specification/cognitiveservices/data-plane/AzureOpenAI/inference/preview/2023-12-01-preview/inference.yaml

openapi: 3.0.0
info:
  title: Azure OpenAI Service API
  description: Azure OpenAI APIs for completions and search
  version: 2023-12-01-preview
servers:
  - url: https://{endpoint}/openai
    variables:
      endpoint:
        default: your-resource-name.openai.azure.com
security:
  - bearer:
      - api.read
  - apiKey: []
paths:
  /deployments/{deployment-id}/completions:
    post:
      summary: Creates a completion for the provided prompt, parameters and chosen model.
      operationId: Completions_Create
      parameters:
        - in: path
          name: deployment-id
          required: true
          schema:
            type: string
            example: davinci
            description: Deployment id of the model which was deployed.
        - in: query
          name: api-version
          required: true
          schema:
            type: string
            example: 2023-12-01-preview
            description: api version
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              properties:
                prompt:
                  description: |-
                    The prompt(s) to generate completions for, encoded as a string or array of strings.
                    Note that <|endoftext|> is the document separator that the model sees during training, so if a prompt is not specified the model will generate as if from the beginning of a new document. Maximum allowed size of string list is 2048.
                  oneOf:
                    - type: string
                      default: ''
                      example: This is a test.
                      nullable: true
                    - type: array
                      items:
                        type: string
                        default: ''
                        example: This is a test.
                        nullable: false
                      description: Array size minimum of 1 and maximum of 2048
                max_tokens:
                  description: The token count of your prompt plus max_tokens cannot exceed the model's context length. Most models have a context length of 2048 tokens (except for the newest models, which support 4096). Has minimum of 0.
                  type: integer
                  default: 16
                  example: 16
                  nullable: true
                temperature:
                  description: |-
                    What sampling temperature to use. Higher values means the model will take more risks. Try 0.9 for more creative applications, and 0 (argmax sampling) for ones with a well-defined answer.
                    We generally recommend altering this or top_p but not both.
                  type: number
                  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.
                    We generally recommend altering this or temperature but not both.
                  type: number
                  default: 1
                  example: 1
                  nullable: true
                logit_bias:
                  description: Defaults to null. Modify the likelihood of specified tokens appearing in the completion. Accepts a json object that maps tokens (specified by their token ID in the GPT tokenizer) to an associated bias value from -100 to 100. You can use this tokenizer tool (which works for both GPT-2 and GPT-3) to convert text to token IDs. 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. As an example, you can pass {"50256" &#58; -100} to prevent the <|endoftext|> token from being generated.
                  type: object
                  nullable: false
                user:
                  description: A unique identifier representing your end-user, which can help monitoring and detecting abuse
                  type: string
                  nullable: false
                'n':
                  description: |-
                    How many completions to generate for each prompt. Minimum of 1 and maximum of 128 allowed.
                    Note: Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for max_tokens and stop.
                  type: integer
                  default: 1
                  example: 1
                  nullable: true
                stream:
                  description: 'Whether to stream back partial progress. If set, 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
                logprobs:
                  description: |-
                    Include the log probabilities on the logprobs most likely tokens, as well the chosen tokens. For example, if logprobs is 5, the API will return a list of the 5 most likely tokens. The API will always return the logprob of the sampled token, so there may be up to logprobs+1 elements in the response.
                    Minimum of 0 and maximum of 5 allowed.
                  type: integer
                  default: null
                  nullable: true
                suffix:
                  type: string
                  nullable: true
                  description: The suffix that comes after a completion of inserted text.
                echo:
                  description: Echo back the prompt in addition to the completion
                  type: boolean
                  default: false
                  nullable: true
                stop:
                  description: Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.
                  oneOf:
                    - type: string
                      default: <|endoftext|>
                      example: |+

                      nullable: true
                    - type: array
                      items:
                        type: string
                        example: |+

                        nullable: false
                      description: Array minimum size of 1 and maximum of 4
                completion_config:
                  type: string
                  nullable: true
                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
                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
                best_of:
                  description: |-
                    Generates best_of completions server-side and returns the "best" (the one with the highest log probability per token). Results cannot be streamed.
                    When used with n, best_of controls the number of candidate completions and n specifies how many to return - best_of must be greater than n.
                    Note: Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for max_tokens and stop. Has maximum value of 128.
                  type: integer
            example:
              prompt: |-
                Negate the following sentence.The price for bubblegum increased on thursday.

                 Negated Sentence:
              max_tokens: 50
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                type: object
                properties:
                  id:
                    type: string
                  object:
                    type: string
                  created:
                    type: integer
                  model:
                    type: string
                  prompt_filter_results:
                    $ref: '#/components/schemas/promptFilterResults'
                  choices:
                    type: array
                    items:
                      type: object
                      properties:
                        text:
                          type: string
                        index:
                          type: integer
                        logprobs:
                          type: object
                          properties:
                            tokens:
                              type: array
                              items:
                                type: string
                            token_logprobs:
                              type: array
                              items:
                                type: number
                            top_logprobs:
                              type: array
                              items:
                                type: object
                                additionalProperties:
                                  type: number
                            text_offset:
                              type: array
                              items:
                                type: integer
                          nullable: true
                        finish_reason:
                          type: string
                        content_filter_results:
                          $ref: '#/components/schemas/contentFilterChoiceResults'
                  usage:
                    type: object
                    properties:
                      completion_tokens:
                        type: number
                        format: int32
                      prompt_tokens:
                        type: number
                        format: int32
                      total_tokens:
                        type: number
                        format: int32
                    required:
                      - prompt_tokens
                      - total_tokens
                      - completion_tokens
                required:
                  - id
                  - object
                  - created
                  - model
                  - choices
              example:
                model: davinci
                object: text_completion
                id: cmpl-4509KAos68kxOqpE2uYGw81j6m7uo
                created: 1637097562
                choices:
                  - index: 0
                    text: The price for bubblegum decreased on thursday.
                    logprobs: null
                    finish_reason: stop
          headers:
            apim-request-id:
              description: Request ID for troubleshooting purposes
              schema:
                type: string
        default:
          description: Service unavailable
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/errorResponse'
          headers:
            apim-request-id:
              description: Request ID for troubleshooting purposes
              schema:
                type: string
  /deployments/{deployment-id}/embeddings:
    post:
      summary: Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms.
      operationId: embeddings_create
      parameters:
        - in: path
          name: deployment-id
          required: true
          schema:
            type: string
            example: ada-search-index-v1
          description: The deployment id of the model which was deployed.
        - in: query
          name: api-version
          required: true
          schema:
            type: string
            example: 2023-12-01-preview
            description: api version
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              additionalProperties: true
              properties:
                input:
                  description: |-
                    Input text to get embeddings for, encoded as a string. To get embeddings for multiple inputs in a single request, pass an array of strings. Each input must not exceed 2048 tokens in length.
                    Unless you are embedding code, we suggest replacing newlines (\n) in your input with a single space, as we have observed inferior results when newlines are present.
                  oneOf:
                    - type: string
                      default: ''
                      example: This is a test.
                      nullable: true
                    - type: array
                      minItems: 1
                      maxItems: 2048
                      items:
                        type: string
                        minLength: 1
                        example: This is a test.
                        nullable: false
                user:
                  description: A unique identifier representing your end-user, which can help monitoring and detecting abuse.
                  type: string
                  nullable: false
                input_type:
                  description: input type of embedding search to use
                  type: string
                  example: query
              required:
                - input
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                type: object
                properties:
                  object:
                    type: string
                  model:
                    type: string
                  data:
                    type: array
                    items:
                      type: object
                      properties:
                        index:
                          type: integer
                        object:
                          type: string
                        embedding:
                          type: array
                          items:
                            type: number
                      required:
                        - index
                        - object
                        - embedding
                  usage:
                    type: object
                    properties:
                      prompt_tokens:
                        type: integer
                      total_tokens:
                        type: integer
                    required:
                      - prompt_tokens
                      - total_tokens
                required:
                  - object
                  - model
                  - data
                  - usage
  /deployments/{deployment-id}/chat/completions:
    post:
      summary: Creates a completion for the chat message
      operationId: ChatCompletions_Create
      parameters:
        - in: path
          name: deployment-id
          required: true
          schema:
            type: string
            description: Deployment id of the model which was deployed.
        - in: query
          name: api-version
          required: true
          schema:
            type: string
            example: 2023-12-01-preview
            description: api version
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/createChatCompletionRequest'
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/createChatCompletionResponse'
          headers:
            apim-request-id:
              description: Request ID for troubleshooting purposes
              schema:
                type: string
        default:
          description: Service unavailable
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/errorResponse'
          headers:
            apim-request-id:
              description: Request ID for troubleshooting purposes
              schema:
                type: string
  /deployments/{deployment-id}/extensions/chat/completions:
    post:
      summary: Using extensions to creates a completion for the chat messages.
      operationId: ExtensionsChatCompletions_Create
      parameters:
        - in: path
          name: deployment-id
          required: true
          schema:
            type: string
            description: Deployment id of the model which was deployed.
        - in: query
          name: api-version
          required: true
          schema:
            type: string
            example: 2023-12-01-preview
            description: api version
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/extensionsChatCompletionsRequest'
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/extensionsChatCompletionsResponse'
          headers:
            apim-request-id:
              description: Request ID for troubleshooting purposes
              schema:
                type: string
        default:
          description: Service unavailable
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/errorResponse'
          headers:
            apim-request-id:
              description: Request ID for troubleshooting purposes
              schema:
                type: string
  /deployments/{deployment-id}/audio/transcriptions:
    post:
      summary: Transcribes audio into the input language.
      operationId: Transcriptions_Create
      parameters:
        - in: path
          name: deployment-id
          required: true
          schema:
            type: string
            example: whisper
            description: Deployment id of the whisper model.
        - in: query
          name: api-version
          required: true
          schema:
            type: string
            example: 2023-12-01-preview
            description: api version
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              $ref: '#/components/schemas/createTranscriptionRequest'
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                oneOf:
                  - $ref: '#/components/schemas/audioResponse'
                  - $ref: '#/components/schemas/audioVerboseResponse'
            text/plain:
              schema:
                type: string
                description: Transcribed text in the output format (when response_format was one of text, vtt or srt).
  /deployments/{deployment-id}/audio/translations:
    post:
      summary: Transcribes and translates input audio into English text.
      operationId: Translations_Create
      parameters:
        - in: path
          name: deployment-id
          required: true
          schema:
            type: string
            example: whisper
            description: Deployment id of the whisper model which was deployed.
        - in: query
          name: api-version
          required: true
          schema:
            type: string
            example: 2023-12-01-preview
            description: api version
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              $ref: '#/components/schemas/createTranslationRequest'
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                oneOf:
                  - $ref: '#/components/schemas/audioResponse'
                  - $ref: '#/components/schemas/audioVerboseResponse'
            text/plain:
              schema:
                type: string
                description: Transcribed text in the output format (when response_format was one of text, vtt or srt).
  /deployments/{deployment-id}/images/generations:
    post:
      summary: Generates a batch of images from a text caption on a given DALLE model deployment
      operationId: ImageGenerations_Create
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/imageGenerationsRequest'
      parameters:
        - in: path
          name: deployment-id
          required: true
          schema:
            type: string
            example: dalle-deployment
            description: Deployment id of the dalle model which was deployed.
        - in: query
          name: api-version
          required: true
          schema:
            type: string
            example: 2023-12-01-preview
            description: api version
      responses:
        '200':
          description: Ok
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/generateImagesResponse'
        default:
          description: An error occurred.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/errorResponse'
components:
  schemas:
    errorResponse:
      type: object
      properties:
        error:
          $ref: '#/components/schemas/error'
    errorBase:
      type: object
      properties:
        code:
          type: string
        message:
          type: string
    error:
      type: object
      allOf:
        - $ref: '#/components/schemas/errorBase'
      properties:
        code:
          type: string
        message:
          type: string
        param:
          type: string
        type:
          type: string
        inner_error:
          $ref: '#/components/schemas/innerError'
    innerError:
      description: Inner error with additional details.
      type: object
      properties:
        code:
          $ref: '#/components/schemas/innerErrorCode'
        content_filter_results:
          $ref: '#/components/schemas/contentFilterPromptResults'
    innerErrorCode:
      description: Error codes for the inner error object.
      enum:
        - ResponsibleAIPolicyViolation
      type: string
      x-ms-enum:
        name: InnerErrorCode
        modelAsString: true
        values:
          - value: ResponsibleAIPolicyViolation
            description: The prompt violated one of more content filter rules.
    contentFilterResultBase:
      type: object
      properties:
        filtered:
          type: boolean
      required:
        - filtered
    contentFilterSeverityResult:
      type: object
      allOf:
        - $ref: '#/components/schemas/contentFilterResultBase'
        - properties:
            severity:
              type: string
              enum:
                - safe
                - low
                - medium
                - high
              x-ms-enum:
                name: ContentFilterSeverity
                modelAsString: true
                values:
                  - value: safe
                    description: General content or related content in generic or non-harmful contexts.
                  - value: low
                    description: Harmful content at a low intensity and risk level.
                  - value: medium
                    description: Harmful content at a medium intensity and risk level.
                  - value: high
                    description: Harmful content at a high intensity and risk level.
      required:
        - severity
        - filtered
    contentFilterDetectedResult:
      type: object
      allOf:
        - $ref: '#/components/schemas/contentFilterResultBase'
        - properties:
            detected:
              type: boolean
      required:
        - detected
        - filtered
    contentFilterDetectedWithCitationResult:
      type: object
      allOf:
        - $ref: '#/components/schemas/contentFilterDetectedResult'
        - properties:
            citation:
              type: object
              properties:
                URL:
                  type: string
                license:
                  type: string
      required:
        - detected
        - filtered
    contentFilterIdResult:
      type: object
      allOf:
        - $ref: '#/components/schemas/contentFilterResultBase'
        - properties:
            id:
              type: string
      required:
        - id
        - filtered
    contentFilterResultsBase:
      type: object
      description: Information about the content filtering results.
      properties:
        sexual:
          $ref: '#/components/schemas/contentFilterSeverityResult'
        violence:
          $ref: '#/components/schemas/contentFilterSeverityResult'
        hate:
          $ref: '#/components/schemas/contentFilterSeverityResult'
        self_harm:
          $ref: '#/components/schemas/contentFilterSeverityResult'
        profanity:
          $ref: '#/components/schemas/contentFilterDetectedResult'
        custom_blocklists:
          items:
            $ref: '#/components/schemas/contentFilterIdResult'
          type: array
        error:
          $ref: '#/components/schemas/errorBase'
    contentFilterPromptResults:
      type: object
      description: Information about the content filtering category (hate, sexual, violence, self_harm), if it has been detected, as well as the severity level (very_low, low, medium, high-scale that determines the intensity and risk level of harmful content) and if it has been filtered or not. Information about jailbreak content and profanity, if it has been detected, and if it has been filtered or not. And information about customer block list, if it has been filtered and its id.
      allOf:
        - $ref: '#/components/schemas/contentFilterResultsBase'
        - properties:
            jailbreak:
              $ref: '#/components/schemas/contentFilterDetectedResult'
    contentFilterChoiceResults:
      type: object
      description: Information about the content filtering category (hate, sexual, violence, self_harm), if it has been detected, as well as the severity level (very_low, low, medium, high-scale that determines the intensity and risk level of harmful content) and if it has been filtered or not. Information about third party text and profanity, if it has been detected, and if it has been filtered or not. And information about customer block list, if it has been filtered and its id.
      allOf:
        - $ref: '#/components/schemas/contentFilterResultsBase'
        - properties:
            protected_material_text:
              $ref: '#/components/schemas/contentFilterDetectedResult'
        - properties:
            protected_material_code:
              $ref: '#/components/schemas/contentFilterDetectedWithCitationResult'
    promptFilterResult:
      type: object
      description: Content filtering results for a single prompt in the request.
      properties:
        prompt_index:
          type: integer
        content_filter_results:
          $ref: '#/components/schemas/contentFilterPromptResults'
    promptFilterResults:
      type: array
      description: Content filtering results for zero or more prompts in the request. In a streaming request, results for different prompts may arrive at different times or in different orders.
      items:
        $ref: '#/components/schemas/promptFilterResult'
    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.
            We 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.
            We 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
    createChatCompletionRequest:
      type: object
      allOf:
        - $ref: '#/components/schemas/chatCompletionsRequestCommon'
        - properties:
            messages:
              description: A list of messages comprising the conversation so far. [Example Python code](https://github.com/openai/openai-cookbook/blob/main/examples/How_to_format_inputs_to_ChatGPT_models.ipynb).
              type: array
              minItems: 1
              items:
                $ref: '#/components/schemas/chatCompletionRequestMessage'
            'n':
              type: integer
              minimum: 1
              maximum: 128
              default: 1
              example: 1
              nullable: true
              description: How many chat completion choices to generate for each input message.
            seed:
              type: integer
              minimum: -9223372036854776000
              maximum: 9223372036854776000
              default: 0
              example: 1
              nullable: true
              description: If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same `seed` and parameters should return the same result.Determinism is not guaranteed, and you should refer to the `system_fingerprint` response parameter to monitor changes in the backend.
            response_format:
              type: object
              description: An object specifying the format that the model must output. Used to enable JSON mode.
              properties:
                type:
                  $ref: '#/components/schemas/chatCompletionResponseFormat'
            tools:
              description: A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for.
              type: array
              minItems: 1
              items:
                $ref: '#/components/schemas/chatCompletionTool'
            tool_choice:
              $ref: '#/components/schemas/chatCompletionToolChoiceOption'
            functions:
              description: Deprecated in favor of `tools`. A list of functions the model may generate JSON inputs for.
              type: array
              minItems: 1
              maxItems: 128
              items:
                $ref: '#/components/schemas/chatCompletionFunction'
            function_call:
              description: Deprecated in favor of `tool_choice`. Controls how the model responds to function calls. "none" means the model does not call a function, and responds to the end-user. "auto" means the model can pick between an end-user or calling a function.  Specifying a particular function via `{"name":\ "my_function"}` forces the model to call that function. "none" is the default when no functions are present. "auto" is the default if functions are present.
              oneOf:
                - type: string
                  enum:
                    - none
                    - auto
                  description: '`none` means the model will not call a function and instead generates a message. `auto` means the model can pick between generating a message or calling a function.'
                - type: object
                  description: 'Specifying a particular function via `{"name": "my_function"}` forces the model to call that function.'
                  properties:
                    name:
                      type: string
                      description: The name of the function to call.
                  required:
                    - name
      required:
        - messages
    chatCompletionResponseFormat:
      type: string
      enum:
        - text
        - json_object
      default: text
      example: json_object
      nullable: true
      description: Setting to `json_object` enables JSON mode. This guarantees that the message the model generates is valid JSON.
      x-ms-enum:
        name: ChatCompletionResponseFormat
        modelAsString: true
        values:
          - value: text
            description: Response format is a plain text string.
          - value: json_object
            description: Response format is a JSON object.
    chatCompletionFunction:
      type: object
      properties:
        name:
          type: string
          description: The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
        description:
          type: string
          description: The description of what the function does.
        parameters:
          $ref: '#/components/schemas/chatCompletionFunctionParameters'
      required:
        - name
    chatCompletionFunctionParameters:
      type: object
      description: The parameters the functions accepts, described as a JSON Schema object. See the [guide](/docs/guides/gpt/function-calling) for examples, and the [JSON Schema reference](https://json-schema.org/understanding-json-schema/) for documentation about the format.
      additionalProperties: true
    chatCompletionRequestMessage:
      type: object
      properties:
        role:
          $ref: '#/components/schemas/chatCompletionRequestMessageRole'
      discriminator:
        propertyName: role
        mapping:
          system: '#/components/schemas/chatCompletionRequestMessageSystem'
          user: '#/components/schemas/chatCompletionRequestMessageUser'
          assistant: '#/components/schemas/chatCompletionRequestMessageAssistant'
          tool: '#/components/schemas/chatCompletionRequestMessageTool'
          function: '#/components/schemas/chatCompletionRequestMessageFunction'
      required:
        - role
    chatCompletionRequestMessageRole:
      type: string
      enum:
        - system
        - user
        - assistant
        - tool
        - function
      description: The role of the messages author.
      x-ms-enum:
        name: ChatCompletionRequestMessageRole
        modelAsString: true
        values:
          - value: system
            description: The message author role is system.
          - value: user
            description: The message author role is user.
          - value: assistant
            description: The message author role is assistant.
          - value: tool
            description: The message author role is tool.
          - value: function
            description: Deprecated. The message author role is function.
    chatCompletionRequestMessageSystem:
      allOf:
        - $ref: '#/components/schemas/chatCompletionRequestMessage'
        - type: object
          properties:
            content:
              type: string
              description: The contents of the message.
              nullable: true
      required:
        - content
    chatCompletionRequestMessageUser:
      allOf:
        - $ref: '#/components/schemas/chatCompletionRequestMessage'
        - type: object
          properties:
            content:
              oneOf:
                - type: string
                  description: The contents of the message.
                - type: array
                  description: An array of content parts with a defined type, each can be of type `text` or `image_url` when passing in images. You can pass multiple images by adding multiple `image_url` content parts. Image input is only supported when using the `gpt-4-visual-preview` model.
                  minimum: 1
                  items:
                    $ref: '#/components/schemas/chatCompletionRequestMessageContentPart'
              nullable: true
      required:
        - content
    chatCompletionRequestMessageContentPart:
      type: object
      properties:
        type:
          $ref: '#/components/schemas/chatCompletionRequestMessageContentPartType'
      discriminator:
        propertyName: type
        mapping:
          text: '#/components/schemas/chatCompletionRequestMessageContentPartText'
          image_url: '#/components/schemas/chatCompletionRequestMessageContentPartImage'
      required:
        - type
    chatCompletionRequestMessageContentPartType:
      type: string
      enum:
        - text
        - image_url
      description: The type of the content part.
      x-ms-enum:
        name: ChatCompletionRequestMessageContentPartType
        modelAsString: true
        values:
          - value: text
            description: The content part type is text.
          - value: image_url
            description: The content part type is image_url.
    chatCompletionRequestMessageContentPartText:
      allOf:
        - $ref: '#/components/schemas/chatCompletionRequestMessageContentPart'
        - type: object
          properties:
            text:
              type: string
              description: The text content.
      required:
        - text
    chatCompletionRequestMessageContentPartImage:
      allOf:
        - $ref: '#/components/schemas/chatCompletionRequestMessageContentPart'
        - type: object
          properties:
            url:
              type: string
              description: Either a URL of the image or the base64 encoded image data.
              format: uri
            detail:
              $ref: '#/components/schemas/imageDetailLevel'
      required:
        - url
    imageDetailLevel:
      type: string
      description: Specifies the detail level of the image.
      enum:
        - auto
        - low
        - high
      default: auto
      x-ms-enum:
        name: ImageDetailLevel
        modelAsString: true
        values:
          - value: auto
            description: The image detail level is auto.
          - value: low
            description: The image detail level is low.
          - value: high
            description: The image detail level is high.
    chatCompletionRequestMessageAssistant:
      allOf:
        - $ref: '#/components/schemas/chatCompletionRequestMessage'
        - type: object
          properties:
            content:
              type: string
              description: The contents of the message.
              nullable: true
            tool_calls:
              type: array
              description: The tool calls generated by the model, such as function calls.
              items:
                $ref: '#/components/schemas/chatCompletionMessageToolCall'
      required:
        - content
    chatCompletionMessageToolCall:
      type: object
      properties:
        id:
          type: string
          description: The ID of the tool call.
        type:
          $ref: '#/components/schemas/toolCallType'
        function:
          type: object
          description: The function that the model called.
          properties:
            name:
              type: string
              description: The name of the function to call.
            arguments:
              type: string
              description: The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function.
          required:
            - name
            - arguments
      required:
        - id
        - type
        - function
    toolCallType:
      type: string
      enum:
        - function
      description: The type of the tool call, in this case `function`.
      x-ms-enum:
        name: ToolCallType
        modelAsString: true
        values:
          - value: function
            description: The tool call type is function.
    chatCompletionRequestMessageTool:
      allOf:
        - $ref: '#/components/schemas/chatCompletionRequestMessage'
        - type: object
          nullable: true
          properties:
            tool_call_id:
              type: string
              description: Tool call that this message is responding to.
            content:
              type: string
              description: The contents of the message.
              nullable: true
      required:
        - tool_call_id
        - content
    chatCompletionRequestMessageFunction:
      allOf:
        - $ref: '#/components/schemas/chatCompletionRequestMessage'
        - type: object
          description: Deprecated. Message that represents a function.
          nullable: true
          properties:
            role:
              type: string
              enum:
                - function
              description: The role of the messages author, in this case `function`.
            name:
              type: string
              description: The contents of the message.
            content:
              type: string
              description: The contents of the message.
              nullable: true
      required:
        - function_call_id
        - content
    createChatCompletionResponse:
      type: object
      allOf:
        - $ref: '#/components/schemas/chatCompletionsResponseCommon'
        - properties:
            prompt_filter_results:
              $ref: '#/components/schemas/promptFilterResults'
            choices:
              type: array
              items:
                type: object
                allOf:
                  - $ref: '#/components/schemas/chatCompletionChoiceCommon'
                  - properties:
                      message:
                        $ref: '#/components/schemas/chatCompletionResponseMessage'
                      content_filter_results:
                        $ref: '#/components/schemas/contentFilterChoiceResults'
      required:
        - id
        - object
        - created
        - model
        - choices
    chatCompletionResponseMessage:
      type: object
      description: A chat completion message generated by the model.
      properties:
        role:
          $ref: '#/components/schemas/chatCompletionResponseMessageRole'
        content:
          type: string
          description: The contents of the message.
          nullable: true
        tool_calls:
          type: array
          description: The tool calls generated by the model, such as function calls.
          items:
            $ref: '#/components/schemas/chatCompletionMessageToolCall'
        function_call:
          $ref: '#/components/schemas/chatCompletionFunctionCall'
    chatCompletionResponseMessageRole:
      type: string
      enum:
        - assistant
      description: The role of the author of the response message.
    chatCompletionToolChoiceOption:
      description: 'Controls which (if any) function is called by the model. `none` means the model will not call a function and instead generates a message. `auto` means the model can pick between generating a message or calling a function. Specifying a particular function via `{"type": "function", "function": {"name": "my_function"}}` forces the model to call that function.'
      oneOf:
        - type: string
          description: '`none` means the model will not call a function and instead generates a message. `auto` means the model can pick between generating a message or calling a function.'
          enum:
            - none
            - auto
        - $ref: '#/components/schemas/chatCompletionNamedToolChoice'
    chatCompletionNamedToolChoice:
      type: object
      description: Specifies a tool the model should use. Use to force the model to call a specific function.
      properties:
        type:
          type: string
          enum:
            - function
          description: The type of the tool. Currently, only `function` is supported.
        function:
          type: object
          properties:
            name:
              type: string
              description: The name of the function to call.
          required:
            - name
    chatCompletionFunctionCall:
      type: object
      description: Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model.
      properties:
        name:
          type: string
          description: The name of the function to call.
        arguments:
          type: string
          description: The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function.
      required:
        - name
        - arguments
    extensionsChatCompletionsRequest:
      type: object
      description: Request for the chat completions using extensions
      required:
        - messages
      allOf:
        - $ref: '#/components/schemas/chatCompletionsRequestCommon'
        - properties:
            messages:
              type: array
              items:
                $ref: '#/components/schemas/message'
            dataSources:
              type: array
              description: The data sources to be used for the Azure OpenAI on your data feature.
              items:
                $ref: '#/components/schemas/dataSource'
            enhancements:
              type: object
              description: The type of enhancements needed.
              properties:
                grounding:
                  type: object
                  description: Request object to specify if grounding enhancement is needed.
                  properties:
                    enabled:
                      type: boolean
                      default: false
                ocr:
                  type: object
                  description: Request object to specify if ocr enhancement is needed.
                  properties:
                    enabled:
                      type: boolean
                      default: false
      example:
        dataSources:
          - type: AzureCognitiveSearch
            parameters:
              endpoint: https://mysearchexample.search.windows.net
              key: '***(admin key)'
              indexName: my-chunk-index
              fieldsMapping:
                titleField: productName
                urlField: productUrl
                filepathField: productFilePath
                contentFields:
                  - productDescription
                contentFieldsSeparator: |+

              topNDocuments: 5
              queryType: semantic
              semanticConfiguration: defaultConfiguration
              inScope: true
              roleInformation: roleInformation
        messages:
          - role: user
            content: Where can I find a hiking place in Seattle?
        temperature: 0.9
    dataSource:
      type: object
      description: The data source to be used for the Azure OpenAI on your data feature.
      properties:
        type:
          type: string
          description: The data source type.
        parameters:
          type: object
          description: The parameters to be used for the data source in runtime.
          additionalProperties: true
      required:
        - type
    message:
      type: object
      description: A chat message.
      properties:
        index:
          type: integer
          description: The index of the message in the conversation.
        role:
          type: string
          enum:
            - system
            - user
            - assistant
            - tool
          description: The role of the author of this message.
        recipient:
          type: string
          example: Contoso.productsUsingGET
          description: The recipient of the message in the format of <namespace>.<operation>. Present if and only if the recipient is tool.
        content:
          type: string
          description: The contents of the message
        end_turn:
          type: boolean
          description: Whether the message ends the turn.
        context:
          type: object
          description: The conversation context
          nullable: true
          properties:
            messages:
              type: array
              description: Messages exchanged between model and extensions prior to final message from model
              minItems: 1
              items:
                $ref: '#/components/schemas/message'
              nullable: true
      required:
        - role
        - content
    chatCompletionsResponseCommon:
      type: object
      properties:
        id:
          type: string
          description: A unique identifier for the chat completion.
        object:
          $ref: '#/components/schemas/chatCompletionResponseObject'
        created:
          type: integer
          format: unixtime
          description: The Unix timestamp (in seconds) of when the chat completion was created.
        model:
          type: string
          description: The model used for the chat completion.
        usage:
          $ref: '#/components/schemas/completionUsage'
        system_fingerprint:
          type: string
          description: Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism.
      required:
        - id
        - object
        - created
        - model
    chatCompletionResponseObject:
      type: string
      description: The object type.
      enum:
        - chat.completion
      x-ms-enum:
        name: ChatCompletionResponseObject
        modelAsString: true
        values:
          - value: chat.completion
            description: The object type is chat completion.
    completionUsage:
      type: object
      description: Usage statistics for the completion request.
      properties:
        prompt_tokens:
          type: integer
          description: Number of tokens in the prompt.
        completion_tokens:
          type: integer
          description: Number of tokens in the generated completion.
        total_tokens:
          type: integer
          description: Total number of tokens used in the request (prompt + completion).
      required:
        - prompt_tokens
        - completion_tokens
        - total_tokens
    chatCompletionTool:
      type: object
      properties:
        type:
          $ref: '#/components/schemas/chatCompletionToolType'
        function:
          type: object
          properties:
            description:
              type: string
              description: A description of what the function does, used by the model to choose when and how to call the function.
            name:
              type: string
              description: The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
            parameters:
              $ref: '#/components/schemas/chatCompletionFunctionParameters'
          required:
            - name
            - parameters
      required:
        - type
        - function
    chatCompletionToolType:
      type: string
      enum:
        - function
      description: The type of the tool. Currently, only `function` is supported.
      x-ms-enum:
        name: ChatCompletionToolType
        modelAsString: true
        values:
          - value: function
            description: The tool type is function.
    chatCompletionChoiceCommon:
      type: object
      properties:
        index:
          type: integer
        finish_reason:
          type: string
    extensionsChatCompletionChoice:
      type: object
      allOf:
        - $ref: '#/components/schemas/chatCompletionChoiceCommon'
        - properties:
            message:
              $ref: '#/components/schemas/message'
            enhancements:
              description: The enhancement results returned by the service.
              $ref: '#/components/schemas/enhancement'
    extensionsChatCompletionsResponse:
      type: object
      description: The response of the extensions chat completions.
      allOf:
        - $ref: '#/components/schemas/chatCompletionsResponseCommon'
        - properties:
            choices:
              type: array
              items:
                $ref: '#/components/schemas/extensionsChatCompletionChoice'
      example:
        id: '1'
        object: extensions.chat.completion
        created: 1679201802
        model: gpt-3.5-turbo-0301
        choices:
          - index: 0
            finish_reason: stop
            message:
              role: assistant
              content: Seattle is a great place for hiking! Here are some of the best hiking places in Seattle according to Contoso Traveler [doc1] and West Coast Traveler, Snow Lake, Mount Si, and Mount Tenerife [doc2]. I hope this helps! Let me know if you need more information.
              end_turn: true
              context:
                messages:
                  - role: tool
                    content: '{"citations":[{"filepath":"ContosoTraveler.pdf","content":"This is the content of the citation 1"},{"filepath":"WestCoastTraveler.html","content":"This is the content of the citation 2"},{"content":"This is the content of the citation 3 without filepath"}],"intent":"hiking place in seattle"}'
                    end_turn: false
    createTranslationRequest:
      type: object
      description: Translation request.
      properties:
        file:
          type: string
          description: The audio file to translate.
          format: binary
        prompt:
          type: string
          description: An optional text to guide the model's style or continue a previous audio segment. The prompt should be in English.
        response_format:
          $ref: '#/components/schemas/audioResponseFormat'
        temperature:
          type: number
          default: 0
          description: The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit.
      required:
        - file
    audioResponse:
      description: Translation or transcription response when response_format was json
      type: object
      properties:
        text:
          type: string
          description: Translated or transcribed text.
      required:
        - text
    audioVerboseResponse:
      description: Translation or transcription response when response_format was verbose_json
      type: object
      allOf:
        - $ref: '#/components/schemas/audioResponse'
        - properties:
            task:
              type: string
              description: Type of audio task.
              enum:
                - transcribe
                - translate
              x-ms-enum:
                modelAsString: true
            language:
              type: string
              description: Language.
            duration:
              type: number
              description: Duration.
            segments:
              type: array
              items:
                $ref: '#/components/schemas/audioSegment'
      required:
        - text
    audioResponseFormat:
      title: AudioResponseFormat
      description: Defines the format of the output.
      enum:
        - json
        - text
        - srt
        - verbose_json
        - vtt
      type: string
      x-ms-enum:
        modelAsString: true
    createTranscriptionRequest:
      type: object
      description: Transcription request.
      properties:
        file:
          type: string
          description: The audio file object to transcribe.
          format: binary
        prompt:
          type: string
          description: An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language.
        response_format:
          $ref: '#/components/schemas/audioResponseFormat'
        temperature:
          type: number
          default: 0
          description: The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit.
        language:
          type: string
          description: The language of the input audio. Supplying the input language in ISO-639-1 format will improve accuracy and latency.
      required:
        - file
    audioSegment:
      type: object
      description: Transcription or translation segment.
      properties:
        id:
          type: integer
          description: Segment identifier.
        seek:
          type: number
          description: Offset of the segment.
        start:
          type: number
          description: Segment start offset.
        end:
          type: number
          description: Segment end offset.
        text:
          type: string
          description: Segment text.
        tokens:
          type: array
          items:
            type: number
            nullable: false
          description: Tokens of the text.
        temperature:
          type: number
          description: Temperature.
        avg_logprob:
          type: number
          description: Average log probability.
        compression_ratio:
          type: number
          description: Compression ratio.
        no_speech_prob:
          type: number
          description: Probability of 'no speech'.
    imageQuality:  
      description: The quality of the image that will be generated.
      type: string
      enum:  
        - standard
        - hd
      default: standard
      x-ms-enum:  
        name: Quality
        modelAsString: true
        values:
          - value: standard 
            description: Standard quality creates images with standard quality.
            name: Standard
          - value: hd
            description: HD quality creates images with finer details and greater consistency across the image.
            name: HD
    imagesResponseFormat:
      description: The format in which the generated images are returned.
      type: string
      enum:
        - url
        - b64_json
      default: url
      x-ms-enum:
        name: ImagesResponseFormat
        modelAsString: true
        values:
          - value: url
            description: The URL that provides temporary access to download the generated images.
            name: Url
          - value: b64_json
            description: The generated images are returned as base64 encoded string.
            name: Base64Json
    imageSize:
      description: The size of the generated images.
      type: string
      enum:
        - 1792x1024
        - 1024x1792
        - 1024x1024
      default: 1024x1024
      x-ms-enum:
        name: Size
        modelAsString: true
        values:
          - value: 1792x1024
            description: The desired size of the generated image is 1792x1024 pixels.
            name: Size1792x1024
          - value: 1024x1792
            description: The desired size of the generated image is 1024x1792 pixels.
            name: Size1024x1792
          - value: 1024x1024
            description: The desired size of the generated image is 1024x1024 pixels.
            name: Size1024x1024
    imageStyle:  
      description: The style of the generated images. 
      type: string
      enum:  
        - vivid
        - natural
      default: vivid
      x-ms-enum:  
        name: Style
        modelAsString: true  
        values:  
          - value: vivid
            description: Vivid creates images that are hyper-realistic and dramatic.
            name: Vivid
          - value: natural
            description: Natural creates images that are more natural and less hyper-realistic.
            name: Natural
    imageGenerationsRequest:
      type: object
      properties:
        prompt:
          description: A text description of the desired image(s). The maximum length is 4000 characters.
          type: string
          format: string
          example: a corgi in a field
          minLength: 1
        'n':
          description: The number of images to generate.
          type: integer
          minimum: 1
          maximum: 1
          default: 1
        size:
          $ref: '#/components/schemas/imageSize'
        response_format:
          $ref: '#/components/schemas/imagesResponseFormat'
        user:
          description: A unique identifier representing your end-user, which can help to monitor and detect abuse.
          type: string
          format: string
          example: user123456
        style:
          $ref: '#/components/schemas/imageStyle'
        quality:
          $ref: '#/components/schemas/imageQuality'
      required:
        - prompt
    generateImagesResponse:
      type: object
      properties:
        created:
          type: integer
          format: unixtime
          description: The unix timestamp when the operation was created.
          example: '1676540381'
        data:
          type: array
          description: The result data of the operation, if successful
          items:
            $ref: '#/components/schemas/imageResult'
        error:
          $ref: '#/components/schemas/error'
      required:
        - created
    imageResult:
      type: object
      description: The image url or encoded image if successful, and an error otherwise.
      properties:
        url:
          type: string
          description: The image url.
          example: https://www.contoso.com
        b64_json:
          type: string
          description: The base64 encoded image
        revised_prompt:
          type: string
          description: The prompt that was used to generate the image, if there was any revision to the prompt.
    enhancement:
      type: object
      properties:
        grounding:
          type: object
          description: The grounding enhancement that returns the bounding box of the objects detected in the image.
          properties:
            lines:
              type: array
              items:
                $ref: '#/components/schemas/line'
          required:
            - lines
    line:
      type: object
      description: A content line object consisting of an adjacent sequence of content elements, such as words and selection marks.
      properties:
        text:
          type: string
        spans:
          type: array
          description: An array of spans that represent detected objects and its bounding box information.
          items:
            $ref: '#/components/schemas/span'
      required:
        - text
        - spans
    span:
      type: object
      description: A span object that represents a detected object and its bounding box information.
      properties:
        text:
          type: string
          description: The text content of the span that represents the detected object.
        offset:
          type: integer
          description: The character offset within the text where the span begins. This offset is defined as the position of the first character of the span, counting from the start of the text as Unicode codepoints.
        length:
          type: integer
          description: The length of the span in characters, measured in Unicode codepoints.
        polygon:
          type: array
          description: An array of objects representing points in the polygon that encloses the detected object.
          items:
            type: object
            properties:
              x:
                type: number
                description: The x-coordinate of the point.
              'y':
                type: number
                description: The y-coordinate of the point.
      required:
        - text
        - offset
        - length
        - polygon
  securitySchemes:
    bearer:
      type: oauth2
      flows:
        implicit:
          authorizationUrl: https://login.microsoftonline.com/common/oauth2/v2.0/authorize
          scopes: {}
      x-tokenInfoFunc: api.middleware.auth.bearer_auth
      x-scopeValidateFunc: api.middleware.auth.validate_scopes
    apiKey:
      type: apiKey
      name: api-key
      in: header