chatCompletionsRequestCommon

API ManagementCloudCloud ComputingEnterpriseInfrastructure as a ServicePlatform as a ServiceT1

Properties

Name	Type	Description
temperature	number	What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recomm
top_p	number	An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 1
stream	boolean	If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a `data: [DONE]` message.
stop	object	Up to 4 sequences where the API will stop generating further tokens.
max_tokens	integer	The maximum number of tokens allowed for the generated answer. By default, the number of tokens the model can return will be (4096 - prompt tokens).
presence_penalty	number	Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.
frequency_penalty	number	Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.
logit_bias	object	Modify the likelihood of specified tokens appearing in the completion. Accepts a json object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 10
user	string	A unique identifier representing your end-user, which can help Azure OpenAI to monitor and detect abuse.

View JSON Schema on GitHub

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "#/components/schemas/chatCompletionsRequestCommon",
  "title": "chatCompletionsRequestCommon",
  "type": "object",
  "properties": {
    "temperature": {
      "description": "What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.\nWe generally recommend altering this or `top_p` but not both.",
      "type": "number",
      "minimum": 0,
      "maximum": 2,
      "default": 1,
      "example": 1,
      "nullable": true
    },
    "top_p": {
      "description": "An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.\nWe generally recommend altering this or `temperature` but not both.",
      "type": "number",
      "minimum": 0,
      "maximum": 1,
      "default": 1,
      "example": 1,
      "nullable": true
    },
    "stream": {
      "description": "If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a `data: [DONE]` message.",
      "type": "boolean",
      "nullable": true,
      "default": false
    },
    "stop": {
      "description": "Up to 4 sequences where the API will stop generating further tokens.",
      "oneOf": [
        {
          "type": "string",
          "nullable": true
        },
        {
          "type": "array",
          "items": {
            "type": "string",
            "nullable": false
          },
          "minItems": 1,
          "maxItems": 4,
          "description": "Array minimum size of 1 and maximum of 4"
        }
      ],
      "default": null
    },
    "max_tokens": {
      "description": "The maximum number of tokens allowed for the generated answer. By default, the number of tokens the model can return will be (4096 - prompt tokens).",
      "type": "integer",
      "default": 4096
    },
    "presence_penalty": {
      "description": "Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.",
      "type": "number",
      "default": 0,
      "minimum": -2,
      "maximum": 2
    },
    "frequency_penalty": {
      "description": "Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.",
      "type": "number",
      "default": 0,
      "minimum": -2,
      "maximum": 2
    },
    "logit_bias": {
      "description": "Modify the likelihood of specified tokens appearing in the completion. Accepts a json object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token.",
      "type": "object",
      "nullable": true
    },
    "user": {
      "description": "A unique identifier representing your end-user, which can help Azure OpenAI to monitor and detect abuse.",
      "type": "string",
      "example": "user-1234",
      "nullable": false
    }
  }
}