Unstructured · Schema
Unstructured API Schemas
JSON Schema definitions extracted from the Unstructured Platform API and Partition API OpenAPI specifications.
document-processingETLRAGLLMPDFOCRdata-ingestionchunkingembeddingsAI
JSON Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://raw.githubusercontent.com/api-evangelist/unstructured/refs/heads/main/json-schema/unstructured-schemas.json",
"title": "Unstructured API Schemas",
"description": "JSON Schema definitions extracted from the Unstructured Platform API and Partition API OpenAPI specifications.",
"$defs": {
"AstraDBConnectorConfig": {
"properties": {
"collection_name": {
"type": "string",
"title": "Collection Name"
},
"keyspace": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Keyspace"
},
"batch_size": {
"type": "integer",
"title": "Batch Size"
},
"binary_encode_vectors": {
"type": "boolean",
"title": "Binary Encode Vectors",
"default": true
},
"api_endpoint": {
"type": "string",
"title": "Api Endpoint"
},
"token": {
"type": "string",
"title": "Token"
}
},
"additionalProperties": true,
"type": "object",
"required": [
"collection_name",
"batch_size",
"api_endpoint",
"token"
],
"title": "AstraDBConnectorConfig"
},
"AstraDBConnectorConfigInput": {
"properties": {
"collection_name": {
"type": "string",
"pattern": "^\\w+$",
"title": "Collection Name"
},
"keyspace": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Keyspace",
"default": "default_keyspace"
},
"batch_size": {
"type": "integer",
"minimum": 1.0,
"title": "Batch Size",
"default": 20
},
"binary_encode_vectors": {
"type": "boolean",
"title": "Binary Encode Vectors",
"default": true
},
"api_endpoint": {
"type": "string",
"title": "Api Endpoint"
},
"token": {
"type": "string",
"title": "Token"
},
"flatten_metadata": {
"type": "boolean",
"title": "Flatten Metadata",
"default": false
}
},
"additionalProperties": true,
"type": "object",
"required": [
"collection_name",
"api_endpoint",
"token"
],
"title": "AstraDBConnectorConfigInput"
},
"AzureDestinationConnectorConfig": {
"properties": {
"remote_url": {
"type": "string",
"title": "Remote Url"
},
"account_name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Name"
},
"account_key": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Key"
},
"connection_string": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Connection String"
},
"sas_token": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Sas Token"
}
},
"additionalProperties": true,
"type": "object",
"required": [
"remote_url"
],
"title": "AzureDestinationConnectorConfig"
},
"AzureDestinationConnectorConfigInput": {
"properties": {
"remote_url": {
"type": "string",
"pattern": "^(az:\\/\\/|abfs:\\/\\/)",
"title": "Remote Url"
},
"account_name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Name"
},
"account_key": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Key"
},
"connection_string": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Connection String"
},
"sas_token": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Sas Token"
}
},
"additionalProperties": true,
"type": "object",
"required": [
"remote_url"
],
"title": "AzureDestinationConnectorConfigInput"
},
"AzureSourceConnectorConfig": {
"properties": {
"remote_url": {
"type": "string",
"title": "Remote Url"
},
"account_name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Name"
},
"account_key": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Key"
},
"connection_string": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Connection String"
},
"sas_token": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Sas Token"
},
"recursive": {
"type": "boolean",
"title": "Recursive"
}
},
"additionalProperties": true,
"type": "object",
"required": [
"remote_url",
"recursive"
],
"title": "AzureSourceConnectorConfig"
},
"AzureSourceConnectorConfigInput": {
"properties": {
"remote_url": {
"type": "string",
"pattern": "^(az:\\/\\/|abfs:\\/\\/)",
"title": "Remote Url"
},
"account_name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Name"
},
"account_key": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Account Key"
},
"connection_string": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Connection String"
},
"sas_token": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Sas Token"
},
"recursive": {
"type": "boolean",
"title": "Recursive",
"default": true
}
},
"additionalProperties": true,
"type": "object",
"required": [
"remote_url"
],
"title": "AzureSourceConnectorConfigInput"
},
"Body_create_job": {
"properties": {
"input_files": {
"anyOf": [
{
"items": {
"type": "string",
"contentMediaType": "application/octet-stream"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Input Files"
},
"request_data": {
"type": "string",
"title": "Request Data"
}
},
"type": "object",
"required": [
"request_data"
],
"title": "Body_create_job"
},
"Body_run_workflow": {
"properties": {
"input_files": {
"anyOf": [
{
"items": {
"type": "string",
"contentMediaType": "application/octet-stream"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Input Files"
}
},
"type": "object",
"title": "Body_run_workflow"
},
"BoxSourceConnectorConfig": {
"properties": {
"box_app_config": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Box App Config"
},
"access_token": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Access Token"
},
"refresh_token": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Refresh Token"
},
"recursive": {
"type": "boolean",
"title": "Recursive"
}
},
"additionalProperties": true,
"type": "object",
"required": [
"recursive"
],
"title": "BoxSourceConnectorConfig"
},
"BoxSourceConnectorConfigInput": {
"properties": {
"box_app_config": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Box App Config"
},
"access_token": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Access Token"
},
"refresh_token": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Refresh Token"
},
"remote_url": {
"type": "string",
"pattern": "^box:\\/\\/",
"title": "Remote Url"
},
"recursive": {
"type": "boolean",
"title": "Recursive",
"default": true
}
},
"additionalProperties": true,
"type": "object",
"required": [
"remote_url"
],
"title": "BoxSourceConnectorConfigInput"
},
"ChannelListResponse": {
"properties": {
"items": {
"items": {
"oneOf": [
{
"$ref": "#/components/schemas/WebhookChannelResponse"
},
{
"$ref": "#/components/schemas/EmailChannelResponse"
}
],
"discriminator": {
"propertyName": "channel_type",
"mapping": {
"email": "#/components/schemas/EmailChannelResponse",
"webhook": "#/components/schemas/WebhookChannelResponse"
}
}
},
"type": "array",
"title": "Items",
"description": "List of channels"
}
},
"type": "object",
"required": [
"items"
],
"title": "ChannelListResponse",
"description": "List response for notification channels (no pagination, max 50 per scope)."
},
"ChannelType": {
"type": "string",
"enum": [
"webhook",
"email"
],
"title": "ChannelType",
"description": "Notification delivery channel types."
},
"ConfluenceSourceConnectorConfig": {
"properties": {
"url": {
"type": "string",
"title": "Url"
},
"username": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Username"
},
"cloud_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Cloud Id"
},
"password": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Password"
},
"api_token": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Api Token"
},
"token": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Token"
},
"oauth_token": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Oauth Token"
},
"refresh_token": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Refresh Token"
},
"cloud": {
"type": "boolean",
"title": "Cloud"
},
"extract_images": {
"type": "boolean",
"title": "Extract Images",
"default": false
},
"extract_files": {
"type": "boolean",
"title": "Extract Files",
"default": false
},
"max_num_of_spaces": {
"type": "integer",
"title": "Max Num Of Spaces"
},
"max_num_of_docs_from_each_space": {
"type": "integer",
"title": "Max Num Of Docs From Each Space"
},
"spaces": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Spaces"
}
},
"additionalProperties": true,
"type": "object",
"required": [
"url",
"cloud",
"max_num_of_spaces",
"max_num_of_docs_from_each_space",
"spaces"
],
"title": "ConfluenceSourceConnectorConfig"
},
"ConfluenceSourceConnectorConfigInput": {
"properties": {
"url": {
"type": "string",
"title": "Url"
},
"username": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Username"
},
"cloud_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Cloud Id"
},
"password": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Password"
},
"api_token": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Api Token"
},
"token": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Token"
},
"oauth_token": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Oauth Token"
},
"refresh_token": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Refresh Token"
},
"cloud": {
"type": "boolean",
"title": "Cloud",
"default": false
},
"extract_images": {
"type": "boolean",
"title": "Extract Images",
"default": false
},
"extract_files": {
"type": "boolean",
"title": "Extract Files",
"default": false
},
"max_num_of_spaces": {
"type": "integer",
"minimum": 1.0,
"title": "Max Num Of Spaces",
"default": 500
},
"max_num_of_docs_from_each_space": {
"type": "integer",
"minimum": 1.0,
"title": "Max Num Of Docs From Each Space",
"default": 150
},
"spaces": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Spaces"
}
},
"additionalProperties": true,
"type": "object",
"required": [
"url"
],
"title": "ConfluenceSourceConnectorConfigInput"
},
"ConnectionCheckStatus": {
"type": "string",
"enum": [
"SCHEDULED",
"SUCCESS",
"FAILURE"
],
"title": "ConnectionCheckStatus"
},
"CouchbaseDestinationConnectorConfig": {
"properties": {
"bucket": {
"type": "string",
"title": "Bucket"
},
"connection_string": {
"type": "string",
"title": "Connection String"
},
"scope": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Scope"
},
"collection": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Collection"
},
"batch_size": {
"type": "integer",
"title": "Batch Size"
},
"username": {
"type": "string",
"title": "Username"
},
"password": {
"type": "string",
"title": "Password"
}
},
"additionalProperties": true,
"type": "object",
"required": [
"bucket",
"connection_string",
"batch_size",
"username",
"password"
],
"title": "CouchbaseDestinationConnectorConfig"
},
"CouchbaseDestinationConnectorConfigInput": {
"properties": {
"bucket": {
"type": "string",
"title": "Bucket"
},
"connection_string": {
"type": "string",
"title": "Connection String"
},
"scope": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Scope"
},
"collection": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Collection"
},
"batch_size": {
"type": "integer",
"title": "Batch Size"
},
"username": {
"type": "string",
"title": "Username"
},
"password": {
"type": "string",
"title": "Password"
}
},
"additionalProperties": true,
"type": "object",
"required": [
"bucket",
"connection_string",
"batch_size",
"username",
"password"
],
"title": "CouchbaseDestinationConnectorConfigInput"
},
"CouchbaseSourceConnectorConfig": {
"properties": {
"bucket": {
"type": "string",
"title": "Bucket"
},
"connection_string": {
"type": "string",
"title": "Connection String"
},
"scope": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Scope"
},
"collection": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Collection"
},
"batch_size": {
"type": "integer",
"title": "Batch Size"
},
"username": {
"type": "string",
"title": "Username"
},
"password": {
"type": "string",
"title": "Password"
},
"collection_id": {
"type": "string",
"title": "Collection Id"
}
},
"additionalProperties": true,
"type": "object",
"required": [
"bucket",
"connection_string",
"batch_size",
"username",
"password",
"collection_id"
],
"title": "CouchbaseSourceConnectorConfig"
},
"CouchbaseSourceConnectorConfigInput": {
"properties": {
"bucket": {
"type": "string",
"title": "Bucket"
},
"connection_string": {
"type": "string",
"title": "Connection String"
},
"scope": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Scope"
},
"collection": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Collection"
},
"batch_size": {
"type": "integer",
"title": "Batch Size"
},
"username": {
"type": "string",
"title": "Username"
},
"password": {
"type": "string",
"title": "Password"
},
"collection_id": {
"type": "string",
"title": "Collection Id"
}
},
"additionalProperties": true,
"type": "object",
"required": [
"bucket",
"connection_string",
"batch_size",
"username",
"password",
"collection_id"
],
"title": "CouchbaseSourceConnectorConfigInput"
},
"CreateDestinationConnector": {
"properties": {
"name": {
"type": "string",
"title": "Name"
},
"type": {
"anyOf": [
{
"$ref": "#/components/schemas/DestinationConnectorType"
},
{
"type": "string"
}
],
"title": "Type"
},
"config": {
"anyOf": [
{
"$ref": "#/components/schemas/AstraDBConnectorConfigInput"
},
{
"$ref": "#/components/schemas/CouchbaseDestinationConnectorConfigInput"
},
{
"$ref": "#/components/schemas/DatabricksVolumesConnectorConfigInput"
},
{
"$ref": "#/components/schemas/DatabricksVDTDestinationConnectorConfigInput"
},
{
"$ref": "#/components/schemas/DeltaTableConnectorConfigInput"
},
{
"$ref": "#/components/schemas/ElasticsearchConnectorConfigInput"
},
{
"$ref": "#/components/schemas/GCSDestinationConnectorConfigInput"
},
{
"$ref": "#/components/schemas/KafkaCloudDestinationConnectorConfigInput"
},
{
"$ref": "#/components/schemas/MilvusDestinationConnectorConfigInput"
},
{
"$ref": "#/components/schemas/MongoDBConnectorConfigInput"
},
{
"$ref": "#/components/schemas/Neo4jDestinationConnectorConfigInput"
},
{
"$ref": "#/components/schemas/OneDriveDestinationConnectorConfigInput"
},
{
"$ref": "#/components/schemas/PineconeDestinationConnectorConfigInput"
},
{
"$ref": "#/components/schemas/PostgresDestinationConnectorConfigInput"
},
{
"$ref": "#/components/schemas/RedisDestinationConnectorConfigInput"
},
{
"$ref": "#/components/schemas/QdrantCloudDestinationConnectorConfigInput"
},
{
"$ref": "#/components/schemas/SnowflakeDestinationConnectorConfigInput"
},
{
"$ref": "#/components/schemas/TeradataDestinationConnectorConfigInput"
},
{
"$ref": "#/components/schemas/WeaviateDestinationConnectorConfigInput"
},
{
"$ref": "#/components/schemas/IBMWatsonxS3DestinationConnectorConfigInput"
},
{
"$ref": "#/components/schemas/S3DestinationConnectorConfigInput"
},
{
"$ref": "#/components/schemas/AzureDestinationConnectorConfigInput"
},
{
"additionalProperties": true,
"type": "object"
}
],
"title": "Config"
},
"key": {
"anyOf": [
{
"type": "string",
"maxLength": 63,
"minLength": 1,
"pattern": "^[a-z0-9](-?[a-z0-9])*$"
},
{
"type": "null"
}
],
"title": "Key",
"description": "Stable identifier for the destination connector, used for cross-environment export. If omitted, derived from `name` with a 6-hex-digit suffix. Immutable once set. 1-63 characters, lowercase alphanumeric and hyphens, no consecutive/leading/trailing hyphens.",
"examples": [
"s3-output-destination"
]
}
},
"type": "object",
"required": [
"name",
"type",
"config"
],
"title": "CreateDestinationConnector"
},
"CreateEmailChannelRequest": {
"properties": {
"channel_type": {
"type": "string",
"const": "email",
"title": "Channel Type",
"default": "email"
},
"description": {
"anyOf": [
{
"type": "string",
"maxLength": 255
},
{
"type": "null"
}
],
"title": "Description",
"description": "Channel description"
},
"event_types": {
"items": {
"$ref": "#/components/schemas/NotificationEventType"
},
"type": "array",
"minItems": 1,
"title": "Event Types",
"description": "Event types to subscribe to"
},
"enabled": {
"type": "boolean",
"title": "Enabled",
"description": "Enable/disable channel",
"default": true
},
"email_config": {
"$ref": "#/components/schemas/EmailChannelConfig",
"description": "Email channel configuration"
}
},
"type": "object",
"required": [
"event_types",
"email_config"
],
"title": "CreateEmailChannelRequest",
"description": "Request to create an email notification channel."
},
"CreateSourceConnector": {
"properties": {
"name": {
"type": "string",
"title": "Name"
},
"type": {
"anyOf": [
{
"$ref": "#/components/schemas/SourceConnectorType"
},
{
"type": "string"
}
],
"title": "Type"
},
"config": {
"anyOf": [
{
"$ref": "#/components/schemas/BoxSourceConnectorConfigInput"
},
{
"$ref": "#/components/schemas/ConfluenceSourceConnectorConfigInput"
},
{
"$ref": "#/components/schemas/CouchbaseSourceConnectorConfigInput"
},
{
"$ref": "#/components/schemas/DatabricksVolumesConnectorConfigInput"
},
{
"$ref": "#/components/schemas/DropboxSourceConnectorConfigInput"
},
{
"$ref": "#/components/schemas/ElasticsearchConnectorConfigInput"
},
{
"$ref": "#/components/schemas/GCSSourceConnectorConfigInput"
},
{
"$ref": "#/components/schemas/GoogleDriveSourceConnectorConfigInput"
},
{
"$ref": "#/components/schemas/KafkaCloudSourceConnectorConfigInput"
},
{
"$ref": "#/components/schemas/MongoDBConnectorConfigInput"
},
{
"$ref": "#/components/schemas/OneDriveSourceConnectorConfigInput"
},
{
"$ref": "#/components/schemas/OutlookSourceConnectorConfigInput"
},
{
"$ref": "#/components/schemas/PostgresSourceConnectorConfigInput"
},
{
"$ref": "#/components/schemas/SalesforceSourceConnectorConfigInput"
},
{
"$ref": "#/components/schemas/SharePointSourceConnectorConfigInput"
},
{
"$ref": "#/components/schemas/SlackSourceConnectorConfigInput"
},
{
"$ref": "#/components/schemas/SnowflakeSourceConnectorConfigInput"
},
{
"$ref": "#/components/schemas/TeradataSourceConnectorConfigInput"
},
{
"$ref": "#/components/schemas/JiraSourceConnectorConfigInput"
},
{
"$ref": "#/components/schemas/ZendeskSourceConnectorConfigInput"
},
{
"$ref": "#/components/schemas/S3SourceConnectorConfigInput"
},
{
"$ref": "#/components/schemas/AzureSourceConnectorConfigInput"
},
{
"additionalProperties": true,
"type": "object"
}
],
"title": "Config"
},
"key": {
"anyOf": [
{
"type": "string",
"maxLength": 63,
"minLength": 1,
"pattern": "^[a-z0-9](-?[a-z0-9])*$"
},
{
"type": "null"
}
],
"title": "Key",
"description": "Stable identifier for the source connector, used for cross-environment export. If omitted, derived from `name` with a 6-hex-digit suffix. Immutable once set. 1-63 characters, lowercase alphanumeric and hyphens, no consecutive/leading/trailing hyphens.",
"examples": [
"s3-invoices-source"
]
}
},
"type": "object",
"required": [
"name",
"type",
"config"
],
"title": "CreateSourceConnector"
},
"CreateWebhookChannelRequest": {
"properties": {
"channel_type": {
"type": "string",
"const": "webhook",
"title": "Channel Type",
"default": "webhook"
},
"description": {
"anyOf": [
{
"type": "string",
"maxLength": 255
},
{
"type": "null"
}
],
"title
# --- truncated at 32 KB (189 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/unstructured/refs/heads/main/json-schema/unstructured-schemas.json