snowflake.core.cortex.inference_service.CompleteRequestMessagesInner¶

class snowflake.core.cortex.inference_service.CompleteRequestMessagesInner(*, role: Annotated[str, Strict(strict=True)] | None = 'user', content: Annotated[str, Strict(strict=True)], content_list: List[Any] | None = None)¶

Bases: BaseModel

A model object representing the CompleteRequestMessagesInner resource.

Constructs an object of type CompleteRequestMessagesInner with the provided properties.

Parameters:
  • content (str) – The text completion prompt, e.g. ‘What is a Large Language Model?’.

  • role (str, default 'user') –

    Indicates the role of the message, one of ‘system’, ‘user’ or ‘assistant’.

    Rules: - A ‘user’ message must be the last message in the list. - If a ‘system’ message is specified, it must be the first message. - If a ‘assistant’ message is specified, it must be immediately before a ‘user’ message in the list.

    Multiple ‘assistant’ and ‘user’ messages can be specified, but they must alternate in sequence.

  • content_list (List[object], optional) – Contents of toolUse and toolResults

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Methods

classmethod from_dict(obj: dict) → CompleteRequestMessagesInner¶

Create an instance of CompleteRequestMessagesInner from a dict.

classmethod from_json(json_str: str) → CompleteRequestMessagesInner¶

Create an instance of CompleteRequestMessagesInner from a JSON string.

to_dict(hide_readonly_properties: bool = False) → dict[str, Any]¶

Returns the dictionary representation of the model using alias.

to_dict_without_readonly_properties() → dict[str, Any]¶

Return the dictionary representation of the model without readonly properties.

to_json() → str¶

Returns the JSON representation of the model using alias.

to_str() → str¶

Returns the string representation of the model using alias.