1---2name: azure-ai-vision-23description: Expert knowledge for Azure AI Vision development including decision making, limits & quotas, configuration, integrations & coding patterns, and deployment. Use when using Image Analysis, Read OCR containers, smart-crop thumbnails, background removal, or video frame analysis, and other Azure AI Vision related development tasks. Not for Azure AI Custom Vision (use azure-custom-vision), Azure AI Video Indexer (use azure-video-indexer), Azure AI Document Intelligence (use azure-document-intelligence), Azure AI Immersive Reader (use azure-immersive-reader).4---5# Azure AI Vision Skill
6
7This skill provides expert guidance for Azure AI Vision. Covers decision making, limits & quotas, configuration, integrations & coding patterns, and deployment. It combines local quick-reference content with remote documentation fetching capabilities.
8
9## How to Use This Skill
10
11> **IMPORTANT for Agent**: Use the **Category Index** below to locate relevant sections. For categories with line ranges (e.g., `L35-L120`), use `read_file` with the specified lines. For categories with file links (e.g., `[security.md](security.md)`), use `read_file` on the linked reference file
12
13> **IMPORTANT for Agent**: If `metadata.generated_at` is more than 3 months old, suggest the user pull the latest version from the repository. If `mcp_microsoftdocs` tools are not available, suggest the user install it: [Installation Guide](https://github.com/MicrosoftDocs/mcp/blob/main/README.md)
14
15This skill requires **network access** to fetch documentation content:
16- **Preferred**: Use `mcp_microsoftdocs:microsoft_docs_fetch` with query string `from=learn-agent-skill`. Returns Markdown.
17- **Fallback**: Use `fetch_webpage` with query string `from=learn-agent-skill&accept=text/markdown`. Returns Markdown.
18
19## Category Index
20
21| Category | Lines | Description |
22|----------|-------|-------------|
23| Decision Making | L33-L39 | Guides for planning and executing migrations and upgrades between Azure Vision Image Analysis and Read OCR versions/containers, including breaking changes and app update steps. |
24| Limits & Quotas | L40-L50 | Limits, thresholds, and taxonomies for Image Analysis: category lists, adult content scores, object/people detection constraints, smart-crop behavior, and OCR language support. |
25| Configuration | L51-L56 | Configuring Vision Read OCR containers and setting up Azure Blob Storage access for image input, including environment settings, storage permissions, and connection details. |
26| Integrations & Coding Patterns | L57-L67 | How to call and configure Azure Vision/Read APIs and SDKs for OCR, embeddings, thumbnails, background removal, domain models, and live video frame analysis. |
27| Deployment | L68-L71 | Installing, configuring, and running the Azure AI Vision Read OCR container locally or on-premises, including prerequisites, deployment steps, and runtime settings. |
28
29### Decision Making
30| Topic | URL |
31|-------|-----|
32| Plan migration from Azure Vision Image Analysis | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/migration-options |
33| Migrate to Azure Vision Read OCR container v3.x | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/read-container-migration-guide |
34| Upgrade applications from Read v2.x to v3.0 | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/upgrade-api-versions |
35
36### Limits & Quotas
37| Topic | URL |
38|-------|-----|
39| Reference taxonomy categories for Azure Vision | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/category-taxonomy |
40| Understand Image Analysis 3.2 categorization taxonomy limits | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/concept-categorizing-images |
41| Interpret adult content detection scores and thresholds | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/concept-detecting-adult-content |
42| Use object detection and understand feature limits | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/concept-object-detection |
43| Understand Image Analysis 4.0 object detection limits | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/concept-object-detection-40 |
44| Use people detection and understand its limits | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/concept-people-detection |
45| Check supported languages for Azure Vision OCR | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/language-support |
46
47### Configuration
48| Topic | URL |
49|-------|-----|
50| Configure Azure Vision Read OCR containers | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/computer-vision-resource-container-config |
51| Configure Azure Blob Storage for Vision image retrieval | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/how-to/blob-storage-search |
52
53### Integrations & Coding Patterns
54| Topic | URL |
55|-------|-----|
56| Call domain-specific models with Azure Vision | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/concept-detecting-domain-content |
57| Analyze live video frames with Azure Vision API | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/how-to/analyze-video |
58| Call and configure Image Analysis 3.2 API | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/how-to/call-analyze-image |
59| Call and configure Image Analysis 4.0 API | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/how-to/call-analyze-image-40 |
60| Call and configure Azure Vision Read v3.2 API | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/how-to/call-read-api |
61| Use multimodal embeddings for image retrieval | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/how-to/image-retrieval |
62| Use OCR client libraries for text extraction | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/quickstarts-sdk/client-library |
63
64### Deployment
65| Topic | URL |
66|-------|-----|
67| Install and run Azure Vision Read OCR container | https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/computer-vision-how-to-install-containers |
luokai0