Python: New Feature: OllamaChatPromptExecutionSettings does not support structured outputs

[xyang2013]

The following does not work:

settings = kernel.get_prompt_execution_settings_from_service_id(service_id)
settings.format = InputScore.model_json_schema()

Links:

https://learn.microsoft.com/en-us/python/api/semantic-kernel/semantic_kernel.connectors.ai.ollama.ollama_prompt_execution_settings.ollamachatpromptexecutionsettings?view=semantic-kernel-python

https://ollama.com/blog/structured-outputs

[xyang2013]

I resolved the issue by modifying ollama_prompt_execution_settings.py.

Original:

class OllamaPromptExecutionSettings(PromptExecutionSettings):
    """Settings for Ollama prompt execution."""

    format: Literal["json"] | None = None
    options: dict[str, Any] | None = None

My fix:

class OllamaPromptExecutionSettings(PromptExecutionSettings):
    """Settings for Ollama prompt execution."""

    format: dict[str, Any] | None = None
    options: dict[str, Any] | None = None