[GH-ISSUE #4391] [FEAT]: Integrate Docker Model Runner as a Local Inferencing provide #2802

Closed
opened 2026-02-22 18:31:19 -05:00 by yindo · 2 comments
Owner

Originally created by @ericcurtin on GitHub (Sep 17, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4391

Originally assigned to: @shatfield4 on GitHub.

What would you like to see?

I remember seeing:

https://www.linkedin.com/posts/docker_docker-genai-llm-activity-7318272558909304832-aBJi?utm_source=share&utm_medium=member_desktop&rcm=ACoAAAZRsnUBW5iL5v_Xf22wBZVUAoKR30FOY_w

and saying cool, hopefully we should see Docker Model Runner + AnythingLLM integrated soon. Installed AnythingLLM today intending on using it as a Docker Model Runner UI and noticed Docker Model Runner isn't an option for a provider. Can we make it an option?

Tagging @kiview @doringeman for awareness

Originally created by @ericcurtin on GitHub (Sep 17, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4391 Originally assigned to: @shatfield4 on GitHub. ### What would you like to see? I remember seeing: https://www.linkedin.com/posts/docker_docker-genai-llm-activity-7318272558909304832-aBJi?utm_source=share&utm_medium=member_desktop&rcm=ACoAAAZRsnUBW5iL5v_Xf22wBZVUAoKR30FOY_w and saying cool, hopefully we should see Docker Model Runner + AnythingLLM integrated soon. Installed AnythingLLM today intending on using it as a Docker Model Runner UI and noticed Docker Model Runner isn't an option for a provider. Can we make it an option? Tagging @kiview @doringeman for awareness
yindo added the enhancementIntegration Requestfeature request labels 2026-02-22 18:31:19 -05:00
yindo closed this issue 2026-02-22 18:31:19 -05:00
Author
Owner

@timothycarambat commented on GitHub (Sep 17, 2025):

Can you not leverage the Generic OpenAI connector - since it runs a generic endpoint? In that video I did with Docker it was all about how we use Docker for ease of use of deployment and container technology - not specifically Docker runner (I don't think that even existed at that time?)

However, I am totally happy to support a more dedicated flow/integration for docker model runner. If you have docker on your machine we can even go one step further and manage runners for you when using AnythingLLM Desktop too.

@timothycarambat commented on GitHub (Sep 17, 2025): Can you not leverage the Generic OpenAI connector - since it runs a generic endpoint? In that video I did with Docker it was all about how we use Docker for ease of use of deployment and container technology - not specifically Docker runner (I don't think that even existed at that time?) However, I am totally happy to support a more dedicated flow/integration for docker model runner. If you have docker on your machine we can even go one step further and manage runners for you when using AnythingLLM Desktop too.
Author
Owner

@kiview commented on GitHub (Sep 29, 2025):

Absolutely, DMR generally works through generic OpenAI integration. So dedicated DMR support is more about ease-of-use for users, and discoverability for DMR.

@kiview commented on GitHub (Sep 29, 2025): Absolutely, DMR generally works through generic OpenAI integration. So dedicated DMR support is more about ease-of-use for users, and discoverability for DMR.
yindo changed title from [FEAT]: Integrate Docker Model Runner as a Local Inferencing provide to [GH-ISSUE #4391] [FEAT]: Integrate Docker Model Runner as a Local Inferencing provide 2026-06-05 14:48:37 -04:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#2802