This is a simple chatbot built on top of Prediction Guard's text generation capabilities.
In order to run this demo:
-
Create a Prediction Guard account and get an access token (as described here)
-
Install the Python requirements:
$ pip install -r requirements.txt
-
Export your Prediction Guard access token to an environmental variable:
$ export PREDICTIONGUARD_TOKEN=<your access token>
-
Run
configure.py
to setup the Prediction Guard endpoint for generating chat responses:$ python configure.py
-
Run
app.py
to start the demo locally:$ python app.py
-
Visit the link displayed to see the Gradio demo. It should be something like
http://127.0.0.1:7860
.