Skip to content

README.MD

Latest commit

 

History

History
47 lines (35 loc) · 1.61 KB

README.MD

File metadata and controls

47 lines (35 loc) · 1.61 KB

FastAPI OpenAI Matcher

This is a FastAPI application that utilizes OpenAI's GPT-3 to match columns from two DataFrames based on their similarity. It provides an API endpoint for matching columns in two DataFrames.

How to Use

Running the Application Locally

  1. Clone this repository to your local machine:

    git clone https://github.com/Assetoni03/OpenAI_API

  2. Start the FastAPI application:

    uvicorn app:app --host 0.0.0.0 --port 8000

  3. The FastAPI application should now be running locally. You can access it at http://localhost:8000.

    Using the API

    Endpoint: /upload/

    • Method: POST
    • Description: Upload two DataFrames and an OpenAI API key to match columns based on their similarity.
    Request
    • table_a: The first DataFrame in JSON format.
    • table_b: The second DataFrame in JSON format.
    • api_key: Your OpenAI GPT-3 API key as a string.

Docker Usage

  1. Build the Docker image: 
    docker build -t fastapi-openai-matcher .
  2. Run the Docker container: 
    docker run -p 8000:8000 fastapi-openai-matcher
  3. The FastAPI application will be accessible at http://localhost:8000 within the Docker container.

OpenAI API

- You will need to sign up for an OpenAI GPT-3 API key to use this application. Replace "your_openai_api_key_here" with your actual API key.

Disclaimer

- This application is for demonstration purposes only. Ensure that you are in compliance with OpenAI's terms of use when using their API.