This is a live understanding/ dry run stream where I’ll attempt to construct an AI-powered pipeline from scrape:
– Ingest and tidy ~ 100s blog site posts
– Generate embeddings with cost-free + API models
– Cluster into coherent subjects utilizing k-means
– Summarize articles and collections
– Publish every little thing in a quick, static Next.js website
This isn’t a sleek tutorial– it’s me functioning it out step by action, so you see the real process (debugging included). If you desire to learn along with me, Perfect.