Insights

The same bet behind both PageIndex and Claude Code: skip the vector DB and let the LLM itself drive retrieval. We explore the rise of agentic retrieval over vector indexing and PageIndex's agentic, vectorless RAG framework. Where Claude Code retrieves over a codebase with simple bash tools instead of a vector database, PageIndex gives long documents an in-context tree index that an LLM agent navigates by reasoning — no chunking, embeddings, or vector store.

We argue that context blindness — the inability of vector-based retrieval to condition on full conversational and reasoning context — is a fundamental limitation of vector RAG, and outline a paradigm shift from semantic similarity to context-dependent relevance classification. In this view, retrieval becomes a relevance decision made by an LLM with full context, scaled efficiently through hierarchical tree search.

We examine the inherent limitations of OCR from an information-theoretic perspective and show why a direct, vision-based approach with PageIndex is more effective. Because flattening a 2D page into a 1D text sequence is inherently lossy, PageIndex acts as a vectorless retrieval layer that selects the relevant pages of a long document, which a VLM then reads directly as images.