snowflake.core.cortex.inference_service.CompleteRequest | Snowflake Documentation (original) (raw)

class snowflake.core.cortex.inference_service.CompleteRequest(*, model: Annotated[str, Strict(strict=True)], messages: Annotated[List[CompleteRequestMessagesInner], MinLen(min_length=1)], temperature: Annotated[float, FieldInfo(annotation=NoneType, required=True, metadata=[Strict(strict=True), Ge(ge=0.0)])] | Annotated[int, FieldInfo(annotation=NoneType, required=True, metadata=[Strict(strict=True), Ge(ge=0)])] | None = None, top_p: Annotated[float, FieldInfo(annotation=NoneType, required=True, metadata=[Strict(strict=True), Ge(ge=0.0), Le(le=1.0)])] | Annotated[int, FieldInfo(annotation=NoneType, required=True, metadata=[Strict(strict=True), Ge(ge=0), Le(le=1)])] | None = 1.0, max_tokens: Annotated[int, FieldInfo(annotation=NoneType, required=True, metadata=[Strict(strict=True), Ge(ge=0)])] | None = 4096, max_output_tokens: Annotated[int, Strict(strict=True)] | None = None, response_format: CompleteRequestResponseFormat | None = None, guardrails: GuardrailsConfig | None = None, tools: List[Tool] | None = None, tool_choice: ToolChoice | None = None, provisioned_throughput_id: Annotated[str, Strict(strict=True)] | None = None, sf_ml_xp_inflight_prompt_action: Annotated[str, Strict(strict=True)] | None = None, sf_ml_xp_inflight_prompt_client_id: Annotated[str, Strict(strict=True)] | None = None, sf_ml_xp_inflight_prompt_public_key: Annotated[str, Strict(strict=True)] | None = None, stream: Annotated[bool, Strict(strict=True)] | None = True)¶

Bases: BaseModel

A model object representing the CompleteRequest resource.

Constructs an object of type CompleteRequest with the provided properties.

Parameters:

• model (str) – The model name. See documentation for possible values.
• messages (List _[_CompleteRequestMessagesInner])
• temperature (float , optional) – Temperature controls the amount of randomness used in response generation. A higher temperature corresponds to more randomness.
• top_p (float , default 1.0) – Threshold probability for nucleus sampling. A higher top-p value increases the diversity of tokens that the model considers, while a lower value results in more predictable output.
• max_tokens (int , default 4096) – The maximum number of output tokens to produce. The default value is model-dependent.
• max_output_tokens (int , optional) – Deprecated in favor of “max_tokens”, which has identical behavior.
• response_format (CompleteRequestResponseFormat , optional)
• guardrails (GuardrailsConfig , optional)
• tools (List [ Tool ] , optional) – List of tools to be used during tool calling
• tool_choice (ToolChoice , optional)
• provisioned_throughput_id (str , optional) – The provisioned throughput ID to be used with the request.
• sf_ml_xp_inflight_prompt_action (str , optional) – Reserved
• sf_ml_xp_inflight_prompt_client_id (str , optional) – Reserved
• sf_ml_xp_inflight_prompt_public_key (str , optional) – Reserved
• stream (bool , default True) – Reserved

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) → CompleteRequest¶

Create an instance of CompleteRequest from a dict.

classmethod from_json(json_str: str) → CompleteRequest¶

Create an instance of CompleteRequest 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.