Back to Details

microsoft-foundry

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Microsoft Foundry Skill

Microsoft Foundry 技能

This skill provides expert guidance for Microsoft Foundry. Covers troubleshooting, 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.
本技能提供Microsoft Foundry相关的专业指导，覆盖故障排查、最佳实践、决策指引、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相关内容，同时结合了本地速查内容与远程文档拉取能力。

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定位相关章节。对于标注了行范围的分类（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
读取关联的参考文件。
Agent 重要提示：如果
metadata.generated_at
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，建议用户安装该工具：安装指南
本技能需要网络访问来拉取文档内容：
  • 优先方案：使用
    mcp_microsoftdocs:microsoft_docs_fetch
    配合查询参数
    from=learn-agent-skill
    调用，返回Markdown格式内容。
  • 兜底方案：使用
    fetch_webpage
    配合查询参数
    from=learn-agent-skill&accept=text/markdown
    调用，返回Markdown格式内容。

Category Index

分类索引

CategoryLinesDescription
TroubleshootingL37-L41Known issues, error codes, limitations, and current workarounds for Microsoft Foundry features, deployments, integrations, and runtime behavior.
Best PracticesL42-L52Best practices for configuring tools, prompts, system messages, vision models, fine-tuning, evaluation, and performance (latency/throughput) for Azure OpenAI agents in Foundry
Decision MakingL53-L80Guides for choosing models, SDKs, deployment types, costs, and migrations (Azure OpenAI, GitHub Models, classic/preview) to design and upgrade Foundry-based AI solutions.
Architecture & Design PatternsL81-L93Architectural patterns for Foundry agents: standard setup, RAG/indexing, HA/DR, regional recovery, provisioned throughput, spillover traffic, and LLM routing optimization.
Limits & QuotasL94-L109Limits, quotas, rate limits, regions, timeouts, caching, and cost controls for Foundry agents, models, vector search, batch jobs, Sora video, RFT, and Azure OpenAI access.
SecurityL110-L142Security, identity, and compliance for Foundry: auth/RBAC, private networking, encryption/CMK, safety guardrails, policy/governance, data privacy, and secure tool/agent configuration.
ConfigurationL143-L202Configuring Foundry agents, models, tools, storage, safety/guardrails, tracing, evaluators, and Azure OpenAI/Fireworks integrations for deployment, monitoring, and advanced capabilities.
Integrations & Coding PatternsL203-L268Integrating Foundry agents and models with external apps, tools, and services: SDK usage, REST APIs, MCP/LangChain, search/speech/browsing tools, fine-tuning, realtime audio, safety, and evaluations.
DeploymentL269-L286Deploying and managing Foundry agents/models: infra setup, container/hosted deployments, Azure/M365 publishing, IaC (Bicep/Terraform), CI/CD evals, and regional availability.
分类行范围描述
故障排查L37-L41Microsoft Foundry功能、部署、集成及运行时行为相关的已知问题、错误码、限制和现有解决方案。
最佳实践L42-L52在Foundry中为Azure OpenAI Agent配置工具、提示词、系统提示词、视觉模型、微调、评估及性能（延迟/吞吐量）的最佳实践。
决策指引L53-L80模型、SDK、部署类型、成本及迁移（Azure OpenAI、GitHub Models、经典/预览版）选择指南，用于设计和升级基于Foundry的AI解决方案。
架构与设计模式L81-L93Foundry Agent的架构模式：标准部署、RAG/索引构建、高可用/灾备、区域恢复、预置吞吐量、流量削峰、LLM路由优化。
限制与配额L94-L109Foundry Agent、模型、向量搜索、批量任务、Sora视频、RFT及Azure OpenAI访问相关的限制、配额、速率限制、区域支持、超时、缓存及成本控制规则。
安全L110-L142Foundry的安全、身份与合规相关内容：认证/RBAC、私有网络、加密/客户管理密钥（CMK）、安全护栏、政策/治理、数据隐私、工具/Agent安全配置。
配置L143-L202配置Foundry Agent、模型、工具、存储、安全护栏、链路追踪、评估器，以及Azure OpenAI/Fireworks集成，用于部署、监控和高级能力扩展。
集成与编码模式L203-L268Foundry Agent和模型与外部应用、工具、服务的集成方案：SDK使用、REST API、MCP/LangChain、搜索/语音/浏览工具、微调、实时音频、安全、评估相关实现。
部署L269-L286Foundry Agent/模型的部署与管理：基础设施搭建、容器/托管部署、Azure/M365发布、IaC（Bicep/Terraform）、CI/CD评估、区域可用性相关内容。

Troubleshooting

故障排查

TopicURL
Review known issues and workarounds for Microsoft Foundryhttps://learn.microsoft.com/en-us/azure/foundry/reference/foundry-known-issues
主题URL
查看Microsoft Foundry的已知问题和解决方案https://learn.microsoft.com/en-us/azure/foundry/reference/foundry-known-issues

Best Practices

最佳实践

TopicURL
Apply tool configuration best practices for agentshttps://learn.microsoft.com/en-us/azure/foundry/agents/concepts/tool-best-practice
Evaluate Foundry agents with built-in quality and safety testshttps://learn.microsoft.com/en-us/azure/foundry/observability/how-to/evaluate-agent
Optimize Foundry agent prompts with Prompt Optimizerhttps://learn.microsoft.com/en-us/azure/foundry/observability/how-to/prompt-optimizer
Design effective system messages for Azure OpenAI in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/openai/concepts/advanced-prompt-engineering
Apply prompt engineering techniques for vision-enabled GPT modelshttps://learn.microsoft.com/en-us/azure/foundry/openai/concepts/gpt-4-v-prompt-engineering
Fine-tune GPT-4 vision models with imageshttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning-vision
Optimize Azure OpenAI latency and throughput in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/latency
主题URL
为Agent应用工具配置最佳实践https://learn.microsoft.com/en-us/azure/foundry/agents/concepts/tool-best-practice
使用内置质量和安全测试评估Foundry Agenthttps://learn.microsoft.com/en-us/azure/foundry/observability/how-to/evaluate-agent
使用提示词优化器优化Foundry Agent提示词https://learn.microsoft.com/en-us/azure/foundry/observability/how-to/prompt-optimizer
为Foundry中的Azure OpenAI设计有效的系统提示词https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/advanced-prompt-engineering
为支持视觉能力的GPT模型应用提示词工程技巧https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/gpt-4-v-prompt-engineering
使用图像微调GPT-4视觉模型https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning-vision
优化Foundry中Azure OpenAI的延迟和吞吐量https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/latency

Decision Making

决策指引

TopicURL
Migrate to the new Foundry Agent Servicehttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/migrate
Choose the right web grounding tool for agentshttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/web-overview
Compare models with Foundry benchmarks and leaderboardshttps://learn.microsoft.com/en-us/azure/foundry/concepts/model-benchmarks
Plan for Foundry model deprecation and retirementhttps://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement
Plan Microsoft Foundry rollout and environment strategyhttps://learn.microsoft.com/en-us/azure/foundry/concepts/planning
Optimize model cost and performance with Ask AIhttps://learn.microsoft.com/en-us/azure/foundry/control-plane/how-to-optimize-cost-performance
Choose Foundry deployment types and data residency optionshttps://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/deployment-types
Manage model versioning and upgrade policies in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/model-versions
Choose Foundry partner and community modelshttps://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-from-partners
Select Azure-sold Foundry Models by capabilities and regionshttps://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure
Decide between GPT-5 and GPT-4.1 for your use casehttps://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/model-choice-guide
Upgrade workloads from GitHub Models to Foundry Modelshttps://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/quickstart-github-models
Use Foundry model leaderboard to compare and choose modelshttps://learn.microsoft.com/en-us/azure/foundry/how-to/benchmark-model-in-catalog
Choose appropriate Microsoft Foundry SDKs and endpointshttps://learn.microsoft.com/en-us/azure/foundry/how-to/develop/sdk-overview
Migrate from Azure AI Inference SDK to OpenAI SDKhttps://learn.microsoft.com/en-us/azure/foundry/how-to/model-inference-to-openai-migration
Plan migration from classic to current Foundryhttps://learn.microsoft.com/en-us/azure/foundry/how-to/navigate-from-classic
Decide and execute upgrade from Azure OpenAI to Foundryhttps://learn.microsoft.com/en-us/azure/foundry/how-to/upgrade-azure-openai
Use Ask AI to upgrade or switch Foundry modelshttps://learn.microsoft.com/en-us/azure/foundry/observability/how-to/optimization-model-upgrade
Choose content streaming and filtering modes in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/openai/concepts/content-streaming
Review retired Azure OpenAI models in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models
Track Azure OpenAI model deprecations and retirementshttps://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirements
Estimate and manage fine-tuning costs in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning-cost-management
Estimate PTU costs and plan capacity for Foundryhttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/provisioned-throughput-onboarding
Migrate from preview to GA Realtime APIhttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/realtime-audio-preview-api-migration-guide
主题URL
迁移到全新的Foundry Agent服务https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/migrate
为Agent选择合适的网络接地工具https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/web-overview
使用Foundry基准测试和排行榜对比模型https://learn.microsoft.com/en-us/azure/foundry/concepts/model-benchmarks
规划Foundry模型弃用和下线安排https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement
规划Microsoft Foundry上线和环境策略https://learn.microsoft.com/en-us/azure/foundry/concepts/planning
使用Ask AI优化模型成本和性能https://learn.microsoft.com/en-us/azure/foundry/control-plane/how-to-optimize-cost-performance
选择Foundry部署类型和数据驻留选项https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/deployment-types
管理Foundry中的模型版本和升级策略https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/model-versions
选择Foundry合作伙伴和社区模型https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-from-partners
根据能力和区域选择Azure售卖的Foundry模型https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure
为业务场景选择合适的GPT-5或GPT-4.1https://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/model-choice-guide
从GitHub Models迁移工作负载到Foundry Modelshttps://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/quickstart-github-models
使用Foundry模型排行榜对比和选择模型https://learn.microsoft.com/en-us/azure/foundry/how-to/benchmark-model-in-catalog
选择合适的Microsoft Foundry SDK和端点https://learn.microsoft.com/en-us/azure/foundry/how-to/develop/sdk-overview
从Azure AI Inference SDK迁移到OpenAI SDKhttps://learn.microsoft.com/en-us/azure/foundry/how-to/model-inference-to-openai-migration
规划从经典版Foundry迁移到当前版本https://learn.microsoft.com/en-us/azure/foundry/how-to/navigate-from-classic
决策并执行从Azure OpenAI升级到Foundryhttps://learn.microsoft.com/en-us/azure/foundry/how-to/upgrade-azure-openai
使用Ask AI升级或切换Foundry模型https://learn.microsoft.com/en-us/azure/foundry/observability/how-to/optimization-model-upgrade
选择Foundry中的内容流和过滤模式https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/content-streaming
查看Foundry中已下线的Azure OpenAI模型https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models
跟踪Azure OpenAI模型的弃用和下线计划https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirements
估算和管理Foundry中的微调成本https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning-cost-management
估算Foundry的PTU成本并规划容量https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/provisioned-throughput-onboarding
从预览版Realtime API迁移到GA版本https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/realtime-audio-preview-api-migration-guide

Architecture & Design Patterns

架构与设计模式

TopicURL
Design standard agent setup with isolated resourceshttps://learn.microsoft.com/en-us/azure/foundry/agents/concepts/standard-agent-setup
Apply RAG and indexing patterns in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/concepts/retrieval-augmented-generation
Plan disaster recovery for Foundry Agent Service in standard modehttps://learn.microsoft.com/en-us/azure/foundry/how-to/agent-service-disaster-recovery
Recover Foundry Agent Service from resource and data losshttps://learn.microsoft.com/en-us/azure/foundry/how-to/agent-service-operator-disaster-recovery
Recover Foundry Agent Service from regional platform outageshttps://learn.microsoft.com/en-us/azure/foundry/how-to/agent-service-platform-disaster-recovery
Plan high availability and resiliency for Foundry projects and agentshttps://learn.microsoft.com/en-us/azure/foundry/how-to/high-availability-resiliency
Use model router to optimize LLM routing in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-router
Plan provisioned throughput architecture for Foundry modelshttps://learn.microsoft.com/en-us/azure/foundry/openai/concepts/provisioned-throughput
Design spillover traffic management for provisioned deploymentshttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/spillover-traffic-management
主题URL
设计资源隔离的标准Agent部署架构https://learn.microsoft.com/en-us/azure/foundry/agents/concepts/standard-agent-setup
在Foundry中应用RAG和索引模式https://learn.microsoft.com/en-us/azure/foundry/concepts/retrieval-augmented-generation
为标准模式的Foundry Agent服务规划灾备方案https://learn.microsoft.com/en-us/azure/foundry/how-to/agent-service-disaster-recovery
从资源和数据丢失中恢复Foundry Agent服务https://learn.microsoft.com/en-us/azure/foundry/how-to/agent-service-operator-disaster-recovery
从区域平台故障中恢复Foundry Agent服务https://learn.microsoft.com/en-us/azure/foundry/how-to/agent-service-platform-disaster-recovery
为Foundry项目和Agent规划高可用和弹性能力https://learn.microsoft.com/en-us/azure/foundry/how-to/high-availability-resiliency
在Foundry中使用模型路由器优化LLM路由https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-router
为Foundry模型规划预置吞吐量架构https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/provisioned-throughput
为预置吞吐量部署设计流量削峰管理方案https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/spillover-traffic-management

Limits & Quotas

限制与配额

TopicURL
Quotas, limits, and regions for Foundry Agent Servicehttps://learn.microsoft.com/en-us/azure/foundry/agents/concepts/limits-quotas-regions
Use vector stores and file search limits in agentshttps://learn.microsoft.com/en-us/azure/foundry/agents/concepts/vector-stores
Implement function calling tools with run time limitshttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/function-calling
Evaluation regions, rate limits, and VNet supporthttps://learn.microsoft.com/en-us/azure/foundry/concepts/evaluation-regions-limits-virtual-network
Configure token rate limits and quotas for modelshttps://learn.microsoft.com/en-us/azure/foundry/control-plane/how-to-enforce-limits-models
Reference quotas and limits for Foundry Modelshttps://learn.microsoft.com/en-us/azure/foundry/foundry-models/quotas-limits
Review Sora video generation capabilities and constraints in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/openai/concepts/video-generation
Use Azure OpenAI global batch processing efficientlyhttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/batch
Configure prompt caching and understand cache limits in Azure OpenAIhttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/prompt-caching
Use reinforcement fine-tuning with cost limitshttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/reinforcement-fine-tuning
Azure OpenAI quotas, rate limits, and timeouts in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/openai/quotas-limits
Understand limited access policy for Azure OpenAIhttps://learn.microsoft.com/en-us/azure/foundry/responsible-ai/openai/limited-access
主题URL
Foundry Agent服务的配额、限制和区域支持https://learn.microsoft.com/en-us/azure/foundry/agents/concepts/limits-quotas-regions
在Agent中使用向量存储和文件搜索限制https://learn.microsoft.com/en-us/azure/foundry/agents/concepts/vector-stores
实现带有运行时限制的函数调用工具https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/function-calling
评估区域支持、速率限制和VNet支持情况https://learn.microsoft.com/en-us/azure/foundry/concepts/evaluation-regions-limits-virtual-network
为模型配置Token速率限制和配额https://learn.microsoft.com/en-us/azure/foundry/control-plane/how-to-enforce-limits-models
Foundry Models的配额和限制参考https://learn.microsoft.com/en-us/azure/foundry/foundry-models/quotas-limits
查看Foundry中Sora视频生成能力和约束https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/video-generation
高效使用Azure OpenAI全局批量处理能力https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/batch
配置提示词缓存并了解Azure OpenAI的缓存限制https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/prompt-caching
带有成本限制的强化微调使用指南https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/reinforcement-fine-tuning
Foundry中Azure OpenAI的配额、速率限制和超时规则https://learn.microsoft.com/en-us/azure/foundry/openai/quotas-limits
了解Azure OpenAI的受限访问政策https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/openai/limited-access

Security

安全

TopicURL
Configure agent identities and RBAC in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/agents/concepts/agent-identity
Configure authentication methods for Agent2Agent toolshttps://learn.microsoft.com/en-us/azure/foundry/agents/concepts/agent-to-agent-authentication
Configure authentication for MCP servers in agentshttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/mcp-authentication
Use computer use tool securely for UI automationhttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/computer-use
Govern MCP tools with an AI gateway in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/governance
Secure OpenAPI tools for Foundry agents with auth optionshttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/openapi
Set up private networking for Foundry Agent Servicehttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/virtual-networks
Configure authentication and authorization for Microsoft Foundryhttps://learn.microsoft.com/en-us/azure/foundry/concepts/authentication-authorization-foundry
Configure customer-managed keys for Microsoft Foundry encryptionhttps://learn.microsoft.com/en-us/azure/foundry/concepts/encryption-keys-portal
Understand and apply RBAC roles in Microsoft Foundryhttps://learn.microsoft.com/en-us/azure/foundry/concepts/rbac-foundry
Govern Foundry agent infrastructure as Entra adminhttps://learn.microsoft.com/en-us/azure/foundry/control-plane/govern-agent-infrastructure-entra-admin
Manage Foundry compliance and security integrationshttps://learn.microsoft.com/en-us/azure/foundry/control-plane/how-to-manage-compliance-security
Create guardrail policies for model deploymentshttps://learn.microsoft.com/en-us/azure/foundry/control-plane/quickstart-create-guardrail-policy
Configure keyless Entra ID authentication for Foundry Modelshttps://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/configure-entra-id
Add Microsoft Foundry resources to a network security perimeterhttps://learn.microsoft.com/en-us/azure/foundry/how-to/add-foundry-to-network-security-perimeter
Configure private endpoint network isolation for Microsoft Foundryhttps://learn.microsoft.com/en-us/azure/foundry/how-to/configure-private-link
Create custom Azure Policies to govern Microsoft Foundryhttps://learn.microsoft.com/en-us/azure/foundry/how-to/custom-policy-definition
Disable preview features in Microsoft Foundry using tags and RBAChttps://learn.microsoft.com/en-us/azure/foundry/how-to/disable-preview-features
Set up managed virtual networks for Microsoft Foundry projectshttps://learn.microsoft.com/en-us/azure/foundry/how-to/managed-virtual-network
Use built-in Azure Policy definitions for Foundry model deploymenthttps://learn.microsoft.com/en-us/azure/foundry/how-to/model-deployment-policy
Apply security best practices for Foundry MCP Serverhttps://learn.microsoft.com/en-us/azure/foundry/mcp/security-best-practices
Understand default guardrail safety policies in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/openai/concepts/default-safety-policies
Use safety system message templates for Azure OpenAI appshttps://learn.microsoft.com/en-us/azure/foundry/openai/concepts/safety-system-message-templates
Author safety-focused system messages for Azure OpenAIhttps://learn.microsoft.com/en-us/azure/foundry/openai/concepts/system-message
Apply safety evaluation to fine-tuned modelshttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning-safety-evaluation
Data privacy and security for Foundry Agent Servicehttps://learn.microsoft.com/en-us/azure/foundry/responsible-ai/agents/data-privacy-security
Understand data privacy and security for Anthropic Claude in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/responsible-ai/claude-models/data-privacy
Implement copyright mitigations for Foundry OpenAIhttps://learn.microsoft.com/en-us/azure/foundry/responsible-ai/openai/customer-copyright-commitment
Understand data, privacy, and security for Azure Direct Modelshttps://learn.microsoft.com/en-us/azure/foundry/responsible-ai/openai/data-privacy
主题URL
在Foundry中配置Agent身份和RBAChttps://learn.microsoft.com/en-us/azure/foundry/agents/concepts/agent-identity
为Agent2Agent工具配置认证方式https://learn.microsoft.com/en-us/azure/foundry/agents/concepts/agent-to-agent-authentication
为Agent中的MCP服务器配置认证https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/mcp-authentication
安全使用计算机操作工具实现UI自动化https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/computer-use
在Foundry中使用AI网关治理MCP工具https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/governance
使用认证选项保护Foundry Agent的OpenAPI工具https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/openapi
为Foundry Agent服务配置私有网络https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/virtual-networks
为Microsoft Foundry配置认证和授权https://learn.microsoft.com/en-us/azure/foundry/concepts/authentication-authorization-foundry
为Microsoft Foundry加密配置客户管理密钥https://learn.microsoft.com/en-us/azure/foundry/concepts/encryption-keys-portal
了解并应用Microsoft Foundry中的RBAC角色https://learn.microsoft.com/en-us/azure/foundry/concepts/rbac-foundry
作为Entra管理员治理Foundry Agent基础设施https://learn.microsoft.com/en-us/azure/foundry/control-plane/govern-agent-infrastructure-entra-admin
管理Foundry合规和安全集成https://learn.microsoft.com/en-us/azure/foundry/control-plane/how-to-manage-compliance-security
为模型部署创建护栏政策https://learn.microsoft.com/en-us/azure/foundry/control-plane/quickstart-create-guardrail-policy
为Foundry Models配置无密钥Entra ID认证https://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/configure-entra-id
将Microsoft Foundry资源添加到网络安全边界https://learn.microsoft.com/en-us/azure/foundry/how-to/add-foundry-to-network-security-perimeter
为Microsoft Foundry配置私有端点网络隔离https://learn.microsoft.com/en-us/azure/foundry/how-to/configure-private-link
创建自定义Azure Policy治理Microsoft Foundryhttps://learn.microsoft.com/en-us/azure/foundry/how-to/custom-policy-definition
使用标签和RBAC禁用Microsoft Foundry中的预览功能https://learn.microsoft.com/en-us/azure/foundry/how-to/disable-preview-features
为Microsoft Foundry项目配置托管虚拟网络https://learn.microsoft.com/en-us/azure/foundry/how-to/managed-virtual-network
使用内置Azure Policy定义治理Foundry模型部署https://learn.microsoft.com/en-us/azure/foundry/how-to/model-deployment-policy
应用Foundry MCP服务器的安全最佳实践https://learn.microsoft.com/en-us/azure/foundry/mcp/security-best-practices
了解Foundry中的默认护栏安全政策https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/default-safety-policies
为Azure OpenAI应用使用安全系统提示词模板https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/safety-system-message-templates
为Azure OpenAI编写聚焦安全的系统提示词https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/system-message
为微调模型应用安全评估https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning-safety-evaluation
Foundry Agent服务的数据隐私和安全https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/agents/data-privacy-security
了解Foundry中Anthropic Claude的数据隐私和安全规则https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/claude-models/data-privacy
为Foundry OpenAI实施版权规避方案https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/openai/customer-copyright-commitment
了解Azure直售模型的数据、隐私和安全规则https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/openai/data-privacy

Configuration

配置

TopicURL
Configure capability hosts for Foundry Agent Servicehttps://learn.microsoft.com/en-us/azure/foundry/agents/concepts/capability-hosts
Manage and disable Grounding with Bing in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/manage-grounding-with-bing
Create and manage long-term memory in Foundry agentshttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/memory-usage
Configure a private tool catalog with Azure API Centerhttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/private-tool-catalog
Configure custom MCP-based code interpreter environmentshttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/custom-code-interpreter
Configure and use image generation tool in Foundry agentshttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/image-generation
Configure Foundry Agent Service to use existing Azure resourceshttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/use-your-own-resources
Configure declarative agent workflows in VS Codehttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/vs-code-agents-workflow-low-code
Create and deploy hosted Foundry agent workflowshttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/vs-code-agents-workflow-pro-code
Reference for all Foundry built-in evaluatorshttps://learn.microsoft.com/en-us/azure/foundry/concepts/built-in-evaluators
Evaluate AI agents with agent-specific evaluatorshttps://learn.microsoft.com/en-us/azure/foundry/concepts/evaluation-evaluators/agent-evaluators
Create and configure custom evaluators in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/concepts/evaluation-evaluators/custom-evaluators
Configure general-purpose evaluators (coherence, fluency)https://learn.microsoft.com/en-us/azure/foundry/concepts/evaluation-evaluators/general-purpose-evaluators
Configure RAG evaluators for groundedness and completenesshttps://learn.microsoft.com/en-us/azure/foundry/concepts/evaluation-evaluators/rag-evaluators
Configure risk and safety evaluators in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/concepts/evaluation-evaluators/risk-safety-evaluators
Use textual similarity evaluators and metricshttps://learn.microsoft.com/en-us/azure/foundry/concepts/evaluation-evaluators/textual-similarity-evaluators
Enable AI Gateway with API Management in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/configuration/enable-ai-api-management-gateway-portal
Register custom agents with Foundry Control Planehttps://learn.microsoft.com/en-us/azure/foundry/control-plane/register-custom-agent
Configure synthetic data generation in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/fine-tuning/data-generation
Use Foundry Models endpoints and authentication correctlyhttps://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/endpoints
Generate text with Foundry Models using the Responses APIhttps://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/generate-responses
Configure Azure Monitor for Foundry model deploymentshttps://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/monitor-models
Deploy and invoke Anthropic Claude models in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/use-foundry-models-claude
Configure Foundry guardrails and safety controlshttps://learn.microsoft.com/en-us/azure/foundry/guardrails/how-to-create-guardrails
Configure Task Adherence signals for agentshttps://learn.microsoft.com/en-us/azure/foundry/guardrails/task-adherence
Configure bring-your-own storage for Microsoft Foundryhttps://learn.microsoft.com/en-us/azure/foundry/how-to/bring-your-own-azure-storage-foundry
Bind customer-managed storage to Foundry Speech and Languagehttps://learn.microsoft.com/en-us/azure/foundry/how-to/bring-your-own-azure-storage-speech-language-services
Add and configure connections in Microsoft Foundry projectshttps://learn.microsoft.com/en-us/azure/foundry/how-to/connections-add
Create and configure Microsoft Foundry projectshttps://learn.microsoft.com/en-us/azure/foundry/how-to/create-projects
Enable and configure Fireworks models in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/how-to/fireworks/enable-fireworks-models
Import and deploy custom Fireworks models in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/how-to/fireworks/import-custom-models
Understand agent tracing and telemetry in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/observability/concepts/trace-agent-concept
Monitor Foundry agents with the Agent Monitoring Dashboardhttps://learn.microsoft.com/en-us/azure/foundry/observability/how-to/how-to-monitor-agents-dashboard
Configure tracing for LangChain, LangGraph, and SK in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/observability/how-to/trace-agent-framework
Set up OpenTelemetry tracing for Foundry agentshttps://learn.microsoft.com/en-us/azure/foundry/observability/how-to/trace-agent-setup
Use Azure OpenAI v1 API in Foundry Modelshttps://learn.microsoft.com/en-us/azure/foundry/openai/api-version-lifecycle
Configure Prompt Shields for Foundry guardrailshttps://learn.microsoft.com/en-us/azure/foundry/openai/concepts/content-filter-prompt-shields
Enable and configure priority processing for Foundry modelshttps://learn.microsoft.com/en-us/azure/foundry/openai/concepts/priority-processing
Understand and configure DALL-E prompt transformation in Azure OpenAIhttps://learn.microsoft.com/en-us/azure/foundry/openai/concepts/prompt-transformation
Call chat completion models with Azure OpenAI in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/chatgpt
Generate and edit images with Azure OpenAI image modelshttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/dall-e
Run deep research with o3-deep-research via Responses APIhttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/deep-research
Generate and use embeddings with Azure OpenAI in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/embeddings
Configure DPO fine-tuning for Azure OpenAIhttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning-direct-preference-optimization
Configure and use function calling with Azure OpenAIhttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/function-calling
Call vision-enabled chat models with Azure OpenAI in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/gpt-with-vision
Enable and tune JSON mode for Azure OpenAI chat completionshttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/json-mode
Configure and call Foundry model router via Chat APIhttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/model-router
Use predicted outputs to reduce Azure OpenAI latencyhttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/predicted-outputs
Create and tune provisioned deployments in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/provisioned-get-started
Invoke Azure OpenAI reasoning models for complex taskshttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/reasoning
Use Azure OpenAI Responses API with tools and streaminghttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/responses
Enforce JSON schema with structured outputs in Azure OpenAIhttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/structured-outputs
Configure web search tool in Azure OpenAI Responses APIhttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/web-search
Work with Azure OpenAI model deployments in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/working-with-models
Monitor Foundry OpenAI with Azure Monitor datahttps://learn.microsoft.com/en-us/azure/foundry/openai/monitor-openai-reference
主题URL
为Foundry Agent服务配置能力主机https://learn.microsoft.com/en-us/azure/foundry/agents/concepts/capability-hosts
管理和禁用Foundry中的Bing接地能力https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/manage-grounding-with-bing
在Foundry Agent中创建和管理长期记忆https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/memory-usage
使用Azure API Center配置私有工具目录https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/private-tool-catalog
配置自定义基于MCP的代码解释器环境https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/custom-code-interpreter
在Foundry Agent中配置和使用图像生成工具https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/image-generation
配置Foundry Agent服务使用现有Azure资源https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/use-your-own-resources
在VS Code中配置声明式Agent工作流https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/vs-code-agents-workflow-low-code
创建并部署托管的Foundry Agent工作流https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/vs-code-agents-workflow-pro-code
Foundry所有内置评估器参考https://learn.microsoft.com/en-us/azure/foundry/concepts/built-in-evaluators
使用Agent专属评估器评估AI Agenthttps://learn.microsoft.com/en-us/azure/foundry/concepts/evaluation-evaluators/agent-evaluators
在Foundry中创建和配置自定义评估器https://learn.microsoft.com/en-us/azure/foundry/concepts/evaluation-evaluators/custom-evaluators
配置通用评估器（连贯性、流畅度）https://learn.microsoft.com/en-us/azure/foundry/concepts/evaluation-evaluators/general-purpose-evaluators
配置RAG评估器检测事实一致性和完整性https://learn.microsoft.com/en-us/azure/foundry/concepts/evaluation-evaluators/rag-evaluators
在Foundry中配置风险和安全评估器https://learn.microsoft.com/en-us/azure/foundry/concepts/evaluation-evaluators/risk-safety-evaluators
使用文本相似度评估器和指标https://learn.microsoft.com/en-us/azure/foundry/concepts/evaluation-evaluators/textual-similarity-evaluators
在Foundry中启用AI网关和API管理https://learn.microsoft.com/en-us/azure/foundry/configuration/enable-ai-api-management-gateway-portal
向Foundry控制平面注册自定义Agenthttps://learn.microsoft.com/en-us/azure/foundry/control-plane/register-custom-agent
在Foundry中配置合成数据生成https://learn.microsoft.com/en-us/azure/foundry/fine-tuning/data-generation
正确使用Foundry Models端点和认证https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/endpoints
使用Responses API通过Foundry Models生成文本https://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/generate-responses
为Foundry模型部署配置Azure Monitorhttps://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/monitor-models
在Foundry中部署和调用Anthropic Claude模型https://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/use-foundry-models-claude
配置Foundry护栏和安全控制https://learn.microsoft.com/en-us/azure/foundry/guardrails/how-to-create-guardrails
为Agent配置任务依从性信号https://learn.microsoft.com/en-us/azure/foundry/guardrails/task-adherence
为Microsoft Foundry配置自带存储https://learn.microsoft.com/en-us/azure/foundry/how-to/bring-your-own-azure-storage-foundry
绑定客户管理存储到Foundry语音和语言服务https://learn.microsoft.com/en-us/azure/foundry/how-to/bring-your-own-azure-storage-speech-language-services
在Microsoft Foundry项目中添加和配置连接https://learn.microsoft.com/en-us/azure/foundry/how-to/connections-add
创建和配置Microsoft Foundry项目https://learn.microsoft.com/en-us/azure/foundry/how-to/create-projects
在Foundry中启用和配置Fireworks模型https://learn.microsoft.com/en-us/azure/foundry/how-to/fireworks/enable-fireworks-models
在Foundry中导入和部署自定义Fireworks模型https://learn.microsoft.com/en-us/azure/foundry/how-to/fireworks/import-custom-models
了解Foundry中的Agent链路追踪和遥测https://learn.microsoft.com/en-us/azure/foundry/observability/concepts/trace-agent-concept
使用Agent监控面板监控Foundry Agenthttps://learn.microsoft.com/en-us/azure/foundry/observability/how-to/how-to-monitor-agents-dashboard
在Foundry中为LangChain、LangGraph和SK配置链路追踪https://learn.microsoft.com/en-us/azure/foundry/observability/how-to/trace-agent-framework
为Foundry Agent配置OpenTelemetry链路追踪https://learn.microsoft.com/en-us/azure/foundry/observability/how-to/trace-agent-setup
在Foundry Models中使用Azure OpenAI v1 APIhttps://learn.microsoft.com/en-us/azure/foundry/openai/api-version-lifecycle
为Foundry护栏配置提示词防护https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/content-filter-prompt-shields
为Foundry模型启用和配置优先级处理https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/priority-processing
了解并配置Azure OpenAI中的DALL-E提示词转换https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/prompt-transformation
在Foundry中通过Azure OpenAI调用聊天补全模型https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/chatgpt
使用Azure OpenAI图像模型生成和编辑图像https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/dall-e
通过Responses API使用o3-deep-research运行深度调研https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/deep-research
在Foundry中通过Azure OpenAI生成和使用嵌入向量https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/embeddings
为Azure OpenAI配置DPO微调https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning-direct-preference-optimization
配置和使用Azure OpenAI的函数调用能力https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/function-calling
在Foundry中通过Azure OpenAI调用支持视觉的聊天模型https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/gpt-with-vision
为Azure OpenAI聊天补全启用和调整JSON模式https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/json-mode
通过Chat API配置和调用Foundry模型路由器https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/model-router
使用预测输出降低Azure OpenAI延迟https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/predicted-outputs
在Foundry中创建和调整预置吞吐量部署https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/provisioned-get-started
调用Azure OpenAI推理模型处理复杂任务https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/reasoning
结合工具和流式传输使用Azure OpenAI Responses APIhttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/responses
通过结构化输出在Azure OpenAI中强制JSON schemahttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/structured-outputs
在Azure OpenAI Responses API中配置网络搜索工具https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/web-search
在Foundry中管理Azure OpenAI模型部署https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/working-with-models
使用Azure Monitor数据监控Foundry OpenAIhttps://learn.microsoft.com/en-us/azure/foundry/openai/monitor-openai-reference

Integrations & Coding Patterns

集成与编码模式

TopicURL
Implement agents, conversations, and responses via SDKshttps://learn.microsoft.com/en-us/azure/foundry/agents/concepts/runtime-components
Connect enterprise AI gateways to Foundry Agent Servicehttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/ai-gateway
Connect Foundry agents to Foundry IQ knowledge baseshttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/foundry-iq-connect
Invoke Foundry Agent Applications via Responses API protocolhttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/publish-responses
Add and configure Agent2Agent endpoints as toolshttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/agent-to-agent
Connect Azure AI Search indexes to Foundry agentshttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/ai-search
Integrate Azure Speech MCP tool with Foundry agentshttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/azure-ai-speech
Use Grounding with Bing Search tools in agentshttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/bing-tools
Automate web browsing with Browser Automation toolhttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/browser-automation
Use Code Interpreter tool with Foundry agentshttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/code-interpreter
Integrate Microsoft Fabric data agent with Foundryhttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/fabric
Configure file search tool and vector stores for agentshttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/file-search
Connect Foundry agents to MCP servers via toolshttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/model-context-protocol
Ground Foundry agents with SharePoint content via APIhttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/sharepoint
Configure and use the web search tool in agentshttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/web-search
Use Azure OpenAI graders in Foundry SDKhttps://learn.microsoft.com/en-us/azure/foundry/concepts/evaluation-evaluators/azure-openai-graders
Run fine-tuning jobs with azd extensionhttps://learn.microsoft.com/en-us/azure/foundry/fine-tuning/fine-tune-cli
Configure Claude Code CLI and VS Code with Foundryhttps://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/configure-claude-code
Deploy and call DeepSeek-R1 in Foundry Modelshttps://learn.microsoft.com/en-us/azure/foundry/foundry-models/tutorials/get-started-deepseek-r1
Apply Task Adherence checks in agent workflowshttps://learn.microsoft.com/en-us/azure/foundry/guardrails/how-to-task-adherence
Integrate third-party safety tools with Foundryhttps://learn.microsoft.com/en-us/azure/foundry/guardrails/third-party-integrations
Run batch cloud evaluations with Foundry SDKhttps://learn.microsoft.com/en-us/azure/foundry/how-to/develop/cloud-evaluation
Integrate LangChain and LangGraph with Foundryhttps://learn.microsoft.com/en-us/azure/foundry/how-to/develop/langchain
Build LangGraph agents with Foundry Agent Servicehttps://learn.microsoft.com/en-us/azure/foundry/how-to/develop/langchain-agents
Add Foundry long-term memory to LangChain appshttps://learn.microsoft.com/en-us/azure/foundry/how-to/develop/langchain-memory
Use LangChain with Foundry model deploymentshttps://learn.microsoft.com/en-us/azure/foundry/how-to/develop/langchain-models
Trace LangChain apps with Foundry and Azure Monitorhttps://learn.microsoft.com/en-us/azure/foundry/how-to/develop/langchain-traces
Run AI Red Teaming Agent scans in cloudhttps://learn.microsoft.com/en-us/azure/foundry/how-to/develop/run-ai-red-teaming-cloud
Run local AI Red Teaming scans with SDKhttps://learn.microsoft.com/en-us/azure/foundry/how-to/develop/run-scans-ai-red-teaming-agent
Integrate Foundry endpoints with external applicationshttps://learn.microsoft.com/en-us/azure/foundry/how-to/integrate-with-other-apps
Set up an Azure Key Vault connection for Microsoft Foundryhttps://learn.microsoft.com/en-us/azure/foundry/how-to/set-up-key-vault-connection
Use Foundry MCP Server tools with example promptshttps://learn.microsoft.com/en-us/azure/foundry/mcp/available-tools
Build and register a custom MCP server for Foundryhttps://learn.microsoft.com/en-us/azure/foundry/mcp/build-your-own-mcp-server
Connect VS Code to Foundry MCP Serverhttps://learn.microsoft.com/en-us/azure/foundry/mcp/get-started
Call Azure OpenAI audio models via APIhttps://learn.microsoft.com/en-us/azure/foundry/openai/audio-completions-quickstart
Authoring operations for Foundry OpenAI REST APIhttps://learn.microsoft.com/en-us/azure/foundry/openai/authoring-reference-preview
Use groundedness detection with Foundry OpenAIhttps://learn.microsoft.com/en-us/azure/foundry/openai/concepts/content-filter-groundedness
Integrate Codex CLI and VS Code with Azure OpenAIhttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/codex
Fine-tune Foundry models via SDK and RESThttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning
Fine-tune tool calling behavior in Azure OpenAIhttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning-functions
Integrate GPT Realtime API for low-latency audiohttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/realtime-audio
Use GPT Realtime API over SIPhttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/realtime-audio-sip
Use GPT Realtime API over WebRTChttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/realtime-audio-webrtc
Use GPT Realtime API over WebSocketshttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/realtime-audio-websockets
Set up and secure Azure OpenAI webhooks in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/webhooks
Integrate with Azure OpenAI v1 REST API in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/openai/latest
Integrate with Azure OpenAI v1 REST API in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/openai/latest
Integrate with Azure OpenAI v1 REST API in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/openai/latest
Integrate with Azure OpenAI v1 REST API in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/openai/latest
Integrate with Azure OpenAI v1 REST API in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/openai/latest
Integrate with Azure OpenAI v1 REST API in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/openai/latest
Integrate with Azure OpenAI v1 REST API in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/openai/latest
Integrate with Azure OpenAI v1 REST API in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/openai/latest
Integrate with Azure OpenAI v1 REST API in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/openai/latest
Implement realtime audio events for Foundry OpenAIhttps://learn.microsoft.com/en-us/azure/foundry/openai/realtime-audio-reference
Call Azure OpenAI inference REST APIs in Foundryhttps://learn.microsoft.com/en-us/azure/foundry/openai/reference
Use Foundry OpenAI preview inference REST APIhttps://learn.microsoft.com/en-us/azure/foundry/openai/reference-preview
Call Foundry OpenAI v1 preview REST endpointshttps://learn.microsoft.com/en-us/azure/foundry/openai/reference-preview-latest
Build document search with Azure OpenAI embeddings APIhttps://learn.microsoft.com/en-us/azure/foundry/openai/tutorials/embeddings
Use Azure OpenAI Whisper for speech to texthttps://learn.microsoft.com/en-us/azure/foundry/openai/whisper-quickstart
Call Microsoft Foundry REST APIs for projectshttps://learn.microsoft.com/en-us/azure/foundry/reference/foundry-project
Use Microsoft Foundry Project REST API (preview)https://learn.microsoft.com/en-us/azure/foundry/reference/foundry-project-rest-preview
主题URL
通过SDK实现Agent、会话和响应能力https://learn.microsoft.com/en-us/azure/foundry/agents/concepts/runtime-components
连接企业AI网关到Foundry Agent服务https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/ai-gateway
连接Foundry Agent到Foundry IQ知识库https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/foundry-iq-connect
通过Responses API协议调用Foundry Agent应用https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/publish-responses
添加和配置Agent2Agent端点作为工具https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/agent-to-agent
连接Azure AI Search索引到Foundry Agenthttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/ai-search
集成Azure Speech MCP工具到Foundry Agenthttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/azure-ai-speech
在Agent中使用Bing搜索接地工具https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/bing-tools
使用浏览器自动化工具实现网页浏览自动化https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/browser-automation
在Foundry Agent中使用代码解释器工具https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/code-interpreter
集成Microsoft Fabric数据Agent到Foundryhttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/fabric
为Agent配置文件搜索工具和向量存储https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/file-search
通过工具连接Foundry Agent到MCP服务器https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/model-context-protocol
通过API为Foundry Agent接入SharePoint内容https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/sharepoint
配置和使用Agent中的网络搜索工具https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/web-search
在Foundry SDK中使用Azure OpenAI评分器https://learn.microsoft.com/en-us/azure/foundry/concepts/evaluation-evaluators/azure-openai-graders
使用azd扩展运行微调任务https://learn.microsoft.com/en-us/azure/foundry/fine-tuning/fine-tune-cli
为Claude Code CLI和VS Code配置Foundry集成https://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/configure-claude-code
在Foundry Models中部署和调用DeepSeek-R1https://learn.microsoft.com/en-us/azure/foundry/foundry-models/tutorials/get-started-deepseek-r1
在Agent工作流中应用任务依从性检查https://learn.microsoft.com/en-us/azure/foundry/guardrails/how-to-task-adherence
集成第三方安全工具到Foundryhttps://learn.microsoft.com/en-us/azure/foundry/guardrails/third-party-integrations
使用Foundry SDK运行批量云评估https://learn.microsoft.com/en-us/azure/foundry/how-to/develop/cloud-evaluation
集成LangChain和LangGraph到Foundryhttps://learn.microsoft.com/en-us/azure/foundry/how-to/develop/langchain
使用Foundry Agent服务构建LangGraph Agenthttps://learn.microsoft.com/en-us/azure/foundry/how-to/develop/langchain-agents
为LangChain应用添加Foundry长期记忆https://learn.microsoft.com/en-us/azure/foundry/how-to/develop/langchain-memory
结合LangChain使用Foundry模型部署https://learn.microsoft.com/en-us/azure/foundry/how-to/develop/langchain-models
使用Foundry和Azure Monitor追踪LangChain应用https://learn.microsoft.com/en-us/azure/foundry/how-to/develop/langchain-traces
在云端运行AI红队Agent扫描https://learn.microsoft.com/en-us/azure/foundry/how-to/develop/run-ai-red-teaming-cloud
使用SDK运行本地AI红队扫描https://learn.microsoft.com/en-us/azure/foundry/how-to/develop/run-scans-ai-red-teaming-agent
集成Foundry端点到外部应用https://learn.microsoft.com/en-us/azure/foundry/how-to/integrate-with-other-apps
为Microsoft Foundry配置Azure Key Vault连接https://learn.microsoft.com/en-us/azure/foundry/how-to/set-up-key-vault-connection
使用Foundry MCP服务器工具及示例提示词https://learn.microsoft.com/en-us/azure/foundry/mcp/available-tools
构建并注册自定义MCP服务器到Foundryhttps://learn.microsoft.com/en-us/azure/foundry/mcp/build-your-own-mcp-server
连接VS Code到Foundry MCP服务器https://learn.microsoft.com/en-us/azure/foundry/mcp/get-started
通过API调用Azure OpenAI音频模型https://learn.microsoft.com/en-us/azure/foundry/openai/audio-completions-quickstart
Foundry OpenAI REST API的创作操作指南https://learn.microsoft.com/en-us/azure/foundry/openai/authoring-reference-preview
在Foundry OpenAI中使用事实一致性检测https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/content-filter-groundedness
集成Codex CLI和VS Code到Azure OpenAIhttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/codex
通过SDK和REST API微调Foundry模型https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning
微调Azure OpenAI的工具调用行为https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning-functions
集成GPT Realtime API实现低延迟音频能力https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/realtime-audio
通过SIP使用GPT Realtime APIhttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/realtime-audio-sip
通过WebRTC使用GPT Realtime APIhttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/realtime-audio-webrtc
通过WebSockets使用GPT Realtime APIhttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/realtime-audio-websockets
在Foundry中配置和保护Azure OpenAI Webhookhttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/webhooks
集成Foundry中的Azure OpenAI v1 REST APIhttps://learn.microsoft.com/en-us/azure/foundry/openai/latest
集成Foundry中的Azure OpenAI v1 REST APIhttps://learn.microsoft.com/en-us/azure/foundry/openai/latest
集成Foundry中的Azure OpenAI v1 REST APIhttps://learn.microsoft.com/en-us/azure/foundry/openai/latest
集成Foundry中的Azure OpenAI v1 REST APIhttps://learn.microsoft.com/en-us/azure/foundry/openai/latest
集成Foundry中的Azure OpenAI v1 REST APIhttps://learn.microsoft.com/en-us/azure/foundry/openai/latest
集成Foundry中的Azure OpenAI v1 REST APIhttps://learn.microsoft.com/en-us/azure/foundry/openai/latest
集成Foundry中的Azure OpenAI v1 REST APIhttps://learn.microsoft.com/en-us/azure/foundry/openai/latest
集成Foundry中的Azure OpenAI v1 REST APIhttps://learn.microsoft.com/en-us/azure/foundry/openai/latest
集成Foundry中的Azure OpenAI v1 REST APIhttps://learn.microsoft.com/en-us/azure/foundry/openai/latest
集成Foundry中的Azure OpenAI v1 REST APIhttps://learn.microsoft.com/en-us/azure/foundry/openai/latest
实现Foundry OpenAI的实时音频事件https://learn.microsoft.com/en-us/azure/foundry/openai/realtime-audio-reference
在Foundry中调用Azure OpenAI推理REST APIhttps://learn.microsoft.com/en-us/azure/foundry/openai/reference
使用Foundry OpenAI预览版推理REST APIhttps://learn.microsoft.com/en-us/azure/foundry/openai/reference-preview
调用Foundry OpenAI v1预览版REST端点https://learn.microsoft.com/en-us/azure/foundry/openai/reference-preview-latest
使用Azure OpenAI嵌入向量API构建文档搜索https://learn.microsoft.com/en-us/azure/foundry/openai/tutorials/embeddings
使用Azure OpenAI Whisper实现语音转文字https://learn.microsoft.com/en-us/azure/foundry/openai/whisper-quickstart
调用Microsoft Foundry项目相关REST APIhttps://learn.microsoft.com/en-us/azure/foundry/reference/foundry-project
使用Microsoft Foundry项目REST API（预览版）https://learn.microsoft.com/en-us/azure/foundry/reference/foundry-project-rest-preview

Deployment

部署

TopicURL
Set up infrastructure for Foundry Agent Servicehttps://learn.microsoft.com/en-us/azure/foundry/agents/environment-setup
Deploy Foundry agents as digital workers in Agent 365https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/agent-365
Deploy custom hosted agents to Foundry Agent Servicehttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/deploy-hosted-agent
Manage lifecycle of hosted agent deploymentshttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/manage-hosted-agent
Publish Foundry agents as managed Azure resourceshttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/publish-agent
Publish Foundry agents to Microsoft 365 Copilot and Teamshttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/publish-copilot
Deploy containerized hosted agents to Foundryhttps://learn.microsoft.com/en-us/azure/foundry/agents/quickstarts/quickstart-hosted-agent
Deploy Foundry Models using Azure CLI and Bicep templateshttps://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/create-model-deployments
Deploy Foundry Models via Foundry portal for inferencehttps://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/deploy-foundry-models
Deploy Microsoft Foundry resources using Bicephttps://learn.microsoft.com/en-us/azure/foundry/how-to/create-resource-template
Provision Foundry with Terraform IaC templateshttps://learn.microsoft.com/en-us/azure/foundry/how-to/create-resource-terraform
Run Foundry evaluations in Azure DevOps pipelineshttps://learn.microsoft.com/en-us/azure/foundry/how-to/evaluation-azure-devops
Run Foundry evaluations in GitHub Actions CIhttps://learn.microsoft.com/en-us/azure/foundry/how-to/evaluation-github-action
Deploy fine-tuned models on Foundry hostinghttps://learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning-deploy
Check Foundry feature and model availability by regionhttps://learn.microsoft.com/en-us/azure/foundry/reference/region-support
主题URL
搭建Foundry Agent服务的基础设施https://learn.microsoft.com/en-us/azure/foundry/agents/environment-setup
将Foundry Agent作为数字员工部署到Agent 365https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/agent-365
部署自定义托管Agent到Foundry Agent服务https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/deploy-hosted-agent
管理托管Agent部署的生命周期https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/manage-hosted-agent
将Foundry Agent发布为托管Azure资源https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/publish-agent
将Foundry Agent发布到Microsoft 365 Copilot和Teamshttps://learn.microsoft.com/en-us/azure/foundry/agents/how-to/publish-copilot
部署容器化托管Agent到Foundryhttps://learn.microsoft.com/en-us/azure/foundry/agents/quickstarts/quickstart-hosted-agent
使用Azure CLI和Bicep模板部署Foundry Modelshttps://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/create-model-deployments
通过Foundry门户部署Foundry Models用于推理https://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/deploy-foundry-models
使用Bicep部署Microsoft Foundry资源https://learn.microsoft.com/en-us/azure/foundry/how-to/create-resource-template
使用Terraform IaC模板预置Foundry资源https://learn.microsoft.com/en-us/azure/foundry/how-to/create-resource-terraform
在Azure DevOps流水线中运行Foundry评估https://learn.microsoft.com/en-us/azure/foundry/how-to/evaluation-azure-devops
在GitHub Actions CI中运行Foundry评估https://learn.microsoft.com/en-us/azure/foundry/how-to/evaluation-github-action
在Foundry托管环境部署微调后的模型https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning-deploy
按区域查看Foundry功能和模型可用性https://learn.microsoft.com/en-us/azure/foundry/reference/region-support