1# Azure AI Vision Image Analysis — Python SDK Quick Reference
2 
3> Condensed from **azure-ai-vision-imageanalysis-py**. Full patterns (dense captions, smart crops, people detection)
4> in the **azure-ai-vision-imageanalysis-py** plugin skill if installed.
5 
6## Install
7```bash
8pip install azure-ai-vision-imageanalysis
9```
10 
11## Quick Start
12```python
13from azure.ai.vision.imageanalysis import ImageAnalysisClient
14from azure.ai.vision.imageanalysis.models import VisualFeatures
15client = ImageAnalysisClient(endpoint=endpoint, credential=credential)
16```
17 
18## Non-Obvious Patterns
19- `analyze_from_url(image_url=..., visual_features=[...])` for URL; `analyze(image_data=bytes)` for file
20- VisualFeatures enum: `CAPTION`, `DENSE_CAPTIONS`, `TAGS`, `OBJECTS`, `READ`, `PEOPLE`, `SMART_CROPS`
21- Async: `from azure.ai.vision.imageanalysis.aio import ImageAnalysisClient`
22 
23## Best Practices
241. Select only needed visual features to optimize latency and cost
252. Use async client for high-throughput scenarios
263. Handle HttpResponseError for invalid images or auth issues
274. Enable `gender_neutral_caption` for inclusive descriptions
285. Specify `language` for localized captions
296. Use `smart_crops_aspect_ratios` matching your thumbnail requirements
307. Cache results when analyzing the same image multiple times
31