DirectExtractionRequest

Request parameters for direct extraction with an inline schema. Extracts structured data from a file according to the provided JSON Schema definition.

Example Usage

import { DirectExtractionRequest } from "@meetkai/mka1/models/components";

let value: DirectExtractionRequest = {
  model: "openai:gpt-4o",
  schema: {
    "type": "object",
    "properties": {
      "invoice_number": {
        "type": "string",
      },
      "total_amount": {
        "type": "number",
      },
      "date": {
        "type": "string",
      },
    },
  },
  file: "<value>",
};

Fields

Field	Type	Required	Description
model	string	✔️	ID of the model to use for extraction. You can use provider:model format or just the model name with a default provider. Vision-capable models are recommended for processing images and PDFs.
schema	components.Schema	✔️	JSON Schema object defining the structure of data to extract from the file. Can be provided as a JSON object or a JSON string (for FormData submissions). The model will extract data matching this schema structure.
metadata	components.DirectExtractionRequestMetadata	➖	Optional metadata providing additional context for the extraction. Can be a JSON object or JSON string. Use this to provide hints, domain knowledge, or additional instructions to improve extraction accuracy.
file	string	✔️	The file to extract structured data from. Supports various formats including images (PNG, JPG, etc.) and documents (PDF, etc.). The file content will be analyzed by the model.
prompt	string	➖	Optional custom system prompt to guide the extraction process. Use this to provide specific instructions about how to interpret the file or what to prioritize during extraction.