Finetuned Model API

Flask API for sentiment classification using Hugging Face's fine-tuned model.

Getting Started

Prerequisites

• Docker
• Python 3.8 or higher

Installing

1. Clone the repository:

   git clone https://github.com/pachecowillians/Finetuned-Model-API.git
   cd Finetuned-Model-API

2. Run the API:

   docker-compose up --build

   The API will be available at http://localhost:5000/api/classify.

3. Train the Model:

   python training/finetune_model.py

Running Tests with pytest

Using Docker

To run tests with Docker, make sure the Docker container is running. Then, execute the following command:

docker exec -it finetuned-model-api pytest app/tests

Local Testing

To run tests locally without Docker, follow these steps:

1. Install the required dependencies:

   pip install -r requirements.txt

2. Make sure the API is not running locally on port 5000.

3. Execute the following command to run the tests:

   pytest app/tests

This will run the tests using pytest locally.

API Endpoints

Classify Text

Endpoint:

POST /api/classify

Request:

{
  "text": "This is a positive example."
}

Response:

{
  "text": "This is a positive example.",
  "predicted_class": "positive",
  "class_probabilities": [0.013937118053436756, 0.9860628843307495]
}

Built With

• Flask - Web framework
• Hugging Face Transformers - Natural language processing library