github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 08:02:14 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #15711] [BUG] Image paths treated as unknown commands when model is launched via TUI (ollama vs ollama run) #72078

New Issue
Closed
opened 2026-05-05 03:25:34 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-05-05 03:25:34 -05:00
Owner
Copy Link

Originally created by @dstadulis on GitHub (Apr 19, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/15711

What is the issue?

Seemingly, a parsing inconsistency exists between the interactive TUI and the direct model runner

Description:

When launching Ollama using the bare ollama command, selecting a model from the interactive TUI, entering a file path for an image (e.g., /path/to/image.png) results in an "Unknown command" error. However, when the same model is launched directly using ollama run <model>, the image path is correctly parsed and "Added."
Steps to Reproduce:

  1. Run ollama in the terminal to open the interactive model selector.
  2. Select a vision-capable model (e.g., qwen3-vl:32b).
  3. Once the prompt appears, add a file path: /Users/username/image.png
  4. Observe Error: Unknown command '/Users/username/image.png'.

Expected Behavior:

The CLI should recognize the path as an image attachment, just as it does when using ollama run.

Environment:

  • Ollama Version: 0.21.0
  • OS:
$ sw_vers
ProductName:		macOS
ProductVersion:		26.4.1
BuildVersion:		25E253
  • Model: qwen3-vl:32b

Additional Context:

Logs

$ ollama
[TUI opens, user selects model]
>>> /Users/username/image.png describe image
Unknown command '/Users/username/image.png'. Type /? for help

$ ollama run qwen3-vl:32b
>>> /Users/username/image.png describe image
Added image '/Users/username/image.png'
Thinking...
So, let's describe the image. First, [snip]

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.21.0

Originally created by @dstadulis on GitHub (Apr 19, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/15711 ### What is the issue? Seemingly, a parsing inconsistency exists between the interactive TUI and the direct model runner ## Description: When launching Ollama using the bare `ollama` command, selecting a model from the interactive TUI, entering a file path for an image (e.g., /path/to/image.png) results in an ["Unknown command"](https://github.com/ollama/ollama/blob/ff23dd343f1f22ce6674569ba122a4749364939d/cmd/interactive.go#L504-L507) error. However, when the same model is launched directly using `ollama run <model>`, the image path is correctly parsed and "Added." Steps to Reproduce: 1. Run ollama in the terminal to open the interactive model selector. 2. Select a vision-capable model (e.g., qwen3-vl:32b). 3. Once the prompt appears, add a file path: /Users/username/image.png 4. Observe Error: Unknown command '/Users/username/image.png'. ## Expected Behavior: The CLI should recognize the path as an image attachment, just as it does when using ollama run. ## Environment: * Ollama Version: 0.21.0 * OS: ```shell $ sw_vers ProductName: macOS ProductVersion: 26.4.1 BuildVersion: 25E253 ``` * Model: qwen3-vl:32b ## Additional Context: ## Logs ```shell $ ollama [TUI opens, user selects model] >>> /Users/username/image.png describe image Unknown command '/Users/username/image.png'. Type /? for help ``` ```shell $ ollama run qwen3-vl:32b >>> /Users/username/image.png describe image Added image '/Users/username/image.png' Thinking... So, let's describe the image. First, [snip] ``` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.21.0
GiteaMirror added the bug label 2026-05-05 03:25:34 -05:00
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#72078
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?