github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #13744] gpt-oss:20b can't use image tool #34768

New Issue
Closed
opened 2026-04-22 18:35:57 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-22 18:35:57 -05:00
Owner
Copy Link

Originally created by @mlgitter on GitHub (Jan 16, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/13744

What is the issue?

I've tried to use gpt-oss:20b in Chatbox to

describe the picture

7 / 7

Deeply thought

(5.3s)

We need to do image description. It's a request to recognize image. We have [img-2] placeholder. Need to call internal tool. According to policy, we can use tools. The tool "image recognition" presumably available. We need to call it. Use appropriate format. Then provide description in English and translated to Russian.

We must follow tool syntax:{
"name":"imagetools",
"arguments":{ "image":"[img-2]" }
}

Then response.

imagetools

Arguments

{
"name": "imagetools",
"arguments": {
"image": "[img-2]"
}
}
Result

{
"error": "Model tried to call unavailable tool 'imagetools'. Available tools: .",
"input": {
"name": "imagetools",
"arguments": {
"image": "[img-2]"
}
},
"toolName": "imagetools"
}
Deeply thought

(0.0s)

We must respond: can't call but should say can't access images.

I don’t have the ability to view or analyze images directly, so I can’t describe the content of [img‑2] for you. If you can provide a text description or specify what you’d like to know about the image, I’ll do my best to help.

tokens used: 708, model: Ollama (gpt-oss:20b)

Relevant log output

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @mlgitter on GitHub (Jan 16, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/13744 ### What is the issue? I've tried to use gpt-oss:20b in Chatbox to describe the picture 7 / 7 Deeply thought (5.3s) We need to do image description. It's a request to recognize image. We have [img-2] placeholder. Need to call internal tool. According to policy, we can use tools. The tool "image recognition" presumably available. We need to call it. Use appropriate format. Then provide description in English and translated to Russian. We must follow tool syntax:{ "name":"imagetools", "arguments":{ "image":"[img-2]" } } Then response. imagetools Arguments { "name": "imagetools", "arguments": { "image": "[img-2]" } } Result { "error": "Model tried to call unavailable tool 'imagetools'. Available tools: .", "input": { "name": "imagetools", "arguments": { "image": "[img-2]" } }, "toolName": "imagetools" } Deeply thought (0.0s) We must respond: can't call but should say can't access images. I don’t have the ability to view or analyze images directly, so I can’t describe the content of [img‑2] for you. If you can provide a text description or specify what you’d like to know about the image, I’ll do my best to help. tokens used: 708, model: Ollama (gpt-oss:20b) ### Relevant log output ```shell ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-22 18:35:57 -05:00
GiteaMirror commented 2026-04-22 18:36:00 -05:00
Author
Owner
Copy Link

@mlgitter commented on GitHub (Jan 16, 2026):

Thanks for your good job, Ollama is great and I like it,
But many models I've tried recently actually can't use vision capabilities nor in the browser app, nor in desktop ones for me.

<!-- gh-comment-id:3757921482 --> @mlgitter commented on GitHub (Jan 16, 2026): Thanks for your good job, Ollama is great and I like it, But many models I've tried recently actually can't use vision capabilities nor in the browser app, nor in desktop ones for me.
GiteaMirror commented 2026-04-22 18:36:00 -05:00
Author
Owner
Copy Link

@Sekousuke commented on GitHub (Jan 16, 2026):

It's a problem with ChatBox, not with ollama.

<!-- gh-comment-id:3757942365 --> @Sekousuke commented on GitHub (Jan 16, 2026): It's a problem with ChatBox, not with ollama.
GiteaMirror commented 2026-04-22 18:36:00 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 8, 2026):

To process images with ollama, the model must support vision. gpt-oss does not.

<!-- gh-comment-id:3868247224 --> @rick-github commented on GitHub (Feb 8, 2026): To process images with ollama, the model must [support vision](https://ollama.com/search?c=vision). gpt-oss does not.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#34768
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?