jaedukseo / rhyme_with_ai_1 Goto Github PK

Create a conda virtual environment and activate it:

conda env create --file environment.yml
conda activate rhyme-with-ai

Install the rhyme_with_ai package and all its dependencies:

pip install --editable .

Download the weights of the models (if you get any errors, make sure these align with those specified in app/app.py)):

make download-data

Run the app:

make streamlit

Test the Docker containers by running:

make docker-build
make docker-serve

This project uses black for code formatting. To incorporate it in your version control follow the instructions below (copied from black's own readme):

Use pre-commit. Once you have it installed, add this to the .pre-commit-config.yaml in your repository:

repos:
-   repo: https://github.com/ambv/black
    rev: stable
    hooks:
    - id: black
      language_version: python3.7

Then run pre-commit install and you're ready to go.

Follow Google's documentation to set up Custom Runtimes in the App Engine Flexible Environment. Deploy the app:

gcloud app deploy

And you're done!

• Integrate TokenWeighter in the RhymeGenerator.
• Don't block on model loading or rhyme mutations (use API?).