https://github.com/litch/lnchat

https://github.com/litch/lnchat

Last synced: 3 months ago
JSON representation

• Host: GitHub
• URL: https://github.com/litch/lnchat
• Owner: litch
• Created: 2023-05-16T15:45:33.000Z (over 1 year ago)
• Default Branch: master
• Last Pushed: 2023-05-16T15:45:52.000Z (over 1 year ago)
• Last Synced: 2024-06-15T12:35:01.762Z (5 months ago)
• Language: Python
• Size: 85 KB
• Stars: 4
• Watchers: 1
• Forks: 2
• Open Issues: 1
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• awesome-ChatGPT-repositories - lnchat - So I built a thing - LNChat. You hook this app up to your node and then you can ask it plaintext questions like, "what is my newest channel", "show me a channel summary". ChatGPT bridges the gap. It's pretty fun, but not super useful. Yet. (NLP)

README

        
# LNChat - Lightning Node Management with ChatGPT

LNChat is a reckless experiment that combines the power of OpenAI's GPT-4 model with the capabilities of managing a Lightning node. 

## ⚠️ Warning: This is Reckless! ⚠️

This application directly executes the Python code generated by the GPT-4 model in response to your queries. While we've tried to ensure safety, there are no guarantees. There is a real risk that errors or malicious responses from the AI could cause you to lose funds.

**Use LNChat at your own risk. If you're not comfortable with this level of risk, do not use this application.**

## Prerequisites

- Python 3.6+

- Flask

- An OpenAI API key

- A Lightning node

## Installation

1. Clone the repository.

2. Install the dependencies with `pip install -r requirements.txt`.

3. Get ahold of your node's macaroon and cert (maybe from nodes.voltage.cloud/) and put them somewhere handy.

4. Copy the `.env.sample` to `.env` and fill in your environment variables.

5. Run the application with `python app.py`.

## Usage

1. Navigate to `http://127.0.0.1:5555` in your web browser.

2. Enter a query about managing your Lightning node. For example, "How many peers are connected to my node?"

3. Submit the query and view the response.

Remember, this application is #reckless. It's fun to experiment with, but use it responsibly and at your own risk.