from mka1 import SDK
with SDK(
bearer_auth="<YOUR_BEARER_TOKEN_HERE>",
) as sdk:
res = sdk.llm.extract.create_schema(name="Invoice Extraction", schema={
"type": "object",
"properties": {
"invoice_number": {
"type": "string",
},
"vendor_name": {
"type": "string",
},
"total_amount": {
"type": "number",
},
"date": {
"type": "string",
"format": "date",
},
},
"required": [
"invoice_number",
"total_amount",
],
}, description="Schema for extracting invoice data from PDF documents", metadata={
"document_type": "invoice",
})
# Handle response
print(res){
"success": true,
"data": {
"id": "schema_invoice_123",
"name": "Invoice Extraction",
"description": "Schema for extracting invoice data from PDF documents",
"schema": {
"type": "object",
"properties": {
"invoice_number": {
"type": "string"
},
"vendor_name": {
"type": "string"
},
"total_amount": {
"type": "number"
},
"date": {
"type": "string",
"format": "date"
}
},
"required": [
"invoice_number",
"total_amount"
]
},
"metadata": {
"document_type": "invoice"
},
"createdAt": "2024-01-15T10:30:00Z",
"updatedAt": "2024-01-15T10:30:00Z"
}
}Creates and stores a reusable JSON Schema template for structured data extraction.
from mka1 import SDK
with SDK(
bearer_auth="<YOUR_BEARER_TOKEN_HERE>",
) as sdk:
res = sdk.llm.extract.create_schema(name="Invoice Extraction", schema={
"type": "object",
"properties": {
"invoice_number": {
"type": "string",
},
"vendor_name": {
"type": "string",
},
"total_amount": {
"type": "number",
},
"date": {
"type": "string",
"format": "date",
},
},
"required": [
"invoice_number",
"total_amount",
],
}, description="Schema for extracting invoice data from PDF documents", metadata={
"document_type": "invoice",
})
# Handle response
print(res){
"success": true,
"data": {
"id": "schema_invoice_123",
"name": "Invoice Extraction",
"description": "Schema for extracting invoice data from PDF documents",
"schema": {
"type": "object",
"properties": {
"invoice_number": {
"type": "string"
},
"vendor_name": {
"type": "string"
},
"total_amount": {
"type": "number"
},
"date": {
"type": "string",
"format": "date"
}
},
"required": [
"invoice_number",
"total_amount"
]
},
"metadata": {
"document_type": "invoice"
},
"createdAt": "2024-01-15T10:30:00Z",
"updatedAt": "2024-01-15T10:30:00Z"
}
}Gateway auth: send Authorization: Bearer <mka1-api-key>. For multi-user server-side integrations, you can also send X-On-Behalf-Of: <external-user-id>.
Schema definition for creating a reusable extraction template. Extraction schemas define the structure and validation rules for data extraction from files.
Name of the extraction schema. Must be between 1 and 100 characters. Used to identify and reference the schema.
1 - 100JSON Schema object defining the structure of data to extract. Specifies the fields, types, and validation rules for the extracted data.
Show child attributes
Optional description of the schema. Maximum 500 characters. Helps document the purpose and usage of the schema.
500Optional metadata for the schema. Can store additional information like version, author, or custom properties.
Show child attributes
Was this page helpful?