[GH-ISSUE #12018] issue: Code Interpreter Not Working & Error: expected string or bytes-like object, got 'list' When Using VLM Models #55102

Closed
opened 2026-05-05 17:08:57 -05:00 by GiteaMirror · 0 comments
Owner

Originally created by @yuchenxie4645 on GitHub (Mar 24, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/12018

Check Existing Issues

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

Installation Method

Docker

Open WebUI Version

V0.5.20

Ollama Version (if applicable)

v0.6.3

Operating System

Ubuntu 24.04

Browser (if applicable)

Chrome

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 listed steps to reproduce the bug in detail.

Expected Behavior

It should've outputted something when I attached a photo and not Error: expected string or bytes-like object, got 'list'. The code interpreter should've worked but instead hangs after finishing coding the analysis.

Actual Behavior

Received this error when attaching ANY photos to ANY VLM: Error: expected string or bytes-like object, got 'list' in both Ollama AND VLLM. Code interpreter hangs.

Steps to Reproduce

For vision:

  1. Upload any screenshot.
  2. Hit generate
  3. Error

For Interpreter:

  1. Ask a math question like 25*93
  2. Attempts to solve it
  3. Writes the code for the analysis
  4. Hangs.

Logs & Screenshots

Image

I do not have a ss for interpreter

Additional Information

No response

Originally created by @yuchenxie4645 on GitHub (Mar 24, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/12018 ### Check Existing Issues - [x] I have searched the existing issues and discussions. - [x] I am using the latest version of Open WebUI. ### Installation Method Docker ### Open WebUI Version V0.5.20 ### Ollama Version (if applicable) v0.6.3 ### Operating System Ubuntu 24.04 ### Browser (if applicable) Chrome ### 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. - [ ] I have included the browser console logs. - [ ] I have included the Docker container logs. - [x] I have listed steps to reproduce the bug in detail. ### Expected Behavior It should've outputted something when I attached a photo and not Error: expected string or bytes-like object, got 'list'. The code interpreter should've worked but instead hangs after finishing coding the analysis. ### Actual Behavior Received this error when attaching ANY photos to ANY VLM: Error: expected string or bytes-like object, got 'list' in both Ollama AND VLLM. Code interpreter hangs. ### Steps to Reproduce For vision: 1. Upload any screenshot. 2. Hit generate 3. Error --- For Interpreter: 1. Ask a math question like 25*93 2. Attempts to solve it 3. Writes the code for the analysis 4. Hangs. ### Logs & Screenshots <img width="658" alt="Image" src="https://github.com/user-attachments/assets/dae39a81-91c4-4eeb-b3aa-19d35f35b2f8" /> I do not have a ss for interpreter ### Additional Information _No response_
GiteaMirror added the bug label 2026-05-05 17:08:57 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#55102