zerolabel

Zero-shot classification made ridiculously simple

✨ What if you could classify anything without training models?

import { classify } from 'zerolabel';

const results = await classify({
  texts: ['I love this product!'],
  labels: ['positive', 'negative', 'neutral'],
  apiKey: process.env.INFERENCE_API_KEY
});

// Done. No training, no datasets, no complexity.

That's it. Text, images, or both. Any labels you want. Results in milliseconds.

🤔 The Problem

Building classification usually means:

• ❌ Collecting thousands of labeled examples
• ❌ Training models for hours/days
• ❌ Managing ML infrastructure
• ❌ Retraining when you need new categories

zerolabel solves this in one line of code.

🤔 The Solution

import { classify } from 'zerolabel';

// Classify anything, instantly
const results = await classify({
  texts: ['I love this product!'],
  labels: ['positive', 'negative', 'neutral'],
  apiKey: process.env.INFERENCE_API_KEY
});

console.log(results[0].predicted_label); // 'positive'

That's it. No training, no infrastructure, no complexity.

⚡ Installation

npm install zerolabel

🚀 Examples

Text Classification

await classify({
  texts: ['Amazing product!', 'Worst purchase ever', 'It\'s okay'],
  labels: ['positive', 'negative', 'neutral'],
  apiKey: process.env.INFERENCE_API_KEY
});

Image Classification

await classify({
  images: ['data:image/jpeg;base64,...'],
  labels: ['cat', 'dog', 'bird'],
  apiKey: process.env.INFERENCE_API_KEY
});

Both Together (Multimodal)

await classify({
  texts: ['Check out this cute animal!'],
  images: ['data:image/jpeg;base64,...'],
  labels: ['cute cat', 'cute dog', 'not cute'],
  apiKey: process.env.INFERENCE_API_KEY
});

Custom Categories

await classify({
  texts: ['Fix login bug', 'Add dark mode', 'Server is down!'],
  labels: ['bug_report', 'feature_request', 'incident'],
  apiKey: process.env.INFERENCE_API_KEY
});

🎯 Real-World Use Cases

🏗️ How It Works

1. You provide: Text/images and your custom labels
2. We handle: The AI model (Google Gemma 3-27B), prompting, and inference
3. You get: Instant predictions with confidence scores

Powered by inference.net infrastructure

📊 Response Format

[
  {
    "text": "I love this product!",
    "predicted_label": "positive", 
    "confidence": 95.2,
    "probabilities": {
      "positive": 0.952,
      "negative": 0.048
    }
  }
]

🔧 Configuration

import { ZeroLabelClient } from 'zerolabel';

const client = new ZeroLabelClient({
  apiKey: process.env.INFERENCE_API_KEY,
  maxRetries: 3
});

const results = await client.classify({
  texts: ['Hello world'],
  labels: ['greeting', 'question']
});

🔑 Getting Your API Key

1. Sign up at inference.net
2. Get your API key from the dashboard
3. Set it as INFERENCE_API_KEY environment variable

export INFERENCE_API_KEY="your-key-here"

💡 Why zerolabel?

🌟 Live Demo

Try it yourself: zerolabel.dev

📚 API Reference

classify(options)

*At least one of texts or images is required

🛠️ TypeScript Support

Full TypeScript definitions included:

import type { 
  ClassificationInput, 
  ClassificationResult,
  ZeroLabelConfig 
} from 'zerolabel';

❓ FAQ

Q: What models does this use?
A: Google Gemma 3-27B, optimized for classification tasks.

Q: How accurate is it?
A: Comparable to fine-tuned models for most classification tasks, especially with descriptive labels.

Q: Can I use custom models?
A: No, we use inference.net's infrastructure with optimized models for best performance.

Q: Is there a rate limit?
A: Limits depend on your inference.net plan.

🤝 Contributing

Issues and PRs welcome! See our GitHub repo.

📄 License

MIT - Use it however you want!