How PageIndex Actually Works — A Technical Deep Dive

No embeddings. No vector databases. Just an LLM reading a smart map of your document. Here’s exactly how. I published a piece last week about why I stopped using vector databases for document RAG. A lot of you asked the same question in the comments: “Okay, but how does it actually work under the hood?” Fair. So let’s go deep. This is a full technical breakdown of PageIndex - the tree-building process, the query mechanism, the two-LLM-call architecture, and the three things it does that vectors simply cannot. If you read this and want to build it yourself, you’ll have everything you need.