Microsoft Azure Completions API

openapi: 3.2.0
info:
  title: Microsoft Azure Azure OpenAI Service Completions API
  description: Azure OpenAI Service provides REST API access to OpenAI's language models including GPT-4, GPT-4 Turbo, GPT-3.5-Turbo, and the Embeddings model series. These models can be adapted to tasks including content generation, summarization, semantic search, and natural language to code translation. Users access the service through REST APIs, Python SDK, or the web-based interface in the Azure AI Foundry portal.
  version: '2024-06-01'
  contact:
    name: Microsoft Azure Support
    url: https://azure.microsoft.com/en-us/support/
    email: azuresupport@microsoft.com
  license:
    name: Microsoft API License
    url: https://learn.microsoft.com/en-us/legal/
  x-logo:
    url: https://azure.microsoft.com/svghandler/azure-logo.png
servers:
- url: https://{endpoint}/openai
  description: Azure OpenAI Service endpoint
  variables:
    endpoint:
      default: your-resource-name.openai.azure.com
      description: 'The Azure OpenAI resource endpoint. Format: https://{resource-name}.openai.azure.com'
security:
- apiKey: []
- oauth2:
  - https://cognitiveservices.azure.com/.default
tags:
- name: Completions
  description: Operations for text completions
paths:
  /deployments/{deployment-id}/completions:
    post:
      operationId: Completions_Create
      summary: Microsoft Azure Create a Text Completion
      description: Creates a completion for the provided prompt and parameters.
      tags:
      - Completions
      parameters:
      - $ref: '#/components/parameters/DeploymentIdParameter'
      - $ref: '#/components/parameters/ApiVersionParameter'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateCompletionRequest'
            examples:
              CompletionsCreateRequestExample:
                summary: Default Completions_Create request
                x-microcks-default: true
                value:
                  prompt: example_value
                  max_tokens: 10
                  temperature: 42.5
                  top_p: 42.5
                  n: 10
                  stream: true
                  stop: example_value
                  presence_penalty: 42.5
                  frequency_penalty: 42.5
                  user: example_value
      responses:
        '200':
          description: Successfully created a completion.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CreateCompletionResponse'
              examples:
                CompletionsCreate200Example:
                  summary: Default Completions_Create 200 response
                  x-microcks-default: true
                  value:
                    id: abc123
                    object: text_completion
                    created: 10
                    model: example_value
                    choices:
                    - text: example_value
                      index: 10
                      finish_reason: stop
                    usage:
                      prompt_tokens: 10
                      completion_tokens: 10
                      total_tokens: 10
        default:
          description: An error occurred.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
              examples:
                CompletionsCreatedefaultExample:
                  summary: Default Completions_Create default response
                  x-microcks-default: true
                  value:
                    error:
                      code: example_value
                      message: example_value
                      param: example_value
                      type: example_value
                      inner_error:
                        code: example_value
                        content_filter_result: example_value
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
components:
  schemas:
    CreateCompletionResponse:
      type: object
      description: Represents a completion response from the API.
      properties:
        id:
          type: string
          description: A unique identifier for the completion.
          example: abc123
        object:
          type: string
          enum:
          - text_completion
          description: The object type.
          example: text_completion
        created:
          type: integer
          description: The Unix timestamp of when the completion was created.
          example: 10
        model:
          type: string
          description: The model used for completion.
          example: example_value
        choices:
          type: array
          description: The list of completion choices.
          items:
            type: object
            properties:
              text:
                type: string
                description: The generated text.
              index:
                type: integer
                description: The index of the choice.
              finish_reason:
                type: string
                enum:
                - stop
                - length
                - content_filter
                description: The reason the model stopped generating tokens.
          example: []
        usage:
          $ref: '#/components/schemas/Usage'
      required:
      - id
      - object
      - created
      - model
      - choices
    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
    Usage:
      type: object
      description: Usage statistics for the API call.
      properties:
        prompt_tokens:
          type: integer
          description: Number of tokens in the prompt.
          example: 10
        completion_tokens:
          type: integer
          description: Number of tokens in the generated completion.
          example: 10
        total_tokens:
          type: integer
          description: Total number of tokens used in the request.
          example: 10
      required:
      - prompt_tokens
      - total_tokens
    ErrorResponse:
      type: object
      description: Error response.
      properties:
        error:
          type: object
          description: The error object.
          properties:
            code:
              type: string
              description: The error code.
            message:
              type: string
              description: The error message.
            param:
              type: string
              description: The parameter that caused the error.
            type:
              type: string
              description: The error type.
            inner_error:
              type: object
              description: Inner error details.
              properties:
                code:
                  type: string
                  description: The inner error code.
                content_filter_result:
                  type: object
                  description: Content filter results, if applicable.
          required:
          - code
          - message
          example: example_value
  parameters:
    DeploymentIdParameter:
      name: deployment-id
      in: path
      required: true
      description: The deployment ID of the model to use for this request.
      schema:
        type: string
    ApiVersionParameter:
      name: api-version
      in: query
      required: true
      description: The API version to use for this operation.
      schema:
        type: string
        default: '2024-06-01'
  securitySchemes:
    apiKey:
      type: apiKey
      name: api-key
      in: header
      description: Azure OpenAI API key authentication.
    oauth2:
      type: oauth2
      flows:
        implicit:
          authorizationUrl: https://login.microsoftonline.com/common/oauth2/v2.0/authorize
          scopes:
            https://cognitiveservices.azure.com/.default: Access Azure OpenAI