Visual inference with LLAVA not working on Mobile device Browsers #695

New Issue

2025-11-11T14:29:15-06:00

GiteaMirror commented

2025-11-11 14:29:15 -06:00

Originally created by @nirabo on GitHub (Apr 22, 2024).

Bug Report

Visual inference with LLAVA not working on Mobile device Browsers

Description

I used to be able to demo LLAVA (latest and 13b) using my mobile phone's browser. Now, whenever I attempt to use it, I get no response whatsoever from the backend.

Bug Summary:
Visual inference with LLAVA not working on Mobile device Browsers

Steps to Reproduce:
Using a mobile device, open the open-webui URL of your deployment, choose model llava:latest, or llava:13b, add an image from your mobile camera to the chat and add your prompt for the image.

Expected Behavior:
The image and prompt to be uploaded to the backend, the backend to load the llava model and to run the inference based on the prompt and image.

Actual Behavior:
NOTE: I run my system via: ./run-compose.sh --enable-gpu[count=1] --enable-api[port=11434] --data[folder=../ollama-data] --build

Observing the logs on the docker composition there is NO log entries whatsoever.

Environment

Open WebUI Version: 0.1.120
Ollama (if applicable): 0.1.32
Operating System: backend runs on Ubuntu 22.04
Browser (if applicable): mobile client fails on any tested browser

Reproduction Details

Confirmation:

[* ] I have read and followed all the instructions provided in the README.md.
[ *] I am on the latest version of both Open WebUI and Ollama.
I have included the browser console logs.
I have included the Docker container logs.

Logs and Screenshots

Browser Console Logs:
[Include relevant browser console logs, if applicable]

Docker Container Logs:
[Include relevant Docker container logs, if applicable]

Screenshots (if applicable):
[Attach any relevant screenshots to help illustrate the issue]

Installation Method

[Describe the method you used to install the project, e.g., manual installation, Docker, package manager, etc.]

Additional Information

[Include any additional details that may help in understanding and reproducing the issue. This could include specific configurations, error messages, or anything else relevant to the bug.]

Note

If the bug report is incomplete or does not follow the provided instructions, it may not be addressed. Please ensure that you have followed the steps outlined in the README.md and troubleshooting.md documents, and provide all necessary information for us to reproduce and address the issue. Thank you!

Originally created by @nirabo on GitHub (Apr 22, 2024). # Bug Report Visual inference with LLAVA not working on Mobile device Browsers ## Description I used to be able to demo LLAVA (latest and 13b) using my mobile phone's browser. Now, whenever I attempt to use it, I get no response whatsoever from the backend. **Bug Summary:** Visual inference with LLAVA not working on Mobile device Browsers **Steps to Reproduce:** Using a mobile device, open the open-webui URL of your deployment, choose model `llava:latest`, or `llava:13b`, add an image from your mobile camera to the chat and add your prompt for the image. **Expected Behavior:** The image and prompt to be uploaded to the backend, the backend to load the llava model and to run the inference based on the prompt and image. **Actual Behavior:** NOTE: I run my system via: `./run-compose.sh --enable-gpu[count=1] --enable-api[port=11434] --data[folder=../ollama-data] --build` Observing the logs on the docker composition there is NO log entries whatsoever. ## Environment - **Open WebUI Version: 0.1.120** - **Ollama (if applicable): 0.1.32** - **Operating System: backend runs on Ubuntu 22.04** - **Browser (if applicable): mobile client fails on any tested browser** ## Reproduction Details **Confirmation:** - [* ] I have read and followed all the instructions provided in the README.md. - [ *] I am on the latest version of both Open WebUI and Ollama. - [ ] I have included the browser console logs. - [ ] I have included the Docker container logs. ## Logs and Screenshots **Browser Console Logs:** [Include relevant browser console logs, if applicable] **Docker Container Logs:** [Include relevant Docker container logs, if applicable] **Screenshots (if applicable):** [Attach any relevant screenshots to help illustrate the issue] ## Installation Method [Describe the method you used to install the project, e.g., manual installation, Docker, package manager, etc.] ## Additional Information [Include any additional details that may help in understanding and reproducing the issue. This could include specific configurations, error messages, or anything else relevant to the bug.] ## Note If the bug report is incomplete or does not follow the provided instructions, it may not be addressed. Please ensure that you have followed the steps outlined in the README.md and troubleshooting.md documents, and provide all necessary information for us to reproduce and address the issue. Thank you!

GiteaMirror closed this issue

2025-11-11 14:29:15 -06:00

GiteaMirror commented

2025-11-11 14:29:16 -06:00