github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #754] Support for Autogen #46867

New Issue
Closed
opened 2026-04-28 01:20:05 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-28 01:20:05 -05:00
Owner
Copy Link

Originally created by @greg-peters on GitHub (Oct 11, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/754

#305 Requesting support to use ollama with Autogen

Originally created by @greg-peters on GitHub (Oct 11, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/754 #305 Requesting support to use ollama with Autogen
GiteaMirror commented 2026-04-28 01:20:12 -05:00
Author
Owner
Copy Link

@technovangelist commented on GitHub (Oct 11, 2023):

It looks like Autogen would need to support calling ollama from them. Looks like there is an existing issue on their repo you could add your use case to: https://github.com/microsoft/autogen/issues/46

<!-- gh-comment-id:1757695368 --> @technovangelist commented on GitHub (Oct 11, 2023): It looks like Autogen would need to support calling ollama from them. Looks like there is an existing issue on their repo you could add your use case to: https://github.com/microsoft/autogen/issues/46
GiteaMirror commented 2026-04-28 01:20:17 -05:00
Author
Owner
Copy Link

@MattBanak commented on GitHub (Nov 12, 2023):

It's still way too early to tell, but it seems more and more like the... "industry" (? can we use that term yet?) seems to be trending towards creating their LLM projects with APIs that treat OpenAI's GPT API as a spec so that smaller projects can be drop-in replacements.

Ollama could decide to follow this trend, or you could use LiteLLM to fit the local models into that spec and keep going! More details in the thread linked on the "completed" status, but here's the last message describing how to do this: https://github.com/jmorganca/ollama/issues/305#issuecomment-1752150867

In my opinion, I think treating OpenAI's API as a spec is a good decision, and seems to be adopted more and more every day. I'm sure a unified spec will come out at some point, but for now that API seems to be the closest thing we have and cross-project plug-and-play compatibility is invaluable when technology is moving at the pace LLMs are.

<!-- gh-comment-id:1807274804 --> @MattBanak commented on GitHub (Nov 12, 2023): It's still _way_ too early to tell, but it seems more and more like the... "industry" (? can we use that term yet?) seems to be trending towards creating their LLM projects with APIs that treat OpenAI's GPT API as a spec so that smaller projects can be drop-in replacements. Ollama _could_ decide to follow this trend, or you could use LiteLLM to fit the local models into that spec and keep going! More details in the thread linked on the "completed" status, but here's the last message describing how to do this: https://github.com/jmorganca/ollama/issues/305#issuecomment-1752150867 In my opinion, I think treating OpenAI's API as a spec is a good decision, and seems to be adopted more and more every day. I'm sure a unified spec will come out at some point, but for now that API seems to be the closest thing we have and cross-project plug-and-play compatibility is invaluable when technology is moving at the pace LLMs are.
GiteaMirror commented 2026-04-28 01:20:21 -05:00
Author
Owner
Copy Link

@dlaliberte commented on GitHub (Dec 19, 2023):

It looks like Autogen would need to support calling ollama from them. Looks like there is an existing issue on their repo you could add your use case to: microsoft/autogen#46

Autogen supports a base_url config option, e.g. "base_url": "http://localhost:8000/v1", so no further change is needed by Autogen. I'm using it now, but can't get anything useful out of Ollama.

It appears Ollama's openai api support is lacking what AutoGen requires. e.g. "/v1/chat/completions". I can't tell what openai api support Ollama does have. I only see "/api/version" working.

<!-- gh-comment-id:1862163583 --> @dlaliberte commented on GitHub (Dec 19, 2023): > It looks like Autogen would need to support calling ollama from them. Looks like there is an existing issue on their repo you could add your use case to: [microsoft/autogen#46](https://github.com/microsoft/autogen/issues/46) Autogen supports a base_url config option, e.g. "base_url": "http://localhost:8000/v1", so no further change is needed by Autogen. I'm using it now, but can't get anything useful out of Ollama. It appears Ollama's openai api support is lacking what AutoGen requires. e.g. "/v1/chat/completions". I can't tell what openai api support Ollama does have. I only see "/api/version" working.
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#46867
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?