Image Analyzer Pack

Analyze and describe images using vision models. Generate descriptions, extract text, identify objects, and classify visual content.

Quick Start

agentnode install image-analyzer-pack

from image_analyzer_pack.tool import run

result = run(
    action="analyze_image",
    image_path="/data/photo.jpg",
    analysis_type="describe"
)
print(result["description"])

Usage

Generate Alt Text

result = run(
    action="analyze_image",
    image_path="/data/hero_banner.png",
    analysis_type="describe",
    context="website hero image",
    output_fields=["alt_text", "description"]
)
print(f"Alt: {result['alt_text']}")

Extract Text (OCR)

result = run(
    action="analyze_image",
    image_path="/data/receipt.jpg",
    analysis_type="extract_text",
    enhance=True
)
for block in result["text_blocks"]:
    print(block["text"])

Object Detection

result = run(
    action="analyze_image",
    image_path="/data/warehouse_shelf.jpg",
    analysis_type="detect_objects"
)
for obj in result["objects"]:
    print(f"{obj['label']}: {obj['count']} ({obj['confidence']:.0%})")

API Reference

Capability	Description
analyze_image	Vision-powered image analysis, OCR, and classification

Analysis types: describe, extract_text, detect_objects, classify, compare

Inputs: PNG, JPG, WebP, GIF (first frame)

Requirements

Variable	Required	Description
OPENAI_API_KEY	Yes	OpenAI API key for GPT-4 Vision model access

License

MIT