Back to Details

microsoft-foundry-tools

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Microsoft Foundry Tools Skill

Microsoft Foundry Tools 技能

This skill provides expert guidance for Microsoft Foundry Tools. Covers best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. It combines local quick-reference content with remote documentation fetching capabilities.
本技能为Microsoft Foundry Tools提供专业指导，涵盖最佳实践、决策制定、架构与设计模式、限制与配额、安全、配置、集成与编码模式以及部署。它结合了本地快速参考内容与远程文档获取能力。

How to Use This Skill

如何使用本技能

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_fetch
    with query string 
    from=learn-agent-skill
    . Returns Markdown.
  • Fallback: Use 
    fetch_webpage
    with query string 
    from=learn-agent-skill&accept=text/markdown
    . Returns Markdown.
Agent 重要提示：使用下方的分类索引查找相关章节。对于带有行范围的分类（例如
L35-L120
），使用
read_file
读取指定行内容。对于带有文件链接的分类（例如
[security.md](security.md)
），使用
read_file
读取链接的参考文件
Agent 重要提示：如果
metadata.generated_at
已超过3个月，建议用户从仓库拉取最新版本。如果
mcp_microsoftdocs
工具不可用，建议用户安装它：安装指南
本技能需要网络访问权限以获取文档内容：
  • 首选方式：使用
    mcp_microsoftdocs:microsoft_docs_fetch
    ，并携带查询参数
    from=learn-agent-skill
    ，返回Markdown格式内容。
  • 备用方式：使用
    fetch_webpage
    ，并携带查询参数
    from=learn-agent-skill&accept=text/markdown
    ，返回Markdown格式内容。

Category Index

分类索引

CategoryLinesDescription
Best PracticesL36-L41Improving Content Understanding accuracy, document extraction quality, and using confidence scores/grounding to make extractions more reliable and trustworthy
Decision MakingL42-L51Guidance on choosing Foundry pricing tiers, selecting Azure AI/Content Understanding modes and tools, comparing Foundry vs Studio, migration steps, and estimating Content Understanding costs.
Architecture & Design PatternsL52-L56Designing and configuring how Content Understanding analyzers are mapped to specific model deployments, including routing strategies and deployment architecture patterns.
Limits & QuotasL57-L65Quotas, rate limits, and throughput for Foundry Tools and Content Moderator/Understanding APIs, including autoscale settings, image/list limits, and supported language constraints.
SecurityL66-L79Securing Foundry: auth methods, Entra-only access, keys/Key Vault, CMK encryption, DLP, VNet rules, API key rotation, Azure Policy and regulatory compliance configuration
ConfigurationL80-L98Configuring Foundry environments and resources: credentials, subdomains, ARM provisioning, logging, and detailed setup for Content Understanding analyzers, layouts, images, faces, and routing.
Integrations & Coding PatternsL99-L114Using Content Moderator and Content Understanding via REST/.NET: calling text/image/video APIs, managing term lists, and consuming/creating multimodal Markdown and custom analyzers.
DeploymentL115-L121Deploying Foundry Tools as containers: setup on Azure AI and Azure Container Instances, offline/disconnected deployment, and multi-container orchestration with Docker Compose.
分类行范围描述
最佳实践L36-L41提升Content Understanding的准确性、文档提取质量，以及使用置信度和基础信息使提取结果更可靠可信
决策制定L42-L51关于选择Foundry定价层级、挑选Azure AI/Content Understanding模式与工具、对比Foundry与Studio、迁移步骤以及估算Content Understanding成本的指导。
架构与设计模式L52-L56设计和配置Content Understanding分析器如何映射到特定模型部署，包括路由策略和部署架构模式。
限制与配额L57-L65Foundry Tools和Content Moderator/Understanding API的配额、速率限制和吞吐量，包括自动缩放设置、图像/列表限制以及支持的语言约束。
安全L66-L79Foundry的安全配置：认证方式、仅Entra访问、密钥/Key Vault、CMK加密、DLP、VNet规则、API密钥轮换、Azure策略和合规性配置
配置L80-L98配置Foundry环境和资源：凭据、子域名、ARM部署、日志记录，以及Content Understanding分析器、布局、图像、人脸和路由的详细设置。
集成与编码模式L99-L114通过REST/.NET使用Content Moderator和Content Understanding：调用文本/图像/视频API、管理术语列表，以及使用/创建多模态Markdown和自定义分析器。
部署L115-L121将Foundry Tools部署为容器：在Azure AI和Azure容器实例上设置、离线/断开连接环境下的部署，以及使用Docker Compose进行多容器编排。

Best Practices

最佳实践

TopicURL
Apply best practices for Content Understanding accuracyhttps://learn.microsoft.com/en-us/azure/ai-services/content-understanding/concepts/best-practices
Improve document extraction with confidence and groundinghttps://learn.microsoft.com/en-us/azure/ai-services/content-understanding/document/analyzer-improvement
主题链接
应用Content Understanding准确性最佳实践https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/concepts/best-practices
利用置信度和基础信息提升文档提取效果https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/document/analyzer-improvement

Decision Making

决策制定

TopicURL
Choose and use Foundry commitment tier pricinghttps://learn.microsoft.com/en-us/azure/ai-services/commitment-tier
Choose Azure AI tools for document processinghttps://learn.microsoft.com/en-us/azure/ai-services/content-understanding/choosing-right-ai-tool
Choose between Content Understanding standard and pro modeshttps://learn.microsoft.com/en-us/azure/ai-services/content-understanding/concepts/standard-pro-modes
Compare Foundry vs Content Understanding Studio featureshttps://learn.microsoft.com/en-us/azure/ai-services/content-understanding/foundry-vs-content-understanding-studio
Migrate Content Understanding from preview to GA APIshttps://learn.microsoft.com/en-us/azure/ai-services/content-understanding/how-to/migration-preview-to-ga
Estimate and plan Content Understanding pricinghttps://learn.microsoft.com/en-us/azure/ai-services/content-understanding/pricing-explainer
主题链接
选择和使用Foundry承诺层级定价https://learn.microsoft.com/en-us/azure/ai-services/commitment-tier
为文档处理选择Azure AI工具https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/choosing-right-ai-tool
选择Content Understanding标准模式和专业模式https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/concepts/standard-pro-modes
对比Foundry与Content Understanding Studio功能https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/foundry-vs-content-understanding-studio
将Content Understanding从预览版API迁移到正式版APIhttps://learn.microsoft.com/en-us/azure/ai-services/content-understanding/how-to/migration-preview-to-ga
估算和规划Content Understanding定价https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/pricing-explainer

Architecture & Design Patterns

架构与设计模式

TopicURL
Map Content Understanding analyzers to model deploymentshttps://learn.microsoft.com/en-us/azure/ai-services/content-understanding/concepts/models-deployments
主题链接
将Content Understanding分析器映射到模型部署https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/concepts/models-deployments

Limits & Quotas

限制与配额

TopicURL
Configure autoscale rate limits for Foundry Toolshttps://learn.microsoft.com/en-us/azure/ai-services/autoscale
Use Content Moderator image lists within quota limitshttps://learn.microsoft.com/en-us/azure/ai-services/content-moderator/image-lists-quickstart-dotnet
Use supported languages in Content Moderator APIhttps://learn.microsoft.com/en-us/azure/ai-services/content-moderator/language-support
Apply Content Moderator .NET samples with list limitshttps://learn.microsoft.com/en-us/azure/ai-services/content-moderator/samples-dotnet
Content Understanding quotas, limits, and throughputhttps://learn.microsoft.com/en-us/azure/ai-services/content-understanding/service-limits
主题链接
配置Foundry Tools的自动缩放速率限制https://learn.microsoft.com/en-us/azure/ai-services/autoscale
在配额限制内使用Content Moderator图像列表https://learn.microsoft.com/en-us/azure/ai-services/content-moderator/image-lists-quickstart-dotnet
在Content Moderator API中使用支持的语言https://learn.microsoft.com/en-us/azure/ai-services/content-moderator/language-support
使用符合列表限制的Content Moderator .NET示例https://learn.microsoft.com/en-us/azure/ai-services/content-moderator/samples-dotnet
Content Understanding的配额、限制和吞吐量https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/service-limits

Security

安全

TopicURL
Configure authentication for Foundry Tools requestshttps://learn.microsoft.com/en-us/azure/ai-services/authentication
Configure data loss prevention for Foundry Toolshttps://learn.microsoft.com/en-us/azure/ai-services/cognitive-services-data-loss-prevention
Secure Foundry resources with virtual network ruleshttps://learn.microsoft.com/en-us/azure/ai-services/cognitive-services-virtual-networks
Secure Content Understanding with keys and identitieshttps://learn.microsoft.com/en-us/azure/ai-services/content-understanding/concepts/secure-communications
Enforce Entra-only auth by disabling Foundry local keyshttps://learn.microsoft.com/en-us/azure/ai-services/disable-local-auth
Configure customer-managed encryption keys for Foundryhttps://learn.microsoft.com/en-us/azure/ai-services/encryption/cognitive-services-encryption-keys-portal
Use built-in Azure Policies for Foundry governancehttps://learn.microsoft.com/en-us/azure/ai-services/policy-reference
Rotate Foundry API keys without downtimehttps://learn.microsoft.com/en-us/azure/ai-services/rotate-keys
Apply regulatory compliance policies to Foundryhttps://learn.microsoft.com/en-us/azure/ai-services/security-controls-policy
Secure Foundry applications using Azure Key Vaulthttps://learn.microsoft.com/en-us/azure/ai-services/use-key-vault
主题链接
配置Foundry Tools请求的身份验证https://learn.microsoft.com/en-us/azure/ai-services/authentication
配置Foundry Tools的数据丢失防护https://learn.microsoft.com/en-us/azure/ai-services/cognitive-services-data-loss-prevention
使用虚拟网络规则保护Foundry资源https://learn.microsoft.com/en-us/azure/ai-services/cognitive-services-virtual-networks
使用密钥和身份保护Content Understandinghttps://learn.microsoft.com/en-us/azure/ai-services/content-understanding/concepts/secure-communications
通过禁用Foundry本地密钥强制使用仅Entra身份验证https://learn.microsoft.com/en-us/azure/ai-services/disable-local-auth
为Foundry配置客户管理的加密密钥https://learn.microsoft.com/en-us/azure/ai-services/encryption/cognitive-services-encryption-keys-portal
使用内置Azure策略进行Foundry治理https://learn.microsoft.com/en-us/azure/ai-services/policy-reference
无停机轮换Foundry API密钥https://learn.microsoft.com/en-us/azure/ai-services/rotate-keys
为Foundry应用合规性监管策略https://learn.microsoft.com/en-us/azure/ai-services/security-controls-policy
使用Azure Key Vault保护Foundry应用https://learn.microsoft.com/en-us/azure/ai-services/use-key-vault

Configuration

配置

TopicURL
Configure custom subdomains for Foundry resourceshttps://learn.microsoft.com/en-us/azure/ai-services/cognitive-services-custom-subdomains
Use environment variables for Foundry credentialshttps://learn.microsoft.com/en-us/azure/ai-services/cognitive-services-environment-variables
Create reusable Azure AI container images with presetshttps://learn.microsoft.com/en-us/azure/ai-services/containers/container-reuse-recipe
Configure Content Understanding analyzers and parametershttps://learn.microsoft.com/en-us/azure/ai-services/content-understanding/concepts/analyzer-reference
Configure Content Understanding classifier and splittinghttps://learn.microsoft.com/en-us/azure/ai-services/content-understanding/concepts/classifier
Use and customize Content Understanding prebuilt analyzershttps://learn.microsoft.com/en-us/azure/ai-services/content-understanding/concepts/prebuilt-analyzers
Configure document layout analysis with Content Understandinghttps://learn.microsoft.com/en-us/azure/ai-services/content-understanding/document/elements
Configure face detection and recognition in Content Understandinghttps://learn.microsoft.com/en-us/azure/ai-services/content-understanding/face/overview
Configure classification and routing in Content Understanding Studiohttps://learn.microsoft.com/en-us/azure/ai-services/content-understanding/how-to/classification-content-understanding-studio
Configure Standard and Pro tasks in Foundry classichttps://learn.microsoft.com/en-us/azure/ai-services/content-understanding/how-to/content-understanding-foundry-classic
Copy Content Understanding custom analyzers across resourceshttps://learn.microsoft.com/en-us/azure/ai-services/content-understanding/how-to/copy-analyzers
Build and refine custom analyzers in Content Understanding Studiohttps://learn.microsoft.com/en-us/azure/ai-services/content-understanding/how-to/customize-analyzer-content-understanding-studio
Configure image analyzers and schemas in Content Understandinghttps://learn.microsoft.com/en-us/azure/ai-services/content-understanding/image/overview
Provision Foundry resources using ARM templateshttps://learn.microsoft.com/en-us/azure/ai-services/create-account-resource-manager-template
Enable and configure Foundry diagnostic logginghttps://learn.microsoft.com/en-us/azure/ai-services/diagnostic-logging
主题链接
为Foundry资源配置自定义子域名https://learn.microsoft.com/en-us/azure/ai-services/cognitive-services-custom-subdomains
使用环境变量存储Foundry凭据https://learn.microsoft.com/en-us/azure/ai-services/cognitive-services-environment-variables
使用预设创建可复用的Azure AI容器镜像https://learn.microsoft.com/en-us/azure/ai-services/containers/container-reuse-recipe
配置Content Understanding分析器和参数https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/concepts/analyzer-reference
配置Content Understanding分类器和拆分功能https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/concepts/classifier
使用和自定义Content Understanding预构建分析器https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/concepts/prebuilt-analyzers
使用Content Understanding配置文档布局分析https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/document/elements
在Content Understanding中配置人脸检测和识别https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/face/overview
在Content Understanding Studio中配置分类和路由https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/how-to/classification-content-understanding-studio
在Foundry classic中配置标准和专业任务https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/how-to/content-understanding-foundry-classic
在资源间复制Content Understanding自定义分析器https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/how-to/copy-analyzers
在Content Understanding Studio中构建和优化自定义分析器https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/how-to/customize-analyzer-content-understanding-studio
在Content Understanding中配置图像分析器和架构https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/image/overview
使用ARM模板部署Foundry资源https://learn.microsoft.com/en-us/azure/ai-services/create-account-resource-manager-template
启用和配置Foundry诊断日志https://learn.microsoft.com/en-us/azure/ai-services/diagnostic-logging

Integrations & Coding Patterns

集成与编码模式

TopicURL
Content Moderator REST API operations referencehttps://learn.microsoft.com/en-us/azure/ai-services/content-moderator/api-reference
Integrate Content Moderator via .NET client libraryhttps://learn.microsoft.com/en-us/azure/ai-services/content-moderator/client-libraries
Call Content Moderator image moderation APIshttps://learn.microsoft.com/en-us/azure/ai-services/content-moderator/image-moderation-api
Call Content Moderator REST APIs from C# sampleshttps://learn.microsoft.com/en-us/azure/ai-services/content-moderator/samples-rest
Use .NET SDK term lists with Content Moderatorhttps://learn.microsoft.com/en-us/azure/ai-services/content-moderator/term-lists-quickstart-dotnet
Use Content Moderator text moderation APIshttps://learn.microsoft.com/en-us/azure/ai-services/content-moderator/text-moderation-api
Moderate video content using Content Moderator .NET SDKhttps://learn.microsoft.com/en-us/azure/ai-services/content-moderator/video-moderation-api
Consume Content Understanding document Markdown outputhttps://learn.microsoft.com/en-us/azure/ai-services/content-understanding/document/markdown
Call Content Understanding REST API for multimodal datahttps://learn.microsoft.com/en-us/azure/ai-services/content-understanding/quickstart/use-rest-api
Create custom Content Understanding analyzers via RESThttps://learn.microsoft.com/en-us/azure/ai-services/content-understanding/tutorial/create-custom-analyzer
Extract structured audiovisual content with Content Understandinghttps://learn.microsoft.com/en-us/azure/ai-services/content-understanding/video/elements
Use audiovisual Markdown output from Content Understandinghttps://learn.microsoft.com/en-us/azure/ai-services/content-understanding/video/markdown
主题链接
Content Moderator REST API操作参考https://learn.microsoft.com/en-us/azure/ai-services/content-moderator/api-reference
通过.NET客户端库集成Content Moderatorhttps://learn.microsoft.com/en-us/azure/ai-services/content-moderator/client-libraries
调用Content Moderator图像审核APIhttps://learn.microsoft.com/en-us/azure/ai-services/content-moderator/image-moderation-api
从C#示例调用Content Moderator REST APIhttps://learn.microsoft.com/en-us/azure/ai-services/content-moderator/samples-rest
将Content Moderator与.NET SDK术语列表结合使用https://learn.microsoft.com/en-us/azure/ai-services/content-moderator/term-lists-quickstart-dotnet
使用Content Moderator文本审核APIhttps://learn.microsoft.com/en-us/azure/ai-services/content-moderator/text-moderation-api
使用Content Moderator .NET SDK审核视频内容https://learn.microsoft.com/en-us/azure/ai-services/content-moderator/video-moderation-api
消费Content Understanding文档Markdown输出https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/document/markdown
调用Content Understanding REST API处理多模态数据https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/quickstart/use-rest-api
通过REST创建自定义Content Understanding分析器https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/tutorial/create-custom-analyzer
使用Content Understanding提取结构化视听内容https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/video/elements
使用Content Understanding的视听Markdown输出https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/video/markdown

Deployment

部署

TopicURL
Deploy Foundry Tools using Azure AI containershttps://learn.microsoft.com/en-us/azure/ai-services/cognitive-services-container-support
Deploy Foundry containers to Azure Container Instanceshttps://learn.microsoft.com/en-us/azure/ai-services/containers/azure-container-instance-recipe
Run Foundry containers in disconnected environmentshttps://learn.microsoft.com/en-us/azure/ai-services/containers/disconnected-containers
Orchestrate multiple Foundry containers with Docker Composehttps://learn.microsoft.com/en-us/azure/ai-services/containers/docker-compose-recipe
主题链接
使用Azure AI容器部署Foundry Toolshttps://learn.microsoft.com/en-us/azure/ai-services/cognitive-services-container-support
将Foundry容器部署到Azure容器实例https://learn.microsoft.com/en-us/azure/ai-services/containers/azure-container-instance-recipe
在断开连接的环境中运行Foundry容器https://learn.microsoft.com/en-us/azure/ai-services/containers/disconnected-containers
使用Docker Compose编排多个Foundry容器https://learn.microsoft.com/en-us/azure/ai-services/containers/docker-compose-recipe