Mintplex-Labs/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-07-21 01:25:28 -04:00
Code Issues 328 Packages Projects Releases 10 Wiki Activity

[GH-ISSUE #1155] [FEAT]: Configuration of AnythingLLM with https #711

New Issue
Closed
opened 2026-02-22 18:20:57 -05:00 by yindo · 2 comments
yindo commented 2026-02-22 18:20:57 -05:00
Owner
Copy Link
Copy Source

Originally created by @flefevre on GitHub (Apr 20, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/1155

What would you like to see?

I have downloaded AnythingLLM for Windows
Thanks a lot for this installer.

At first step it ask for "AnythingLLM can work with many LLM providers. This will be the service which handles chatting."
I was not able to put httpS://ollama.myowninstllation.com/
The secure https was not recognized and it does not load the models.

Do you have an idea on how to do it?
For llm Models but also for Embedding ? or the Vector databases ?

Thanks a lot.

Originally created by @flefevre on GitHub (Apr 20, 2024). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/1155 ### What would you like to see? I have downloaded AnythingLLM for Windows Thanks a lot for this installer. At first step it ask for "AnythingLLM can work with many LLM providers. This will be the service which handles chatting." I was not able to put httpS://ollama.myowninstllation.com/ The secure https was not recognized and it does not load the models. Do you have an idea on how to do it? For llm Models but also for Embedding ? or the Vector databases ? Thanks a lot.
yindo added the enhancementfeature request labels 2026-02-22 18:20:57 -05:00
yindo closed this issue 2026-02-22 18:20:57 -05:00
yindo commented 2026-02-22 18:20:57 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Apr 21, 2024):

This is out of scope as an issue for AnythingLLM. I would assert the issue is how you have your Ollama server set up & configured wherever it may be running. All we do in the code is make a fetch request to the documented Ollama endpoints.
https://github.com/Mintplex-Labs/anything-llm/blob/a3b7239d057d1bbb424641760099af96d0065ffb/server/utils/AiProviders/ollama/index.js#L32

So http/https - we have no preference. Either a port is required in that URL or some other configuration/response setup is required where ollama is running.

@timothycarambat commented on GitHub (Apr 21, 2024): This is out of scope as an issue for AnythingLLM. I would assert the issue is how you have your Ollama server set up & configured wherever it may be running. All we do in the code is make a fetch request to the documented Ollama endpoints. https://github.com/Mintplex-Labs/anything-llm/blob/a3b7239d057d1bbb424641760099af96d0065ffb/server/utils/AiProviders/ollama/index.js#L32 So http/https - we have no preference. Either a port is required in that URL or some other configuration/response setup is required where ollama is running.
yindo commented 2026-02-22 18:20:57 -05:00
Author
Owner
Copy Link
Copy Source

@flefevre commented on GitHub (Apr 21, 2024):

Bonjour,

Thanks for your answer.
My ollama setup is well configured, I can reach it through litellm or open
webui or directly by a curl command.

But when I put the https address in anythingllm windows client, it did not
display the different available models.
The behaviour is different in the anythingllm server mode since I put
http://ollama:11434

Perhaps is it due because I use a reverse proxy
https//ollama.mylabo.com/ that linked to https://traefik.mylabo.com
Si anythingllm is not able to retrieve the model list?

I would look again

François

Le dim. 21 avr. 2024, 20:37, Timothy Carambat @.***> a
écrit :

This is out of scope as an issue for AnythingLLM. I would assert the issue
is how you have your Ollama server set up & configured wherever it may be
running. All we do in the code is make a fetch request to the documented
Ollama endpoints.

https://github.com/Mintplex-Labs/anything-llm/blob/a3b7239d057d1bbb424641760099af96d0065ffb/server/utils/AiProviders/ollama/index.js#L32

So http/https - we have no preference. Either a port is required in that
URL or some other configuration/response setup is required where ollama is
running.

—
Reply to this email directly, view it on GitHub
https://github.com/Mintplex-Labs/anything-llm/issues/1155#issuecomment-2068161283,
or unsubscribe
https://github.com/notifications/unsubscribe-auth/ABKZRFAM255KMGQVROLLGSTY6QBOTAVCNFSM6AAAAABGQ2FZMOVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDANRYGE3DCMRYGM
.
You are receiving this because you authored the thread.Message ID:
@.***>

@flefevre commented on GitHub (Apr 21, 2024): Bonjour, Thanks for your answer. My ollama setup is well configured, I can reach it through litellm or open webui or directly by a curl command. But when I put the https address in anythingllm windows client, it did not display the different available models. The behaviour is different in the anythingllm server mode since I put http://ollama:11434 Perhaps is it due because I use a reverse proxy https//ollama.mylabo.com/ that linked to https://traefik.mylabo.com Si anythingllm is not able to retrieve the model list? I would look again François Le dim. 21 avr. 2024, 20:37, Timothy Carambat ***@***.***> a écrit : > This is out of scope as an issue for AnythingLLM. I would assert the issue > is how you have your Ollama server set up & configured wherever it may be > running. All we do in the code is make a fetch request to the documented > Ollama endpoints. > > https://github.com/Mintplex-Labs/anything-llm/blob/a3b7239d057d1bbb424641760099af96d0065ffb/server/utils/AiProviders/ollama/index.js#L32 > > So http/https - we have no preference. Either a port is required in that > URL or some other configuration/response setup is required where ollama is > running. > > — > Reply to this email directly, view it on GitHub > <https://github.com/Mintplex-Labs/anything-llm/issues/1155#issuecomment-2068161283>, > or unsubscribe > <https://github.com/notifications/unsubscribe-auth/ABKZRFAM255KMGQVROLLGSTY6QBOTAVCNFSM6AAAAABGQ2FZMOVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDANRYGE3DCMRYGM> > . > You are receiving this because you authored the thread.Message ID: > ***@***.***> >
yindo changed title from [FEAT]: Configuration of AnythingLLM with https to [GH-ISSUE #1155] [FEAT]: Configuration of AnythingLLM with https 2026-06-05 14:36:47 -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#711
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?