Skip to main content
function extractStructuredDataFromContent(content, options): Promise<any>
Extracts structured data from content items (text or images).

​
Examples

import { extractStructuredDataFromContent } from "@intuned/sdk/ai-extractors";

const content = [
  { type: "text", data: "Sample text data" },
  {
    type: "image-url",
    image_type: "jpeg",
    data: "https://example.com/image.jpg"
  }
];

const options = {
  label: "extract_contact_info",
  dataSchema: {
    type: "object",
    properties: {
      name: { type: "string", description: "contact name" },
      phone: { type: "string", description: "contact info" }
    }
  },
  model: "gpt4-turbo"
};

const data = await extractStructuredDataFromContent(content, options);
console.log(data);

​
Parameters

• content: TextContentItem | ImageBufferContentItem | ImageUrlContentItem | (TextContentItem | ImageBufferContentItem | ImageUrlContentItem)[] The content items from which to extract the structured data. • options • options.dataSchema: ObjectSchema The JSON schema of the data you’re trying to extract. • options.label: string A label for this extraction process, used for billing and monitoring. • options.model: | "claude-3-opus" | "claude-3-sonnet" | "claude-3.5-sonnet" | "claude-3-haiku" | "gpt4-turbo" | "gpt-4o" | "gpt3.5-turbo" The model to use for extraction. • options.prompt?: string Optional. A prompt to guide the extraction process.

​
Returns

Promise<any> A promise that resolves to the extracted structured data.