[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-microsoft-azure-ai-language-conversations-py":3,"mdc-ne3p5u-key":42,"related-repo-microsoft-azure-ai-language-conversations-py":947,"related-org-microsoft-azure-ai-language-conversations-py":1048},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":25,"repoUrl":26,"updatedAt":27,"license":28,"forks":29,"topics":30,"repo":37,"sourceUrl":40,"mdContent":41},"azure-ai-language-conversations-py","implement conversational language understanding with Python","Implement Conversational Language Understanding (CLU) using the azure-ai-language-conversations Python SDK. Use when working with ConversationAnalysisClient to analyze conversation intent and entities, building NLP features, or integrating language understanding into applications.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"microsoft","Microsoft","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fmicrosoft.png",[12,16,19,22],{"name":13,"slug":14,"type":15},"Azure","azure","tag",{"name":17,"slug":18,"type":15},"LLM","llm",{"name":20,"slug":21,"type":15},"Python","python",{"name":23,"slug":24,"type":15},"Analytics","analytics",2804,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills","2026-07-31T05:54:29.068751","MIT",315,[31,32,14,33,34,35,36],"agent-skills","agents","foundry","mcp","sdk","skills",{"repoUrl":26,"stars":25,"forks":29,"topics":38,"description":39},[31,32,14,33,34,35,36],"Skills, MCP servers, Custom Agents, Agents.md for SDKs to ground Coding Agents","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Ftree\u002FHEAD\u002F.github\u002Fplugins\u002Fazure-sdk-python\u002Fskills\u002Fazure-ai-language-conversations-py","---\nname: azure-ai-language-conversations-py\ndescription: Implement Conversational Language Understanding (CLU) using the azure-ai-language-conversations Python SDK. Use when working with ConversationAnalysisClient to analyze conversation intent and entities, building NLP features, or integrating language understanding into applications.\nlicense: MIT\nmetadata:\n  author: Microsoft\n  version: \"1.0.0\"\n---\n\n# Azure AI Language Conversations for Python\n\n## System Prompt\nYou are an expert Python developer specializing in Azure AI Services and Natural Language Processing.\nYour task is to help users implement Conversational Language Understanding (CLU) using the `azure-ai-language-conversations` SDK.\n\nWhen responding to requests about Azure AI Language Conversations:\n1. Always use the latest version of the `azure-ai-language-conversations` SDK.\n2. Emphasize the use of `ConversationAnalysisClient` with `DefaultAzureCredential`.\n3. Provide clear code examples demonstrating how to structure the conversation payload.\n4. Handle exceptions properly.\n\n## Authentication & Lifecycle\n\n> **🔑 Two rules apply to every code sample below:**\n>\n> 1. **Prefer `DefaultAzureCredential`.** It works locally (Azure CLI \u002F VS Code \u002F Developer CLI) and in Azure (managed identity, workload identity) with no code change. Avoid connection strings, account\u002FAPI keys — they bypass Entra audit and rotation.\n>    - Local dev: `DefaultAzureCredential` works as-is.\n>    - Production: set `AZURE_TOKEN_CREDENTIALS=prod` (or `AZURE_TOKEN_CREDENTIALS=\u003Cspecific_credential>`) to constrain the credential chain to production-safe credentials.\n> 2. **Wrap every client in a context manager** so HTTP transports, sockets, and token caches are released deterministically:\n>    - Sync: `with \u003CClient>(...) as client:`\n>    - Async: `async with \u003CClient>(...) as client:` **and** `async with DefaultAzureCredential() as credential:` (from `azure.identity.aio`)\n>\n> Snippets may abbreviate this setup, but production code should always follow both rules.\n\n`ConversationAnalysisClient` accepts a `TokenCredential` such as `DefaultAzureCredential`. Use the token credential — it works locally (Azure CLI \u002F VS Code \u002F Developer CLI) and in Azure (managed identity, workload identity) with no code change.\n\n### Legacy: API Key (existing keyed deployments)\n\nNew code should use `DefaultAzureCredential`. Use `AzureKeyCredential` only if you have an existing keyed deployment that hasn't been migrated to Entra ID yet — for example, regulated environments still completing their Entra rollout.\n\n```python\nimport os\nfrom azure.core.credentials import AzureKeyCredential\nfrom azure.ai.language.conversations import ConversationAnalysisClient\n\nendpoint = os.environ[\"AZURE_CONVERSATIONS_ENDPOINT\"]\nkey = os.environ[\"AZURE_CONVERSATIONS_KEY\"]\n\nwith ConversationAnalysisClient(endpoint, AzureKeyCredential(key)) as client:\n    # See \"Basic Conversation Analysis\" below for the analyze_conversation payload\n    ...\n```\n\n## Best Practices\n- **Pick sync OR async and stay consistent.** Do not mix `azure.ai.language.conversations` sync clients with `azure.ai.language.conversations.aio` async clients in the same call path. Choose one mode per module.\n- **Always use context managers for clients and async credentials.** Wrap every client in `with ConversationAnalysisClient(...) as client:` (sync) or `async with ConversationAnalysisClient(...) as client:` (async). For async `DefaultAzureCredential` from `azure.identity.aio`, also use `async with credential:` so tokens and transports are cleaned up.\n- **Use `DefaultAzureCredential`** for portable auth across local dev and Azure (avoid API keys; they bypass Entra audit and rotation).\n- Use environment variables for the endpoint, project name, and deployment name.\n- Clearly map the `participantId` and `id` in the `conversationItem` payload.\n\n## Examples\n\n### Basic Conversation Analysis\n```python\nimport os\nfrom azure.identity import DefaultAzureCredential\nfrom azure.ai.language.conversations import ConversationAnalysisClient\n\nendpoint = os.environ[\"AZURE_CONVERSATIONS_ENDPOINT\"]\nproject_name = os.environ[\"AZURE_CONVERSATIONS_PROJECT\"]\ndeployment_name = os.environ[\"AZURE_CONVERSATIONS_DEPLOYMENT\"]\n\n# DefaultAzureCredential works locally and in Azure with no code change.\ncredential = DefaultAzureCredential()\n\nwith ConversationAnalysisClient(endpoint, credential) as client:\n    query = \"Send an email to Carol about the tomorrow's meeting\"\n    result = client.analyze_conversation(\n        task={\n            \"kind\": \"Conversation\",\n            \"analysisInput\": {\n                \"conversationItem\": {\n                    \"participantId\": \"1\",\n                    \"id\": \"1\",\n                    \"modality\": \"text\",\n                    \"language\": \"en\",\n                    \"text\": query\n                },\n                \"isLoggingEnabled\": False\n            },\n            \"parameters\": {\n                \"projectName\": project_name,\n                \"deploymentName\": deployment_name,\n                \"verbose\": True\n            }\n        }\n    )\n\n    print(f\"Top intent: {result['result']['prediction']['topIntent']}\")\n```\n\n## Reference Files\n\n| File | Contents |\n|------|----------|\n| [references\u002Fcapabilities.md](references\u002Fcapabilities.md) | Additional non-hero capabilities, operation-group coverage, and production checklists. |\n| [references\u002Fnon-hero-scenarios.md](references\u002Fnon-hero-scenarios.md) | Dedicated non-hero examples for secondary\u002Fadvanced scenarios. |\n",{"data":43,"body":46},{"name":4,"description":6,"license":28,"metadata":44},{"author":9,"version":45},"1.0.0",{"type":47,"children":48},"root",[49,58,65,80,85,132,138,271,296,303,323,425,431,557,563,569,874,880,941],{"type":50,"tag":51,"props":52,"children":54},"element","h1",{"id":53},"azure-ai-language-conversations-for-python",[55],{"type":56,"value":57},"text","Azure AI Language Conversations for Python",{"type":50,"tag":59,"props":60,"children":62},"h2",{"id":61},"system-prompt",[63],{"type":56,"value":64},"System Prompt",{"type":50,"tag":66,"props":67,"children":68},"p",{},[69,71,78],{"type":56,"value":70},"You are an expert Python developer specializing in Azure AI Services and Natural Language Processing.\nYour task is to help users implement Conversational Language Understanding (CLU) using the ",{"type":50,"tag":72,"props":73,"children":75},"code",{"className":74},[],[76],{"type":56,"value":77},"azure-ai-language-conversations",{"type":56,"value":79}," SDK.",{"type":50,"tag":66,"props":81,"children":82},{},[83],{"type":56,"value":84},"When responding to requests about Azure AI Language Conversations:",{"type":50,"tag":86,"props":87,"children":88},"ol",{},[89,101,122,127],{"type":50,"tag":90,"props":91,"children":92},"li",{},[93,95,100],{"type":56,"value":94},"Always use the latest version of the ",{"type":50,"tag":72,"props":96,"children":98},{"className":97},[],[99],{"type":56,"value":77},{"type":56,"value":79},{"type":50,"tag":90,"props":102,"children":103},{},[104,106,112,114,120],{"type":56,"value":105},"Emphasize the use of ",{"type":50,"tag":72,"props":107,"children":109},{"className":108},[],[110],{"type":56,"value":111},"ConversationAnalysisClient",{"type":56,"value":113}," with ",{"type":50,"tag":72,"props":115,"children":117},{"className":116},[],[118],{"type":56,"value":119},"DefaultAzureCredential",{"type":56,"value":121},".",{"type":50,"tag":90,"props":123,"children":124},{},[125],{"type":56,"value":126},"Provide clear code examples demonstrating how to structure the conversation payload.",{"type":50,"tag":90,"props":128,"children":129},{},[130],{"type":56,"value":131},"Handle exceptions properly.",{"type":50,"tag":59,"props":133,"children":135},{"id":134},"authentication-lifecycle",[136],{"type":56,"value":137},"Authentication & Lifecycle",{"type":50,"tag":139,"props":140,"children":141},"blockquote",{},[142,151,266],{"type":50,"tag":66,"props":143,"children":144},{},[145],{"type":50,"tag":146,"props":147,"children":148},"strong",{},[149],{"type":56,"value":150},"🔑 Two rules apply to every code sample below:",{"type":50,"tag":86,"props":152,"children":153},{},[154,207],{"type":50,"tag":90,"props":155,"children":156},{},[157,168,170],{"type":50,"tag":146,"props":158,"children":159},{},[160,162,167],{"type":56,"value":161},"Prefer ",{"type":50,"tag":72,"props":163,"children":165},{"className":164},[],[166],{"type":56,"value":119},{"type":56,"value":121},{"type":56,"value":169}," It works locally (Azure CLI \u002F VS Code \u002F Developer CLI) and in Azure (managed identity, workload identity) with no code change. Avoid connection strings, account\u002FAPI keys — they bypass Entra audit and rotation.\n",{"type":50,"tag":171,"props":172,"children":173},"ul",{},[174,186],{"type":50,"tag":90,"props":175,"children":176},{},[177,179,184],{"type":56,"value":178},"Local dev: ",{"type":50,"tag":72,"props":180,"children":182},{"className":181},[],[183],{"type":56,"value":119},{"type":56,"value":185}," works as-is.",{"type":50,"tag":90,"props":187,"children":188},{},[189,191,197,199,205],{"type":56,"value":190},"Production: set ",{"type":50,"tag":72,"props":192,"children":194},{"className":193},[],[195],{"type":56,"value":196},"AZURE_TOKEN_CREDENTIALS=prod",{"type":56,"value":198}," (or ",{"type":50,"tag":72,"props":200,"children":202},{"className":201},[],[203],{"type":56,"value":204},"AZURE_TOKEN_CREDENTIALS=\u003Cspecific_credential>",{"type":56,"value":206},") to constrain the credential chain to production-safe credentials.",{"type":50,"tag":90,"props":208,"children":209},{},[210,215,217],{"type":50,"tag":146,"props":211,"children":212},{},[213],{"type":56,"value":214},"Wrap every client in a context manager",{"type":56,"value":216}," so HTTP transports, sockets, and token caches are released deterministically:\n",{"type":50,"tag":171,"props":218,"children":219},{},[220,231],{"type":50,"tag":90,"props":221,"children":222},{},[223,225],{"type":56,"value":224},"Sync: ",{"type":50,"tag":72,"props":226,"children":228},{"className":227},[],[229],{"type":56,"value":230},"with \u003CClient>(...) as client:",{"type":50,"tag":90,"props":232,"children":233},{},[234,236,242,244,249,250,256,258,264],{"type":56,"value":235},"Async: ",{"type":50,"tag":72,"props":237,"children":239},{"className":238},[],[240],{"type":56,"value":241},"async with \u003CClient>(...) as client:",{"type":56,"value":243}," ",{"type":50,"tag":146,"props":245,"children":246},{},[247],{"type":56,"value":248},"and",{"type":56,"value":243},{"type":50,"tag":72,"props":251,"children":253},{"className":252},[],[254],{"type":56,"value":255},"async with DefaultAzureCredential() as credential:",{"type":56,"value":257}," (from ",{"type":50,"tag":72,"props":259,"children":261},{"className":260},[],[262],{"type":56,"value":263},"azure.identity.aio",{"type":56,"value":265},")",{"type":50,"tag":66,"props":267,"children":268},{},[269],{"type":56,"value":270},"Snippets may abbreviate this setup, but production code should always follow both rules.",{"type":50,"tag":66,"props":272,"children":273},{},[274,279,281,287,289,294],{"type":50,"tag":72,"props":275,"children":277},{"className":276},[],[278],{"type":56,"value":111},{"type":56,"value":280}," accepts a ",{"type":50,"tag":72,"props":282,"children":284},{"className":283},[],[285],{"type":56,"value":286},"TokenCredential",{"type":56,"value":288}," such as ",{"type":50,"tag":72,"props":290,"children":292},{"className":291},[],[293],{"type":56,"value":119},{"type":56,"value":295},". Use the token credential — it works locally (Azure CLI \u002F VS Code \u002F Developer CLI) and in Azure (managed identity, workload identity) with no code change.",{"type":50,"tag":297,"props":298,"children":300},"h3",{"id":299},"legacy-api-key-existing-keyed-deployments",[301],{"type":56,"value":302},"Legacy: API Key (existing keyed deployments)",{"type":50,"tag":66,"props":304,"children":305},{},[306,308,313,315,321],{"type":56,"value":307},"New code should use ",{"type":50,"tag":72,"props":309,"children":311},{"className":310},[],[312],{"type":56,"value":119},{"type":56,"value":314},". Use ",{"type":50,"tag":72,"props":316,"children":318},{"className":317},[],[319],{"type":56,"value":320},"AzureKeyCredential",{"type":56,"value":322}," only if you have an existing keyed deployment that hasn't been migrated to Entra ID yet — for example, regulated environments still completing their Entra rollout.",{"type":50,"tag":324,"props":325,"children":329},"pre",{"className":326,"code":327,"language":21,"meta":328,"style":328},"language-python shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","import os\nfrom azure.core.credentials import AzureKeyCredential\nfrom azure.ai.language.conversations import ConversationAnalysisClient\n\nendpoint = os.environ[\"AZURE_CONVERSATIONS_ENDPOINT\"]\nkey = os.environ[\"AZURE_CONVERSATIONS_KEY\"]\n\nwith ConversationAnalysisClient(endpoint, AzureKeyCredential(key)) as client:\n    # See \"Basic Conversation Analysis\" below for the analyze_conversation payload\n    ...\n","",[330],{"type":50,"tag":72,"props":331,"children":332},{"__ignoreMap":328},[333,344,353,362,372,381,390,398,407,416],{"type":50,"tag":334,"props":335,"children":338},"span",{"class":336,"line":337},"line",1,[339],{"type":50,"tag":334,"props":340,"children":341},{},[342],{"type":56,"value":343},"import os\n",{"type":50,"tag":334,"props":345,"children":347},{"class":336,"line":346},2,[348],{"type":50,"tag":334,"props":349,"children":350},{},[351],{"type":56,"value":352},"from azure.core.credentials import AzureKeyCredential\n",{"type":50,"tag":334,"props":354,"children":356},{"class":336,"line":355},3,[357],{"type":50,"tag":334,"props":358,"children":359},{},[360],{"type":56,"value":361},"from azure.ai.language.conversations import ConversationAnalysisClient\n",{"type":50,"tag":334,"props":363,"children":365},{"class":336,"line":364},4,[366],{"type":50,"tag":334,"props":367,"children":369},{"emptyLinePlaceholder":368},true,[370],{"type":56,"value":371},"\n",{"type":50,"tag":334,"props":373,"children":375},{"class":336,"line":374},5,[376],{"type":50,"tag":334,"props":377,"children":378},{},[379],{"type":56,"value":380},"endpoint = os.environ[\"AZURE_CONVERSATIONS_ENDPOINT\"]\n",{"type":50,"tag":334,"props":382,"children":384},{"class":336,"line":383},6,[385],{"type":50,"tag":334,"props":386,"children":387},{},[388],{"type":56,"value":389},"key = os.environ[\"AZURE_CONVERSATIONS_KEY\"]\n",{"type":50,"tag":334,"props":391,"children":393},{"class":336,"line":392},7,[394],{"type":50,"tag":334,"props":395,"children":396},{"emptyLinePlaceholder":368},[397],{"type":56,"value":371},{"type":50,"tag":334,"props":399,"children":401},{"class":336,"line":400},8,[402],{"type":50,"tag":334,"props":403,"children":404},{},[405],{"type":56,"value":406},"with ConversationAnalysisClient(endpoint, AzureKeyCredential(key)) as client:\n",{"type":50,"tag":334,"props":408,"children":410},{"class":336,"line":409},9,[411],{"type":50,"tag":334,"props":412,"children":413},{},[414],{"type":56,"value":415},"    # See \"Basic Conversation Analysis\" below for the analyze_conversation payload\n",{"type":50,"tag":334,"props":417,"children":419},{"class":336,"line":418},10,[420],{"type":50,"tag":334,"props":421,"children":422},{},[423],{"type":56,"value":424},"    ...\n",{"type":50,"tag":59,"props":426,"children":428},{"id":427},"best-practices",[429],{"type":56,"value":430},"Best Practices",{"type":50,"tag":171,"props":432,"children":433},{},[434,460,508,523,528],{"type":50,"tag":90,"props":435,"children":436},{},[437,442,444,450,452,458],{"type":50,"tag":146,"props":438,"children":439},{},[440],{"type":56,"value":441},"Pick sync OR async and stay consistent.",{"type":56,"value":443}," Do not mix ",{"type":50,"tag":72,"props":445,"children":447},{"className":446},[],[448],{"type":56,"value":449},"azure.ai.language.conversations",{"type":56,"value":451}," sync clients with ",{"type":50,"tag":72,"props":453,"children":455},{"className":454},[],[456],{"type":56,"value":457},"azure.ai.language.conversations.aio",{"type":56,"value":459}," async clients in the same call path. Choose one mode per module.",{"type":50,"tag":90,"props":461,"children":462},{},[463,468,470,476,478,484,486,491,493,498,500,506],{"type":50,"tag":146,"props":464,"children":465},{},[466],{"type":56,"value":467},"Always use context managers for clients and async credentials.",{"type":56,"value":469}," Wrap every client in ",{"type":50,"tag":72,"props":471,"children":473},{"className":472},[],[474],{"type":56,"value":475},"with ConversationAnalysisClient(...) as client:",{"type":56,"value":477}," (sync) or ",{"type":50,"tag":72,"props":479,"children":481},{"className":480},[],[482],{"type":56,"value":483},"async with ConversationAnalysisClient(...) as client:",{"type":56,"value":485}," (async). For async ",{"type":50,"tag":72,"props":487,"children":489},{"className":488},[],[490],{"type":56,"value":119},{"type":56,"value":492}," from ",{"type":50,"tag":72,"props":494,"children":496},{"className":495},[],[497],{"type":56,"value":263},{"type":56,"value":499},", also use ",{"type":50,"tag":72,"props":501,"children":503},{"className":502},[],[504],{"type":56,"value":505},"async with credential:",{"type":56,"value":507}," so tokens and transports are cleaned up.",{"type":50,"tag":90,"props":509,"children":510},{},[511,521],{"type":50,"tag":146,"props":512,"children":513},{},[514,516],{"type":56,"value":515},"Use ",{"type":50,"tag":72,"props":517,"children":519},{"className":518},[],[520],{"type":56,"value":119},{"type":56,"value":522}," for portable auth across local dev and Azure (avoid API keys; they bypass Entra audit and rotation).",{"type":50,"tag":90,"props":524,"children":525},{},[526],{"type":56,"value":527},"Use environment variables for the endpoint, project name, and deployment name.",{"type":50,"tag":90,"props":529,"children":530},{},[531,533,539,541,547,549,555],{"type":56,"value":532},"Clearly map the ",{"type":50,"tag":72,"props":534,"children":536},{"className":535},[],[537],{"type":56,"value":538},"participantId",{"type":56,"value":540}," and ",{"type":50,"tag":72,"props":542,"children":544},{"className":543},[],[545],{"type":56,"value":546},"id",{"type":56,"value":548}," in the ",{"type":50,"tag":72,"props":550,"children":552},{"className":551},[],[553],{"type":56,"value":554},"conversationItem",{"type":56,"value":556}," payload.",{"type":50,"tag":59,"props":558,"children":560},{"id":559},"examples",[561],{"type":56,"value":562},"Examples",{"type":50,"tag":297,"props":564,"children":566},{"id":565},"basic-conversation-analysis",[567],{"type":56,"value":568},"Basic Conversation Analysis",{"type":50,"tag":324,"props":570,"children":572},{"className":326,"code":571,"language":21,"meta":328,"style":328},"import os\nfrom azure.identity import DefaultAzureCredential\nfrom azure.ai.language.conversations import ConversationAnalysisClient\n\nendpoint = os.environ[\"AZURE_CONVERSATIONS_ENDPOINT\"]\nproject_name = os.environ[\"AZURE_CONVERSATIONS_PROJECT\"]\ndeployment_name = os.environ[\"AZURE_CONVERSATIONS_DEPLOYMENT\"]\n\n# DefaultAzureCredential works locally and in Azure with no code change.\ncredential = DefaultAzureCredential()\n\nwith ConversationAnalysisClient(endpoint, credential) as client:\n    query = \"Send an email to Carol about the tomorrow's meeting\"\n    result = client.analyze_conversation(\n        task={\n            \"kind\": \"Conversation\",\n            \"analysisInput\": {\n                \"conversationItem\": {\n                    \"participantId\": \"1\",\n                    \"id\": \"1\",\n                    \"modality\": \"text\",\n                    \"language\": \"en\",\n                    \"text\": query\n                },\n                \"isLoggingEnabled\": False\n            },\n            \"parameters\": {\n                \"projectName\": project_name,\n                \"deploymentName\": deployment_name,\n                \"verbose\": True\n            }\n        }\n    )\n\n    print(f\"Top intent: {result['result']['prediction']['topIntent']}\")\n",[573],{"type":50,"tag":72,"props":574,"children":575},{"__ignoreMap":328},[576,583,591,598,605,612,620,628,635,643,651,659,668,677,686,695,704,713,722,731,740,749,758,767,776,785,794,803,812,821,830,839,848,857,865],{"type":50,"tag":334,"props":577,"children":578},{"class":336,"line":337},[579],{"type":50,"tag":334,"props":580,"children":581},{},[582],{"type":56,"value":343},{"type":50,"tag":334,"props":584,"children":585},{"class":336,"line":346},[586],{"type":50,"tag":334,"props":587,"children":588},{},[589],{"type":56,"value":590},"from azure.identity import DefaultAzureCredential\n",{"type":50,"tag":334,"props":592,"children":593},{"class":336,"line":355},[594],{"type":50,"tag":334,"props":595,"children":596},{},[597],{"type":56,"value":361},{"type":50,"tag":334,"props":599,"children":600},{"class":336,"line":364},[601],{"type":50,"tag":334,"props":602,"children":603},{"emptyLinePlaceholder":368},[604],{"type":56,"value":371},{"type":50,"tag":334,"props":606,"children":607},{"class":336,"line":374},[608],{"type":50,"tag":334,"props":609,"children":610},{},[611],{"type":56,"value":380},{"type":50,"tag":334,"props":613,"children":614},{"class":336,"line":383},[615],{"type":50,"tag":334,"props":616,"children":617},{},[618],{"type":56,"value":619},"project_name = os.environ[\"AZURE_CONVERSATIONS_PROJECT\"]\n",{"type":50,"tag":334,"props":621,"children":622},{"class":336,"line":392},[623],{"type":50,"tag":334,"props":624,"children":625},{},[626],{"type":56,"value":627},"deployment_name = os.environ[\"AZURE_CONVERSATIONS_DEPLOYMENT\"]\n",{"type":50,"tag":334,"props":629,"children":630},{"class":336,"line":400},[631],{"type":50,"tag":334,"props":632,"children":633},{"emptyLinePlaceholder":368},[634],{"type":56,"value":371},{"type":50,"tag":334,"props":636,"children":637},{"class":336,"line":409},[638],{"type":50,"tag":334,"props":639,"children":640},{},[641],{"type":56,"value":642},"# DefaultAzureCredential works locally and in Azure with no code change.\n",{"type":50,"tag":334,"props":644,"children":645},{"class":336,"line":418},[646],{"type":50,"tag":334,"props":647,"children":648},{},[649],{"type":56,"value":650},"credential = DefaultAzureCredential()\n",{"type":50,"tag":334,"props":652,"children":654},{"class":336,"line":653},11,[655],{"type":50,"tag":334,"props":656,"children":657},{"emptyLinePlaceholder":368},[658],{"type":56,"value":371},{"type":50,"tag":334,"props":660,"children":662},{"class":336,"line":661},12,[663],{"type":50,"tag":334,"props":664,"children":665},{},[666],{"type":56,"value":667},"with ConversationAnalysisClient(endpoint, credential) as client:\n",{"type":50,"tag":334,"props":669,"children":671},{"class":336,"line":670},13,[672],{"type":50,"tag":334,"props":673,"children":674},{},[675],{"type":56,"value":676},"    query = \"Send an email to Carol about the tomorrow's meeting\"\n",{"type":50,"tag":334,"props":678,"children":680},{"class":336,"line":679},14,[681],{"type":50,"tag":334,"props":682,"children":683},{},[684],{"type":56,"value":685},"    result = client.analyze_conversation(\n",{"type":50,"tag":334,"props":687,"children":689},{"class":336,"line":688},15,[690],{"type":50,"tag":334,"props":691,"children":692},{},[693],{"type":56,"value":694},"        task={\n",{"type":50,"tag":334,"props":696,"children":698},{"class":336,"line":697},16,[699],{"type":50,"tag":334,"props":700,"children":701},{},[702],{"type":56,"value":703},"            \"kind\": \"Conversation\",\n",{"type":50,"tag":334,"props":705,"children":707},{"class":336,"line":706},17,[708],{"type":50,"tag":334,"props":709,"children":710},{},[711],{"type":56,"value":712},"            \"analysisInput\": {\n",{"type":50,"tag":334,"props":714,"children":716},{"class":336,"line":715},18,[717],{"type":50,"tag":334,"props":718,"children":719},{},[720],{"type":56,"value":721},"                \"conversationItem\": {\n",{"type":50,"tag":334,"props":723,"children":725},{"class":336,"line":724},19,[726],{"type":50,"tag":334,"props":727,"children":728},{},[729],{"type":56,"value":730},"                    \"participantId\": \"1\",\n",{"type":50,"tag":334,"props":732,"children":734},{"class":336,"line":733},20,[735],{"type":50,"tag":334,"props":736,"children":737},{},[738],{"type":56,"value":739},"                    \"id\": \"1\",\n",{"type":50,"tag":334,"props":741,"children":743},{"class":336,"line":742},21,[744],{"type":50,"tag":334,"props":745,"children":746},{},[747],{"type":56,"value":748},"                    \"modality\": \"text\",\n",{"type":50,"tag":334,"props":750,"children":752},{"class":336,"line":751},22,[753],{"type":50,"tag":334,"props":754,"children":755},{},[756],{"type":56,"value":757},"                    \"language\": \"en\",\n",{"type":50,"tag":334,"props":759,"children":761},{"class":336,"line":760},23,[762],{"type":50,"tag":334,"props":763,"children":764},{},[765],{"type":56,"value":766},"                    \"text\": query\n",{"type":50,"tag":334,"props":768,"children":770},{"class":336,"line":769},24,[771],{"type":50,"tag":334,"props":772,"children":773},{},[774],{"type":56,"value":775},"                },\n",{"type":50,"tag":334,"props":777,"children":779},{"class":336,"line":778},25,[780],{"type":50,"tag":334,"props":781,"children":782},{},[783],{"type":56,"value":784},"                \"isLoggingEnabled\": False\n",{"type":50,"tag":334,"props":786,"children":788},{"class":336,"line":787},26,[789],{"type":50,"tag":334,"props":790,"children":791},{},[792],{"type":56,"value":793},"            },\n",{"type":50,"tag":334,"props":795,"children":797},{"class":336,"line":796},27,[798],{"type":50,"tag":334,"props":799,"children":800},{},[801],{"type":56,"value":802},"            \"parameters\": {\n",{"type":50,"tag":334,"props":804,"children":806},{"class":336,"line":805},28,[807],{"type":50,"tag":334,"props":808,"children":809},{},[810],{"type":56,"value":811},"                \"projectName\": project_name,\n",{"type":50,"tag":334,"props":813,"children":815},{"class":336,"line":814},29,[816],{"type":50,"tag":334,"props":817,"children":818},{},[819],{"type":56,"value":820},"                \"deploymentName\": deployment_name,\n",{"type":50,"tag":334,"props":822,"children":824},{"class":336,"line":823},30,[825],{"type":50,"tag":334,"props":826,"children":827},{},[828],{"type":56,"value":829},"                \"verbose\": True\n",{"type":50,"tag":334,"props":831,"children":833},{"class":336,"line":832},31,[834],{"type":50,"tag":334,"props":835,"children":836},{},[837],{"type":56,"value":838},"            }\n",{"type":50,"tag":334,"props":840,"children":842},{"class":336,"line":841},32,[843],{"type":50,"tag":334,"props":844,"children":845},{},[846],{"type":56,"value":847},"        }\n",{"type":50,"tag":334,"props":849,"children":851},{"class":336,"line":850},33,[852],{"type":50,"tag":334,"props":853,"children":854},{},[855],{"type":56,"value":856},"    )\n",{"type":50,"tag":334,"props":858,"children":860},{"class":336,"line":859},34,[861],{"type":50,"tag":334,"props":862,"children":863},{"emptyLinePlaceholder":368},[864],{"type":56,"value":371},{"type":50,"tag":334,"props":866,"children":868},{"class":336,"line":867},35,[869],{"type":50,"tag":334,"props":870,"children":871},{},[872],{"type":56,"value":873},"    print(f\"Top intent: {result['result']['prediction']['topIntent']}\")\n",{"type":50,"tag":59,"props":875,"children":877},{"id":876},"reference-files",[878],{"type":56,"value":879},"Reference Files",{"type":50,"tag":881,"props":882,"children":883},"table",{},[884,903],{"type":50,"tag":885,"props":886,"children":887},"thead",{},[888],{"type":50,"tag":889,"props":890,"children":891},"tr",{},[892,898],{"type":50,"tag":893,"props":894,"children":895},"th",{},[896],{"type":56,"value":897},"File",{"type":50,"tag":893,"props":899,"children":900},{},[901],{"type":56,"value":902},"Contents",{"type":50,"tag":904,"props":905,"children":906},"tbody",{},[907,925],{"type":50,"tag":889,"props":908,"children":909},{},[910,920],{"type":50,"tag":911,"props":912,"children":913},"td",{},[914],{"type":50,"tag":915,"props":916,"children":918},"a",{"href":917},"references\u002Fcapabilities.md",[919],{"type":56,"value":917},{"type":50,"tag":911,"props":921,"children":922},{},[923],{"type":56,"value":924},"Additional non-hero capabilities, operation-group coverage, and production checklists.",{"type":50,"tag":889,"props":926,"children":927},{},[928,936],{"type":50,"tag":911,"props":929,"children":930},{},[931],{"type":50,"tag":915,"props":932,"children":934},{"href":933},"references\u002Fnon-hero-scenarios.md",[935],{"type":56,"value":933},{"type":50,"tag":911,"props":937,"children":938},{},[939],{"type":56,"value":940},"Dedicated non-hero examples for secondary\u002Fadvanced scenarios.",{"type":50,"tag":942,"props":943,"children":944},"style",{},[945],{"type":56,"value":946},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":948,"total":1047},[949,963,982,997,1012,1019,1032],{"slug":950,"name":950,"fn":951,"description":952,"org":953,"tags":954,"stars":25,"repoUrl":26,"updatedAt":962},"azure-ai-agents-persistent-dotnet","build AI agents with Azure .NET SDK","Azure AI Agents Persistent SDK for .NET. Low-level SDK for creating and managing AI agents with threads, messages, runs, and tools. Use for agent CRUD, conversation threads, streaming responses, function calling, file search, and code interpreter. Triggers: \"PersistentAgentsClient\", \"persistent agents\", \"agent threads\", \"agent runs\", \"streaming agents\", \"function calling agents .NET\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[955,958,960,961],{"name":956,"slug":957,"type":15},".NET","net",{"name":959,"slug":32,"type":15},"Agents",{"name":13,"slug":14,"type":15},{"name":17,"slug":18,"type":15},"2026-07-03T16:32:10.297433",{"slug":964,"name":964,"fn":965,"description":966,"org":967,"tags":968,"stars":25,"repoUrl":26,"updatedAt":981},"azure-ai-anomalydetector-java","build anomaly detection applications with Java","Build anomaly detection applications with Azure AI Anomaly Detector SDK for Java. Use when implementing univariate\u002Fmultivariate anomaly detection, time-series analysis, or AI-powered monitoring.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[969,970,971,974,977,978],{"name":23,"slug":24,"type":15},{"name":13,"slug":14,"type":15},{"name":972,"slug":973,"type":15},"Data Analysis","data-analysis",{"name":975,"slug":976,"type":15},"Java","java",{"name":9,"slug":8,"type":15},{"name":979,"slug":980,"type":15},"Monitoring","monitoring","2026-05-13T06:14:16.261754",{"slug":983,"name":983,"fn":984,"description":985,"org":986,"tags":987,"stars":25,"repoUrl":26,"updatedAt":996},"azure-ai-contentsafety-java","build content moderation applications with Azure AI","Build content moderation applications with Azure AI Content Safety SDK for Java. Use when implementing text\u002Fimage analysis, blocklist management, or harm detection for hate, violence, sexual content, and self-harm.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[988,991,992,993],{"name":989,"slug":990,"type":15},"AI Infrastructure","ai-infrastructure",{"name":13,"slug":14,"type":15},{"name":975,"slug":976,"type":15},{"name":994,"slug":995,"type":15},"Security","security","2026-07-07T06:53:31.293235",{"slug":998,"name":998,"fn":999,"description":1000,"org":1001,"tags":1002,"stars":25,"repoUrl":26,"updatedAt":1011},"azure-ai-contentsafety-py","detect harmful content with Azure AI Content Safety","Azure AI Content Safety SDK for Python. Use for detecting harmful content in text and images with multi-severity classification.\nTriggers: \"azure-ai-contentsafety\", \"ContentSafetyClient\", \"content moderation\", \"harmful content\", \"text analysis\", \"image analysis\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1003,1004,1007,1008,1009,1010],{"name":13,"slug":14,"type":15},{"name":1005,"slug":1006,"type":15},"Compliance","compliance",{"name":17,"slug":18,"type":15},{"name":9,"slug":8,"type":15},{"name":20,"slug":21,"type":15},{"name":994,"slug":995,"type":15},"2026-07-18T05:14:23.017504",{"slug":4,"name":4,"fn":5,"description":6,"org":1013,"tags":1014,"stars":25,"repoUrl":26,"updatedAt":27},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1015,1016,1017,1018],{"name":23,"slug":24,"type":15},{"name":13,"slug":14,"type":15},{"name":17,"slug":18,"type":15},{"name":20,"slug":21,"type":15},{"slug":1020,"name":1020,"fn":1021,"description":1022,"org":1023,"tags":1024,"stars":25,"repoUrl":26,"updatedAt":1031},"azure-ai-translation-text-py","translate text using Azure AI services","Azure AI Text Translation SDK for real-time text translation, transliteration, language detection, and dictionary lookup. Use for translating text content in applications.\nTriggers: \"text translation\", \"translator\", \"translate text\", \"transliterate\", \"TextTranslationClient\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1025,1028,1029,1030],{"name":1026,"slug":1027,"type":15},"API Development","api-development",{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},{"name":20,"slug":21,"type":15},"2026-07-18T05:14:16.988376",{"slug":1033,"name":1033,"fn":1034,"description":1035,"org":1036,"tags":1037,"stars":25,"repoUrl":26,"updatedAt":1046},"azure-ai-vision-imageanalysis-py","analyze images with Azure AI Vision","Azure AI Vision Image Analysis SDK for captions, tags, objects, OCR, people detection, and smart cropping. Use for computer vision and image understanding tasks.\nTriggers: \"image analysis\", \"computer vision\", \"OCR\", \"object detection\", \"ImageAnalysisClient\", \"image caption\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1038,1039,1042,1045],{"name":13,"slug":14,"type":15},{"name":1040,"slug":1041,"type":15},"Computer Vision","computer-vision",{"name":1043,"slug":1044,"type":15},"Images","images",{"name":20,"slug":21,"type":15},"2026-07-18T05:14:18.007737",38,{"items":1049,"total":1184},[1050,1072,1079,1088,1095,1104,1111,1118,1125,1140,1159,1172],{"slug":1051,"name":1051,"fn":1052,"description":1053,"org":1054,"tags":1055,"stars":1069,"repoUrl":1070,"updatedAt":1071},"rushstack-best-practices","manage Rush monorepos with best practices","Provides best practices and guidance for working with Rush monorepos. Use when the user is working in a Rush-based repository, asks about Rush commands (install, update, build, rebuild), needs help with project selection, dependency management, build caching, subspace configuration, or troubleshooting Rush-specific issues.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1056,1059,1062,1063,1066],{"name":1057,"slug":1058,"type":15},"Engineering","engineering",{"name":1060,"slug":1061,"type":15},"Local Development","local-development",{"name":9,"slug":8,"type":15},{"name":1064,"slug":1065,"type":15},"Project Management","project-management",{"name":1067,"slug":1068,"type":15},"Rush","rush",6484,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Frushstack","2026-04-06T18:34:44.965032",{"slug":950,"name":950,"fn":951,"description":952,"org":1073,"tags":1074,"stars":25,"repoUrl":26,"updatedAt":962},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1075,1076,1077,1078],{"name":956,"slug":957,"type":15},{"name":959,"slug":32,"type":15},{"name":13,"slug":14,"type":15},{"name":17,"slug":18,"type":15},{"slug":964,"name":964,"fn":965,"description":966,"org":1080,"tags":1081,"stars":25,"repoUrl":26,"updatedAt":981},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1082,1083,1084,1085,1086,1087],{"name":23,"slug":24,"type":15},{"name":13,"slug":14,"type":15},{"name":972,"slug":973,"type":15},{"name":975,"slug":976,"type":15},{"name":9,"slug":8,"type":15},{"name":979,"slug":980,"type":15},{"slug":983,"name":983,"fn":984,"description":985,"org":1089,"tags":1090,"stars":25,"repoUrl":26,"updatedAt":996},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1091,1092,1093,1094],{"name":989,"slug":990,"type":15},{"name":13,"slug":14,"type":15},{"name":975,"slug":976,"type":15},{"name":994,"slug":995,"type":15},{"slug":998,"name":998,"fn":999,"description":1000,"org":1096,"tags":1097,"stars":25,"repoUrl":26,"updatedAt":1011},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1098,1099,1100,1101,1102,1103],{"name":13,"slug":14,"type":15},{"name":1005,"slug":1006,"type":15},{"name":17,"slug":18,"type":15},{"name":9,"slug":8,"type":15},{"name":20,"slug":21,"type":15},{"name":994,"slug":995,"type":15},{"slug":4,"name":4,"fn":5,"description":6,"org":1105,"tags":1106,"stars":25,"repoUrl":26,"updatedAt":27},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1107,1108,1109,1110],{"name":23,"slug":24,"type":15},{"name":13,"slug":14,"type":15},{"name":17,"slug":18,"type":15},{"name":20,"slug":21,"type":15},{"slug":1020,"name":1020,"fn":1021,"description":1022,"org":1112,"tags":1113,"stars":25,"repoUrl":26,"updatedAt":1031},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1114,1115,1116,1117],{"name":1026,"slug":1027,"type":15},{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},{"name":20,"slug":21,"type":15},{"slug":1033,"name":1033,"fn":1034,"description":1035,"org":1119,"tags":1120,"stars":25,"repoUrl":26,"updatedAt":1046},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1121,1122,1123,1124],{"name":13,"slug":14,"type":15},{"name":1040,"slug":1041,"type":15},{"name":1043,"slug":1044,"type":15},{"name":20,"slug":21,"type":15},{"slug":1126,"name":1126,"fn":1127,"description":1128,"org":1129,"tags":1130,"stars":25,"repoUrl":26,"updatedAt":1139},"azure-appconfiguration-java","manage configuration with Azure App Configuration","Azure App Configuration SDK for Java. Centralized application configuration management with key-value settings, feature flags, and snapshots.\nTriggers: \"ConfigurationClient java\", \"app configuration java\", \"feature flag java\", \"configuration setting java\", \"azure config java\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1131,1132,1135,1138],{"name":13,"slug":14,"type":15},{"name":1133,"slug":1134,"type":15},"Configuration","configuration",{"name":1136,"slug":1137,"type":15},"Feature Flags","feature-flags",{"name":975,"slug":976,"type":15},"2026-07-03T16:32:01.278468",{"slug":1141,"name":1141,"fn":1142,"description":1143,"org":1144,"tags":1145,"stars":25,"repoUrl":26,"updatedAt":1158},"azure-cosmos-rust","build applications with Azure Cosmos DB","Azure Cosmos DB library for Rust (NoSQL API). Document CRUD, containers, and globally distributed data.\nTriggers: \"cosmos db rust\", \"CosmosClient rust\", \"document crud rust\", \"NoSQL rust\", \"partition key rust\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1146,1149,1152,1155],{"name":1147,"slug":1148,"type":15},"Cosmos DB","cosmos-db",{"name":1150,"slug":1151,"type":15},"Database","database",{"name":1153,"slug":1154,"type":15},"NoSQL","nosql",{"name":1156,"slug":1157,"type":15},"Rust","rust","2026-07-31T05:54:27.021432",{"slug":1160,"name":1160,"fn":1142,"description":1161,"org":1162,"tags":1163,"stars":25,"repoUrl":26,"updatedAt":1171},"azure-cosmos-ts","Azure Cosmos DB JavaScript\u002FTypeScript SDK (@azure\u002Fcosmos) for data plane operations. Use for CRUD operations on documents, queries, bulk operations, and container management. Triggers: \"Cosmos DB\", \"@azure\u002Fcosmos\", \"CosmosClient\", \"document CRUD\", \"NoSQL queries\", \"bulk operations\", \"partition key\", \"container.items\".\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1164,1165,1166,1167,1168],{"name":1147,"slug":1148,"type":15},{"name":1150,"slug":1151,"type":15},{"name":9,"slug":8,"type":15},{"name":1153,"slug":1154,"type":15},{"name":1169,"slug":1170,"type":15},"TypeScript","typescript","2026-07-03T16:31:19.368382",{"slug":1173,"name":1173,"fn":1174,"description":1175,"org":1176,"tags":1177,"stars":25,"repoUrl":26,"updatedAt":1183},"azure-data-tables-java","build table storage applications with Java","Build table storage applications with Azure Tables SDK for Java. Use when working with Azure Table Storage or Cosmos DB Table API for NoSQL key-value data, schemaless storage, or structured data at scale.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1178,1179,1180,1181,1182],{"name":13,"slug":14,"type":15},{"name":1147,"slug":1148,"type":15},{"name":1150,"slug":1151,"type":15},{"name":975,"slug":976,"type":15},{"name":1153,"slug":1154,"type":15},"2026-05-13T06:14:17.582229",267]