Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

epic: Better Design abstraction for Remote AI (and Engineering abstraction) #994

Closed
0xSage opened this issue Dec 14, 2023 · 6 comments
Closed
Assignees
Labels
type: epic A major feature or initiative

Comments

@0xSage
Copy link
Contributor

0xSage commented Dec 14, 2023

Problem
image

  • It's not clear to users they need to add an API key to chat with remote models.
  • It's not clear to users the diff btw remote vs local model.
  • Right now it just looks like its broken.

Success Criteria

  1. RightPanel should indicate this model is not set up yet. Let's try the label API key needed
  2. We should somehow link the user to settings > models to set it up
image

Additional context
Add any other context or screenshots about the feature request here.

@0xSage 0xSage added the type: feature request A new feature label Dec 14, 2023
@0xSage 0xSage added this to the Jan as the default Assistant milestone Dec 14, 2023
@0xSage 0xSage changed the title feat: improve ux around chatting with remote models feat: improve ux around starting, configuring, chatting with remote models Dec 14, 2023
@0xSage 0xSage added the type: epic A major feature or initiative label Dec 14, 2023
@0xSage 0xSage modified the milestones: Jan as the default Assistant, Jan works with Remote Models Dec 14, 2023
@0xSage 0xSage changed the title feat: improve ux around starting, configuring, chatting with remote models epic: remote models Dec 18, 2023
@0xSage 0xSage changed the title epic: remote models epic: Remote models Dec 18, 2023
@0xSage 0xSage removed this from the Jan Works with Remote Models milestone Dec 27, 2023
@0xSage 0xSage added needs designs Needs designs and removed roadmap: Jan Hub labels Dec 27, 2023
@imtuyethan
Copy link
Contributor

imtuyethan commented Dec 28, 2023

@0xSage 0xSage added the needs eng decision Needs product or engineering specs label Dec 29, 2023
@imtuyethan imtuyethan assigned 0xSage and imtuyethan and unassigned imtuyethan and 0xSage Jan 4, 2024
@imtuyethan imtuyethan added roadmap: My models and removed needs eng decision Needs product or engineering specs labels Jan 4, 2024
@imtuyethan imtuyethan assigned imtuyethan and unassigned 0xSage Jan 5, 2024
@imtuyethan
Copy link
Contributor

Archive original comment from @0xSage
Problem
image

  • It's not clear to users they need to add an API key to chat with remote models.
  • It's not clear to users the diff btw remote vs local model.
  • Right now it just looks like its broken.

Success Criteria

  1. RightPanel should indicate this model is not set up yet. Let's try the label API key needed
  2. We should somehow link the user to settings > models to set it up
image

Additional context
Add any other context or screenshots about the feature request here.

@imtuyethan imtuyethan added the needs eng decision Needs product or engineering specs label Jan 5, 2024
@kha84
Copy link

kha84 commented Jan 23, 2024

I looked through the UI mockups and I can see there's one thing is missing - to allow user to specify it's own URL, for OpenAI-compatible models. Like for instance I do have a model running on my server via oobabooga (it provides OpenAI-compatible API out of the box) or via ollama LiteLLM. And I want to be able to chat with that model from Jan - for that I need to be able to add a remotely inferenced model with OpenAI-compatible API on a custom URL.

@imtuyethan
Copy link
Contributor

imtuyethan commented Jan 24, 2024

I looked through the UI mockups and I can see there's one thing is missing - to allow user to specify it's own URL, for OpenAI-compatible models. Like for instance I do have a model running on my server via oobabooga (it provides OpenAI-compatible API out of the box) or via ollama LiteLLM. And I want to be able to chat with that model from Jan - for that I need to be able to add a remotely inferenced model with OpenAI-compatible API on a custom URL.

Thanks for flagging this @kha84. I'll add this user story as well!

@dan-homebrew dan-homebrew changed the title epic: Remote models epic: Better UX for using Remote models Jan 25, 2024
@dan-homebrew dan-homebrew changed the title epic: Better UX for using Remote models epic: Better Engineering and Design abstraction for Remote AI Feb 15, 2024
@dan-homebrew dan-homebrew changed the title epic: Better Engineering and Design abstraction for Remote AI epic: Better Design abstraction for Remote AI Feb 16, 2024
@dan-homebrew dan-homebrew changed the title epic: Better Design abstraction for Remote AI epic: Better Design abstraction for Remote AI (and Engineering abstraction) Feb 16, 2024
@imtuyethan imtuyethan assigned Van-QA and unassigned imtuyethan Feb 16, 2024
@imtuyethan imtuyethan added roadmap: Refactoring & Tech Debt and removed needs designs Needs designs needs eng decision Needs product or engineering specs labels Feb 16, 2024
@imtuyethan imtuyethan assigned louis-jan and unassigned urmauur Feb 16, 2024
@dan-homebrew
Copy link
Contributor

I am sunsetting this issue in favor for a more holistic redesign of the "Provider" abstraction:

https://www.notion.so/jan-ai/Provider-Abstraction-for-Local-and-Remote-AI-d54448ad5ce34cb2845d986870b9395e?pvs=4

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
type: epic A major feature or initiative
Projects
Archived in project
Development

No branches or pull requests

7 participants