CONTEXT (NOV 2023): This application was originally developed before Code Interpreter was released by OpenAI so users could still have ChatGPT interact with their spreadsheets.
This application provides a simple interface for users to upload CSV files or spreadsheets, input a question, and receive an answer from GPT-4 about the data in the sheets. The application uses Express.js as the backend framework and EJS for server-side rendering of the views. The CSV file is previewed on the client side before being uploaded and analyzed by GPT-4.
These instructions will get you a copy of the project up and running on your local machine for development and testing purposes.
- Node.js
- npm
- Clone the repository:
git clone https://github.com/bijx/csv-analyzer-GPT.git- Install the dependencies:
cd csv-analyzer-GPT
npm install- Rename the
config.template.jsonfile in the root directory of the project toconfig.jsonand add your GPT-4 API key:
{
"OPENAI_AUTH": "your-api-key-here",
"GPT_MODEL": "gpt-4"
}Optionally, you can also choose which version of GPT you wish to use, as gpt-3.5-turbo is just as good at handling simple queries.
- Run the application:
npm start- Open your browser and navigate to
http://localhost:3000to access the application.
-
Navigate to the application's homepage.
-
Click the "CSV File" input field and select a CSV file.
-
Enter your question in the "Question" input field.
-
Click the "Upload" button to upload the CSV file and wait for an answer from GPT based on your question.
-
The application will display the analysis results on a new page.
- Express.js - The backend framework used
- EJS - Embedded JavaScript templating for server-side rendering
- Multer - Middleware for handling
multipart/form-data - Tailwind CSS - A utility-first CSS framework
This project is licensed under the MIT License - see the LICENSE for details.
- OpenAI for providing the GPT-4 API