Mintplex-Labs/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-07-19 14:13:35 -04:00
Code Issues 328 Packages Projects Releases 10 Wiki Activity

[GH-ISSUE #3765] [FEAT]: Add Codebert and other code embeding #2420

New Issue
Closed
opened 2026-02-22 18:29:36 -05:00 by yindo · 1 comment
yindo commented 2026-02-22 18:29:36 -05:00
Owner
Copy Link
Copy Source

Originally created by @rksharma1401 on GitHub (May 4, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3765

What would you like to see?

I see anythingllm by default has text embeder enabled, can you add codebert and such like options for developers to set code base as context without GitHub or bitbucket.
I have tried docker model runner to run the llm and it seems working fine for chat but fails as embeding.

Originally created by @rksharma1401 on GitHub (May 4, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3765 ### What would you like to see? I see anythingllm by default has text embeder enabled, can you add codebert and such like options for developers to set code base as context without GitHub or bitbucket. I have tried docker model runner to run the llm and it seems working fine for chat but fails as embeding.
yindo added the enhancementfeature request labels 2026-02-22 18:29:36 -05:00
yindo closed this issue 2026-02-22 18:29:37 -05:00
yindo commented 2026-02-22 18:29:37 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (May 5, 2025):

You can easily use another provider to run the codebert embedding model. Our default is a generic catch-all that works OK across the board. If you want to use a specialized embedding model you should pull it into something like Ollama or LMStudio and set that as your embedder in AnythingLLM.

Any specialized models you want to use for embedding, you can certainly use, but we will not build an explicit default for it into AnythingLLM since we try to be as model agnostic as possible. Our default embedder is small, fast, and works for most use cases - which is why it is the default, but is also why we offer the ability to change your preferred embedder for your use case.

@timothycarambat commented on GitHub (May 5, 2025): You can easily use another provider to run the codebert embedding model. Our default is a generic catch-all that works OK across the board. If you want to use a specialized embedding model you should pull it into something like Ollama or LMStudio and set that as your embedder in AnythingLLM. Any specialized models you want to use for embedding, you can certainly use, but we will not build an explicit default for it into AnythingLLM since we try to be as model agnostic as possible. Our default embedder is small, fast, and works for most use cases - which is why it is the default, but is also why we offer the ability to change your preferred embedder for your use case.
yindo changed title from [FEAT]: Add Codebert and other code embeding to [GH-ISSUE #3765] [FEAT]: Add Codebert and other code embeding 2026-06-05 14:46:27 -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#2420
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?