Mintplex-Labs/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-07-19 22:23:50 -04:00
Code Issues 328 Packages Projects Releases 10 Wiki Activity

[GH-ISSUE #1567] [FEAT]: Multiple LLM Preferences #1014

New Issue
Closed
opened 2026-02-22 18:22:40 -05:00 by yindo · 6 comments
yindo commented 2026-02-22 18:22:40 -05:00
Owner
Copy Link
Copy Source

Originally created by @wcwong on GitHub (May 29, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/1567

What would you like to see?

I would like to be able to instantiate multiple instances of a LLM provider. For example, with Azure I can create multiple endpoints (in different regions or different models). It'd be nice not to have to continually change the one option.

Originally created by @wcwong on GitHub (May 29, 2024). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/1567 ### What would you like to see? I would like to be able to instantiate multiple instances of a LLM provider. For example, with Azure I can create multiple endpoints (in different regions or different models). It'd be nice not to have to continually change the one option.
yindo added the enhancementfeature request labels 2026-02-22 18:22:40 -05:00
yindo closed this issue 2026-02-22 18:22:40 -05:00
yindo commented 2026-02-22 18:22:40 -05:00
Author
Owner
Copy Link
Copy Source

@wallartup commented on GitHub (May 30, 2024):

Check workspace settings and you can change models per workspace. LM studio is however missing from the list.

@wallartup commented on GitHub (May 30, 2024): Check workspace settings and you can change models per workspace. LM studio is however missing from the list.
yindo commented 2026-02-22 18:22:40 -05:00
Author
Owner
Copy Link
Copy Source

@wcwong commented on GitHub (May 30, 2024):

Check workspace settings and you can change models per workspace. LM studio is however missing from the list.

Yes, once I configure a model, I can assign that model to a workspace. However, once I configure, for example, the Generic OpenAI model, I am not able to reconfigure it per workspace.

The OpenAI configuration has a separate drop down so using the same API key I can have different models per workspace but it doesn't appear to allow me to have different API keys for different workspaces.

@wcwong commented on GitHub (May 30, 2024): > Check workspace settings and you can change models per workspace. LM studio is however missing from the list. Yes, once I configure a model, I can assign that model to a workspace. However, once I configure, for example, the Generic OpenAI model, I am not able to reconfigure it per workspace. The OpenAI configuration has a separate drop down so using the same API key I can have different models per workspace but it doesn't appear to allow me to have different API keys for different workspaces.
yindo commented 2026-02-22 18:22:40 -05:00
Author
Owner
Copy Link
Copy Source

@mrdjohnson commented on GitHub (May 31, 2024):

Check workspace settings and you can change models per workspace. LM studio is however missing from the list.

I found this comment in the codebase actually: Some providers can only be associated with a single model.

I'm pretty positive thats an error actually, double checking now

edit; created an issue around this: https://github.com/Mintplex-Labs/anything-llm/issues/1582

@mrdjohnson commented on GitHub (May 31, 2024): > Check workspace settings and you can change models per workspace. LM studio is however missing from the list. > I found this comment in the codebase actually: `Some providers can only be associated with a single model.` I'm pretty positive thats an error actually, double checking now edit; created an issue around this: https://github.com/Mintplex-Labs/anything-llm/issues/1582
yindo commented 2026-02-22 18:22:41 -05:00
Author
Owner
Copy Link
Copy Source

@johannoriel commented on GitHub (Jun 3, 2024):

same here, I would like to be able to use different key API per workspace (each user can already have it's own API key different from the other user)

@johannoriel commented on GitHub (Jun 3, 2024): same here, I would like to be able to use different key API per workspace (each user can already have it's own API key different from the other user)
yindo commented 2026-02-22 18:22:41 -05:00
Author
Owner
Copy Link
Copy Source

@manzke commented on GitHub (Jun 4, 2024):

the issue is that generic open ai and others are using the variables. when you create a workspace and configure it, it will write the settings into the .env file.
when you create another workspace and set different url for example, it will overwrite it. llm settings should be stored in the database and not the .env file.
i would also introduce the idea of llm instances, so you can configure multiple llm instances with different settings and just apply one of it to a workspace.

@manzke commented on GitHub (Jun 4, 2024): the issue is that generic open ai and others are using the variables. when you create a workspace and configure it, it will write the settings into the .env file. when you create another workspace and set different url for example, it will overwrite it. llm settings should be stored in the database and not the .env file. i would also introduce the idea of llm instances, so you can configure multiple llm instances with different settings and just apply one of it to a workspace.
yindo commented 2026-02-22 18:22:41 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (May 25, 2025):

moving to #3871

@timothycarambat commented on GitHub (May 25, 2025): moving to #3871
yindo changed title from [FEAT]: Multiple LLM Preferences to [GH-ISSUE #1567] [FEAT]: Multiple LLM Preferences 2026-06-05 14:38:29 -04:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Desktop
Docker
Integration Request
Integration Request
OS: Linux
OS: Mobile
OS: Windows
UI/UX
blocked
bug
bug
core-team-only
documentation
duplicate
embed-widget
enhancement
feature request
github_actions
good first issue
investigating
needs info / can't replicate
possible bug
pull-request
Mirrored from GitHub Pull Request
 question
stage: specifications
wontfix
No Label enhancement feature request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#1014
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?