Climate-GPT is a chatbot that raises awareness of climate change in a nuanced way, serving all types of mass-customized mediums. Implemented by Qing Feng (Harvard GSD Mediums '23), this app is part of his MDes Open Project. Climate-GPT is built on top of OpenAI APIs for the chat, image generation, and voice transcription endpoints, and Eleven Labs APIs for sythesized speeches.
You can follow the instructions below to get set up. Also, check out our deployment here. Climate-GPT leverages OpenAI's GPT-3.5, Dall-e-2, and whisper-1 models.
-
If you don’t have Python installed, install it from here
-
Clone this repository
-
Navigate into the project directory
$ cd Climate-GPT
-
Create a new virtual environment
$ python -m venv venv $ . venv/bin/activate
-
Install the requirements
$ pip install -r requirements.txt
-
Make a copy of the example environment variables file
$ cp .env.example .env
-
Add your Open AI API key to the newly created
.env
file. Optionally, you can fill up other fields accordingly for full features. -
Run the app
$ flask run
You should now be able to access the app at http://localhost:5000!