microsoft / microsoft/ai-dev-gallery

[FEATURE] Add more model details to help in sample model selection dialog

Open
#473 0 comments 2 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement
Dominant language
C#
Stars
1.5k
Forks
223
PR merge metrics
No merged PRs in 30d

Description

Is your feature request related to a problem? Please describe.
For the app to be a gateway into learning about utilizing AI in an application, the first thing after choosing an appealing scenario is to be prompted with a model selection dialog without much context...

Related to #327

Describe the solution you'd like

  1. It'd be great for the "No models downloaded" card to have a link or more info about what a model is and why it's needed, e.g. "models help transform or translate data from your given input to the desired output. Different models have different capabilities. Read more about each model below."

  2. In the example screenshot below, I have no context to decide what the difference between the "L6" and the "L12" models are as the only discernable difference. I did discover the "..." and the ability to look at the "model card" (which is more of a page). However, that's pretty dense information and while useful, looking at the pages for these two models, they look identical to me. Nothing here helps me understand which one I should pick or if I should use one in one scenario vs. another. Having a bit more of a description here attached to the model on the card would be great. e.g. "Use the L6 model here for quicker responses that may not be as accurate." and "Use the L12 model for deeper analysis which may be more accurate but require more resources/time."

Describe alternatives you've considered
Would need to go do research elsewhere and leave the app.

Additional context

Image

(Similarly the more complex select dialog with the different providers is even less clear, what is the benefit one provider has over the other? E.g. using OpenAI Key requires subscription and is cloud only I assume vs. Windows AI which runs more efficiently on NPU but only on a device with an NPU. What about Foundry Local or the other model option???)

Image

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

No files or tests are named; start by locating the sample model selection dialog and the more complex provider-selection dialog described in the issue. Review how model cards and model pages expose information, then define and implement concise guidance so users can understand model and provider trade-offs without leaving the app.

Written by the indexing model from the issue text.

Assessment

Tech stack
csharp
Domain
ai, design, desktop
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
38/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.