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 #5523] [BUG]: deepseek models suddenly gone #5144

New Issue
Closed
opened 2026-06-05 14:52:17 -04:00 by yindo · 4 comments
yindo commented 2026-06-05 14:52:17 -04:00
Owner
Copy Link
Copy Source

Originally created by @ohromeo on GitHub (Apr 24, 2026).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/5523

How are you running AnythingLLM?

Docker (local)

What happened?

yesterday the app was happily running via anyhtingLLM api using deepseek and deepseek-chat models - with purchased api key, today they are totally gone from the LLM deekseek options and replaced with 2 preview models. deepseek-flash / deepseek-pro, which you broke our functions by doing this out of the blue.

as well these models are returning there "thinking" and we are unable to stop the thinking from returning in the results stream, which we are now scrambling to try to rectifiy.

why did you have to completely remove the deepseek-chat, can you put it back please.

Are there known steps to reproduce?

select deepseek llm, the options for deepseek-chat are removed from the list and replaced with "preview" models

LLM Provider & Model (if applicable)

No response

Embedder Provider & Model (if applicable)

No response

Originally created by @ohromeo on GitHub (Apr 24, 2026). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/5523 ### How are you running AnythingLLM? Docker (local) ### What happened? yesterday the app was happily running via anyhtingLLM api using deepseek and deepseek-chat models - with purchased api key, today they are totally gone from the LLM deekseek options and replaced with 2 preview models. deepseek-flash / deepseek-pro, which you broke our functions by doing this out of the blue. as well these models are returning there "thinking" and we are unable to stop the thinking from returning in the results stream, which we are now scrambling to try to rectifiy. why did you have to completely remove the deepseek-chat, can you put it back please. ### Are there known steps to reproduce? select deepseek llm, the options for deepseek-chat are removed from the list and replaced with "preview" models ### LLM Provider & Model (if applicable) _No response_ ### Embedder Provider & Model (if applicable) _No response_
yindo added the possible bug label 2026-06-05 14:52:17 -04:00
yindo closed this issue 2026-06-05 14:52:17 -04:00
yindo commented 2026-06-05 14:52:17 -04:00
Author
Owner
Copy Link
Copy Source

@ohromeo commented on GitHub (Apr 24, 2026):

as well these models don't respond/recognize the anythingLLM slash command. please put back the deepseek-chat options

<!-- gh-comment-id:4316700801 --> @ohromeo commented on GitHub (Apr 24, 2026): as well these models don't respond/recognize the anythingLLM slash command. please put back the deepseek-chat options
yindo commented 2026-06-05 14:52:17 -04:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Apr 24, 2026):

yesterday the app was happily running via anyhtingLLM api using deepseek and deepseek-chat models - with purchased api key, today they are totally gone from the LLM deekseek options and replaced with 2 preview models. deepseek-flash / deepseek-pro, which you broke our functions by doing this out of the blue.

This is because deepseek API removed the models and so the API no longer shows them. They also changed their API as well which also broke that integration.

We did do anything - they broke their API by removing models as well as making backward compatibility impossible.

That is all that is going on.

<!-- gh-comment-id:4316708645 --> @timothycarambat commented on GitHub (Apr 24, 2026): > yesterday the app was happily running via anyhtingLLM api using deepseek and deepseek-chat models - with purchased api key, today they are totally gone from the LLM deekseek options and replaced with 2 preview models. deepseek-flash / deepseek-pro, which you broke our functions by doing this out of the blue. This is because deepseek API _removed_ the models and so the API no longer shows them. They also changed their API as well which also broke that integration. We did _do_ anything - they broke their API by removing models as well as making backward compatibility impossible. That is all that is going on.
yindo commented 2026-06-05 14:52:17 -04:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Apr 24, 2026):

Note: If you manually set the DEEPSEEK_MODEL_PREF ENV in the appropriate env file location
Docker - this is in your storage folder you use with the container
Desktop- https://docs.anythingllm.com/installation-desktop/storage should be potentially invisible .env file.

Edit this file, restart container or kill & restart app.

This will allow you to still use these deprecated models despite the fact the Deepseek official API does not show them - everything will still work while we work on https://github.com/Mintplex-Labs/anything-llm/issues/5509 for official support and also bringing that patch to desktop!

Valid values for legacy models are:
deepseek-reasoner or deepseek-chat

<!-- gh-comment-id:4316797794 --> @timothycarambat commented on GitHub (Apr 24, 2026): Note: If you manually set the DEEPSEEK_MODEL_PREF ENV in the appropriate env file location Docker - this is in your storage folder you use with the container Desktop- https://docs.anythingllm.com/installation-desktop/storage should be potentially invisible .env file. Edit this file, restart container or kill & restart app. This will allow you to still use these deprecated models despite the fact the Deepseek official API does not show them - everything will still work while we work on https://github.com/Mintplex-Labs/anything-llm/issues/5509 for official support and also bringing that patch to desktop! Valid values for legacy models are: deepseek-reasoner or deepseek-chat
yindo commented 2026-06-05 14:52:18 -04:00
Author
Owner
Copy Link
Copy Source

@ohromeo commented on GitHub (Apr 24, 2026):

side-stepped settigns to "generic-openai" [deepseek] - [deepseek-chat], got us back in business as well...

thanks

<!-- gh-comment-id:4317126711 --> @ohromeo commented on GitHub (Apr 24, 2026): side-stepped settigns to "generic-openai" [deepseek] - [deepseek-chat], got us back in business as well... thanks
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 possible bug
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#5144
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?