aws-samples/sample-extreme-text-classifier

A Python text classifier for large-scale multi-class classification using Amazon Bedrock. Supports classification of 1000+ classes with LLM reranking and attribute validation.

46
/ 100
Emerging

This tool helps you automatically sort documents or text snippets into thousands of categories with high accuracy. You provide text (or PDF documents) and a list of your custom categories, and it outputs the best matching category along with a confidence score. It's ideal for anyone managing large volumes of varied text, like operations specialists, compliance officers, or data analysts.

Use this if you need to reliably classify a large number of texts or PDF documents into 1000+ distinct categories and want to ensure classifications meet specific business rules.

Not ideal if you only have a few dozen categories or don't require the advanced validation features for business-critical accuracy.

document-management information-extraction workflow-automation data-categorization compliance-automation
No Package No Dependents
Maintenance 10 / 25
Adoption 5 / 25
Maturity 15 / 25
Community 16 / 25

How are scores calculated?

Stars

10

Forks

6

Language

Python

License

MIT-0

Last pushed

Feb 14, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/aws-samples/sample-extreme-text-classifier"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.