https://github.com/mor10/basic-models-demo

https://github.com/mor10/basic-models-demo

Last synced: about 2 months ago
JSON representation

• Host: GitHub
• URL: https://github.com/mor10/basic-models-demo
• Owner: mor10
• Created: 2024-08-08T04:20:09.000Z (5 months ago)
• Default Branch: main
• Last Pushed: 2024-08-09T03:12:45.000Z (5 months ago)
• Last Synced: 2024-08-09T06:19:15.766Z (5 months ago)
• Language: Python
• Size: 19.5 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Basic GitHub Models Demo

Basic stand-alone Python AI weather app using [GitHub Models](https://docs.github.com/en/github-models/prototyping-with-ai-models) to leverage models from Mistral and OpenAI that pull and interpret data from OpenWeather's API.

## Connecting to OpenWeather

The app uses live weather data from OpenWeather, so to use the app you need a free [OpenWeather API key](https://home.openweathermap.org/api_keys).

To add the key, rename `.env-template` to `.env` and paste the key in the obvious space.

## Running the app in GitHub Codespaces

The app connects to GitHub Models using a GitHub Personal Access Token. If you use GitHub Codespaces,  you're already logged in and your authentication is handled automatically. To run the app:

1. Spin up a Codespace from the repo

2. Open terminal

3. Enter `python weather.py` and follow the instructions in the app.

## Running the app in a local editor

If you use a local clone in a stand alone editor or IDE, you need to add a GitHub Personal Access Token:

0. Make sure you have a local Python environment

1. Visit [https://github.com/settings/tokens](https://github.com/settings/tokens) and generate a new token with default settings

2. Copy the token (you only get to see it once)

3. To authenticate your connection, either:

   - add the token to your environment from bash using `export GITHUB_TOKEN=""`

   - add the token to the `.env` file with the name "GITHUB_TOKEN"

4. Open terminal

5. Install Python dependencies `pip install -r requirements.txt`

6. Enter `python weather.py` and follow the instructions in the app