azure-ai-vision-imageanalysis-py

Files (1)

• SKILL.md

SKILL.md (first lines)

# Azure AI Vision Image Analysis SDK for Python

Client library for Azure AI Vision 4.0 image analysis including captions, tags, objects, OCR, and more.

## Installation

```bash
pip install azure-ai-vision-imageanalysis
```

## Environment Variables

```bash
VISION_ENDPOINT=https://<resource>.cognitiveservices.azure.com
VISION_KEY=<your-api-key>  # If using API key
```

## Authentication

### API Key

```python
import os
from azure.ai.vision.imageanalysis import ImageAnalysisClient
from azure.core.credentials import AzureKeyCredential

endpoint = os.environ["VISION_ENDPOINT"]
key = os.environ["VISION_KEY"]

client = ImageAnalysisClient(
    endpoint=endpoint,
    credential=AzureKeyCredential(key)
)
```

### Entra ID (Recommended)

```python
from azure.ai.vision.imageanalysis import ImageAnalysisClient
from azure.identity import DefaultAzureCredential

client = ImageAnalysisClient(
    endpoint=os.environ["VISION_ENDPOINT"],
    credential=DefaultAzureCredential()
)
```

## Data and inference boundary

Calls disclose supplied images or URLs to Azure. Confirm rights and privacy scope, region, service availability and current supported features. OCR/captions can be wrong; people detection does not identify people or establish age, identity, consent or sensitive traits. Review output before consequential use and avoid logging private OCR text.

## Analyze Image from URL

```python
from azure.ai.vision.imageanalysis.models import VisualFeatures

image_url = "https://example.com/image.jpg"

result = client.analyze_from_url(
    image_url=image_url,
    visual_features=[
        VisualFeatures.CAPTION,
        VisualFeatures.TAGS,
        VisualFeatures.OBJECTS,
        VisualFeatures.READ,
        VisualFeatures.PEOPLE,
        VisualFeatures.SMART_CROPS,
        VisualFeatures.DENSE_CAPTIONS
    ],
    gender_neutral_caption=True,
    language="en"
)
```

## Analyze Image from File

```python
with open("image.jpg", "rb") as f:
    image_data = f.read()

result = client.analyze(
    image_data=image_data,
    visual_features=[VisualFeatures.CAPTION, VisualFeatures.TAGS]
)
```

## Image Caption

```python
result = client.analyze_from_url(
    image_url=image_url,
    visual_features=[VisualFeatures.CAPTION],
    gender_neutral_caption=True
)

if result.caption:
    print(f"Caption: {result.caption.text}")
    print(f"Confidence: {result.caption.confidence:.2f}")
```

## Dense Captions (Multiple Regions)

```python
result = client.analyze_from_url(
    image_url=image_url,
    visual_features=[VisualFeatures.DENSE_CAPTIONS]
)

if result.dense_captions:
    for caption in result.dense_captions.list:
        print(f"Caption: {caption.text}")
        print(f"  Confidence: {caption.confidence:.2f}")
        print(f"  Bounding box: {caption.bounding_box}")
```

## Tags

```python
result = client.analyze_from_url(

From sickn33/agentic-awesome-skills, MIT.

More from sickn33/agentic-awesome-skills