github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 17:49:24 -05:00
Code Issues 14.5k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #11979] How to enable and disable the thinking function of the model when openai calls ollama #70012

New Issue
Open
opened 2026-05-04 20:04:12 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-05-04 20:04:12 -05:00
Owner
Copy Link

Originally created by @zkj12321 on GitHub (Aug 20, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11979

When using the OpenAI library to call a model deployed locally in Olama, how to set the model to enable and disable the thinking function? I tried adding relevant configurations to the 'extra-body' field, but it did not take effect. Have you made any adaptations in this area yet

Originally created by @zkj12321 on GitHub (Aug 20, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11979 When using the OpenAI library to call a model deployed locally in Olama, how to set the model to enable and disable the thinking function? I tried adding relevant configurations to the 'extra-body' field, but it did not take effect. Have you made any adaptations in this area yet
GiteaMirror added the feature request label 2026-05-04 20:04:12 -05:00
GiteaMirror commented 2026-05-04 20:04:14 -05:00
Author
Owner
Copy Link

@mbenchwevioo commented on GitHub (Aug 20, 2025):

Also how to hide thinking from output? display only the response
An env variable will be more suitable speacially for docker-compose, something like OLLAMA_HIDE_THINKING=1

<!-- gh-comment-id:3206725768 --> @mbenchwevioo commented on GitHub (Aug 20, 2025): Also how to hide thinking from output? display only the response An env variable will be more suitable speacially for docker-compose, something like OLLAMA_HIDE_THINKING=1
GiteaMirror commented 2026-05-04 20:04:15 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Aug 20, 2025):

@mbenchwevioo do you mean hide it from the OpenAI API, or hide it from the CLI?

<!-- gh-comment-id:3207590209 --> @pdevine commented on GitHub (Aug 20, 2025): @mbenchwevioo do you mean hide it from the OpenAI API, or hide it from the CLI?
GiteaMirror commented 2026-05-04 20:04:16 -05:00
Author
Owner
Copy Link

@mbenchwevioo commented on GitHub (Aug 20, 2025):

When I use API chat/completion with a reasoning model I get the thinking output with the response
It would be better if we can choose when we start ollama with an env variable THINK with values: enable / disable / hide
Enable: enable thinking
Disable: disable thinking
Hide: enable thinking but hide it and show only the response

<!-- gh-comment-id:3207620558 --> @mbenchwevioo commented on GitHub (Aug 20, 2025): When I use API chat/completion with a reasoning model I get the thinking output with the response It would be better if we can choose when we start ollama with an env variable THINK with values: enable / disable / hide Enable: enable thinking Disable: disable thinking Hide: enable thinking but hide it and show only the response
GiteaMirror commented 2026-05-04 20:04:16 -05:00
Author
Owner
Copy Link

@zkj12321 commented on GitHub (Aug 21, 2025):

@pdevine Olama previously added '-- think=false' to implement the think of closing the model, but what should be done to hide it from OpenAI API

<!-- gh-comment-id:3208675577 --> @zkj12321 commented on GitHub (Aug 21, 2025): @pdevine Olama previously added '-- think=false' to implement the think of closing the model, but what should be done to hide it from OpenAI API
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 feature request
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#70012
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?