← Back to Projects Content Classification

Text Classification API

FastAPI multi-class text classification service using fine-tuned DistilBERT and BERT on AG News, with model versioning and A/B testing infrastructure.

HuggingFace Transformers
DistilBERT
BERT
FastAPI
Docker

Overview

Production text classification API with model versioning and A/B testing for continuous improvement.

Architecture

  • Fine-tuned DistilBERT and BERT models
  • FastAPI serving with async inference
  • Model version management system
  • A/B testing infrastructure for model comparison
  • Comprehensive latency benchmarks

Key Features

  • Multi-model serving with version control
  • A/B testing for production model selection
  • Batch and single inference endpoints
  • Latency and throughput monitoring