bfpill/Gekko

openAI whisper linked to langchain and then ported to notion - Listens to conversations, decides if they are important or not, and then adds the conversations to a Notion database

Currently in POC stage.

Gekko

This project uses Open AI whisper, Langchain, and the Notion API. Below you will find all the necessary steps to get the project up and running on your local machine.

Getting Started

To get a local copy up and running, follow these simple steps:

1. Fork the repository

Click on the "Fork" button in the upper right corner of this repository's page to create a copy of this project in your own GitHub account.

2. Clone the repository

After you have forked the repository, you can make a clone on your local machine by using the following command:

git clone https://github.com/<Your GitHub Username>/Gekko.git

3. Add Your Notion ENV Variables

Create a new file in the root directory of the project named .env. Here, you'll add your Notion environment variables. It should look something like this:

NOTION_API_KEY=your-notion-api-key

Please replace your-notion-api-key with your actual Notion API key.

Starting the Servers

Notion Manager API

The Notion Manager API is used to interact with Notion. To start the Notion Manager API, use the following commands:

cd frontend
yarn run dev

This will start the server at http://localhost:3000.

Gekko

Gekko is a Python-based application. To start Gekko, use the following commands:

cd gekko
python -m app

This will start the server at http://127.0.0.1:8000.

Starting the Project

To start the project, make a POST request to the following endpoint:

http://127.0.0.1:8000/gekko/start

This will start whisper in real time, add text to the queue, run your conversation past the AI, and then add to notion.

---

Thank you for using this project. If you encounter any issues or have any questions, feel free to open an issue. Happy coding!