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 #4808] [BUG]: LiteLLM Connection Error #3025

New Issue
Closed
opened 2026-02-22 18:32:18 -05:00 by yindo · 3 comments
yindo commented 2026-02-22 18:32:18 -05:00
Owner
Copy Link
Copy Source

Originally created by @Ne0nd0g on GitHub (Dec 24, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4808

How are you running AnythingLLM?

AnythingLLM desktop app

What happened?

My issue is similar to #4691 and noticed it was closed without resolution. I've tried all of the options mentioned here and I'm still unable to get the models listed. I've tried:

I also noticed that despite putting my api key in every time, when I come back, that field is empty. For other providers, the secret field has dots indicating it has the password.

The backend logs show a connection error. How do I get more information to understand what the connection error is?

{"level":"info","message":"\u001b[32m[Event Logged]\u001b[0m - update_llm_provider","service":"backend"}
{"level":"error","message":"LiteLLM:listModels Connection error.","service":"backend"}
{"level":"error","message":"LiteLLM:listModels Connection error.","service":"backend"}
{"level":"error","message":"LiteLLM:listModels Connection error.","service":"backend"}
{"level":"error","message":"LiteLLM:listModels Connection error.","service":"backend"}
{"level":"error","message":"LiteLLM:listModels Connection error.","service":"backend"}

Are there known steps to reproduce?

Open Settings -> AI Providers: LLM -> Set LLM provider to LiteLLM -> Add API Key -> Add Base URL -> Save
Notice that Chat Model Selection never populates.
Exit from this menu and come back and see the API Key is no longer populated.

Originally created by @Ne0nd0g on GitHub (Dec 24, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4808 ### How are you running AnythingLLM? AnythingLLM desktop app ### What happened? My issue is similar to #4691 and noticed it was closed without resolution. I've tried all of the options mentioned here and I'm still unable to get the models listed. I've tried: - https://my.internal.service:8080/v1 - https://my.internal.service:8080/v1/models - https://myinternal.service:8080/models I also noticed that despite putting my api key in every time, when I come back, that field is empty. For other providers, the secret field has dots indicating it has the password. The backend logs show a connection error. How do I get more information to understand what the connection error is? ``` {"level":"info","message":"\u001b[32m[Event Logged]\u001b[0m - update_llm_provider","service":"backend"} {"level":"error","message":"LiteLLM:listModels Connection error.","service":"backend"} {"level":"error","message":"LiteLLM:listModels Connection error.","service":"backend"} {"level":"error","message":"LiteLLM:listModels Connection error.","service":"backend"} {"level":"error","message":"LiteLLM:listModels Connection error.","service":"backend"} {"level":"error","message":"LiteLLM:listModels Connection error.","service":"backend"} ``` ### Are there known steps to reproduce? Open Settings -> AI Providers: LLM -> Set LLM provider to LiteLLM -> Add API Key -> Add Base URL -> Save Notice that Chat Model Selection never populates. Exit from this menu and come back and see the API Key is no longer populated.
yindo added the possible bug label 2026-02-22 18:32:18 -05:00
yindo closed this issue 2026-02-22 18:32:18 -05:00
yindo commented 2026-02-22 18:32:18 -05:00
Author
Owner
Copy Link
Copy Source

@Ne0nd0g commented on GitHub (Dec 24, 2025):

I don't think that models should be included in the Base URL. I temporarily sent the traffic over plain-text HTTP (the service doesn't actually listen on that protocol) and captured the HTTP traffic. If you include models in the URL you get: GET /v1/models/models HTTP/1.1

@Ne0nd0g commented on GitHub (Dec 24, 2025): I don't think that `models` should be included in the Base URL. I temporarily sent the traffic over plain-text HTTP (the service doesn't actually listen on that protocol) and captured the HTTP traffic. If you include `models` in the URL you get: `GET /v1/models/models HTTP/1.1`
yindo commented 2026-02-22 18:32:19 -05:00
Author
Owner
Copy Link
Copy Source

@Ne0nd0g commented on GitHub (Dec 24, 2025):

I executed a curl command with the exact same format and headers as the captured HTTP traffic of LiteLLM talking to LiteLLM, and it worked successfully. I'm still thinking the original connection error is more about the Certificate Authority and AnythingLLM not trusting my internal service's certificate.

@Ne0nd0g commented on GitHub (Dec 24, 2025): I executed a curl command with the exact same format and headers as the captured HTTP traffic of LiteLLM talking to LiteLLM, and it worked successfully. I'm still thinking the original connection error is more about the Certificate Authority and AnythingLLM not trusting my internal service's certificate.
yindo commented 2026-02-22 18:32:19 -05:00
Author
Owner
Copy Link
Copy Source

@Ne0nd0g commented on GitHub (Dec 24, 2025):

OK, got it resolved. I ran the following command to get NodeJS to use the custom Certificate Authority. I would be nice if this can be done inside of AnythingLLM and not have to set an environment variable.

launchctl setenv NODE_EXTRA_CA_CERTS /Users/me/Documents/my-custom-ca-chain.crt

Following this, relaunch AnythingLLM and it worked for me.

@Ne0nd0g commented on GitHub (Dec 24, 2025): OK, got it resolved. I ran the following command to get NodeJS to use the custom Certificate Authority. I would be nice if this can be done inside of AnythingLLM and not have to set an environment variable. `launchctl setenv NODE_EXTRA_CA_CERTS /Users/me/Documents/my-custom-ca-chain.crt` Following this, relaunch AnythingLLM and it worked for me.
yindo changed title from [BUG]: LiteLLM Connection Error to [GH-ISSUE #4808] [BUG]: LiteLLM Connection Error 2026-06-05 14:49:55 -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 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#3025
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?