nrcrews/bracket-picker

Uses LLMs to pick March Madness bracket winners.

Bracket Picker

Fill out a March Madness Bracket with a prompt.

Setup

If you don’t have Python installed, install it from here.

1. Clone this repository

2. Navigate into the project directory

   $ cd bracket-picker

3. Create a new virtual environment

   $ virtualenv virt
   $ source virt/bin/activate

4. Install the requirements

   $ pip install -r cli_requirements.txt

5. Make a copy of the example environment variables file

   $ cp .env.example .env

6. Add your OpenAI API key to the newly created .env file

CLI

1. Run the application

   $ ./cli.sh

Lambda Deployment

1. Build docker image

   $ docker build --platform linux/arm64 -t ${DOCKER_IMAGE} .

2. Run docker image

   $ docker run --platform linux/arm64 --env-file=.env -p 9000:8080 --name ${DOCKER_CONTAINER} ${DOCKER_IMAGE}

3. Test function

   $ curl -XPOST "http://localhost:9000/2015-03-31/functions/function/invocations" -d '{}'

4. Login to aws ecr

   $ aws ecr get-login-password --region ${AWS_REGION} | docker login --username AWS --password-stdin ${ACCOUNT_ID}.dkr.ecr.${AWS_REGION}.amazonaws.com

5. Create docker tag

   $ docker tag ${DOCKER_IMAGE}:latest ${ACCOUNT_ID}.dkr.ecr.${AWS_REGION}.amazonaws.com/${DOCKER_IMAGE_REPO}:latest

6. Push docker image

   $ docker push ${ACCOUNT_ID}.dkr.ecr.${AWS_REGION}.amazonaws.com/${DOCKER_IMAGE_REPO}:latest

For more information on deployments, refer to the deployment docs.

Contributing

All contributions are welcome! Reach out for more information.