🚀 Sentiment Analysis API - MLOps Project

A production-ready sentiment analysis API built with FastAPI, Hugging Face Transformers, and deployed using modern MLOps practices.

🎯 Features

• ✅ Real-time sentiment analysis using DistilBERT model
• ✅ RESTful API with FastAPI
• ✅ Dockerized application
• ✅ CI/CD pipeline with GitHub Actions
• ✅ Deployed on Render (free tier)
• ✅ Interactive API documentation (Swagger UI)

🛠️ Tech Stack

• Backend: Python 3.10, FastAPI
• ML Model: Hugging Face Transformers (DistilBERT)
• Containerization: Docker
• CI/CD: GitHub Actions
• Deployment: Render.com

🚀 Live Demo

API URL: https://your-app-name.onrender.com

Endpoints:

• GET / - Welcome message
• GET /health - Health check
• POST /predict - Sentiment prediction
• GET /docs - Interactive API documentation
• GET /examples - Example texts to test

📦 Local Setup

Prerequisites

• Python 3.10+
• Docker (optional)

Installation

1. Clone the repository:

git clone https://github.com/yourusername/sentiment-mlops.git
cd sentiment-mlops

2. Install dependencies:

pip install -r app/requirements.txt

3. Run the application:

cd app
python main.py

4. Open browser: http://localhost:8000/docs

Docker Setup

# Build image
docker build -t sentiment-mlops .

# Run container
docker run -p 8000:8000 sentiment-mlops

🧪 API Usage

cURL Example:

curl -X POST "http://localhost:8000/predict" \
     -H "Content-Type: application/json" \
     -d '{"text": "I love machine learning!"}'

Python Example:

import requests

response = requests.post(
    "http://localhost:8000/predict",
    json={"text": "This MLOps project is awesome!"}
)
print(response.json())

Response Format:

{
  "text": "I love machine learning!",
  "sentiment": "POSITIVE",
  "confidence": 0.9998,
  "model": "distilbert-base-uncased-finetuned-sst-2"
}

📊 MLOps Pipeline

1. Code Push → GitHub
2. Automated Testing → GitHub Actions
3. Docker Build → Containerization
4. Deployment → Render.com
5. Live API → Production

🎓 Skills Demonstrated

• Machine Learning model deployment
• API development with FastAPI
• Docker containerization
• CI/CD pipeline implementation
• Cloud deployment (Render)
• Git version control
• RESTful API design

📈 Future Improvements

• Add unit tests with pytest
• Implement API rate limiting
• Add authentication
• Support batch predictions
• Add model monitoring
• Implement A/B testing for models

👨‍💻 Author

Your Name

• GitHub: @yourusername
• LinkedIn: Your LinkedIn

📝 License

MIT License

---

⭐ If you found this project helpful, please give it a star!