github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-15 12:48:05 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #7450] Run LLM directly in Golang App without Ollama Server #4738

New Issue
Open
opened 2026-04-12 15:41:02 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 15:41:02 -05:00
Owner
Copy Link

Originally created by @faelp22 on GitHub (Oct 31, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7450

Hello everyone, I would like to know if it is possible to run an all-minilm LLM model directly in my Golang App without having to make calls to the Ollama Server http://localhost:11434/api

I would like to take a small "all-minilm" model and use the //go:embed model/* to already have the tool embedded in the Golang binary.

The idea would be to simplify the use and infrastructure so as not to need to set up an extra Docker Container or VM, not to mention avoiding network latency.

I would like to use Ollama as a library and import the necessary parts in my Golang App.

I couldn't find any examples, if there is someone more experienced and can help me, I would appreciate it.

Originally created by @faelp22 on GitHub (Oct 31, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7450 Hello everyone, I would like to know if it is possible to run an all-minilm LLM model directly in my Golang App without having to make calls to the Ollama Server http://localhost:11434/api I would like to take a small "all-minilm" model and use the //go:embed model/* to already have the tool embedded in the Golang binary. The idea would be to simplify the use and infrastructure so as not to need to set up an extra Docker Container or VM, not to mention avoiding network latency. I would like to use Ollama as a library and import the necessary parts in my Golang App. I couldn't find any examples, if there is someone more experienced and can help me, I would appreciate it.
GiteaMirror added the feature request label 2026-04-12 15:41:02 -05:00
GiteaMirror commented 2026-04-12 15:41:03 -05:00
Author
Owner
Copy Link

@brightpuddle commented on GitHub (Nov 29, 2024):

Found your issue because I had the same question.

The Cobra CLI function cmd.RunServer is exposed here and doesn't use any parameters, i.e. cmd.RunServer(nil, nil) is fine.

I tried this and got "unable to initialize llm runners unable to locate runners in any search path," so I suspect there's some other environment initialization that the CLI is doing before this. Probably nothing particularly complicated, but I need to take a deeper look into it.

Did you ever get this working? If not, I can report back once I sort it out.

<!-- gh-comment-id:2508167264 --> @brightpuddle commented on GitHub (Nov 29, 2024): Found your issue because I had the same question. The Cobra CLI function `cmd.RunServer` is exposed [here](https://github.com/ollama/ollama/blob/39e29ae5ddb9ff710c0e28652b61850f458e1205/cmd/cmd.go#L1165) and doesn't use any parameters, i.e. `cmd.RunServer(nil, nil)` is fine. I tried this and got "unable to initialize llm runners unable to locate runners in any search path," so I suspect there's some other environment initialization that the CLI is doing before this. Probably nothing particularly complicated, but I need to take a deeper look into it. Did you ever get this working? If not, I can report back once I sort it out.
GiteaMirror commented 2026-04-12 15:41:04 -05:00
Author
Owner
Copy Link

@youngk123 commented on GitHub (Feb 13, 2025):

I have same problem， I build v0.5.0，Error: unable to initialize llm runners unable to locate runners in any search path

<!-- gh-comment-id:2657110260 --> @youngk123 commented on GitHub (Feb 13, 2025): I have same problem， I build v0.5.0，Error: unable to initialize llm runners unable to locate runners in any search path
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#4738
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?