Research

PageIndex is a vectorless, reasoning-based retrieval framework that simulates how human experts extract knowledge from complex documents. Instead of relying on vector similarity search, it builds a tree-structured index from documents and enables LLMs to perform agentic reasoning over that structure for context-aware retrieval. The retrieval process is traceable and interpretable, and requires no vector DBs or chunking.

We introduce Model Augmented Fine-tuning (Mafin) — a novel approach for fine-tuning a black-box embedding model by augmenting it with a trainable embedding model.

We propose a practical acquisition function for prompt/completion pairs based on the predictive entropy of the language model and a measure of certainty of the implicit preference model optimized by DPO.