This is a demonstration showcasing the effectiveness of 'text-davinci-003' in simulating Turkish appointment requests using NLP. The service operates on port 3000, supports concurrent HTTP connections, and offers a single endpoint: /extract-intent.
- Node.js (version 12 or above)
- npm (Node Package Manager)
- Clone the repository:
git clone https://github.com/halilbrhmtrn/gpt-example.git
- Navigate to the project directory:
cd gpt-example
- Install the dependencies:
npm install
- Start the server:
npm run start
- The server will now be running and listening on port 3000.
To submit a message to the server, make a POST request to the /extract-intent endpoint. You should provide the message in the request body as JSON data with the message.
Example using cURL:
curl -X POST -H "Content-Type: application/json" -d "{\"message\": \"Ağustosun son haftası herhangi bir gün öğleden sonra 3'te müsait misiniz?\"}" http://localhost:3000/extract-intent
Run example test cases by:
npm run test