Project Napkin is a knowledge-focused database API with AI agents. It is built with Rust and uses Actix-web for the web framework and PostgreSQL with pgvector for the database. The purpose of Project Napkin is to generate a standardized method of mapping out data for the AI agent using network graphs and vector databases. The goal is to more accurately describe the requirements or other information for the agent, promoting more accurate and efficient interactions with data.
These instructions will get you a copy of the project up and running on your local machine for development and testing purposes.
You will need to have the following installed on your machine:
git clone https://github.com/Z90-Studios/napkin.git
cd napkin
Create a PostgreSQL database and configure the connection string in your .env file.
DATABASE_URL=postgres://username:password@localhost/your_database
Then, set up the pgvector extension:
CREATE EXTENSION IF NOT EXISTS pgvector;
You can run the application with the following command:
cargo run
If you want hot reloading during coding, you can use:
cargo watch -x run
We would love for you to contribute to Project Napkin
and help make it even better than it is today! Check out our Contributing Guide to get started.
This project is licensed under the MIT License - see the LICENSE file for details.