Enhance Structured Output Interface

[GirinMan]

What does this PR do?

This PR enhances the /v1/chat/completions API in LoRAX to improve compatibility with OpenAI’s structured output interface. The changes include:

• Adding support for text, json_object, and json_schema as valid type options in response_format.
• Making the schema (or json_schema) field optional, allowing the generation of arbitrary JSON objects when using json_object without requiring a predefined schema.
• Retaining the original LoRAX interface behavior for backward compatibility.

This update brings LoRAX's API closer in line with OpenAI’s, allowing developers to more easily switch between or integrate both systems.

Fixes #643

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Was this discussed/approved via a Github issue or the discord / slack channel? Please add a link
  to it if that's the case.
• Did you write any new necessary tests?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

@tgaddair
@donggyukimc

[tgaddair]

Love this! Will review today :)

[tgaddair]

LGTM! I think the one thing I might do as a follow-up is allow specifying a JSON schema even when the format is json_object, that would ensure backwards compatibility for existing LoRAX users. Do you have any objections to making that change?