Inference register fix

[heyjustinai]

Do not land - pending issue on sdk

What does this PR do?

Added register model in inference examples, modified message structure to typed dict

from SystemMessage to{"content": "You are a helpful assistant", "role": "system"}

Closes #113

Feature/Issue validation/testing/test plan

Please describe the tests that you ran to verify your changes and relevant result summary. Provide instructions so it can be reproduced.

Please also list any relevant details for your test configuration or test plan.

Sources

Please link relevant resources if necessary.

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you read the contributor guideline,
  Pull Request section?
• Was this discussed/approved via a Github issue? Please add a link
  to it if that's the case.
• Did you make sure to update the documentation with your changes?
• Did you write any new necessary tests?

Thanks for contributing 🎉!

[yanxi0830]

We do not need to call register anymore. Update your run.yaml file to start the server with the pre-registred resources. E.g.

inference:
  - provider_id: fireworks-0
    provider_type: remote::fireworks
    config:
      url: https://api.fireworks.ai/inference
      api_key: null
...
models: 
  - model_id: Llama3.2-3B-Instruct
    provider_id: fireworks-0