OCR Reader Pack

★Trustedv1.0.0MIT✔Verified88

by AgentNode · published 22 days ago · toolpack

Extract text from images and scanned documents using OCR.

Optical character recognition for images, screenshots, and scanned PDFs. Supports 100+ languages via Tesseract and EasyOCR.

langchaincrewaigeneric

Quick Start

bash
agentnode install ocr-reader-pack

Usage

From package
python
from ocr_reader_pack.tool import run

result = run(
    action="ocr_read",
    image_path="/tmp/invoice-scan-march.png",
    language="eng",
    output_format="text"
)

print("Extracted text:")
print(result["text"])
print(f"\nConfidence: {result['confidence']:.1%}")
print(f"Words detected: {result['word_count']}")
print(f"Language: {result['detected_language']}")

Verification

high confidence88/100✔ Verified
smokeReturned valid result
+25/25
testsAuto-generated tests only
+8/15
importAll tools imported successfully
+15/15
installInstalled in 2.0s
+15/15
contractAll contract checks passed
+10/10
warningsNo warnings
0/0
determinismOutput consistency check
+5/5
reliability3/3 runs passed
+10/10

Package installs and imports correctly. runtime checks passed.

✔install2.0s
✔import182ms
✔smoke751ms
✔tests997ms

This package was executed and validated by AgentNode before listing. Install, import, and runtime checks passed.

Python 3.12.3ffmpegpopplertesseractuv

Last verified 18d ago· Runner v2.0.0

Use this when you need to...

  • ›Extract text from scanned invoices and receipts for bookkeeping
  • ›Digitize handwritten notes from whiteboard photos
  • ›Read text overlays and captions from screenshot images
  • ›Convert scanned legal documents into searchable plain text
  • ›Extract multilingual text from product labels and packaging photos

README

OCR Reader Pack

Extract text from images and scanned documents using OCR. Supports 100+ languages via Tesseract and EasyOCR engines with confidence scoring and bounding box detection.

Quick Start

agentnode install ocr-reader-pack

from ocr_reader_pack.tool import run

result = run(action="ocr_read", image_path="/tmp/scan.png")
print(result["text"])

Usage

Basic Text Extraction

result = run(
    action="ocr_read",
    image_path="/tmp/receipt.jpg",
    language="eng"
)
print(result["text"])
print(f"Confidence: {result['confidence']:.1%}")

Detailed Output with Bounding Boxes

result = run(
    action="ocr_read",
    image_path="/tmp/form.png",
    output_format="detailed"
)
for block in result["blocks"]:
    print(f"{block['text']} @ {block['bbox']} ({block['confidence']:.0%})")

Multi-Language Recognition

result = run(
    action="ocr_read",
    image_path="/tmp/multilingual-doc.png",
    language=["eng", "fra", "deu"],
    engine="easyocr"
)
print(result["text"])

API Reference

CapabilityDescription
ocr_readExtract text from images using Tesseract or EasyOCR with language detection

Supported image formats: PNG, JPEG, TIFF, BMP, WebP.

Requirements

No API keys required. Tesseract and EasyOCR are bundled with the package.

License

MIT

Version History

v1.0.0latestverified
3/16/2026

Capabilities

ocr_readingocr_readtool

Permissions

This package declares the following access levels. Review before installing.

Networknone
Filesystemtemp
Code Executionnone
Data Accessinput_only
User Approvalnever
bash
agentnode install ocr-reader-pack

Files (3)

License

MIT

Stats

Downloads0
Installs0
Versionv1.0.0
Published3/16/2026
Channelstable
Typetoolpack
Entrypointocr_reader_pack.tool

Compatibility

Frameworks

langchaincrewaigeneric

Runtime

python

Python Version

>=3.10

Trust & Security

Publisher★Trusted
SignatureNone
ProvenanceNone
Security Issues0

Publisher

A

AgentNode

@agentnode

Report an issue with this package