🤖 Text Classifier API

A backend service built with FastAPI that classifies text sentiment into one of three categories: positive, negative, or neutral, using OpenAI LLMs.

This project is structured in a clean and scalable way, separating configuration, services, models, and routes.

---

✨ Features

• POST /classify → classify any text as positive, negative, or neutral.
• GET /health → health check endpoint (confirms API is running and OpenAI key is loaded).
• Automatic interactive documentation with Swagger UI (/docs) and ReDoc (/redoc).
• Modular architecture (services, models, routes) for scalability and testability.

---

📂 Project Structure

text-classifier-api/ ├─ app/ │ ├─ main.py # FastAPI entry point │ ├─ api/classify.py # Endpoints (routes) │ ├─ core/config.py # Settings and environment variables │ ├─ models/schemas.py # Request/response models (Pydantic) │ ├─ services/openai_client.py # OpenAI client loader │ ├─ services/classifier.py # Classification logic │ └─ init.py ├─ requirements.txt ├─ .env # API key (not committed) ├─ .gitignore └─ README.md

---

🛠️ Installation

1. Clone the repo

git clone https://github.com/IreHurtado/text-classifier-api.git
cd text-classifier-api

2. Create and activate a virtual environment

Ubuntu/macOS

python3 -m venv .venv
source .venv/bin/activate

Windows (PowerShell)

python -m venv .venv
.venv\Scripts\Activate.ps1

3. Install dependencies

pip install -r requirements.txt

4. Configure environment variables

Create a .env file in the root directory:

OPENAI_API_KEY=sk-xxxxxxxxxxxxxxxx

▶️ Run the server

Start the FastAPI app with Uvicorn:

uvicorn app.main:app --reload

The server will be available at:

Swagger docs → http://127.0.0.1:8000/docs

ReDoc docs → http://127.0.0.1:8000/redoc

📌 Usage Examples

Classify a text (Swagger UI)

Go to /docs, open POST /classify, click Try it out, and send:

{
  "text": "The service was excellent!"
}

Response:

{
  "text": "The service was excellent!",
  "category": "positive"
}

CURL Request

curl -X POST "http://127.0.0.1:8000/classify" \
     -H "Content-Type: application/json" \
     -d '{"text":"The product broke after 2 days"}'

Response:

{
  "text": "The product broke after 2 days",
  "category": "negative"
}

🧰 Tech Stack

• FastAPI
• Uvicorn
• OpenAI Python SDK
• pydantic-settings: for environment management

👩‍💻 Author

[Irene Hurtado] (https://github.com/IreHurtado)

📄 License

This project is licensed under the MIT License - you are free to use, copy, modify, and distribute this software with attribution.