---
title: "Turn receipt images into searchable records — Kition"
description: "Extract vendor, address, category, structured JSON, and plain OCR text from receipt attachments in the same table row."
canonical: "https://kition.ai/docs/scenarios/receipt-ocr"
---

> Canonical HTML: [https://kition.ai/docs/scenarios/receipt-ocr](https://kition.ai/docs/scenarios/receipt-ocr)

[Kition](https://kition.ai/)[Docs](https://kition.ai/docs)[Scenarios](https://kition.ai/docs/scenarios)Turn receipt images into searchable records

Scenarios

# Turn receipt images into searchable records

Extract vendor, address, category, structured JSON, and plain OCR text from receipt attachments in the same table row.

Language[English](https://kition.ai/docs/scenarios/receipt-ocr)[简体中文](https://kition.ai/zh-CN/docs/scenarios/receipt-ocr)[Русский](https://kition.ai/ru-RU/docs/scenarios/receipt-ocr)[日本語](https://kition.ai/ja-JP/docs/scenarios/receipt-ocr)[Tiếng Việt](https://kition.ai/vi-VN/docs/scenarios/receipt-ocr)[Français](https://kition.ai/fr-FR/docs/scenarios/receipt-ocr)[Deutsch](https://kition.ai/de-DE/docs/scenarios/receipt-ocr)[Español](https://kition.ai/es-ES/docs/scenarios/receipt-ocr)

![Kition receipt OCR table extracting vendor, address, category, structured JSON, and plain text from attached receipt images](https://kition.ai/media/scenarios/receipt-ocr.webp)

Kition receipt OCR table extracting vendor, address, category, structured JSON, and plain text from attached receipt images

## When to use this scenario

Use this for expense archives, reimbursement intake, bookkeeping preparation, or any process where receipt images need searchable, correctable structure.

## What you provide

-   One receipt image per row.
-   A file name or other primary identifier.
-   Optional business fields such as owner, project, cost center, or reimbursement status.

## What Kition produces

-   Vendor name and street address.
-   A category such as Food, Fuel, Software, Travel, Office supplies, or Healthcare.
-   Structured JSON containing dates, currency, subtotal, tax, total, payment method, and line items when visible.
-   Plain OCR text preserving receipt line order.

## How the workflow runs

1.  Create a row and attach the receipt image.
    
2.  Vision extraction fields automatically read vendor and address while classification assigns a category.
    
3.  A structured extraction field builds machine-readable JSON and a second field preserves the full plain-text transcription.
    
4.  Filter, correct, export, or ask the Agent to summarize the resulting records.
    

## What to review

-   Compare totals, currency, tax, and line items against the original image.
-   Correct low-quality or ambiguous text before downstream accounting use.
-   Check that the assigned category and vendor capitalization match your reporting rules.

## Ways to adapt it

01

Add reimbursement status, employee, project, tax treatment, and cost-center fields.

02

Flag high-value or duplicate receipts with a workflow.

03

Export approved rows to CSV/JSON or hand them to another bookkeeping process.

[Back to scenarios](https://kition.ai/docs/scenarios)[Expand one product brief into a complete asset pipeline](https://kition.ai/docs/scenarios/product-asset-pipeline)

[Download Kition](https://kition.ai/download)