All Posts

We explore the rise of agentic retrieval over vector indexing and how PageIndex can be used to build agentic RAG systems.

PageIndex OCR is the world's first OCR model that understands documents as a whole — preserving full structure and section hierarchy across pages, instead of treating each page as an independent unit.

We introduce Mafin2.5, which is built based on PageIndex, with a 98.7% accuracy rate on the finance industry question-answering benchmark.

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.