name: Check Links

on:
  pull_request:
    branches:
      - main
  push:
    branches:
      - main
  schedule:
    - cron: "0 5 * * *"
  workflow_dispatch:

env:
  POETRY_VERSION: "1.7.1"

jobs:
  markdown-link-check:
    runs-on: ubuntu-latest
    steps:
      - name: Checkout code
        uses: actions/checkout@v4
      - name: Check links in Markdown files
        uses: gaurav-nelson/github-action-markdown-link-check@v1
        with:
          folder-path: 'examples/'
          file-path: './README.md'

  notebook-link-check:
    runs-on: ubuntu-latest
    steps:
      - name: Checkout code
        uses: actions/checkout@v4
      - name: Set up Python 3.x + Poetry ${{ env.POETRY_VERSION }}
        uses: "./.github/actions/poetry_setup"
        with:
          python-version: "3.11"
          poetry-version: ${{ env.POETRY_VERSION }}
          cache-key: core

      - name: Install dependencies
        shell: bash
        run: |
          python -m pip install --upgrade pip
          poetry install --with test
          poetry run pip install -U pytest pytest-check-links langsmith langchain GitPython
      - name: Check links in notebooks
        env:
          LANGCHAIN_API_KEY: test
          shell: bash
        run: poetry run pytest -o python_files=non_python_only --check-links --ignore="*.py" -k .ipynb --check-links-ignore "https://(api|web)\.smith\.langchain\.com/.*" --check-links-ignore "https://x.com/.*" ./examples