Microsoft Azure Open Ai API Version 20240215preview

The Microsoft Azure Open Ai API Version 20240215preview is a tool that leverages artificial intelligence to help developers build innovative applications and services. This API allows users to access a wide range of pre-trained machine learning models, including natural language processing, computer vision, and speech recognition.

OpenAPI Specification

azure-openai-api-version-2024-02-15-preview-openapi-original.yml Raw ↑
swagger: '2.0'
info:
  title: Microsoft Azure Azure OpenAI API version 2024-02-15-preview
  description: APIs for fine-tuning and managing deployments of OpenAI models.
  version: 2024-02-15-preview
paths:
  /files:
    get:
      tags:
        - 'Files:'
      summary: "Microsoft Azure Gets A List Of All Files Owned By The Azure Openai Resource \r\nthese Include User Uploaded Content Like Files With Purpose \"fine Tune\" For Training Or Validation Of Fine Tunes Models\r\nas Well As Files That Are Generated By The Service Such As \"fine Tune Results\" Which Contains Various Metrics For The Corresponding Fine Tune Job"
      operationId: microsoftAzureFilesList
      produces:
        - application/json
      parameters:
        - in: query
          name: purpose
          description: Only return files with the given purpose.
          type: string
          enum:
            - fine-tune
            - fine-tune-results
            - assistants
            - assistants_output
          x-ms-enum:
            name: Purpose
            modelAsString: true
            values:
              - value: fine-tune
                description: This file contains training data for a fine tune job.
              - value: fine-tune-results
                description: This file contains the results of a fine tune job.
              - value: assistants
                description: This file contains data to be used in assistants.
              - value: assistants_output
                description: This file contains the results of an assistant.
        - $ref: '#/parameters/apiVersionQueryParameter'
      responses:
        '200':
          description: Success
          schema:
            $ref: '#/definitions/FileList'
        default:
          description: An error occurred.
          schema:
            $ref: '#/definitions/ErrorResponse'
      x-ms-examples:
        Getting all files owned by this account.:
          $ref: ./examples/get_files.json
      description: Needs a more full description created.
    post:
      tags:
        - 'Files:'
      summary: >-
        Microsoft Azure Creates A New File Entity By Uploading Data From A Local Machine Uploaded Files Can, For Example, Be Used For Training Or Evaluating Fine Tuned Models
      operationId: microsoftAzureFilesUpload
      consumes:
        - multipart/form-data
      produces:
        - application/json
      parameters:
        - $ref: '#/parameters/apiVersionQueryParameter'
        - in: formData
          name: purpose
          description: >-
            The intended purpose of the uploaded documents. Use "fine-tune" for
            fine-tuning. This allows us to validate the format of the uploaded
            file.
          required: true
          type: string
          enum:
            - fine-tune
            - fine-tune-results
            - assistants
          x-ms-enum:
            name: Purpose
            modelAsString: true
            values:
              - value: fine-tune
                description: This file contains training data for a fine tune job.
              - value: fine-tune-results
                description: This file contains the results of a fine tune job.
              - value: assistants
                description: This file contains data that can be attached to an assistant.
        - in: formData
          name: file
          description: Gets or sets the file to upload into Azure OpenAI.
          required: true
          type: file
      responses:
        '201':
          description: The file has been successfully created.
          schema:
            $ref: '#/definitions/File'
          headers:
            Location:
              description: The location of the newly created item.
              type: string
              format: url
        default:
          description: An error occurred.
          schema:
            $ref: '#/definitions/ErrorResponse'
      x-ms-examples:
        Upload a file.:
          $ref: ./examples/upload_file.json
      description: Needs a more full description created.
  /files/{file-id}:
    get:
      tags:
        - 'Files:'
      summary: >-
        Microsoft Azure Gets Details For A Single File Specified By The Given File Id Including Status, Size, Purpose, Etc
      operationId: microsoftAzureFilesGet
      produces:
        - application/json
      parameters:
        - in: path
          name: file-id
          description: The identifier of the file.
          required: true
          type: string
        - $ref: '#/parameters/apiVersionQueryParameter'
      responses:
        '200':
          description: Success
          schema:
            $ref: '#/definitions/File'
        default:
          description: An error occurred.
          schema:
            $ref: '#/definitions/ErrorResponse'
      x-ms-examples:
        Getting a file.:
          $ref: ./examples/get_file.json
      description: Needs a more full description created.
    delete:
      tags:
        - 'Files:'
      summary: "Microsoft Azure Deletes The File With The Given File Id \r\ndeletion Is Also Allowed If A File Was Used, E G , As Training File In A Fine Tune Job"
      operationId: microsoftAzureFilesDelete
      produces:
        - application/json
      parameters:
        - in: path
          name: file-id
          description: The identifier of the file.
          required: true
          type: string
        - $ref: '#/parameters/apiVersionQueryParameter'
      responses:
        '204':
          description: The file was successfully deleted.
        default:
          description: An error occurred.
          schema:
            $ref: '#/definitions/ErrorResponse'
      x-ms-examples:
        Deleting a file.:
          $ref: ./examples/delete_file.json
      description: Needs a more full description created.
  /files/{file-id}/content:
    get:
      tags:
        - 'Files:'
      summary: "Microsoft Azure Gets The Content Of The File Specified By The Given File Id \r\nfiles Can Be User Uploaded Content Or Generated By The Service Like Result Metrics Of A Fine Tune Job"
      operationId: microsoftAzureFilesGetcontent
      produces:
        - application/octet-stream
        - application/json
      parameters:
        - in: path
          name: file-id
          description: The identifier of the file.
          required: true
          type: string
        - $ref: '#/parameters/apiVersionQueryParameter'
      responses:
        '200':
          description: Success
          schema:
            type: file
        default:
          description: An error occurred.
          schema:
            $ref: '#/definitions/ErrorResponse'
      x-ms-examples:
        Getting the file content.:
          $ref: ./examples/get_file_content.json
      description: Needs a more full description created.
  /files/import:
    post:
      tags:
        - 'Files:'
      summary: >-
        Microsoft Azure Creates A New File Entity By Importing Data From A Provided Url Uploaded Files Can, For Example, Be Used For Training Or Evaluating Fine Tuned Models
      operationId: microsoftAzureFilesImport
      consumes:
        - application/json
      produces:
        - application/json
      parameters:
        - $ref: '#/parameters/apiVersionQueryParameter'
        - in: body
          name: fileImport
          description: >-
            The definition of the file to create including its purpose, the file
            name and the url of the file location.
          required: true
          schema:
            $ref: '#/definitions/FileImport'
      responses:
        '201':
          description: The file has been successfully created.
          schema:
            $ref: '#/definitions/File'
          headers:
            Location:
              description: The location of the newly created item.
              type: string
              format: url
        default:
          description: An error occurred.
          schema:
            $ref: '#/definitions/ErrorResponse'
      x-ms-examples:
        Importing a file with a blob url as source.:
          $ref: ./examples/import_file.json
      description: Needs a more full description created.
  /fine_tuning/jobs:
    get:
      tags:
        - 'Fine-Tuning:'
      summary: "Microsoft Azure Gets A List Of All Fine Tune Jobs Owned By The Azure Openai Resource \r\nthe Details That Are Returned For Each Fine Tune Job Contain Besides Its Identifier\r\nthe Base Model, Training And Validation Files, Hyper Parameters, Time Stamps, Status And Events \r\nevents Are Created When The Job Status Changes, E G Running Or Complete, And When Results Are Uploaded"
      operationId: microsoftAzureFinetuningList
      produces:
        - application/json
      parameters:
        - in: query
          name: after
          description: Identifier for the last event from the previous pagination request.
          type: string
        - in: query
          name: limit
          description: Number of events to retrieve. Defaults to 20.
          type: integer
          format: int32
          default: 20
        - $ref: '#/parameters/apiVersionQueryParameter'
      responses:
        '200':
          description: Success
          schema:
            $ref: '#/definitions/FineTuningJobList'
        default:
          description: An error occurred.
          schema:
            $ref: '#/definitions/ErrorResponse'
      x-ms-examples:
        Getting all fine tune jobs owned by this account.:
          $ref: ./examples/get_finetuning_jobs.json
      description: Needs a more full description created.
    post:
      tags:
        - 'Fine-Tuning:'
      summary: "Microsoft Azure Creates A Job That Fine Tunes A Specified Model From A Given Training File \r\nresponse Includes Details Of The Enqueued Job Including Job Status And Hyper Parameters \r\nthe Name Of The Fine Tuned Model Is Added To The Response Once Complete"
      operationId: microsoftAzureFinetuningCreate
      consumes:
        - application/json
      produces:
        - application/json
      parameters:
        - $ref: '#/parameters/apiVersionQueryParameter'
        - in: body
          name: fineTuningJob
          description: "The specification of the fine-tuned model to create.\r\nRequired parameters are the base model and the training file to use.\r\nOptionally a validation file can be specified to compute validation metrics during training.\r\nHyper parameters will be set to default values or can by optionally specified.\r\nThese include batch size, learning rate multiplier, number of epochs and others."
          required: true
          schema:
            $ref: '#/definitions/FineTuningJobCreation'
      responses:
        '201':
          description: The fine tune has been successfully created.
          schema:
            $ref: '#/definitions/FineTuningJob'
          headers:
            Location:
              description: The location of the newly created item.
              type: string
              format: url
        default:
          description: An error occurred.
          schema:
            $ref: '#/definitions/ErrorResponse'
      x-ms-examples:
        Creating a fine tune job.:
          $ref: ./examples/post_finetuning_job.json
      description: Needs a more full description created.
  /fine_tuning/jobs/{fine-tuning-job-id}:
    get:
      tags:
        - 'Fine-Tuning:'
      summary: "Microsoft Azure Gets Details For A Single Fine Tune Job Specified By The Given Fine Tune Id \r\nthe Details Contain The Base Model, Training And Validation Files, Hyper Parameters, Time Stamps, Status And Events \r\nevents Are Created When The Job Status Changes, E G Running Or Complete, And When Results Are Uploaded"
      operationId: microsoftAzureFinetuningGet
      produces:
        - application/json
      parameters:
        - in: path
          name: fine-tuning-job-id
          description: The identifier of the fine-tune job.
          required: true
          type: string
        - $ref: '#/parameters/apiVersionQueryParameter'
      responses:
        '200':
          description: Success
          schema:
            $ref: '#/definitions/FineTuningJob'
        default:
          description: An error occurred.
          schema:
            $ref: '#/definitions/ErrorResponse'
      x-ms-examples:
        Getting a fine tune job.:
          $ref: ./examples/get_finetuning_job.json
      description: Needs a more full description created.
    delete:
      tags:
        - 'Fine-Tuning:'
      summary: 'Microsoft Azure Deletes The Fine Tune Job Specified By The Given Fine Tune Id'
      operationId: microsoftAzureFinetuningDelete
      produces:
        - application/json
      parameters:
        - in: path
          name: fine-tuning-job-id
          description: The identifier of the fine-tune job.
          required: true
          type: string
        - $ref: '#/parameters/apiVersionQueryParameter'
      responses:
        '204':
          description: The fine tune was successfully deleted.
        default:
          description: An error occurred.
          schema:
            $ref: '#/definitions/ErrorResponse'
      x-ms-examples:
        Deleting a fine tune job.:
          $ref: ./examples/delete_finetuning_job.json
      description: Needs a more full description created.
  /fine_tuning/jobs/{fine-tuning-job-id}/events:
    get:
      tags:
        - 'Fine-Tuning:'
      summary: "Microsoft Azure Gets The Events For The Fine Tune Job Specified By The Given Fine Tune Id \r\nevents Are Created When The Job Status Changes, E G Running Or Complete, And When Results Are Uploaded"
      operationId: microsoftAzureFinetuningGetevents
      produces:
        - application/json
      parameters:
        - in: path
          name: fine-tuning-job-id
          description: The identifier of the fine-tune job.
          required: true
          type: string
        - in: query
          name: after
          description: Identifier for the last event from the previous pagination request.
          type: string
        - in: query
          name: limit
          description: Number of events to retrieve. Defaults to 20.
          type: integer
          format: int32
          default: 20
        - $ref: '#/parameters/apiVersionQueryParameter'
      responses:
        '200':
          description: Success
          schema:
            $ref: '#/definitions/FineTuningJobEventList'
        default:
          description: An error occurred.
          schema:
            $ref: '#/definitions/ErrorResponse'
      x-ms-examples:
        Getting events of a fine tune job.:
          $ref: ./examples/get_finetuning_job_events.json
      description: Needs a more full description created.
  /fine_tuning/jobs/{fine-tuning-job-id}/cancel:
    post:
      tags:
        - 'Fine-Tuning:'
      summary: >-
        Microsoft Azure Cancels The Processing Of The Fine Tune Job Specified By The Given Fine Tune Id
      operationId: microsoftAzureFinetuningCancel
      produces:
        - application/json
      parameters:
        - in: path
          name: fine-tuning-job-id
          description: The identifier of the fine-tune job.
          required: true
          type: string
        - $ref: '#/parameters/apiVersionQueryParameter'
      responses:
        '200':
          description: The fine tune has been successfully canceled
          schema:
            $ref: '#/definitions/FineTuningJob'
        default:
          description: An error occurred.
          schema:
            $ref: '#/definitions/ErrorResponse'
      x-ms-examples:
        Canceling a fine tune job.:
          $ref: ./examples/cancel_finetuning_job.json
      description: Needs a more full description created.
  /models:
    get:
      tags:
        - 'Models:'
      summary: "Microsoft Azure Gets A List Of All Models That Are Accessible By The Azure Openai Resource \r\nthese Include Base Models As Well As All Successfully Completed Fine Tuned Models Owned By The Azure Openai Resource"
      operationId: microsoftAzureModelsList
      produces:
        - application/json
      parameters:
        - $ref: '#/parameters/apiVersionQueryParameter'
      responses:
        '200':
          description: Success
          schema:
            $ref: '#/definitions/ModelList'
        default:
          description: An error occurred.
          schema:
            $ref: '#/definitions/ErrorResponse'
      x-ms-examples:
        Getting all models owned by account.:
          $ref: ./examples/get_models.json
      description: Needs a more full description created.
  /models/{model-id}:
    get:
      tags:
        - 'Models:'
      summary: 'Microsoft Azure Gets Details For The Model Specified By The Given Modelid'
      operationId: microsoftAzureModelsGet
      produces:
        - application/json
      parameters:
        - in: path
          name: model-id
          description: The identifier of the model.
          required: true
          type: string
        - $ref: '#/parameters/apiVersionQueryParameter'
      responses:
        '200':
          description: Success
          schema:
            $ref: '#/definitions/Model'
        default:
          description: An error occurred.
          schema:
            $ref: '#/definitions/ErrorResponse'
      x-ms-examples:
        Getting a base model.:
          $ref: ./examples/get_model_base.json
        Getting a fine-tuned model.:
          $ref: ./examples/get_model_finetune.json
      description: Needs a more full description created.
definitions:
  Capabilities:
    title: Capabilities
    description: The capabilities of a base or fine tune model.
    required:
      - chat_completion
      - completion
      - embeddings
      - fine_tune
      - inference
    type: object
    properties:
      fine_tune:
        description: A value indicating whether a model can be used for fine tuning.
        type: boolean
      inference:
        description: A value indicating whether a model can be deployed.
        type: boolean
      completion:
        description: A value indicating whether a model supports completion.
        type: boolean
      chat_completion:
        description: A value indicating whether a model supports chat completion.
        type: boolean
      embeddings:
        description: A value indicating whether a model supports embeddings.
        type: boolean
  Deprecation:
    title: Deprecation
    description: "Defines the dates of deprecation for the different use cases of a model.\r\nUsually base models support 1 year of fine tuning after creation. Inference is typically supported 2 years after creation of base or\r\nfine tuned models. The exact dates are specified in the properties."
    required:
      - inference
    type: object
    properties:
      fine_tune:
        format: unixtime
        description: >-
          The end date of fine tune support of this model. Will be `null` for
          fine tune models.
        type: integer
      inference:
        format: unixtime
        description: The end date of inference support of this model.
        type: integer
  Error:
    title: Error
    description: "Error content as defined in the Microsoft REST guidelines\r\n(https://github.com/microsoft/api-guidelines/blob/vNext/Guidelines.md#7102-error-condition-responses)."
    required:
      - code
      - message
    type: object
    properties:
      code:
        $ref: '#/definitions/ErrorCode'
      message:
        description: The message of this error.
        minLength: 1
        type: string
      target:
        description: The location where the error happened if available.
        type: string
      details:
        description: The error details if available.
        type: array
        items:
          $ref: '#/definitions/Error'
      innererror:
        $ref: '#/definitions/InnerError'
  ErrorCode:
    title: ErrorCode
    description: "Error codes as defined in the Microsoft REST guidelines\r\n(https://github.com/microsoft/api-guidelines/blob/vNext/Guidelines.md#7102-error-condition-responses)."
    enum:
      - conflict
      - invalidPayload
      - forbidden
      - notFound
      - unexpectedEntityState
      - itemDoesAlreadyExist
      - serviceUnavailable
      - internalFailure
      - quotaExceeded
      - jsonlValidationFailed
      - fileImportFailed
      - tooManyRequests
      - unauthorized
      - contentFilter
    type: string
    x-ms-enum:
      name: ErrorCode
      modelAsString: true
      values:
        - value: conflict
          description: The requested operation conflicts with the current resource state.
        - value: invalidPayload
          description: The request data is invalid for this operation.
        - value: forbidden
          description: The operation is forbidden for the current user/api key.
        - value: notFound
          description: The resource is not found.
        - value: unexpectedEntityState
          description: The operation cannot be executed in the current resource's state.
        - value: itemDoesAlreadyExist
          description: The item does already exist.
        - value: serviceUnavailable
          description: The service is currently not available.
        - value: internalFailure
          description: Internal error. Please retry.
        - value: quotaExceeded
          description: Quota exceeded.
        - value: jsonlValidationFailed
          description: Validation of jsonl data failed.
        - value: fileImportFailed
          description: Import of file failed.
        - value: tooManyRequests
          description: Too many requests. Please retry later.
        - value: unauthorized
          description: The current user/api key is not authorized for the operation.
        - value: contentFilter
          description: Image generation failed as a result of our safety system.
  ErrorResponse:
    title: ErrorResponse
    description: "Error response as defined in the Microsoft REST guidelines\r\n(https://github.com/microsoft/api-guidelines/blob/vNext/Guidelines.md#7102-error-condition-responses)."
    required:
      - error
    type: object
    properties:
      error:
        $ref: '#/definitions/Error'
  EventType:
    title: EventType
    description: Defines the severity of a content filter result.
    enum:
      - message
      - metrics
    type: string
    x-ms-enum:
      name: EventType
      modelAsString: true
      values:
        - value: message
          description: Event only contains human readable messages.
        - value: metrics
          description: Event contains metrics.
  File:
    title: File
    description: >-
      A file is a document usable for training and validation. It can also be a
      service generated document with result details.
    required:
      - filename
      - purpose
    type: object
    properties:
      object:
        $ref: '#/definitions/TypeDiscriminator'
      created_at:
        format: unixtime
        description: A timestamp when this job or item was created (in unix epochs).
        type: integer
        readOnly: true
      id:
        description: The identity of this item.
        type: string
        readOnly: true
      status:
        $ref: '#/definitions/FileState'
      bytes:
        format: int64
        description: "The size of this file when available (can be null). File sizes larger than 2^53-1 are not supported to ensure compatibility\r\nwith JavaScript integers."
        type: integer
        readOnly: true
      purpose:
        $ref: '#/definitions/Purpose'
      filename:
        description: The name of the file.
        minLength: 1
        type: string
      status_details:
        description: The error message with details in case processing of this file failed.
        type: string
        readOnly: true
  FileImport:
    title: FileImport
    description: >-
      Defines a document to import from an external content url to be usable
      with Azure OpenAI.
    required:
      - content_url
      - filename
      - purpose
    type: object
    properties:
      purpose:
        $ref: '#/definitions/Purpose'
      filename:
        description: "The name of the [JSON Lines](https://jsonlines.readthedocs.io/en/latest/) file to be uploaded.\r\nIf the `purpose` is set to \"fine-tune\", each line is a JSON record with \"prompt\" and \"completion\" fields representing your training examples."
        minLength: 1
        type: string
      content_url:
        format: url
        description: >-
          The url to download the document from (can be SAS url of a blob or any
          other external url accessible with a GET request).
        type: string
  FileList:
    title: FileList
    description: Represents a list of files.
    type: object
    properties:
      object:
        $ref: '#/definitions/TypeDiscriminator'
      data:
        description: The list of items.
        type: array
        items:
          $ref: '#/definitions/File'
  FileState:
    title: FileState
    description: The state of a file.
    enum:
      - uploaded
      - pending
      - running
      - processed
      - error
      - deleting
      - deleted
    type: string
    readOnly: true
    x-ms-enum:
      name: FileState
      modelAsString: true
      values:
        - value: uploaded
          description: >-
            The file has been uploaded but it's not yet processed. This state is
            not returned by Azure OpenAI and exposed only for compatibility. It
            can be categorized as an inactive state.
        - value: pending
          description: >-
            The operation was created and is not queued to be processed in the
            future. It can be categorized as an inactive state.
        - value: running
          description: >-
            The operation has started to be processed. It can be categorized as
            an active state.
        - value: processed
          description: >-
            The operation has successfully be processed and is ready for
            consumption. It can be categorized as a terminal state.
        - value: error
          description: >-
            The operation has completed processing with a failure and cannot be
            further consumed. It can be categorized as a terminal state.
        - value: deleting
          description: >-
            The entity is ni the process to be deleted. This state is not
            returned by Azure OpenAI and exposed only for compatibility. It can
            be categorized as an active state.
        - value: deleted
          description: >-
            The entity has been deleted but may still be referenced by other
            entities predating the deletion. It can be categorized as a terminal
            state.
  FineTuningHyperParameters:
    title: FineTuningHyperParameters
    description: The hyper parameter settings used in a fine tune job.
    type: object
    properties:
      n_epochs:
        format: int32
        description: >-
          The number of epochs to train the model for. An epoch refers to one
          full cycle through the training dataset.
        type: integer
      batch_size:
        format: int32
        description: "The batch size to use for training. The batch size is the number of training examples used to train a single forward and backward pass.\r\nIn general, we've found that larger batch sizes tend to work better for larger datasets.\r\nThe default value as well as the maximum value for this property are specific to a base model."
        type: integer
      learning_rate_multiplier:
        format: double
        description: "The learning rate multiplier to use for training. The fine-tuning learning rate is the original learning rate used for pre-training multiplied by this value.\r\nLarger learning rates tend to perform better with larger batch sizes.\r\nWe recommend experimenting with values in the range 0.02 to 0.2 to see what produces the best results."
        type: number
  FineTuningJob:
    title: FineTuningJob
    description: Defines the values of a fine tune job.
    required:
      - model
      - training_file
    type: object
    properties:
      object:
        $ref: '#/definitions/TypeDiscriminator'
      created_at:
        format: unixtime
        description: A timestamp when this job or item was created (in unix epochs).
        type: integer
        readOnly: true
      id:
        description: The identity of this item.
        type: string
        readOnly: true
      status:
        $ref: '#/definitions/FineTuningState'
      model:
        description: The identifier (model-id) of the base model used for the fine-tune.
        minLength: 1
        type: string
      fine_tuned_model:
        description: "The identifier (model-id) of the resulting fine tuned model. This property is only populated for successfully completed fine-tune runs.\r\nUse this identifier to create a deployment for inferencing."
        type: string
      training_file:
        description: The file which is used for training.
        minLength: 1
        type: string
      validation_file:
        description: >-
          The file which is used to evaluate the fine tuned model during
          training.
        type: string
      result_files:
        description: "The result file identities (file-id) containing training and evaluation metrics in csv format.\r\nThe file is only available for successfully completed fine-tune runs."
        type: array
        items:
          type: string
      finished_at:
        format: int32
        description: >-
          A timestamp when this job or item has finished successfully (in unix
          epochs).
        type: integer
        readOnly: true
      organisation_id:
        description: >-
          The organisation id of this fine tune job. Unused on Azure OpenAI;
          compatibility for OpenAI only.
        type: string
      trained_tokens:
        format: int32
        description: The total number of billable tokens processed by this fine tuning job.
        type: integer
        readOnly: true
      hyperparameters:
        $ref: '#/definitions/FineTuningHyperParameters'
      suffix:
        description: >-
          The suffix used to identify the fine-tuned model. The suffix can
          contain up to 40 characters (a-z, A-Z, 0-9,- and _) that will be added
          to your fine-tuned model name.
        type: string
  FineTuningJobCreation:
    title: FineTuningJobCreation
    description: Defines the values of a fine tune job.
    required:
      - model
      - training_file
    type: object
    properties:
      model:
        description: The identifier (model-id) of the base model used for this fine-tune.
        minLength: 1
        type: string
      training_file:
        description: >-
          The file identity (file-id) that is used for training this fine tuned
          model.
        minLength: 1
        type: string
      validation_file:
        description: >-
          The file identity (file-id) that is used to evaluate the fine tuned
          model during training.
        type: string
      hyperparameters:
        $ref: '#/definitions/FineTuningHyperParameters'
      suffix:
        description: >-
          The suffix used to identify the fine-tuned model. The suffix can
          contain up to 40 characters (a-z, A-Z, 0-9,- and _) that will be added
          to your fine-tuned model name.
        type: string
  FineTuningJobEvent:
    title: FineTuningJobEvent
    required:
      - created_at
      - level
      - message
      - type
    type: object
    properties:
      object:
        $ref: '#/definitions/TypeDiscriminator'
      id:
        description: The identity of this event.
        type: string
        readOnly: true
      created_at:
        format: unixtime
        description: A timestamp when this event was created (in unix epochs).
        type: integer
      level:
        $ref: '#/definitions/LogLevel'
      message:
        description: >-
          The message describing the event. This can be a change of state, e.g.,
          enqueued, started, failed or completed, or other events like uploaded
          results.
        minLength: 1
        type: string
      type:
        $ref: '#/definitions/EventType'
      data:
        description: Machine readable data of this event.
  FineTuningJobEventList:
    title: FineTuningJobEventList
    description: Represents a list of events.
    type: object
    properties:
      object:
        $ref: '#/definitions/TypeDiscriminator'
      data:
        description: The list of items.
        t

# --- truncated at 32 KB (40 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/microsoft-azure/refs/heads/main/openapi/azure-openai-api-version-2024-02-15-preview-openapi-original.yml