docs[minor]ci[minor]: Add script & CI to check recurring links daily (l…

…angchain-ai#19100)

.github/workflows/check-broken-links.yml

@@ -0,0 +1,21 @@
+name: Check Broken Links
+
+on:
+  workflow_dispatch:
+  schedule:
+    - cron:  '0 13 * * *'
+
+jobs:
+  check-links:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Use Node.js 18.x
+        uses: actions/setup-node@v3
+        with:
+          node-version: 18.x
+          cache: "yarn"
+      - name: Install dependencies
+        run: cd ./docs && yarn install --immutable --mode=skip-build
+      - name: Check broken links
+        run: cd ./docs && yarn check-broken-links

docs/package.json

@@ -18,7 +18,8 @@
     "format": "prettier --write \"**/*.{js,jsx,ts,tsx,md,mdx}\"",
     "format:check": "prettier --check \"**/*.{js,jsx,ts,tsx,md,mdx}\"",
     "gen": "yarn gen:supabase",
-    "gen:supabase": "npx supabase gen types typescript --project-id 'xsqpnijvmbodcxyapnyq' --schema public > ./src/supabase.d.ts"
+    "gen:supabase": "npx supabase gen types typescript --project-id 'xsqpnijvmbodcxyapnyq' --schema public > ./src/supabase.d.ts",
+    "check-broken-links": "bash vercel_build.sh && node ./scripts/check-broken-links.js"
   },
   "dependencies": {
     "@docusaurus/core": "2.4.3",
@@ -38,6 +39,7 @@
   },
   "devDependencies": {
     "@babel/eslint-parser": "^7.18.2",
+    "@langchain/scripts": "^0.0.9",
     "docusaurus-plugin-typedoc": "next",
     "dotenv": "^16.4.5",
     "eslint": "^8.19.0",

docs/scripts/check-broken-links.js

@@ -0,0 +1,7 @@
+// Sorry py folks, gotta be js for this one
+const { checkBrokenLinks } = require("@langchain/scripts/check_broken_links");
+
+checkBrokenLinks("docs", {
+  timeout: 10000,
+  whitelist: ["microsoft.com"],
+});