---
title: "OCR Extract Data"
description: "Local-first visual environment for building and running AI workflows. Build agents visually, deploy anywhere, privacy by design."
canonical: https://docs.nodetool.ai/nodes/lib/ocr/ocrextractdata
markdown: https://docs.nodetool.ai/nodes/lib/ocr/ocrextractdata.md
product: NodeTool
source: https://github.com/nodetool-ai/nodetool/blob/main/docs/nodes/lib/ocr/ocrextractdata.md
---

# OCR Extract Data

**Type:** `lib.ocr.ExtractData`

**Namespace:** `lib.ocr`

## Description

Run OCR on an image and return structured data: full text, mean confidence, and per-word boxes.
    ocr, image, text, words, confidence, bounding boxes

## Properties

_(none)_

## Outputs

| Output | Type | Description |
|--------|------|-------------|
| output | `dict` |  |

## Related Nodes

Browse other nodes in the [lib.ocr](./) namespace.