025 • bug
#19481issue: admin panel not working by kybeq • Nov 25, 2025 • bug
#19417issue: v0.6.37 SQL Error by AKHYP • Nov 24, 2025 • bug
💡Tips:
If this is a duplicate, please consider closing this issue and adding any additional details to the existing one
If you found a solution in any of these issues, please share it here to help others
This comment was generated automatically by a bot. Please react with a 👍 if this comment was helpful, or a 👎 if it was not.
<!-- gh-comment-id:3841386998 -->
@owui-terminator[bot] commented on GitHub (Feb 3, 2026):
🔍 **Similar Issues Found**
I found some existing issues that might be related to this one. Please check if any of these are duplicates or contain helpful solutions:
1. [#21024](https://github.com/open-webui/open-webui/issues/21024) **issue: Open WebUI does not distinguish the difference between image editing and image creation prompts.**
*by MattariOnline • Jan 29, 2026 • `bug`*
2. [#20448](https://github.com/open-webui/open-webui/issues/20448) **issue: The user is unable to create a new conversation**
*by ineffable-love • Jan 07, 2026 • `bug`*
3. [#14497](https://github.com/open-webui/open-webui/issues/14497) **issue: User hangs on creation**
*by RamboRogers • May 29, 2025 • `bug`*
4. [#19853](https://github.com/open-webui/open-webui/issues/19853) **issue: NOT ABLE TO CREATE A NEW API KEY:**
*by Code-With-Samuel • Dec 10, 2025 • `bug`*
5. [#20219](https://github.com/open-webui/open-webui/issues/20219) **issue: Can't upload collection while creating new folder**
*by LiorZadah • Dec 28, 2025 • `bug`, `confirmed issue`*
<details>
<summary>Show 5 more related issues</summary>
6. [#19758](https://github.com/open-webui/open-webui/issues/19758) **issue: unable to disable channels creation from regular users**
*by stronk7 • Dec 04, 2025 • `bug`*
7. [#17386](https://github.com/open-webui/open-webui/issues/17386) **issue: [ERROR: 400: [ERROR: Error creating function]]**
*by abxis • Sep 12, 2025 • `bug`*
8. [#19496](https://github.com/open-webui/open-webui/issues/19496) **issue: 500 internal server error appears in v0.6.40**
*by cloudtuotuo • Nov 26, 2025 • `bug`*
9. [#19481](https://github.com/open-webui/open-webui/issues/19481) **issue: admin panel not working**
*by kybeq • Nov 25, 2025 • `bug`*
10. [#19417](https://github.com/open-webui/open-webui/issues/19417) **issue: v0.6.37 SQL Error**
*by AKHYP • Nov 24, 2025 • `bug`*
</details>
---
💡 **Tips:**
- If this is a duplicate, please consider closing this issue and adding any additional details to the existing one
- If you found a solution in any of these issues, please share it here to help others
*This comment was generated automatically by a bot.* Please react with a 👍 if this comment was helpful, or a 👎 if it was not.
LLMs just generate text.
You need a tool which the llm can call to create files.
Not a bug.
<!-- gh-comment-id:3841709238 -->
@Classic298 commented on GitHub (Feb 3, 2026):
LLMs just generate text.
You need a tool which the llm can call to create files.
Not a bug.
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 @Sebastian-SWP on GitHub (Feb 3, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/21125
Check Existing Issues
Installation Method
Docker
Open WebUI Version
0.7.2
Ollama Version (if applicable)
No response
Operating System
Ubuntu 24.04
Browser (if applicable)
147.0.2
Confirmation
README.md.Expected Behavior
Type "Tell me five countries with his capitals and put it into a pdf-file!" (or xlsx/csv) in the chat and get a pdf/xlsx/csv-file (like on chatgpt.com).
Actual Behavior
I got the answer:
or
Steps to Reproduce
Logs & Screenshots
Additional Information
console-export-2026-2-3_14-26-17.log
docker logs openwebui.log
@owui-terminator[bot] commented on GitHub (Feb 3, 2026):
🔍 Similar Issues Found
I found some existing issues that might be related to this one. Please check if any of these are duplicates or contain helpful solutions:
#21024 issue: Open WebUI does not distinguish the difference between image editing and image creation prompts.
by MattariOnline • Jan 29, 2026 •
bug#20448 issue: The user is unable to create a new conversation
by ineffable-love • Jan 07, 2026 •
bug#14497 issue: User hangs on creation
by RamboRogers • May 29, 2025 •
bug#19853 issue: NOT ABLE TO CREATE A NEW API KEY:
by Code-With-Samuel • Dec 10, 2025 •
bug#20219 issue: Can't upload collection while creating new folder
by LiorZadah • Dec 28, 2025 •
bug,confirmed issueShow 5 more related issues
#19758 issue: unable to disable channels creation from regular users
by stronk7 • Dec 04, 2025 •
bug#17386 issue: [ERROR: 400: [ERROR: Error creating function]]
by abxis • Sep 12, 2025 •
bug#19496 issue: 500 internal server error appears in v0.6.40
by cloudtuotuo • Nov 26, 2025 •
bug#19481 issue: admin panel not working
by kybeq • Nov 25, 2025 •
bug#19417 issue: v0.6.37 SQL Error
by AKHYP • Nov 24, 2025 •
bug💡 Tips:
This comment was generated automatically by a bot. Please react with a 👍 if this comment was helpful, or a 👎 if it was not.
@Classic298 commented on GitHub (Feb 3, 2026):
LLMs just generate text.
You need a tool which the llm can call to create files.
Not a bug.