npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2024 – Pkg Stats / Ryan Hefner

@dmitryrechkin/data-extractor

v1.0.1

Published

**Data Extractor is a TypeScript library designed to facilitate the extraction of structured data from text using AI and schema validation.** This library leverages AI models and Zod schemas to accurately parse and validate data from input text.

Downloads

1

Readme

Data Extractor

Data Extractor is a TypeScript library designed to facilitate the extraction of structured data from text using AI and schema validation. This library leverages AI models and Zod schemas to accurately parse and validate data from input text.

Installation

Install the package using pnpm:

pnpm add @dmitryrechkin/data-extractor

Features

  • AI-Powered Extraction: Utilizes AI models to extract structured data from unstructured text.
  • Schema Validation: Ensures extracted data conforms to a defined Zod schema.
  • Error Handling: Provides detailed error types including validation errors, parsing errors, and unknown errors.

Usage

Setting Up AI Data Extraction

import { z } from 'zod';
import { createOpenAI } from '@ai-sdk/openai';
import { AiDataExtractor } from '@dmitryrechkin/data-extractor';

// Set up the AI provider and model
const aiProvider = createOpenAI({
	apiKey: process.env.OPENAI_API_KEY!,
	compatibility: 'strict'
});
const aiModel = process.env.OPENAI_MODEL!;

// Define the schema for the expected data structure
const schema = z.object({
	name: z.string().describe('Full name of the person'),
	date: z.string().describe('Date converted to Y-m-d format'),
	fromTime: z.string().describe('Time in 24 hour format'),
	toTime: z.string().describe('Time in 24 hour format')
});

// Create an instance of AiDataExtractor with the schema
const extractor = new AiDataExtractor<typeof schema>(aiProvider, aiModel, schema);

Extracting Data from Text

const input = 'Hi, my name is John Doe. I would like to book a room for 2024-08-15 from 10:00 AM until 2:00 PM.';

// Extract data using the AI extractor
const result = await extractor.extract(input);

console.log(result);
// Output: { name: 'John Doe', date: '2024-08-15', fromTime: '10:00', toTime: '14:00' }

Handling Errors

The AiDataExtractor handles errors that may occur during data extraction. Errors are returned as objects containing a type and message:

import { EnumDataExtractorErrorType } from '@dmitryrechkin/data-extractor';

const result = await extractor.extract('Invalid input data');

if ('type' in result) {
    switch (result.type) {
        case EnumDataExtractorErrorType.VALIDATION_ERROR:
            console.error('Validation Error:', result.message);
            break;
        case EnumDataExtractorErrorType.PARSE_ERROR:
            console.error('Parse Error:', result.message);
            break;
        default:
            console.error('Unknown Error:', result.message);
    }
}

When to Use

This library is ideal for projects that require extracting structured data from unstructured text, such as:

  • Data Parsing Pipelines: Automatically parse and validate data from textual inputs.
  • AI-Driven Applications: Use AI models to intelligently extract relevant information from user inputs.
  • Schema Validation: Ensure data extracted from text meets your application’s requirements.

Installation & Setup

Install the package using pnpm:

pnpm add @dmitryrechkin/data-extractor

Ensure that your project is set up to handle TypeScript and supports ES modules, as this library is built with modern JavaScript standards.

Contributing

Contributions are welcome! Feel free to fork this project and submit pull requests. Before submitting, please ensure your code passes all linting and unit tests.

You can run unit tests using:

pnpm test