Snowflake · Schema

CompleteRequest

LLM text completion request.

Data LakesData SharingData WarehousingDatabaseSQL

Properties

Name Type Description
model string The model name. See documentation for possible values.
messages array
temperature number Temperature controls the amount of randomness used in response generation. A higher temperature corresponds to more randomness.
top_p number 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 integer The maximum number of output tokens to produce. The default value is model-dependent.
max_output_tokens integer Deprecated in favor of "max_tokens", which has identical behavior.
response_format object An object describing response format config for structured-output mode.
tools array List of tools to be used during tool calling
provisioned_throughput_id string The provisioned throughput ID to be used with the request.
sf-ml-xp-inflight-prompt-action string Reserved
sf-ml-xp-inflight-prompt-client-id string Reserved
sf-ml-xp-inflight-prompt-public-key string Reserved
stream boolean Reserved
View JSON Schema on GitHub

JSON Schema

cortex-inference-complete-request-schema.json Raw ↑ 
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "CompleteRequest",
  "type": "object",
  "description": "LLM text completion request.",
  "properties": {
    "model": {
      "type": "string",
      "description": "The model name. See documentation for possible values."
    },
    "messages": {
      "type": "array"
    },
    "temperature": {
      "type": "number",
      "description": "Temperature controls the amount of randomness used in response generation. A higher temperature corresponds to more randomness."
    },
    "top_p": {
      "type": "number",
      "description": "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": {
      "type": "integer",
      "description": "The maximum number of output tokens to produce. The default value is model-dependent."
    },
    "max_output_tokens": {
      "type": "integer",
      "description": "Deprecated in favor of \"max_tokens\", which has identical behavior."
    },
    "response_format": {
      "type": "object",
      "description": "An object describing response format config for structured-output mode."
    },
    "tools": {
      "type": "array",
      "description": "List of tools to be used during tool calling"
    },
    "provisioned_throughput_id": {
      "type": "string",
      "description": "The provisioned throughput ID to be used with the request."
    },
    "sf-ml-xp-inflight-prompt-action": {
      "type": "string",
      "description": "Reserved"
    },
    "sf-ml-xp-inflight-prompt-client-id": {
      "type": "string",
      "description": "Reserved"
    },
    "sf-ml-xp-inflight-prompt-public-key": {
      "type": "string",
      "description": "Reserved"
    },
    "stream": {
      "type": "boolean",
      "description": "Reserved"
    }
  }
}