ci[minor]: Add GitHub action to check broken links

.github/workflows/link_check.yml

@@ -0,0 +1,57 @@
+name: Check Docs & Links
+
+on:
+  push:
+    branches: ["main"]
+  pull_request:
+    paths:
+      - '**.ipynb'
+  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
+        with:
+          fetch-depth: 0
+
+      - name: Check links in Markdown files
+        uses: gaurav-nelson/github-action-markdown-link-check@v1
+        with:
+          folder-path: "examples/,docs/"
+          check-modified-files-only: ${{ github.event_name != 'schedule' }}
+          file-path: "./README.md"
+          config-file: "./.markdown-link-check.config.json"
+
+  notebook-link-check:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Node.js
+        uses: actions/setup-node@v3
+        with:
+          node-version: '16.x'
+          cache: 'yarn'
+
+      - name: Install dependencies
+        run: |
+          yarn install --frozen-lockfile
+
+      - name: Get changed files
+        id: changed-files
+        uses: tj-actions/changed-files@v35
+
+      - name: Check links in notebooks
+        env:
+          CHANGED_FILES: ${{ steps.changed-files.outputs.all_changed_files }}
+        run: |
+          yarn check-links

.markdown-link-check.config.json

@@ -0,0 +1,4 @@
+{
+  "aliveStatusCodes": [200, 206, 402],
+  "ignorePatterns": ["*dcbadge.vercel.app*"]
+}

examples/how-tos/breakpoints.ipynb

@@ -58,7 +58,7 @@
     "\n",
     "Below, we do two things:\n",
     "\n",
-    "1) We specify the [breakpoint](https://langchain-ai.github.io/langgraph/concepts/low_level/#breakpoints) using `interruptBefore` the specified step.\n",
+    "1) We specify the [breakpoint](https://langchain-ai.github.io/langgraph/concepts/low_level/#breakpoints2) using `interruptBefore` the specified step.\n",
     "\n",
     "2) We set up a [checkpointer](https://langchain-ai.github.io/langgraphjs/concepts/#checkpoints) to save the state of the graph."
    ]

package.json

@@ -28,7 +28,8 @@
     "test:exports:docker": "docker compose -f environment_tests/docker-compose.yml up --force-recreate",
     "format": "turbo run format",
     "format:check": "turbo run format:check",
-    "release": "node scripts/release_workspace.cjs --workspace"
+    "release": "node scripts/release_workspace.cjs --workspace",
+    "check-links": "node scripts/check-links.cjs"
   },
   "author": "LangChain",
   "license": "MIT",
@@ -41,6 +42,8 @@
     "cheminfo-types": "^1.4.0",
     "d3": "^7.9.0",
     "esm-hook": "^0.1.4",
+    "linkinator": "^4.0.5",
+    "markdown-link-check": "^3.10.3",
     "readline": "^1.3.0",
     "release-it": "^17.6.0",
     "semver": "^7.6.3",
@@ -59,5 +62,8 @@
   "publishConfig": {
     "access": "public",
     "registry": "https://registry.npmjs.org/"
+  },
+  "dependencies": {
+    "linkinator": "^6.1.1"
   }
 }

scripts/check-links.cjs

@@ -0,0 +1,30 @@
+const { execSync } = require('child_process');
+
+const ignorePatterns = [
+  'https://(api|web)\\.smith\\.langchain\\.com/.*',
+  'https://x\\.com/.*'
+];
+
+function checkLinks() {
+  const changedFiles = process.env.CHANGED_FILES ? process.env.CHANGED_FILES.split(' ') : [];
+  const ipynbFiles = changedFiles.filter(file => file.endsWith('.ipynb'));
+
+  console.log('Changed .ipynb files:', ipynbFiles);
+
+  if (ipynbFiles.length === 0) {
+    console.log('No .ipynb files were changed. Skipping link check.');
+    return;
+  }
+
+  for (const file of ipynbFiles) {
+    console.log(`Checking links in ${file}`);
+    try {
+      execSync(`yarn linkinator ${file} ${ignorePatterns.map(pattern => `--skip "${pattern}"`).join(' ')}`, { stdio: 'inherit' });
+    } catch (error) {
+      console.error(`Error checking links in ${file}:`, error);
+      process.exit(1);
+    }
+  }
+}
+
+checkLinks();