Table

🤖 AI Drafted (Not reviewed)

Extract tables from images

Tool id	table_extract
Category	vision
Uses a language model	yes
Needs a generative model	yes
Runs over many items	yes
Item handling	batch
Structured output	yes
Human-verified	not yet

What it reads

Port	Type	Required	What it is
Files (files)	files	yes	Image files
Context (context)	any	no	Previous text/transcription
Metadata (metadata)	json	no	Existing metadata
Documents (documents)	json	no	Document metadata

What it emits

Port	Type	Required	What it is
Text (text)	text	—	Raw text response
Value (value)	any	—	Parsed value
Texts (texts)	array	—	Per-item texts
Values (values)	array	—	Per-item values
Results (results)	json	—	Full results
Records (records)	array	—	Per-document text records [{doc_id, text}, …].
Artifacts (artifacts)	json	—	Artifact IDs

Options

Option	Type	Default	What it does
choices	array	—	Valid choices. (Not shown in the editor.)
chunk_size_chars	integer	0	Chunk large input text above this character budget (0=auto).
force_ocr	boolean	no	Force image processing instead of existing text.
include_headers	boolean	yes	Detect header row.
match_mode	string	prefer	Match mode. One of: prefer, strict, inform.
max_image_dimension	integer	8192	Max image size.
max_items	integer	10	List max items.
max_tokens	integer	8192	Max response.
max_words	integer	50	Word limit.
metadata_field	string	—	Save to field.
model_name	string	—	Model name.
output_format	string	text	Response format. One of: text, boolean, choice, number, words, list, json.
output_style	string	csv	Table output format. One of: csv, json_rows, json_columns, markdown.
prompt	string	—	Custom prompt.
provider_name	string	—	LLM provider. One of: openai, anthropic, google, ollama, lmstudio, groq, together, deepseek, mistral, openrouter, dashscope, xai, perplexity, fireworks, deepl.
quality_gate	boolean	yes	Stop the run if output is unreadable.
reference_values	object	—	Known values to match. (Not shown in the editor.)
save_to_db	boolean	yes	Save to library.
save_to_file	boolean	no	Export to file.
temperature	number	0.7	Creativity.
thinking_mode	string	off	Chain-of-thought reasoning depth. One of: off, short, medium, long.
vision_mode	string	auto	Vision engine. ‘auto’ picks based on the resolved provider: apple → Apple Vision OCR; anything else → LLM vision path. One of: auto, apple, llm. (Not shown in the editor.)

The prompt it sends

This is what the tool asks a model, with every option left at its default. Changing the options above changes this text.

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.