Extract Tables

This procedure extracts a table from a source, such as a document or file.

Before using this procedure, ensure you have learned the Document Processing Book in your agent. After learning the Book, make sure to publish your Agent and create a new Playground for it to take effect.

Syntax

extract a table from {source}
   the description is "{description}"
   the creativity is {creativity}
   the openai model is "{model}"
   the gemini model is "{gemini model}"
   the visual reference is {visual reference}
   the extraction mode is "{extraction mode}"

Inputs

Required

1. source

   • A variable to represent the information source to extract a table from.

   • Examples: document, file, text

2. description

   • A description of the table to be extracted.

Optional

1. creativity

   • A number that controls the creativity of the response. Higher values produce more creative responses.

   • Default: 0.0

   • Range: 0.0-2.0.

2. model

   • The OpenAI model to use to generate the response.

   • Default: gpt-4o-latest

3. gemini model

   • Specifies the Gemini model to use to generate the response.

   • A model must be specified when using this field; no default is set.

   • Example: gemini-2.5-pro

4. visual reference

   • A variable to represent a document or image that serves as a visual reference, helping GPT enhance its accuracy. This refers to data defined earlier in the automation.

   • Examples the file, the document, the text

5. extraction mode

   • A string that represents the accuracy as it sends location data to GPT

   • Allowed Values: precise

Example

extract a table from the document
  the openai model is "gpt-4o"
  the visual reference is the document
  the extraction mode is "precise"
  the description is "The table has invoice number, date and amount. the amount should not have the currency
  in it. Keep only the first 4 digits of the invoice number. It has only one row of data."