embed.yml

name: Embed the transcripts and add to chroma

on:
  workflow_dispatch:
  schedule:
    # Let 5 minutes after download_transcripts.yml
    - cron: "46 23 * * 6"  # “At 23:46 on Saturday.”

env:
  HF_ACCESS_TOKEN: ${{ secrets.HF_ACCESS_TOKEN }}
  TALKING_PYTHON_ACCESS_TOKEN: ${{ secrets.TALKING_PYTHON_ACCESS_TOKEN }}

jobs:
  scheduled:
    runs-on: ubuntu-latest
    steps:
    - name: Check out this repo
      uses: actions/checkout@v3

    - name: Set up Python ${{ matrix.python-version }}
      uses: actions/setup-python@v4
      with:
        python-version: "3.10"
        cache: 'pip' # caching pip dependencies

    - name: Install dependencies
      run: |
        python -m pip install --upgrade pip
        pip install -r requirements/requirements_embed.txt
        pip install ./src

    - name: Run flow
      run: python flows/embed.py hugging_face release download

    - name: Commit and push if it changed
      run: |-
        git config user.name "Automated"
        git config user.email "actions@users.noreply.github.com"
        git add -A
        timestamp=$(date -u)
        git commit -m "embed transcript: ${timestamp}" || exit 0
        git push