What are the image requirements for Azure AI Vision?

The SDK supports formats like JPEG, PNG, GIF, BMP, and WEBP. Images should be between 50x50 and 16000x16000 pixels and under 20 MB.

Can I use this skill for asynchronous Python applications?

Yes, the skill includes implementation patterns for the azure.ai.vision.imageanalysis.aio asynchronous client to support high-throughput scenarios.

How does authentication work with this skill?

The skill provides implementation patterns for both AzureKeyCredential (API Key) and DefaultAzureCredential (Entra ID/Managed Identity), which is the recommended security practice.

What visual features does this skill support?

It supports a wide range of features including single-sentence captions, dense captions for multiple regions, tags, object detection, OCR (read), people detection, and smart cropping.

Does it support multilingual image analysis?

Yes, you can specify the language parameter in the analysis methods to receive localized captions and tags for your images.

Azure AI Vision Image Analysis Python

Name: Azure AI Vision Image Analysis Python
Author: microsoft

bymicrosoft

•

1,777

•

데이터 과학 및 ML

Integrates Azure AI Vision services to perform automated image captioning, OCR, object detection, and visual analysis in Python.

This skill empowers Claude to implement and configure the Azure AI Vision 4.0 SDK for Python, enabling sophisticated image understanding capabilities within your applications. It provides standardized patterns for extracting visual features such as text (OCR), object coordinates, human detection, and descriptive captions. The skill includes best practices for both synchronous and asynchronous implementations, secure authentication via Entra ID or API keys, and optimized error handling to ensure robust computer vision workflows.

주요 기능

01Integrated best practices for Entra ID authentication and error handling

021,777 GitHub stars

03Comprehensive visual feature extraction including captions, tags, and objects

04Intelligent people detection and smart cropping for thumbnail generation

05High-accuracy OCR capabilities for text extraction from images

06Support for both synchronous and asynchronous Python clients

사용 사례

01Extracting structured text from scanned documents using advanced OCR

02Building intelligent media galleries with automated tagging and object-based search

03Automating image alt-text generation for web accessibility compliance

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add microsoft/skills azure-ai-vision-imageanalysis-py

For use in Claude.ai and ChatGPT

Download Skill