Towards Data Science August 25, 2026 By Angela and Kezhan Shi

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

Read the original on Towards Data Science →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Towards Data Science.

Towards Data Science

Aug 22

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.

By angela shi

rag

Towards Data Science

Jun 10

Beyond extract_text: The Two Layers of a PDF That Drive RAG Quality

Enterprise Document Intelligence [Vol. 1 #5A] - Document signals (metadata, native TOC, source software) and page-level content (text vs scans, tables, images, columns, page profile) The post Beyond extract_text: The Two Layers of a PDF That Drive RAG Quality appeared first on Towards Data Science .

By Kezhan Shi

rag

Towards Data Science

Jun 24

Anchor Detection for RAG: Parallel Detectors, Then One LLM Call at the End

Enterprise Document Intelligence [Vol. 1 #7B] - Retrieval is filtering on structured tables: keywords first, TOC second, embeddings last The post Anchor Detection for RAG: Parallel Detectors, Then One LLM Call at the End appeared first on Towards Data Science .

By angela shi

llms rag

Towards Data Science

Aug 21

Retrieve One Row from a Table, Not the Whole Table: Row-Level Chunks for RAG

Enterprise Document Intelligence [Vol. 1 #7sexies] - The unit of retrieval doesn’t have to be a page or a paragraph.

By Kezhan Shi

rag

Towards Data Science

Jun 24

Finding the right anchors for RAG: keyword, embedding, and TOC signals in parallel

Enterprise Document Intelligence [Vol. 1 #7B] - Retrieval is filtering on structured tables: keywords first, TOC second, embeddings last The post Finding the right anchors for RAG: keyword, embedding, and TOC signals in parallel appeared first on Towards Data Science .

By angela shi

rag

Towards Data Science

Jul 7

A Production RAG Pipeline for PDFs: Relational Parsing, TOC Retrieval, Typed Answers

Enterprise Document Intelligence [Vol. 1 #9A] - Same paper, same question as Article 1.

By angela shi

rag

One email a morning, machine-written

Related stories

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

Beyond extract_text: The Two Layers of a PDF That Drive RAG Quality

Anchor Detection for RAG: Parallel Detectors, Then One LLM Call at the End

Retrieve One Row from a Table, Not the Whole Table: Row-Level Chunks for RAG

Finding the right anchors for RAG: keyword, embedding, and TOC signals in parallel

A Production RAG Pipeline for PDFs: Relational Parsing, TOC Retrieval, Typed Answers