BuildDocumentClassifierRequest

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://artifacts.apis.io/azure-ai-foundry/json-schema/azure-ai-foundry-build-document-classifier-request-schema.json",
  "title": "BuildDocumentClassifierRequest",
  "description": "Request body to build a new custom document classifier.",
  "x-generated": "2026-11-12",
  "x-method": "derived",
  "x-generator": "derive-json-schema.py",
  "x-source": "openapi/azure-ai-foundry-document-classifiers-build-api-openapi.yml#/components/schemas/BuildDocumentClassifierRequest",
  "type": "object",
  "properties": {
    "classifierId": {
      "type": "string",
      "description": "Unique document classifier name.",
      "pattern": "^[a-zA-Z0-9][a-zA-Z0-9._~-]{1,63}$"
    },
    "description": {
      "type": "string",
      "description": "Document classifier description.",
      "maxLength": 4096
    },
    "baseClassifierId": {
      "type": "string",
      "description": "Base classifierId on top of which to train the classifier.",
      "pattern": "^[a-zA-Z0-9][a-zA-Z0-9._~-]{1,63}$"
    },
    "docTypes": {
      "type": "object",
      "description": "List of document types to classify against.",
      "additionalProperties": {
        "$ref": "#/$defs/ClassifierDocumentTypeDetails"
      }
    },
    "allowOverwrite": {
      "type": "boolean",
      "description": "Allow overwriting an existing classifier with the same name.",
      "default": false
    }
  },
  "required": [
    "classifierId",
    "docTypes"
  ],
  "$defs": {
    "AzureBlobContentSource": {
      "type": "object",
      "description": "Azure Blob Storage content.",
      "properties": {
        "containerUrl": {
          "type": "string",
          "format": "uri",
          "description": "Azure Blob Storage container URL."
        },
        "prefix": {
          "type": "string",
          "description": "Blob name prefix."
        }
      },
      "required": [
        "containerUrl"
      ]
    },
    "AzureBlobFileListContentSource": {
      "type": "object",
      "description": "File list in Azure Blob Storage.",
      "properties": {
        "containerUrl": {
          "type": "string",
          "format": "uri",
          "description": "Azure Blob Storage container URL."
        },
        "fileList": {
          "type": "string",
          "description": "Path to a JSONL file within the container specifying a subset of documents."
        }
      },
      "required": [
        "containerUrl",
        "fileList"
      ]
    },
    "ClassifierDocumentTypeDetails": {
      "type": "object",
      "description": "Classifier document type info.",
      "properties": {
        "sourceKind": {
          "$ref": "#/$defs/ContentSourceKind",
          "description": "Type of training data source."
        },
        "azureBlobSource": {
          "$ref": "#/$defs/AzureBlobContentSource",
          "description": "Azure Blob Storage location containing the training data for a classifier\ndocument type.  Either azureBlobSource or azureBlobFileListSource must be\nspecified."
        },
        "azureBlobFileListSource": {
          "$ref": "#/$defs/AzureBlobFileListContentSource",
          "description": "Azure Blob Storage file list specifying the training data for a classifier\ndocument type.  Either azureBlobSource or azureBlobFileListSource must be\nspecified."
        }
      }
    },
    "ContentSourceKind": {
      "type": "string",
      "description": "Type of content source.",
      "enum": [
        "url",
        "base64",
        "azureBlob",
        "azureBlobFileList"
      ],
      "x-ms-enum": {
        "name": "ContentSourceKind",
        "modelAsString": true,
        "values": [
          {
            "name": "url",
            "value": "url",
            "description": "Content at a specific URL."
          },
          {
            "name": "base64",
            "value": "base64",
            "description": "Content represented via Base64 encoding."
          },
          {
            "name": "azureBlob",
            "value": "azureBlob",
            "description": "Files in a path within an Azure Blob Storage container."
          },
          {
            "name": "azureBlobFileList",
            "value": "azureBlobFileList",
            "description": "A file list specifying individual files in an Azure Blob Storage container."
          }
        ]
      }
    }
  }
}