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 #3639] How can I make anythingllm call Xinference? #2351

New Issue
Closed
opened 2026-02-22 18:29:18 -05:00 by yindo · 2 comments
yindo commented 2026-02-22 18:29:18 -05:00
Owner
Copy Link
Copy Source

Originally created by @jeerychao on GitHub (Apr 13, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3639

Hello everyone,

I have deployed and installed anythingllm and Xinference in Docker. Both are running properly, and I have tested Xinference using curl and found no issues. However, in the settings of anythingllm, there is no option for the LLM provider to choose Xinference. How can I make anythingllm call Xinference? Please tell me how to do it.

Additionally, I have loaded embedding models and re-ranking models in Xinference. How can I select and call these models in anythingllm?

Thank you!

Originally created by @jeerychao on GitHub (Apr 13, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3639 Hello everyone, I have deployed and installed anythingllm and Xinference in Docker. Both are running properly, and I have tested Xinference using curl and found no issues. However, in the settings of anythingllm, there is no option for the LLM provider to choose Xinference. How can I make anythingllm call Xinference? Please tell me how to do it. Additionally, I have loaded embedding models and re-ranking models in Xinference. How can I select and call these models in anythingllm? Thank you!
yindo closed this issue 2026-02-22 18:29:18 -05:00
yindo commented 2026-02-22 18:29:18 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Apr 14, 2025):

This is still an outstanding feature request: https://github.com/Mintplex-Labs/anything-llm/issues/2614

However you can always just use the generic OpenAI connector at the bottom of the available LLM provider list. Then just use the normal base url you would normally use. This can also apply for embedder as well.

Your base URL would be something like http://[some-host-url]:[port]/v1 If Xinference is running in a separate docker container it would be something like http://docker.host.internal:port/v1 - but all depends on how XInference works and how you deployed both services and the OS that docker is running on.

Either way, all user-config stuff, nothing prevents you from using that service today even though we dont have a connector dedicated to XInference at this time.

@timothycarambat commented on GitHub (Apr 14, 2025): This is still an outstanding feature request: https://github.com/Mintplex-Labs/anything-llm/issues/2614 However you can always just use the generic OpenAI connector at the bottom of the available LLM provider list. Then just use the normal base url you would normally use. This can also apply for embedder as well. Your base URL would be something like `http://[some-host-url]:[port]/v1` If Xinference is running in a separate docker container it would be something like `http://docker.host.internal:port/v1` - but all depends on how XInference works and how you deployed both services and the OS that docker is running on. Either way, all user-config stuff, nothing prevents you from using that service today even though we dont have a connector dedicated to XInference at this time.
yindo commented 2026-02-22 18:29:18 -05:00
Author
Owner
Copy Link
Copy Source

@jeerychao commented on GitHub (Apr 14, 2025):

This is still an outstanding feature request: #2614

However you can always just use the generic OpenAI connector at the bottom of the available LLM provider list. Then just use the normal base url you would normally use. This can also apply for embedder as well.

Your base URL would be something like http://[some-host-url]:[port]/v1 If Xinference is running in a separate docker container it would be something like http://docker.host.internal:port/v1 - but all depends on how XInference works and how you deployed both services and the OS that docker is running on.

Either way, all user-config stuff, nothing prevents you from using that service today even though we dont have a connector dedicated to XInference at this time.

Thank you!

@jeerychao commented on GitHub (Apr 14, 2025): > This is still an outstanding feature request: [#2614](https://github.com/Mintplex-Labs/anything-llm/issues/2614) > > However you can always just use the generic OpenAI connector at the bottom of the available LLM provider list. Then just use the normal base url you would normally use. This can also apply for embedder as well. > > Your base URL would be something like `http://[some-host-url]:[port]/v1` If Xinference is running in a separate docker container it would be something like `http://docker.host.internal:port/v1` - but all depends on how XInference works and how you deployed both services and the OS that docker is running on. > > Either way, all user-config stuff, nothing prevents you from using that service today even though we dont have a connector dedicated to XInference at this time. Thank you!
yindo changed title from How can I make anythingllm call Xinference? to [GH-ISSUE #3639] How can I make anythingllm call Xinference? 2026-06-05 14:46:03 -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
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#2351
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?