Towards Data Science September 3, 2026 By Kezhan Shi

Tables in PDFs for RAG: Don’t Flatten the Grid

Read the original on Towards Data Science →

The article titled "Tables in PDFs for RAG: Don’t Flatten the Grid" discusses Enterprise Document Intelligence, presenting a diagnostic and five composable operations rather than a decision tree. It appears in the Vol.1 #B4 issue of the publication and was first posted on Towards Data Science.

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

Jun 11

Stop Returning Flat Text from a PDF: The Relational Tables RAG Needs

Enterprise Document Intelligence [Vol. 1 #5B] - One PDF in, a relational set of DataFrames out: lines, pages, TOC, images, cross-references, captions, spans, and a parsing summary The post Stop Returning Flat Text from a PDF: The Relational Tables RAG Needs appeared first on Towards Data Science .

By Kezhan Shi

rag

Towards Data Science

Jun 13

Parse PDFs for RAG Locally with Docling: Rich Tables, No Cloud Upload

Enterprise Document Intelligence [Vol. 1 #5ter] - Table cells, OCR, captions, headings: cloud-grade structure, running on your own machine.

By Kezhan Shi

rag computer-vision

Towards Data Science

Jun 21

Reconstructing the Table of Contents a PDF Forgot to Ship, So RAG Can Scope by Section

Enterprise Document Intelligence [Vol. 1 #5septies] - When a PDF prints a contents page but exposes no outline, two ways to turn it back into structure, plus the page-alignment step everyone forgets The post Reconstructing the Table of Contents a PDF Forgot to Ship, So RAG Can Scope by Section appeared first on Towards Data Science .

By Kezhan Shi

rag safety

Towards Data Science

Jun 12

When PyMuPDF Can’t See the Table: Parse PDFs for RAG with Azure Layout

Enterprise Document Intelligence [Vol. 1 #5bis] - The same relational tables.

By Kezhan Shi

rag computer-vision

Towards Data Science

Jun 11

Stop Returning Flat Text from a PDF: The Relational Shape RAG Needs

Enterprise Document Intelligence [Vol. 1 #5B] - One PDF in, a relational set of DataFrames out: lines, pages, TOC, images, cross-references, captions, spans, and a parsing summary The post Stop Returning Flat Text from a PDF: The Relational Shape RAG Needs appeared first on Towards Data Science .

By Kezhan 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

One email a morning, machine-written

Related stories

Stop Returning Flat Text from a PDF: The Relational Tables RAG Needs

Parse PDFs for RAG Locally with Docling: Rich Tables, No Cloud Upload

Reconstructing the Table of Contents a PDF Forgot to Ship, So RAG Can Scope by Section

When PyMuPDF Can’t See the Table: Parse PDFs for RAG with Azure Layout

Stop Returning Flat Text from a PDF: The Relational Shape RAG Needs

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