github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #1048] Add Timeout as User Configurable #512

New Issue
Closed
opened 2026-04-12 10:12:28 -05:00 by GiteaMirror · 9 comments
GiteaMirror commented 2026-04-12 10:12:28 -05:00
Owner
Copy Link

Originally created by @valentimarco on GitHub (Nov 8, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1048

I have read that the timer is hardcoded with a timeout of 5 minutes and i don't wanna send a empty string every 5m to let it alive...
What are at the moment, the complications of a User Configurable timeout?

Originally created by @valentimarco on GitHub (Nov 8, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1048 I have read that the timer is hardcoded with a timeout of 5 minutes and i don't wanna send a empty string every 5m to let it alive... What are at the moment, the complications of a User Configurable timeout?
GiteaMirror commented 2026-04-12 10:12:30 -05:00
Author
Owner
Copy Link

@horw commented on GitHub (Nov 9, 2023):

Hi! If maintainer agree, It will be nice if I can try to implement it.
Looks like good first issue.

<!-- gh-comment-id:1803200905 --> @horw commented on GitHub (Nov 9, 2023): Hi! If maintainer agree, It will be nice if I can try to implement it. Looks like good first issue.
GiteaMirror commented 2026-04-12 10:12:30 -05:00
Author
Owner
Copy Link

@horw commented on GitHub (Nov 13, 2023):

@valentimarco I tested it, and the server woke up after sending a request to it.

<!-- gh-comment-id:1808397969 --> @horw commented on GitHub (Nov 13, 2023): @valentimarco I tested it, and the server woke up after sending a request to it.
GiteaMirror commented 2026-04-12 10:12:30 -05:00
Author
Owner
Copy Link

@valentimarco commented on GitHub (Nov 13, 2023):

@horw i know but i wanna have It 24/7. the model Needs to serve multiple clients with different Active time...

<!-- gh-comment-id:1808421081 --> @valentimarco commented on GitHub (Nov 13, 2023): @horw i know but i wanna have It 24/7. the model Needs to serve multiple clients with different Active time...
GiteaMirror commented 2026-04-12 10:12:30 -05:00
Author
Owner
Copy Link

@horw commented on GitHub (Nov 13, 2023):

Which API do you call?

<!-- gh-comment-id:1808460550 --> @horw commented on GitHub (Nov 13, 2023): Which API do you call?
GiteaMirror commented 2026-04-12 10:12:31 -05:00
Author
Owner
Copy Link

@horw commented on GitHub (Nov 13, 2023):

@valentimarco Do you use the following API: http://127.0.0.1:11434/api/generate?

<!-- gh-comment-id:1808483787 --> @horw commented on GitHub (Nov 13, 2023): @valentimarco Do you use the following API: http://127.0.0.1:11434/api/generate?
GiteaMirror commented 2026-04-12 10:12:32 -05:00
Author
Owner
Copy Link

@valentimarco commented on GitHub (Nov 13, 2023):

I use langchain class but the problem Is the. Same etheir langchain or end point

<!-- gh-comment-id:1808607141 --> @valentimarco commented on GitHub (Nov 13, 2023): I use langchain class but the problem Is the. Same etheir langchain or end point
GiteaMirror commented 2026-04-12 10:12:32 -05:00
Author
Owner
Copy Link

@Hill-Brandon-M commented on GitHub (Nov 19, 2023):

I've been using the following on my instance, which has been working fine for me:

curl -G http://$HOST:11434/

<!-- gh-comment-id:1817743186 --> @Hill-Brandon-M commented on GitHub (Nov 19, 2023): I've been using the following on my instance, which has been working fine for me: `curl -G http://$HOST:11434/`
GiteaMirror commented 2026-04-12 10:12:33 -05:00
Author
Owner
Copy Link

@trenta3 commented on GitHub (Nov 19, 2023):

I'd like to know if the runner startup timeout (currently 30secs) can be made user configurable as well

<!-- gh-comment-id:1818014396 --> @trenta3 commented on GitHub (Nov 19, 2023): I'd like to know if the runner startup timeout (currently 30secs) can be made user configurable as well
GiteaMirror commented 2026-04-12 10:12:33 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Feb 20, 2024):

This is now fixed! You can specify the keep_alive option in the API: https://github.com/ollama/ollama/blob/main/docs/api.md#generate-a-completion

<!-- gh-comment-id:1953332091 --> @jmorganca commented on GitHub (Feb 20, 2024): This is now fixed! You can specify the `keep_alive` option in the API: https://github.com/ollama/ollama/blob/main/docs/api.md#generate-a-completion
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
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#512
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?