Retry behavior configuration

[ailectra]

The BaseAgent class currently doesn't support retry functionality through the max_retries parameter that instructor provides. In the get_response and run_async methods, API calls to instructor don't pass any retry configuration:

# Current implementation in get_response
response = self.client.chat.completions.create(
    messages=messages,
    model=self.model,
    response_model=response_model,
    temperature=self.temperature,
    max_tokens=self.max_tokens,
)

Adding max_retries to the BaseAgentConfig would be a simple yet valuable improvement.

Also, maybe other instructor parameters should be added such as context or validation_context.

[KennyVaneetvelde]

This and #75 are related (in that the fix for both would be the same)

A good solution here would be to allow for extra kwargs to be passed