Add token validation for GPT4_o model

What does this merge request do and why?

Add token validation for GPT4_o model.

How to set up and validate locally

1. Check out to this merge request's branch.
2. Ensure OPENAI_TOKEN is not set as an environment variable.
3. Run a pipeline with OpenAI models, either as an answering or evaluating model.
4. Confirm that a validation error is raised.

   pydantic_core._pydantic_core.ValidationError: 2 validation errors for DuoChatEvalConfig
   eval_setup.answering_models.2
     Assertion failed, OpenAI token not provided. Please set OPENAI_TOKEN env variable. [type=assertion_error, input_value={'name': 'gpt-4o', 'promp..._system.example.txt'}]}}, input_type=dict]
       For further information visit https://errors.pydantic.dev/2.7/v/assertion_error
   eval_setup.metrics.2.evaluating_models.0
     Assertion failed, OpenAI token not provided. Please set OPENAI_TOKEN env variable. [type=assertion_error, input_value={'name': 'gpt-4o', 'promp...ependent-system.txt'}]}}, input_type=dict]
       For further information visit https://errors.pydantic.dev/2.7/v/assertion_error

Merge request checklist

• I've ran the affected pipeline(s) to validate that nothing is broken.
• Tests added for new functionality. If not, please raise an issue to follow up.
• Documentation added/updated, if needed.