[GH-ISSUE #793] Use gradio.live link from colab notebook as Local AI Base URL or LMStudio Base URL #462

Closed
opened 2026-02-22 18:19:37 -05:00 by yindo · 1 comment
Owner

Originally created by @PpiNeaPpLe on GitHub (Feb 24, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/793

How are you running AnythingLLM?

AnythingLLM desktop app

What happened?

usually when I run program that depends on Local AI i can simply put in my gradio.live link which comes from my google colab notebook which is hosting mistral 7b v.2 and it will act as if I am running it locally. However I get an error that my link must contain a "/v1" I have never experienced anything like this before on other applications. This is my first time using anything LLM and I am trying to avoid having to run mistral 7b on my PC locally and would prefer to run it through my google colab.

Are there known steps to reproduce?

No response

Originally created by @PpiNeaPpLe on GitHub (Feb 24, 2024). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/793 ### How are you running AnythingLLM? AnythingLLM desktop app ### What happened? usually when I run program that depends on Local AI i can simply put in my gradio.live link which comes from my google colab notebook which is hosting mistral 7b v.2 and it will act as if I am running it locally. However I get an error that my link must contain a "/v1" I have never experienced anything like this before on other applications. This is my first time using anything LLM and I am trying to avoid having to run mistral 7b on my PC locally and would prefer to run it through my google colab. ### Are there known steps to reproduce? _No response_
yindo added the possible bug label 2026-02-22 18:19:37 -05:00
yindo closed this issue 2026-02-22 18:19:37 -05:00
Author
Owner

@timothycarambat commented on GitHub (Feb 24, 2024):

If you are using LocalAI, the endpoint for inferencing with LocalAI API requires /v1 because it uses the OpenAI format to communicate - which is what AnythingLLM uses. Is there an API endpoint you can use on Gradio to generate a response? Because if using LocalAI this would still require the /v1 since that is just how LocalAI works for its API.

@timothycarambat commented on GitHub (Feb 24, 2024): If you are using LocalAI, the endpoint for inferencing with LocalAI API requires `/v1` because it uses the OpenAI format to communicate - which is what AnythingLLM uses. Is there an API endpoint you can use on Gradio to generate a response? Because if using LocalAI this would still require the `/v1` since that is just how LocalAI works for its API.
yindo changed title from Use gradio.live link from colab notebook as Local AI Base URL or LMStudio Base URL to [GH-ISSUE #793] Use gradio.live link from colab notebook as Local AI Base URL or LMStudio Base URL 2026-06-05 14:35:26 -04:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#462