Cleaning, Validation, calculation Blocks

Welcome to your comprehensive support page for Docsumo’s Field Setup! This guide will walk you through the process of using AI-powered, plain-English prompts to extract, transform, and validate data from documents—no coding required.

Video

Overview

Docsumo’s Field Setup allows you to:

• Create extraction rules using natural-language prompts
• Normalize, calculate, and validate document data with AI
• Test and iterate your rules instantly before production

Key Features & Prompt Examples

1. No-Code Extraction with Natural Language

Define what you want to extract in everyday English.
Prompt Examples:

• Extract the "Invoice Number" and "Invoice Date" from the document.
• Find and extract the "Customer Name" and "Total Amount Due".
• Extract all line items including "Description", "Quantity", and "Unit Price".

📘

More detail: Extraction block and best practices

2. Cleaning

Standardize data to fit your database conventions, even if vendors use different formats.

Prompt Examples:

• Normalize all variations of vendor names such as "Acme Corp", "ACME CORPORATION", or "Acme Co." to "ACME CORP".
• Convert all dates to the YYYY-MM-DD format.
• Map payment terms like "Net 30", "30 days", and "Due in 30" to "Net 30".

3. Calculations

Let Docsumo compute values on the fly, directly from your documents.
Prompt Examples:

• Calculate the total sum of all {{field name}} and extract as {{file name}}.
• Extract all {{field name}} values and calculate the average.
• Sum all {{field name}} across the invoice and output as {{field name}}.

4. Validation

Ensure extracted data meets your requirements before further processing.
Prompt Examples:

• Validate that the "Account Number" field contains exactly 11 digits.
• Check if "Invoice Date" is not later than "Due Date".
• Ensure "Total Amount" is a positive number and not blank.

5. Instant Testing & Iteration

Test your prompts and see the results immediately. Adjust as needed for accuracy.
Prompt Examples:

• Extract "PO Number" and validate it starts with "PO-" followed by 6 digits.
• Test extraction of "Vendor Email" and ensure it matches a valid email format.

Best Practices & Tips

• Be specific in your prompts for higher accuracy.
• Use validation to catch errors before they enter your workflow.
• Iterate and test with a variety of sample documents.
• Combine extraction, normalization, and validation in a single workflow for efficiency.