text/README.md

API Documentation: Text Sentiment Analysis

This API uses a fine-tuned GPT-3.5-turbo model to predict the sentiment of a given text. It accepts a short paragraph and returns the predicted sentiment (positive, negative, or neutral). Run python .\test.py to start the FastAPI server in http://0.0.0.0:8000.

---

Base URL

http://0.0.0.0:8000

---

Endpoints

1. Predict Sentiment

This endpoint accepts a short paragraph of text and returns the predicted sentiment.

• Endpoint: POST /predict-sentiment/
• Request Body:

  {
    "text": "I absolutely loved the product! It exceeded all my expectations."
  }
  

• Response:
  • Success (200 OK):

    {
      "sentiment": "positive"
    }
    

  • Error (500 Internal Server Error):

    {
      "detail": "Error message describing the issue."
    }
    

---

Example Usage

Request

curl -X POST "http://0.0.0.0:8000/predict-sentiment/" \
-H "Content-Type: application/json" \
-d '{"text": "I absolutely loved the product! It exceeded all my expectations."}'

Response

{
  "sentiment": "positive"
}

---

Notes

• The API uses a fine-tuned GPT-3.5-turbo model for sentiment analysis.
• The text field in the request body should contain a short paragraph.
• The response will always include a sentiment field with one of the following values: positive, negative, or neutral.
• Replace value of the api_key parameter with the actual OpenAI key