Story (Required)

As a user of the 'bac' CLI for importing new AI Models,  I want the AI Models I've deployed from/to HuggingFace to be translated into Catalog content.

Background (Required)

The ‘huggingface-cli’ is a python wrapper around a combination of Hugging Face REST API interactions and Git upload/down to the Git repositories and organizations hosted on Hugging Face.

It employs the <action> <options> syntax pattern.

Python libraries, JavaScript/TypeScript libraries also exist.

Out of scope

<Defines what is not included in this story>Ollama has a REST API defined at https://github.com/ollama/ollama/blob/main/docs/api.md and from there you can list running models (and their access URLs) as well as model information that can fill in descriptions and tags.

Approach (Required)

Deploying models from HuggingFace onto OCP, connect to the environment and via REST API see if metadata, most notably inference endpoints, for any models there can be pulled and provide sufficient model catalog representations.

Dependencies

Acceptance Criteria (Mandatory)

merged PR to our CLI repo that includes unit tests

INVEST Checklist

Dependencies identified

Blockers noted and expected delivery timelines set

Design is implementable

Acceptance criteria agreed upon

Story estimated

Legend

Unknown

Verified

Unsatisfied

Done Checklist

• Code is completed, reviewed, documented and checked in
• Unit and integration test automation have been delivered and running cleanly in continuous integration/staging/canary environment
• Continuous Delivery pipeline(s) is able to proceed with new code included
• Customer facing documentation, API docs etc. are produced/updated, reviewed and published
• Acceptance criteria are met