github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 21:25:46 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #3419] Ollama local discovery #27867

New Issue
Closed
opened 2026-04-22 05:30:24 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-22 05:30:24 -05:00
Owner
Copy Link

Originally created by @rakyll on GitHub (Mar 30, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3419

What are you trying to do?

It's a common use case for LLM tool builders to wish they can rely on a local model rather than relying on a hosted one to save costs. Currently, there is no official way to discover whether a local ollama server is running.

How should we solve this?

Provide a mechanism so it becomes possible to programmatically discover the ollama server endpoint. It could be a subcommand in the ollama CLI:

$ ollama info
{ "status": "running", "api_endpoint": "...." }

What is the impact of not solving this?

This would open up the possibility of being able to fall back to a local model if ollama is available and running. It would open up wider adoption of ollama because cost and latency are both critical concerns for LLM applications.

Anything else?

No response

Originally created by @rakyll on GitHub (Mar 30, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3419 ### What are you trying to do? It's a common use case for LLM tool builders to wish they can rely on a local model rather than relying on a hosted one to save costs. Currently, there is no official way to discover whether a local ollama server is running. ### How should we solve this? Provide a mechanism so it becomes possible to programmatically discover the ollama server endpoint. It could be a subcommand in the ollama CLI: ``` $ ollama info { "status": "running", "api_endpoint": "...." } ``` ### What is the impact of not solving this? This would open up the possibility of being able to fall back to a local model if ollama is available and running. It would open up wider adoption of ollama because cost and latency are both critical concerns for LLM applications. ### Anything else? _No response_
GiteaMirror commented 2026-04-22 05:30:25 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (May 15, 2024):

Hey @rakyll , you can do this w/ ollama -v. If the server and client's versions match it will say something like ollama version 0.1.33. If the server isn't running it will tell you that it can't contact the server.

Alternatively you can just try to curl the server on the 11434 port:

% curl localhost:11434
Ollama is running

LMK if that makes sense.

<!-- gh-comment-id:2111384253 --> @pdevine commented on GitHub (May 15, 2024): Hey @rakyll , you can do this w/ `ollama -v`. If the server and client's versions match it will say something like `ollama version 0.1.33`. If the server isn't running it will tell you that it can't contact the server. Alternatively you can just try to curl the server on the `11434` port: ``` % curl localhost:11434 Ollama is running ``` LMK if that makes sense.
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#27867
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?