CreateCompletionRequest

Request body for creating a text completion.

API ManagementCloudCloud ComputingEnterpriseInfrastructure as a ServicePlatform as a ServiceT1

Properties

Name	Type	Description
prompt	object	The prompt(s) to generate completions for.
max_tokens	integer	The maximum number of tokens that can be generated.
temperature	number	Sampling temperature to use.
top_p	number	Nucleus sampling parameter.
n	integer	How many completions to generate for each prompt.
stream	boolean	Whether to stream back partial progress.
stop	object	Up to 4 sequences where the API will stop generating further tokens.
presence_penalty	number	Penalizes new tokens based on whether they appear in the text so far.
frequency_penalty	number	Penalizes new tokens based on their existing frequency in the text.
user	string	A unique identifier representing your end-user.

View JSON Schema on GitHub

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "#/components/schemas/CreateCompletionRequest",
  "title": "CreateCompletionRequest",
  "type": "object",
  "description": "Request body for creating a text completion.",
  "properties": {
    "prompt": {
      "description": "The prompt(s) to generate completions for.",
      "oneOf": [
        {
          "type": "string"
        },
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        }
      ],
      "example": "example_value"
    },
    "max_tokens": {
      "type": "integer",
      "default": 16,
      "description": "The maximum number of tokens that can be generated.",
      "example": 10
    },
    "temperature": {
      "type": "number",
      "default": 1,
      "minimum": 0,
      "maximum": 2,
      "description": "Sampling temperature to use.",
      "example": 42.5
    },
    "top_p": {
      "type": "number",
      "default": 1,
      "minimum": 0,
      "maximum": 1,
      "description": "Nucleus sampling parameter.",
      "example": 42.5
    },
    "n": {
      "type": "integer",
      "default": 1,
      "minimum": 1,
      "maximum": 128,
      "description": "How many completions to generate for each prompt.",
      "example": 10
    },
    "stream": {
      "type": "boolean",
      "default": false,
      "description": "Whether to stream back partial progress.",
      "example": true
    },
    "stop": {
      "description": "Up to 4 sequences where the API will stop generating further tokens.",
      "oneOf": [
        {
          "type": "string"
        },
        {
          "type": "array",
          "items": {
            "type": "string"
          },
          "maxItems": 4
        }
      ],
      "example": "example_value"
    },
    "presence_penalty": {
      "type": "number",
      "default": 0,
      "minimum": -2,
      "maximum": 2,
      "description": "Penalizes new tokens based on whether they appear in the text so far.",
      "example": 42.5
    },
    "frequency_penalty": {
      "type": "number",
      "default": 0,
      "minimum": -2,
      "maximum": 2,
      "description": "Penalizes new tokens based on their existing frequency in the text.",
      "example": 42.5
    },
    "user": {
      "type": "string",
      "description": "A unique identifier representing your end-user.",
      "example": "example_value"
    }
  },
  "required": [
    "prompt"
  ]
}