Extract Table

🤖 AI Drafted (Not reviewed)

Detect and extract tabular data from each image/page using vision, emitting CSV you can paste into a spreadsheet. Feeds the spreadsheet (Table) representation in the document viewer. The output style and header handling are editable on the Table node.

Folder	/Extract
Steps	2
Tags	preset, table, extract, representation

Steps, in run order

1. Files

Tool: Files — Pass through input files from workflow context

2. Extract Table

Tool: Table — Extract tables from images

Settings this step uses:

Option	Value
include_headers	yes
output_style	csv

What this step asks the model:

Extract the table data from this image as CSV format.

The first row contains column headers.

Rules:
- Use comma as separator
- Wrap EVERY field in double quotes, without exception. A ledger column full
  of dates and comma'd lists produces ragged rows the moment quoting is
  optional, and the model is the only place that can get it right — nothing
  downstream can recover the column boundaries afterwards.
- Escape a literal double quote inside a field by doubling it ("")
- Every row must have exactly the same number of fields as the header row;
  emit "" for an empty cell rather than dropping it
- First row is the header row if one is visible
- One row per line

Return ONLY the CSV content, no code fences or explanations.

If the image contains no table, output exactly NO TABLE and nothing
else. That is a correct and complete answer — never invent rows to fill the
reply.

A table is data laid out in rows and columns as part of the DOCUMENT. It is not
a measuring ruler or scale bar laid beside the page, a colour calibration
chart, a strip of page or folio numbers, a margin, or any other photographic
furniture that belongs to the act of scanning rather than to the document.