Classification

Classify text into predefined categories using fine-tuned transformer models. Useful for sentiment analysis, content moderation, and topic detection.

For full API reference (classify(), classifyMany(), options, result types, and custom providers), see the Core Classification guide.

See it in action

Try the Sentiment Analyzer block — it runs DistilBERT SST-2 sentiment on single inputs and large batches with throughput. Install it with npx shadcn add @localmode/ui/blocks/text-insights/sentiment-analyzer.

Recommended Models

Model	Size	Labels	Use Case
`Xenova/distilbert-base-uncased-finetuned-sst-2-english`	~67MB	POSITIVE/NEGATIVE	Sentiment analysis
`Xenova/twitter-roberta-base-sentiment-latest`	~125MB	Positive/Neutral/Negative	Social media sentiment
`Xenova/toxic-bert`	~110MB	Toxic/Non-toxic	Content moderation

Best Practices

Classification Tips

Choose task-specific models — Sentiment models work best for sentiment, not topic detection
Check allScores — Low confidence scores may indicate ambiguous input
Batch when possible — classifyMany() is more efficient than multiple classify() calls
Cache the model — Create the model instance once and reuse it

Composed Block

Block	Description	Links
Sentiment Analyzer	DistilBERT SST-2 sentiment on single inputs and large batches with throughput	Live · Install: `npx shadcn add @localmode/ui/blocks/text-insights/sentiment-analyzer`

Next Steps

Core Classification API

Full API reference, options, result types, and custom providers.

Zero-Shot Classification

Classify into arbitrary labels without fine-tuning.

NER

Extract named entities from text.