github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-23 06:01:37 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #4440] Add support for third-party hosted APIs #28532

New Issue
Open
opened 2026-04-22 06:46:46 -05:00 by GiteaMirror · 9 comments
GiteaMirror commented 2026-04-22 06:46:46 -05:00
Owner
Copy Link

Originally created by @19h on GitHub (May 14, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4440

We've been coding against the Ollama API internally and eventually it hit me .. Ollama should be able to support third-party API providers, making it a de-facto gateway to LLMs.

For example, it would easily blur the lines between an OpenAI's assistant / user and a Gemini model / user conversation; it could transparently speak Cohere Command R+ completion-like while eloquently talking to Claude, too.

Might sound utterly off-topic, but think about it.

I implemented a hard-coded model into Ollama for local use so I can use unsupported, hosted LLMs in Cody for coding, and I feel like this could very well be a Modelfile-level thing with providers happily providing integrations, putting even more spotlight on Ollama while forcing LLM providers to be less fuzzy about their API integrations, given that the Modelfile spec is rigid enough.

Originally created by @19h on GitHub (May 14, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4440 We've been coding against the Ollama API internally and eventually it hit me .. Ollama should be able to support third-party API providers, making it a de-facto gateway to LLMs. For example, it would easily blur the lines between an OpenAI's assistant / user and a Gemini model / user conversation; it could transparently speak Cohere Command R+ completion-like while eloquently talking to Claude, too. Might sound utterly off-topic, but think about it. I implemented a hard-coded model into Ollama for local use so I can use unsupported, hosted LLMs in Cody for coding, and I feel like this could very well be a Modelfile-level thing with providers happily providing integrations, putting even more spotlight on Ollama while forcing LLM providers to be less fuzzy about their API integrations, given that the Modelfile spec is rigid enough.
GiteaMirror added the feature requestapi labels 2026-04-22 06:46:46 -05:00
GiteaMirror commented 2026-04-22 06:46:48 -05:00
Author
Owner
Copy Link

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

Isn't this something that LiteLLM can do?

<!-- gh-comment-id:2111737868 --> @ProjectMoon commented on GitHub (May 15, 2024): Isn't this something that LiteLLM can do?
GiteaMirror commented 2026-04-22 06:46:49 -05:00
Author
Owner
Copy Link

@oldgithubman commented on GitHub (May 18, 2024):

Isn't this something that LiteLLM can do?

It is, but combining efforts could be a good thing. This space needs more standardization, IMO

<!-- gh-comment-id:2119018882 --> @oldgithubman commented on GitHub (May 18, 2024): > Isn't this something that LiteLLM can do? It is, but combining efforts *could* be a good thing. This space needs more standardization, IMO
GiteaMirror commented 2026-04-22 06:46:49 -05:00
Author
Owner
Copy Link

@royjhan commented on GitHub (Jul 31, 2024):

OpenAI compatibility is the main focus on this front

<!-- gh-comment-id:2261064448 --> @royjhan commented on GitHub (Jul 31, 2024): OpenAI compatibility is the main focus on this front
GiteaMirror commented 2026-04-22 06:46:50 -05:00
Author
Owner
Copy Link

@19h commented on GitHub (Jul 31, 2024):

@royjhan completed where?

<!-- gh-comment-id:2261111700 --> @19h commented on GitHub (Jul 31, 2024): @royjhan completed where?
GiteaMirror commented 2026-04-22 06:46:51 -05:00
Author
Owner
Copy Link

@oldgithubman commented on GitHub (Jul 31, 2024):

@royjhan completed where?

I think some people don't know what "completed" means. I've shifted focus to mistral.rs. Seems like a better project. Still in early stages. Join us!

<!-- gh-comment-id:2261152923 --> @oldgithubman commented on GitHub (Jul 31, 2024): > @royjhan completed where? I think some people don't know what "completed" means. I've shifted focus to mistral.rs. Seems like a better project. Still in early stages. Join us!
GiteaMirror commented 2026-04-22 06:46:52 -05:00
Author
Owner
Copy Link

@royjhan commented on GitHub (Jul 31, 2024):

@19h Refer to https://github.com/ollama/ollama/blob/main/server/routes.go#L1082 for all major compatible endpoints. Doc updates are around the corner

<!-- gh-comment-id:2261495788 --> @royjhan commented on GitHub (Jul 31, 2024): @19h Refer to https://github.com/ollama/ollama/blob/main/server/routes.go#L1082 for all major compatible endpoints. Doc updates are around the corner
GiteaMirror commented 2026-04-22 06:46:52 -05:00
Author
Owner
Copy Link

@19h commented on GitHub (Aug 1, 2024):

Did you even read the issue, or do you just interact with the issues for the sake of it?

<!-- gh-comment-id:2261975448 --> @19h commented on GitHub (Aug 1, 2024): Did you even read the issue, or do you just interact with the issues for the sake of it?
GiteaMirror commented 2026-04-22 06:46:54 -05:00
Author
Owner
Copy Link

@royjhan commented on GitHub (Aug 1, 2024):

Apologies if I'm misunderstanding the issue! Reopened and will let someone else address it – thanks

<!-- gh-comment-id:2262025007 --> @royjhan commented on GitHub (Aug 1, 2024): Apologies if I'm misunderstanding the issue! Reopened and will let someone else address it – thanks
GiteaMirror commented 2026-04-22 06:46:54 -05:00
Author
Owner
Copy Link

@DennisDyallo commented on GitHub (Nov 6, 2024):

I mean using ollama in the terminal as an interface to start a session towards Claude or OpenAI would be great. That way I can do all my stuff locally without changing tools. Although, I am not yet well enough experienced with ollama. I only started using it a couple of days ago with OpenWebUI.

<!-- gh-comment-id:2460065332 --> @DennisDyallo commented on GitHub (Nov 6, 2024): I mean using ollama in the terminal as an interface to start a session towards Claude or OpenAI would be great. That way I can do all my stuff locally without changing tools. Although, I am not yet well enough experienced with ollama. I only started using it a couple of days ago with OpenWebUI.
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 api 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#28532
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?