Skip to main content
POST
/
api
/
v1
/
llm
/
extract
/
schema
Typescript (SDK)
import { SDK } from "@meetkai/mka1";

const sdk = new SDK({
  bearerAuth: "<YOUR_BEARER_TOKEN_HERE>",
});

async function run() {
  const result = await sdk.llm.extract.createSchema({
    extractionSchema: {
      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",
      },
    },
  });

  console.log(result);
}

run();
{
  "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"
  }
}

Authorizations

​
Authorization
string
header
required

Authenticate with your MKA1 API key at the API gateway: Authorization: Bearer <mka1-api-key>. For multi-user server-side integrations, also send X-On-Behalf-Of to identify the end user making the request.

Headers

​
X-On-Behalf-Of
string

Optional external user identifier for multi-user server-side integrations. Use this when acting on behalf of one of your end users.

Body

application/json

Schema definition for creating a reusable extraction template. Extraction schemas define the structure and validation rules for data extraction from files.

​
name
string
required

Name of the extraction schema. Must be between 1 and 100 characters. Used to identify and reference the schema.

Required string length: 1 - 100
​
schema
object
required

JSON Schema object defining the structure of data to extract. Specifies the fields, types, and validation rules for the extracted data.

​
description
string

Optional description of the schema. Maximum 500 characters. Helps document the purpose and usage of the schema.

Maximum string length: 500
​
metadata
object

Optional metadata for the schema. Can store additional information like version, author, or custom properties.

Response

200 - application/json

OK

Response from creating a new extraction schema.

​
success
boolean
required

Indicates whether the schema creation was successful

​
data
object
required

The created extraction schema with generated ID and timestamps