Towards Data Science

Multi-Document RAG: A Folder of Unrelated PDFs Is One Long Document with a Nested Outline

The article discusses a method for handling a folder of unrelated PDFs as a single long document with a nested outline. It highlights that without shared fields, an index cannot be built, so the approach uses one summary line per file and each file’s own table of contents, with retrieval routes extending down two levels. This structure enables retrieval-augmented generation (RAG) across multiple documents.

Towards Data Science
6d ago

Parse the Folder, Not Just the PDFs: The Relational Tables RAG Needs on a Case File

The article discusses how Enterprise Document Intelligence should begin by parsing the folder structure rather than just PDFs, emphasizing that the index must reflect the case type’s requirements before any folder is accessed. It highlights that the two key questions to develop are not retrieval questions but rather focus on the relational tables needed for Retrieval-Augmented Generation (RAG) in a case file context.

By angela shi
Towards Data Science
5d ago

One Document Type, a Million Files: Structured Extraction into the SQL Table RAG Queries

The article discusses a case study in enterprise document intelligence where a single document type contains a million files. It outlines a workflow that takes about an hour with two people to extract six to ten structured fields, emphasizing the importance of identifying two key signals that distinguish a valid column from one that could break a filter later. The focus is on converting unstructured documents into a structured SQL table for Retrieval-Augmented Generation (RAG) queries.

By Angela and Kezhan Shi
Towards Data Science
Aug 20

Three Kinds of RAG Corpus, and What It Costs to Build for the Wrong One

The article explains that enterprise document intelligence can be categorized into three distinct corpus types, each requiring a specific architecture. It outlines how to determine the shape of a document collection through three key questions. The piece also discusses the costs associated with building a system for the incorrect corpus type.

By angela shi