Sentiment Analysis with FastAPI and Transformers

Description

This project uses FastAPI to create a sentiment classification API based on Hugging Face's Transformers model. A front-end is developed with Streamlit to interact with the API.

Table of Contents

1. Installation
2. Interface
3. Usage

Installation

Prerequisites

• Python 3.6 or higher

Steps

1. Clone the repository:

git clone https://github.com/chrfsa/sentiments_analysis.git
cd sentiments_analysis

2. Create a virtual environment and activate it:

python -m venv venv
# On Windows
.\venv\Scripts\activate
# On macOS and Linux
source venv/bin/activate

3. Install dependencies:

pip install -r requirements.txt

4. Launch the FastAPI server:

   # with uvicorn
   uvicorn api:app --reload
   # with fastapi
   fastapi dev api.py
   

5. Launch the Streamlit application:

   streamlit run app.py
   

Usage

API

The FastAPI API exposes a /analysis endpoint for sentiment analysis. Send a POST request with JSON containing the text to be analyzed:

{
    “prompts”: “your text here”
}