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

Add a way to list all available models I can use with %%ai #28

Closed
JasonWeill opened this issue Apr 4, 2023 · 1 comment · Fixed by #100
Closed

Add a way to list all available models I can use with %%ai #28

JasonWeill opened this issue Apr 4, 2023 · 1 comment · Fixed by #100
Assignees
Labels
enhancement New feature or request @jupyter-ai/magics
Milestone

Comments

@JasonWeill
Copy link
Collaborator

Problem

There is no command I can run to get a list of models I can use with the %%ai magic command.

Proposed Solution

Add a command such as %%ai list that lists all supported models.

@JasonWeill JasonWeill added the enhancement New feature or request label Apr 4, 2023
@dlqqq
Copy link
Member

dlqqq commented Apr 7, 2023

Each provider exposes a class attribute called models, for example:

>>> AI21Provider.models
[
    "j1-large",
    "j1-grande",
    "j1-jumbo",
    "j1-grande-instruct",
    "j2-large",
    "j2-grande",
    "j2-jumbo",
    "j2-grande-instruct",
    "j2-jumbo-instruct",
]

Some providers are "registry" providers that have a dynamic, unknown, or extremely large list of supported models. For example, HuggingFace Hub is a good example. In this case, the returned list is just the wildcard specifier ["*"].

The %%ai list command should do a good job of rendering a long list of models in a human-readable format (i.e. not a raw list that extends all the way to the right). Furthermore, there should be some helpful messaging when a model provider is a registry provider. Perhaps each registry provider could have a help message stored as a class attribute that tells users how to discover new models.

  • HuggingFace Hub: "Available models can be found on https://huggingface.co/"
  • SageMaker Endpoint: "Available endpoint names can be found on your AWS Console."

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request @jupyter-ai/magics
Projects
None yet
Development

Successfully merging a pull request may close this issue.

3 participants