azure-content-understanding
Expert knowledge for Azure Content Understanding in Foundry Tools development including troubleshooting, best practices, decision making, architectu…
它会碰到什么
这一栏是扫描器报的事实,不是结论。命中多不等于有毒(安全工具、规则库、示例脚本本来就会包含危险写法),命中少也不等于干净。它和你手上的凭据、文件、网络有什么关系,需要你自己看。
技能内容
Azure Content Understanding in Foundry Tools Skill
This skill provides expert guidance for Azure Content Understanding in Foundry Tools. Covers troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, and integrations & coding patterns. It combines local quick-reference content with remote documentation fetching capabilities.
How to Use This Skill
> 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
> 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
This skill requires network access to fetch documentation content:
- Preferred: Use
mcp_microsoftdocs:microsoft_docs_fetchwith query stringfrom=learn-agent-skill. Returns Markdown. - Fallback: Use
fetch_webpagewith query stringfrom=learn-agent-skill&accept=text/markdown. Returns Markdown.
Category Index
| Category | Lines | Description |
|----------|-------|-------------|
| Troubleshooting | L36-L40 | Using diagnostics from the Content Understanding REST API to investigate failures, interpret error codes, and troubleshoot processing or configuration issues. |
| Best Practices | L41-L46 | Improving Content Understanding accuracy using layout, labels, and feedback, plus using confidence scores and grounding to validate and refine document analysis results. |
| Decision Making | L47-L55 | Guidance on choosing tools, deployments, and analyzers, deciding between Studio vs Foundry, migrating preview to GA, and estimating/optimizing Content Understanding costs |
| Architecture & Design Patterns | L56-L62 | Guidance on when to use agentic mode, how to design RAG-based document solutions, and how to build RPA workflows using Azure Content Understanding. |
| Limits & Quotas | L63-L68 | Guidance on safe use of synchronous Content Understanding calls and detailed quotas/limits (throughput, payload sizes, concurrency) to avoid throttling and design compliant workloads |
| Security | L69-L73 | Securing Content Understanding analyzers and data: encryption, access control, network isolation, compliance, and best practices for protecting customer content and telemetry. |
| Configuration | L74-L87 | Configuring and managing Content Understanding: analyzers, classifiers, splitting, workflows, capacity, audiovisual analysis, Markdown outputs, and creating/customizing analyzers via Studio or REST. |
| Integrations & Coding Patterns | L88-L94 | Patterns and code samples for calling Content Understanding via REST/SDKs, integrating with Microsoft Agent Framework/LangChain, and implementing agentic workflows. |
Troubleshooting
| Topic | URL |
|-------|-----|
| Use diagnostics from Content Understanding REST API | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/how-to/retrieve-diagnostics |
Best Practices
| Topic | URL |
|-------|-----|
| Apply best practices for Content Understanding accuracy | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/concepts/best-practices |
| Improve document analysis with confidence and grounding | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/document/analyzer-improvement |
Decision Making
| Topic | URL |
|-------|-----|
| Choose Azure AI tools for document processing | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/choosing-right-ai-tool |
| Choose and map Foundry model deployments for analyzers | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/concepts/models-deployments |
| Choose between Content Understanding Studio and Foundry | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/foundry-vs-content-understanding-studio |
| Migrate Content Understanding from preview to GA | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/how-to/migration-preview-to-ga |
| Estimate and optimize Content Understanding pricing | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/pricing-explainer |
Architecture & Design Patterns
| Topic | URL |
|-------|-----|
| Decide when to use agentic mode for documents | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/concepts/agentic-mode |
| Design a RAG solution with Content Understanding | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/tutorial/build-rag-solution |
| Design RPA workflows using Content Understanding | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/tutorial/robotic-process-automation |
Limits & Quotas
| Topic | URL |
|-------|-----|
| Use synchronous Content Understanding operations safely | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/quickstart/use-synchronous-rest-api |
| Apply Content Understanding service quotas and limits | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/service-limits |
Security
| Topic | URL |
|-------|-----|
| Secure Content Understanding analyzers and data | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/concepts/secure-communications |
Configuration
| Topic | URL |
|-------|-----|
| Configure Content Understanding analyzers and parameters | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/concepts/analyzer-reference |
| Configure Content Understanding classifier and splitting | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/concepts/classifier |
| Interpret Content Understanding Markdown document output | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/document/markdown |
| Configure classification and routing workflows in Content Understanding | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/how-to/classification-content-understanding-studio |
| Copy custom analyzers within and across resources | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/how-to/copy-analyzers |
| Create and manage Microsoft Foundry resources | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/how-to/create-multi-service-resource |
| Build and refine custom analyzers in Studio | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/how-to/customize-analyzer-content-understanding-studio |
| Create custom analyzers via Content Understanding REST API | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/tutorial/create-custom-analyzer |
| Configure audiovisual analysis and structured output | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/video/elements |
| Use Markdown output for audiovisual content | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/video/markdown |
Integrations & Coding Patterns
| Topic | URL |
|-------|-----|
| Integrate Content Understanding with Microsoft Agent Framework | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/integrations/agent-framework |
| Use Content Understanding as a LangChain document loader | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/integrations/langchain |
| Implement agentic mode with Content Understanding API | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/quickstart/agentic-mode |
| Call Content Understanding REST APIs and SDKs | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/quickstart/use-rest-api |
想直接用这个技能?
本站把开放许可(MIT / Apache 等)的技能按仓库打包整理到网盘,点一下转存到你自己的网盘,不用一个个从 GitHub 拉。许可未声明的技能只给原始仓库链接,不打包。