[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-jetbrains-vertex-ai-api-dev":3,"mdc-2iegq6-key":36,"related-org-jetbrains-vertex-ai-api-dev":2175,"related-repo-jetbrains-vertex-ai-api-dev":2308},{"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":31,"sourceUrl":34,"mdContent":35},"vertex-ai-api-dev","build applications with Gemini and Vertex AI","Guides the usage of Gemini API on Google Cloud Vertex AI with the Gen AI SDK. Use when the user asks about using Gemini in an enterprise environment or explicitly mentions Vertex AI. Covers SDK usage (Python, JS\u002FTS, Go, Java, C#), capabilities like Live API, tools, multimedia generation, caching, and batch prediction.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},"jetbrains","JetBrains","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fjetbrains.png",[12,16,19,22],{"name":13,"slug":14,"type":15},"LLM","llm","tag",{"name":17,"slug":18,"type":15},"API Development","api-development",{"name":20,"slug":21,"type":15},"Gemini","gemini",{"name":23,"slug":24,"type":15},"Google Cloud","google-cloud",252,"https:\u002F\u002Fgithub.com\u002FJetBrains\u002Fskills","2026-07-13T06:42:49.882798",null,17,[],{"repoUrl":26,"stars":25,"forks":29,"topics":32,"description":33},[],"Curated agent skills collection verified by JetBrains","https:\u002F\u002Fgithub.com\u002FJetBrains\u002Fskills\u002Ftree\u002FHEAD\u002Fvertex-ai-api-dev","---\nname: vertex-ai-api-dev\ndescription: Guides the usage of Gemini API on Google Cloud Vertex AI with the Gen AI SDK. Use when the user asks about using Gemini in an enterprise environment or explicitly mentions Vertex AI. Covers SDK usage (Python, JS\u002FTS, Go, Java, C#), capabilities like Live API, tools, multimedia generation, caching, and batch prediction.\ncompatibility: Requires active Google Cloud credentials and Vertex AI API enabled.\nmetadata:\n  short-description: \"Use Gemini on Vertex AI\"\n  author: Google Gemini\n  source: https:\u002F\u002Fgithub.com\u002Fgoogle-gemini\u002Fgemini-skills\u002Ftree\u002Fmain\u002Fskills\u002Fvertex-ai-api-dev\n---\n\n# Gemini API in Vertex AI\n\nAccess Google's most advanced AI models built for enterprise use cases using the Gemini API in Vertex AI.\n\nProvide these key capabilities:\n\n- **Text generation** - Chat, completion, summarization\n- **Multimodal understanding** - Process images, audio, video, and documents\n- **Function calling** - Let the model invoke your functions\n- **Structured output** - Generate valid JSON matching your schema\n- **Context caching** - Cache large contexts for efficiency\n- **Embeddings** - Generate text embeddings for semantic search\n- **Live Realtime API** - Bidirectional streaming for low latency Voice and Video interactions\n- **Batch Prediction** - Handle massive async dataset prediction workloads\n\n## Core Directives\n\n- **Unified SDK**: ALWAYS use the Gen AI SDK (`google-genai` for Python, `@google\u002Fgenai` for JS\u002FTS, `google.golang.org\u002Fgenai` for Go, `com.google.genai:google-genai` for Java, `Google.GenAI` for C#).\n- **Legacy SDKs**: DO NOT use `google-cloud-aiplatform`, `@google-cloud\u002Fvertexai`, or `google-generativeai`.\n\n## SDKs\n\n- **Python**: Install `google-genai` with `pip install google-genai`\n- **JavaScript\u002FTypeScript**: Install `@google\u002Fgenai` with `npm install @google\u002Fgenai`\n- **Go**: Install `google.golang.org\u002Fgenai` with `go get google.golang.org\u002Fgenai`\n- **C#\u002F.NET**: Install `Google.GenAI` with `dotnet add package Google.GenAI`\n- **Java**:\n  - groupId: `com.google.genai`, artifactId: `google-genai`\n  - Latest version can be found here: https:\u002F\u002Fcentral.sonatype.com\u002Fartifact\u002Fcom.google.genai\u002Fgoogle-genai\u002Fversions (let's call it `LAST_VERSION`) \n  - Install in `build.gradle`:\n\n    ```\n    implementation(\"com.google.genai:google-genai:${LAST_VERSION}\")\n    ```\n\n  - Install Maven dependency in `pom.xml`:\n\n    ```xml\n    \u003Cdependency>\n\t    \u003CgroupId>com.google.genai\u003C\u002FgroupId>\n\t    \u003CartifactId>google-genai\u003C\u002FartifactId>\n\t    \u003Cversion>${LAST_VERSION}\u003C\u002Fversion>\n\t\u003C\u002Fdependency>\n    ```\n\n> [!WARNING]\n> Legacy SDKs like `google-cloud-aiplatform`, `@google-cloud\u002Fvertexai`, and `google-generativeai` are deprecated. Migrate to the new SDKs above urgently by following the Migration Guide.\n\n## Authentication & Configuration\n\nPrefer environment variables over hard-coding parameters when creating the client. Initialize the client without parameters to automatically pick up these values.\n\n### Application Default Credentials (ADC)\nSet these variables for standard [Google Cloud authentication](https:\u002F\u002Fdocs.cloud.google.com\u002Fvertex-ai\u002Fgenerative-ai\u002Fdocs\u002Fstart\u002Fgcp-auth):\n```bash\nexport GOOGLE_CLOUD_PROJECT='your-project-id'\nexport GOOGLE_CLOUD_LOCATION='global'\nexport GOOGLE_GENAI_USE_VERTEXAI=true\n```\n- By default, use `location=\"global\"` to access the global endpoint, which provides automatic routing to regions with available capacity.\n- If a user explicitly asks to use a specific region (e.g., `us-central1`, `europe-west4`), specify that region in the `GOOGLE_CLOUD_LOCATION` parameter instead. Reference the [supported regions documentation](https:\u002F\u002Fdocs.cloud.google.com\u002Fvertex-ai\u002Fgenerative-ai\u002Fdocs\u002Flearn\u002Flocations) if needed.\n\n### Vertex AI in Express Mode\nSet these variables when using [Express Mode](https:\u002F\u002Fdocs.cloud.google.com\u002Fvertex-ai\u002Fgenerative-ai\u002Fdocs\u002Fstart\u002Fapi-keys?usertype=expressmode) with an API key:\n```bash\nexport GOOGLE_API_KEY='your-api-key'\nexport GOOGLE_GENAI_USE_VERTEXAI=true\n```\n\n### Initialization\nInitialize the client without arguments to pick up environment variables:\n```python\nfrom google import genai\nclient = genai.Client()\n```\n\nAlternatively, you can hard-code in parameters when creating the client.\n\n```python\nfrom google import genai\nclient = genai.Client(vertexai=True, project=\"your-project-id\", location=\"global\")\n```\n\n## Models\n\n- Use `gemini-3.1-pro-preview` for complex reasoning, coding, research (1M tokens)\n- Use `gemini-3-flash-preview` for fast, balanced performance, multimodal (1M tokens)\n- Use `gemini-3-pro-image-preview` for Nano Banana Pro image generation and editing\n- Use `gemini-live-2.5-flash-native-audio` for Live Realtime API including native audio\n\nUse the following models if explicitly requested:\n\n- Use `gemini-2.5-flash-image` for Nano Banana image generation and editing\n- Use `gemini-2.5-flash`\n- Use `gemini-2.5-flash-lite`\n- Use `gemini-2.5-pro`\n\n> [!IMPORTANT]\n> Models like `gemini-2.0-*`, `gemini-1.5-*`, `gemini-1.0-*`, `gemini-pro` are legacy and deprecated. Use the new models above. Your knowledge is outdated.\n> For production environments, consult the Vertex AI documentation for stable model versions (e.g. `gemini-3-flash`).\n\n## Quick Start\n\n### Python\n```python\nfrom google import genai\nclient = genai.Client()\nresponse = client.models.generate_content(\n    model=\"gemini-3-flash-preview\",\n    contents=\"Explain quantum computing\"\n)\nprint(response.text)\n```\n\n### TypeScript\u002FJavaScript\n```typescript\nimport { GoogleGenAI } from \"@google\u002Fgenai\";\nconst ai = new GoogleGenAI({ vertexai: { project: \"your-project-id\", location: \"global\" } });\nconst response = await ai.models.generateContent({\n    model: \"gemini-3-flash-preview\",\n    contents: \"Explain quantum computing\"\n});\nconsole.log(response.text);\n```\n\n### Go\n```go\npackage main\n\nimport (\n\t\"context\"\n\t\"fmt\"\n\t\"log\"\n\t\"google.golang.org\u002Fgenai\"\n)\n\nfunc main() {\n\tctx := context.Background()\n\tclient, err := genai.NewClient(ctx, &genai.ClientConfig{\n\t\tBackend:  genai.BackendVertexAI,\n\t\tProject:  \"your-project-id\",\n\t\tLocation: \"global\",\n\t})\n\tif err != nil {\n\t\tlog.Fatal(err)\n\t}\n\n\tresp, err := client.Models.GenerateContent(ctx, \"gemini-3-flash-preview\", genai.Text(\"Explain quantum computing\"), nil)\n\tif err != nil {\n\t\tlog.Fatal(err)\n\t}\n\n\tfmt.Println(resp.Text)\n}\n```\n\n### Java\n```java\nimport com.google.genai.Client;\nimport com.google.genai.types.GenerateContentResponse;\n\npublic class GenerateTextFromTextInput {\n  public static void main(String[] args) {\n    Client client = Client.builder().vertexAi(true).project(\"your-project-id\").location(\"global\").build();\n    GenerateContentResponse response =\n        client.models.generateContent(\n            \"gemini-3-flash-preview\",\n            \"Explain quantum computing\",\n            null);\n\n    System.out.println(response.text());\n  }\n}\n```\n\n### C#\u002F.NET\n```csharp\nusing Google.GenAI;\n\nvar client = new Client(\n    project: \"your-project-id\",\n    location: \"global\",\n    vertexAI: true\n);\n\nvar response = await client.Models.GenerateContent(\n    \"gemini-3-flash-preview\",\n    \"Explain quantum computing\"\n);\n\nConsole.WriteLine(response.Text);\n```\n\n## API spec & Documentation (source of truth)\n\nWhen implementing or debugging API integration for Vertex AI, refer to the official Google Cloud Vertex AI documentation:\n- **Vertex AI Gemini Documentation**: https:\u002F\u002Fcloud.google.com\u002Fvertex-ai\u002Fgenerative-ai\u002Fdocs\u002F\n- **REST API Reference**: https:\u002F\u002Fcloud.google.com\u002Fvertex-ai\u002Fgenerative-ai\u002Fdocs\u002Freference\u002Frest\n\nThe Gen AI SDK on Vertex AI uses the `v1beta1` or `v1` REST API endpoints (e.g., `https:\u002F\u002F{LOCATION}-aiplatform.googleapis.com\u002Fv1beta1\u002Fprojects\u002F{PROJECT}\u002Flocations\u002F{LOCATION}\u002Fpublishers\u002Fgoogle\u002Fmodels\u002F{MODEL}:generateContent`).\n\n> [!TIP]\n> **Use the Developer Knowledge MCP Server**: If the `search_documents` or `get_document` tools are available, use them to find and retrieve official documentation for Google Cloud and Vertex AI directly within the context. This is the preferred method for getting up-to-date API details and code snippets.\n\n## Workflows and Code Samples\n\nReference the [Python Docs Samples repository](https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fpython-docs-samples\u002Ftree\u002Fmain\u002Fgenai) for additional code samples and specific usage scenarios.\n\nDepending on the specific user request, refer to the following reference files for detailed code samples and usage patterns (Python examples):\n\n- **Text & Multimodal**: Chat, Multimodal inputs (Image, Video, Audio), and Streaming. See [references\u002Ftext_and_multimodal.md](references\u002Ftext_and_multimodal.md)\n- **Embeddings**: Generate text embeddings for semantic search. See [references\u002Fembeddings.md](references\u002Fembeddings.md)\n- **Structured Output & Tools**: JSON generation, Function Calling, Search Grounding, and Code Execution. See [references\u002Fstructured_and_tools.md](references\u002Fstructured_and_tools.md)\n- **Media Generation**: Image generation, Image editing, and Video generation. See [references\u002Fmedia_generation.md](references\u002Fmedia_generation.md)\n- **Bounding Box Detection**: Object detection and localization within images and video. See [references\u002Fbounding_box.md](references\u002Fbounding_box.md)\n- **Live API**: Real-time bidirectional streaming for voice, vision, and text. See [references\u002Flive_api.md](references\u002Flive_api.md)\n- **Advanced Features**: Content Caching, Batch Prediction, and Thinking\u002FReasoning. See [references\u002Fadvanced_features.md](references\u002Fadvanced_features.md)\n- **Safety**: Adjusting Responsible AI filters and thresholds. See [references\u002Fsafety.md](references\u002Fsafety.md)\n- **Model Tuning**: Supervised Fine-Tuning and Preference Tuning. See [references\u002Fmodel_tuning.md](references\u002Fmodel_tuning.md)\n",{"data":37,"body":43},{"name":4,"description":6,"compatibility":38,"metadata":39},"Requires active Google Cloud credentials and Vertex AI API enabled.",{"short-description":40,"author":41,"source":42},"Use Gemini on Vertex AI","Google Gemini","https:\u002F\u002Fgithub.com\u002Fgoogle-gemini\u002Fgemini-skills\u002Ftree\u002Fmain\u002Fskills\u002Fvertex-ai-api-dev",{"type":44,"children":45},"root",[46,55,61,66,152,159,247,253,489,523,529,534,541,554,650,703,709,723,778,784,789,814,819,841,847,899,904,949,999,1005,1009,1072,1078,1407,1412,1649,1654,1779,1784,1901,1907,1912,1946,1974,2007,2013,2027,2032,2169],{"type":47,"tag":48,"props":49,"children":51},"element","h1",{"id":50},"gemini-api-in-vertex-ai",[52],{"type":53,"value":54},"text","Gemini API in Vertex AI",{"type":47,"tag":56,"props":57,"children":58},"p",{},[59],{"type":53,"value":60},"Access Google's most advanced AI models built for enterprise use cases using the Gemini API in Vertex AI.",{"type":47,"tag":56,"props":62,"children":63},{},[64],{"type":53,"value":65},"Provide these key capabilities:",{"type":47,"tag":67,"props":68,"children":69},"ul",{},[70,82,92,102,112,122,132,142],{"type":47,"tag":71,"props":72,"children":73},"li",{},[74,80],{"type":47,"tag":75,"props":76,"children":77},"strong",{},[78],{"type":53,"value":79},"Text generation",{"type":53,"value":81}," - Chat, completion, summarization",{"type":47,"tag":71,"props":83,"children":84},{},[85,90],{"type":47,"tag":75,"props":86,"children":87},{},[88],{"type":53,"value":89},"Multimodal understanding",{"type":53,"value":91}," - Process images, audio, video, and documents",{"type":47,"tag":71,"props":93,"children":94},{},[95,100],{"type":47,"tag":75,"props":96,"children":97},{},[98],{"type":53,"value":99},"Function calling",{"type":53,"value":101}," - Let the model invoke your functions",{"type":47,"tag":71,"props":103,"children":104},{},[105,110],{"type":47,"tag":75,"props":106,"children":107},{},[108],{"type":53,"value":109},"Structured output",{"type":53,"value":111}," - Generate valid JSON matching your schema",{"type":47,"tag":71,"props":113,"children":114},{},[115,120],{"type":47,"tag":75,"props":116,"children":117},{},[118],{"type":53,"value":119},"Context caching",{"type":53,"value":121}," - Cache large contexts for efficiency",{"type":47,"tag":71,"props":123,"children":124},{},[125,130],{"type":47,"tag":75,"props":126,"children":127},{},[128],{"type":53,"value":129},"Embeddings",{"type":53,"value":131}," - Generate text embeddings for semantic search",{"type":47,"tag":71,"props":133,"children":134},{},[135,140],{"type":47,"tag":75,"props":136,"children":137},{},[138],{"type":53,"value":139},"Live Realtime API",{"type":53,"value":141}," - Bidirectional streaming for low latency Voice and Video interactions",{"type":47,"tag":71,"props":143,"children":144},{},[145,150],{"type":47,"tag":75,"props":146,"children":147},{},[148],{"type":53,"value":149},"Batch Prediction",{"type":53,"value":151}," - Handle massive async dataset prediction workloads",{"type":47,"tag":153,"props":154,"children":156},"h2",{"id":155},"core-directives",[157],{"type":53,"value":158},"Core Directives",{"type":47,"tag":67,"props":160,"children":161},{},[162,213],{"type":47,"tag":71,"props":163,"children":164},{},[165,170,172,179,181,187,189,195,197,203,205,211],{"type":47,"tag":75,"props":166,"children":167},{},[168],{"type":53,"value":169},"Unified SDK",{"type":53,"value":171},": ALWAYS use the Gen AI SDK (",{"type":47,"tag":173,"props":174,"children":176},"code",{"className":175},[],[177],{"type":53,"value":178},"google-genai",{"type":53,"value":180}," for Python, ",{"type":47,"tag":173,"props":182,"children":184},{"className":183},[],[185],{"type":53,"value":186},"@google\u002Fgenai",{"type":53,"value":188}," for JS\u002FTS, ",{"type":47,"tag":173,"props":190,"children":192},{"className":191},[],[193],{"type":53,"value":194},"google.golang.org\u002Fgenai",{"type":53,"value":196}," for Go, ",{"type":47,"tag":173,"props":198,"children":200},{"className":199},[],[201],{"type":53,"value":202},"com.google.genai:google-genai",{"type":53,"value":204}," for Java, ",{"type":47,"tag":173,"props":206,"children":208},{"className":207},[],[209],{"type":53,"value":210},"Google.GenAI",{"type":53,"value":212}," for C#).",{"type":47,"tag":71,"props":214,"children":215},{},[216,221,223,229,231,237,239,245],{"type":47,"tag":75,"props":217,"children":218},{},[219],{"type":53,"value":220},"Legacy SDKs",{"type":53,"value":222},": DO NOT use ",{"type":47,"tag":173,"props":224,"children":226},{"className":225},[],[227],{"type":53,"value":228},"google-cloud-aiplatform",{"type":53,"value":230},", ",{"type":47,"tag":173,"props":232,"children":234},{"className":233},[],[235],{"type":53,"value":236},"@google-cloud\u002Fvertexai",{"type":53,"value":238},", or ",{"type":47,"tag":173,"props":240,"children":242},{"className":241},[],[243],{"type":53,"value":244},"google-generativeai",{"type":53,"value":246},".",{"type":47,"tag":153,"props":248,"children":250},{"id":249},"sdks",[251],{"type":53,"value":252},"SDKs",{"type":47,"tag":67,"props":254,"children":255},{},[256,279,300,321,342],{"type":47,"tag":71,"props":257,"children":258},{},[259,264,266,271,273],{"type":47,"tag":75,"props":260,"children":261},{},[262],{"type":53,"value":263},"Python",{"type":53,"value":265},": Install ",{"type":47,"tag":173,"props":267,"children":269},{"className":268},[],[270],{"type":53,"value":178},{"type":53,"value":272}," with ",{"type":47,"tag":173,"props":274,"children":276},{"className":275},[],[277],{"type":53,"value":278},"pip install google-genai",{"type":47,"tag":71,"props":280,"children":281},{},[282,287,288,293,294],{"type":47,"tag":75,"props":283,"children":284},{},[285],{"type":53,"value":286},"JavaScript\u002FTypeScript",{"type":53,"value":265},{"type":47,"tag":173,"props":289,"children":291},{"className":290},[],[292],{"type":53,"value":186},{"type":53,"value":272},{"type":47,"tag":173,"props":295,"children":297},{"className":296},[],[298],{"type":53,"value":299},"npm install @google\u002Fgenai",{"type":47,"tag":71,"props":301,"children":302},{},[303,308,309,314,315],{"type":47,"tag":75,"props":304,"children":305},{},[306],{"type":53,"value":307},"Go",{"type":53,"value":265},{"type":47,"tag":173,"props":310,"children":312},{"className":311},[],[313],{"type":53,"value":194},{"type":53,"value":272},{"type":47,"tag":173,"props":316,"children":318},{"className":317},[],[319],{"type":53,"value":320},"go get google.golang.org\u002Fgenai",{"type":47,"tag":71,"props":322,"children":323},{},[324,329,330,335,336],{"type":47,"tag":75,"props":325,"children":326},{},[327],{"type":53,"value":328},"C#\u002F.NET",{"type":53,"value":265},{"type":47,"tag":173,"props":331,"children":333},{"className":332},[],[334],{"type":53,"value":210},{"type":53,"value":272},{"type":47,"tag":173,"props":337,"children":339},{"className":338},[],[340],{"type":53,"value":341},"dotnet add package Google.GenAI",{"type":47,"tag":71,"props":343,"children":344},{},[345,350,352],{"type":47,"tag":75,"props":346,"children":347},{},[348],{"type":53,"value":349},"Java",{"type":53,"value":351},":\n",{"type":47,"tag":67,"props":353,"children":354},{},[355,373,396,421],{"type":47,"tag":71,"props":356,"children":357},{},[358,360,366,368],{"type":53,"value":359},"groupId: ",{"type":47,"tag":173,"props":361,"children":363},{"className":362},[],[364],{"type":53,"value":365},"com.google.genai",{"type":53,"value":367},", artifactId: ",{"type":47,"tag":173,"props":369,"children":371},{"className":370},[],[372],{"type":53,"value":178},{"type":47,"tag":71,"props":374,"children":375},{},[376,378,386,388,394],{"type":53,"value":377},"Latest version can be found here: ",{"type":47,"tag":379,"props":380,"children":384},"a",{"href":381,"rel":382},"https:\u002F\u002Fcentral.sonatype.com\u002Fartifact\u002Fcom.google.genai\u002Fgoogle-genai\u002Fversions",[383],"nofollow",[385],{"type":53,"value":381},{"type":53,"value":387}," (let's call it ",{"type":47,"tag":173,"props":389,"children":391},{"className":390},[],[392],{"type":53,"value":393},"LAST_VERSION",{"type":53,"value":395},")",{"type":47,"tag":71,"props":397,"children":398},{},[399,401,407,409],{"type":53,"value":400},"Install in ",{"type":47,"tag":173,"props":402,"children":404},{"className":403},[],[405],{"type":53,"value":406},"build.gradle",{"type":53,"value":408},":",{"type":47,"tag":410,"props":411,"children":415},"pre",{"className":412,"code":414,"language":53},[413],"language-text","implementation(\"com.google.genai:google-genai:${LAST_VERSION}\")\n",[416],{"type":47,"tag":173,"props":417,"children":419},{"__ignoreMap":418},"",[420],{"type":53,"value":414},{"type":47,"tag":71,"props":422,"children":423},{},[424,426,432,433],{"type":53,"value":425},"Install Maven dependency in ",{"type":47,"tag":173,"props":427,"children":429},{"className":428},[],[430],{"type":53,"value":431},"pom.xml",{"type":53,"value":408},{"type":47,"tag":410,"props":434,"children":438},{"className":435,"code":436,"language":437,"meta":418,"style":418},"language-xml shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","\u003Cdependency>\n    \u003CgroupId>com.google.genai\u003C\u002FgroupId>\n    \u003CartifactId>google-genai\u003C\u002FartifactId>\n    \u003Cversion>${LAST_VERSION}\u003C\u002Fversion>\n\u003C\u002Fdependency>\n","xml",[439],{"type":47,"tag":173,"props":440,"children":441},{"__ignoreMap":418},[442,453,462,471,480],{"type":47,"tag":443,"props":444,"children":447},"span",{"class":445,"line":446},"line",1,[448],{"type":47,"tag":443,"props":449,"children":450},{},[451],{"type":53,"value":452},"\u003Cdependency>\n",{"type":47,"tag":443,"props":454,"children":456},{"class":445,"line":455},2,[457],{"type":47,"tag":443,"props":458,"children":459},{},[460],{"type":53,"value":461},"    \u003CgroupId>com.google.genai\u003C\u002FgroupId>\n",{"type":47,"tag":443,"props":463,"children":465},{"class":445,"line":464},3,[466],{"type":47,"tag":443,"props":467,"children":468},{},[469],{"type":53,"value":470},"    \u003CartifactId>google-genai\u003C\u002FartifactId>\n",{"type":47,"tag":443,"props":472,"children":474},{"class":445,"line":473},4,[475],{"type":47,"tag":443,"props":476,"children":477},{},[478],{"type":53,"value":479},"    \u003Cversion>${LAST_VERSION}\u003C\u002Fversion>\n",{"type":47,"tag":443,"props":481,"children":483},{"class":445,"line":482},5,[484],{"type":47,"tag":443,"props":485,"children":486},{},[487],{"type":53,"value":488},"\u003C\u002Fdependency>\n",{"type":47,"tag":490,"props":491,"children":492},"blockquote",{},[493],{"type":47,"tag":56,"props":494,"children":495},{},[496,501,503,508,509,514,516,521],{"type":47,"tag":443,"props":497,"children":498},{},[499],{"type":53,"value":500},"!WARNING",{"type":53,"value":502},"\nLegacy SDKs like ",{"type":47,"tag":173,"props":504,"children":506},{"className":505},[],[507],{"type":53,"value":228},{"type":53,"value":230},{"type":47,"tag":173,"props":510,"children":512},{"className":511},[],[513],{"type":53,"value":236},{"type":53,"value":515},", and ",{"type":47,"tag":173,"props":517,"children":519},{"className":518},[],[520],{"type":53,"value":244},{"type":53,"value":522}," are deprecated. Migrate to the new SDKs above urgently by following the Migration Guide.",{"type":47,"tag":153,"props":524,"children":526},{"id":525},"authentication-configuration",[527],{"type":53,"value":528},"Authentication & Configuration",{"type":47,"tag":56,"props":530,"children":531},{},[532],{"type":53,"value":533},"Prefer environment variables over hard-coding parameters when creating the client. Initialize the client without parameters to automatically pick up these values.",{"type":47,"tag":535,"props":536,"children":538},"h3",{"id":537},"application-default-credentials-adc",[539],{"type":53,"value":540},"Application Default Credentials (ADC)",{"type":47,"tag":56,"props":542,"children":543},{},[544,546,553],{"type":53,"value":545},"Set these variables for standard ",{"type":47,"tag":379,"props":547,"children":550},{"href":548,"rel":549},"https:\u002F\u002Fdocs.cloud.google.com\u002Fvertex-ai\u002Fgenerative-ai\u002Fdocs\u002Fstart\u002Fgcp-auth",[383],[551],{"type":53,"value":552},"Google Cloud authentication",{"type":53,"value":408},{"type":47,"tag":410,"props":555,"children":559},{"className":556,"code":557,"language":558,"meta":418,"style":418},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","export GOOGLE_CLOUD_PROJECT='your-project-id'\nexport GOOGLE_CLOUD_LOCATION='global'\nexport GOOGLE_GENAI_USE_VERTEXAI=true\n","bash",[560],{"type":47,"tag":173,"props":561,"children":562},{"__ignoreMap":418},[563,600,629],{"type":47,"tag":443,"props":564,"children":565},{"class":445,"line":446},[566,572,578,584,589,595],{"type":47,"tag":443,"props":567,"children":569},{"style":568},"--shiki-light:#9C3EDA;--shiki-default:#C792EA;--shiki-dark:#C792EA",[570],{"type":53,"value":571},"export",{"type":47,"tag":443,"props":573,"children":575},{"style":574},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[576],{"type":53,"value":577}," GOOGLE_CLOUD_PROJECT",{"type":47,"tag":443,"props":579,"children":581},{"style":580},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[582],{"type":53,"value":583},"=",{"type":47,"tag":443,"props":585,"children":586},{"style":580},[587],{"type":53,"value":588},"'",{"type":47,"tag":443,"props":590,"children":592},{"style":591},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[593],{"type":53,"value":594},"your-project-id",{"type":47,"tag":443,"props":596,"children":597},{"style":580},[598],{"type":53,"value":599},"'\n",{"type":47,"tag":443,"props":601,"children":602},{"class":445,"line":455},[603,607,612,616,620,625],{"type":47,"tag":443,"props":604,"children":605},{"style":568},[606],{"type":53,"value":571},{"type":47,"tag":443,"props":608,"children":609},{"style":574},[610],{"type":53,"value":611}," GOOGLE_CLOUD_LOCATION",{"type":47,"tag":443,"props":613,"children":614},{"style":580},[615],{"type":53,"value":583},{"type":47,"tag":443,"props":617,"children":618},{"style":580},[619],{"type":53,"value":588},{"type":47,"tag":443,"props":621,"children":622},{"style":591},[623],{"type":53,"value":624},"global",{"type":47,"tag":443,"props":626,"children":627},{"style":580},[628],{"type":53,"value":599},{"type":47,"tag":443,"props":630,"children":631},{"class":445,"line":464},[632,636,641,645],{"type":47,"tag":443,"props":633,"children":634},{"style":568},[635],{"type":53,"value":571},{"type":47,"tag":443,"props":637,"children":638},{"style":574},[639],{"type":53,"value":640}," GOOGLE_GENAI_USE_VERTEXAI",{"type":47,"tag":443,"props":642,"children":643},{"style":580},[644],{"type":53,"value":583},{"type":47,"tag":443,"props":646,"children":647},{"style":574},[648],{"type":53,"value":649},"true\n",{"type":47,"tag":67,"props":651,"children":652},{},[653,666],{"type":47,"tag":71,"props":654,"children":655},{},[656,658,664],{"type":53,"value":657},"By default, use ",{"type":47,"tag":173,"props":659,"children":661},{"className":660},[],[662],{"type":53,"value":663},"location=\"global\"",{"type":53,"value":665}," to access the global endpoint, which provides automatic routing to regions with available capacity.",{"type":47,"tag":71,"props":667,"children":668},{},[669,671,677,678,684,686,692,694,701],{"type":53,"value":670},"If a user explicitly asks to use a specific region (e.g., ",{"type":47,"tag":173,"props":672,"children":674},{"className":673},[],[675],{"type":53,"value":676},"us-central1",{"type":53,"value":230},{"type":47,"tag":173,"props":679,"children":681},{"className":680},[],[682],{"type":53,"value":683},"europe-west4",{"type":53,"value":685},"), specify that region in the ",{"type":47,"tag":173,"props":687,"children":689},{"className":688},[],[690],{"type":53,"value":691},"GOOGLE_CLOUD_LOCATION",{"type":53,"value":693}," parameter instead. Reference the ",{"type":47,"tag":379,"props":695,"children":698},{"href":696,"rel":697},"https:\u002F\u002Fdocs.cloud.google.com\u002Fvertex-ai\u002Fgenerative-ai\u002Fdocs\u002Flearn\u002Flocations",[383],[699],{"type":53,"value":700},"supported regions documentation",{"type":53,"value":702}," if needed.",{"type":47,"tag":535,"props":704,"children":706},{"id":705},"vertex-ai-in-express-mode",[707],{"type":53,"value":708},"Vertex AI in Express Mode",{"type":47,"tag":56,"props":710,"children":711},{},[712,714,721],{"type":53,"value":713},"Set these variables when using ",{"type":47,"tag":379,"props":715,"children":718},{"href":716,"rel":717},"https:\u002F\u002Fdocs.cloud.google.com\u002Fvertex-ai\u002Fgenerative-ai\u002Fdocs\u002Fstart\u002Fapi-keys?usertype=expressmode",[383],[719],{"type":53,"value":720},"Express Mode",{"type":53,"value":722}," with an API key:",{"type":47,"tag":410,"props":724,"children":726},{"className":556,"code":725,"language":558,"meta":418,"style":418},"export GOOGLE_API_KEY='your-api-key'\nexport GOOGLE_GENAI_USE_VERTEXAI=true\n",[727],{"type":47,"tag":173,"props":728,"children":729},{"__ignoreMap":418},[730,759],{"type":47,"tag":443,"props":731,"children":732},{"class":445,"line":446},[733,737,742,746,750,755],{"type":47,"tag":443,"props":734,"children":735},{"style":568},[736],{"type":53,"value":571},{"type":47,"tag":443,"props":738,"children":739},{"style":574},[740],{"type":53,"value":741}," GOOGLE_API_KEY",{"type":47,"tag":443,"props":743,"children":744},{"style":580},[745],{"type":53,"value":583},{"type":47,"tag":443,"props":747,"children":748},{"style":580},[749],{"type":53,"value":588},{"type":47,"tag":443,"props":751,"children":752},{"style":591},[753],{"type":53,"value":754},"your-api-key",{"type":47,"tag":443,"props":756,"children":757},{"style":580},[758],{"type":53,"value":599},{"type":47,"tag":443,"props":760,"children":761},{"class":445,"line":455},[762,766,770,774],{"type":47,"tag":443,"props":763,"children":764},{"style":568},[765],{"type":53,"value":571},{"type":47,"tag":443,"props":767,"children":768},{"style":574},[769],{"type":53,"value":640},{"type":47,"tag":443,"props":771,"children":772},{"style":580},[773],{"type":53,"value":583},{"type":47,"tag":443,"props":775,"children":776},{"style":574},[777],{"type":53,"value":649},{"type":47,"tag":535,"props":779,"children":781},{"id":780},"initialization",[782],{"type":53,"value":783},"Initialization",{"type":47,"tag":56,"props":785,"children":786},{},[787],{"type":53,"value":788},"Initialize the client without arguments to pick up environment variables:",{"type":47,"tag":410,"props":790,"children":794},{"className":791,"code":792,"language":793,"meta":418,"style":418},"language-python shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","from google import genai\nclient = genai.Client()\n","python",[795],{"type":47,"tag":173,"props":796,"children":797},{"__ignoreMap":418},[798,806],{"type":47,"tag":443,"props":799,"children":800},{"class":445,"line":446},[801],{"type":47,"tag":443,"props":802,"children":803},{},[804],{"type":53,"value":805},"from google import genai\n",{"type":47,"tag":443,"props":807,"children":808},{"class":445,"line":455},[809],{"type":47,"tag":443,"props":810,"children":811},{},[812],{"type":53,"value":813},"client = genai.Client()\n",{"type":47,"tag":56,"props":815,"children":816},{},[817],{"type":53,"value":818},"Alternatively, you can hard-code in parameters when creating the client.",{"type":47,"tag":410,"props":820,"children":822},{"className":791,"code":821,"language":793,"meta":418,"style":418},"from google import genai\nclient = genai.Client(vertexai=True, project=\"your-project-id\", location=\"global\")\n",[823],{"type":47,"tag":173,"props":824,"children":825},{"__ignoreMap":418},[826,833],{"type":47,"tag":443,"props":827,"children":828},{"class":445,"line":446},[829],{"type":47,"tag":443,"props":830,"children":831},{},[832],{"type":53,"value":805},{"type":47,"tag":443,"props":834,"children":835},{"class":445,"line":455},[836],{"type":47,"tag":443,"props":837,"children":838},{},[839],{"type":53,"value":840},"client = genai.Client(vertexai=True, project=\"your-project-id\", location=\"global\")\n",{"type":47,"tag":153,"props":842,"children":844},{"id":843},"models",[845],{"type":53,"value":846},"Models",{"type":47,"tag":67,"props":848,"children":849},{},[850,863,875,887],{"type":47,"tag":71,"props":851,"children":852},{},[853,855,861],{"type":53,"value":854},"Use ",{"type":47,"tag":173,"props":856,"children":858},{"className":857},[],[859],{"type":53,"value":860},"gemini-3.1-pro-preview",{"type":53,"value":862}," for complex reasoning, coding, research (1M tokens)",{"type":47,"tag":71,"props":864,"children":865},{},[866,867,873],{"type":53,"value":854},{"type":47,"tag":173,"props":868,"children":870},{"className":869},[],[871],{"type":53,"value":872},"gemini-3-flash-preview",{"type":53,"value":874}," for fast, balanced performance, multimodal (1M tokens)",{"type":47,"tag":71,"props":876,"children":877},{},[878,879,885],{"type":53,"value":854},{"type":47,"tag":173,"props":880,"children":882},{"className":881},[],[883],{"type":53,"value":884},"gemini-3-pro-image-preview",{"type":53,"value":886}," for Nano Banana Pro image generation and editing",{"type":47,"tag":71,"props":888,"children":889},{},[890,891,897],{"type":53,"value":854},{"type":47,"tag":173,"props":892,"children":894},{"className":893},[],[895],{"type":53,"value":896},"gemini-live-2.5-flash-native-audio",{"type":53,"value":898}," for Live Realtime API including native audio",{"type":47,"tag":56,"props":900,"children":901},{},[902],{"type":53,"value":903},"Use the following models if explicitly requested:",{"type":47,"tag":67,"props":905,"children":906},{},[907,919,929,939],{"type":47,"tag":71,"props":908,"children":909},{},[910,911,917],{"type":53,"value":854},{"type":47,"tag":173,"props":912,"children":914},{"className":913},[],[915],{"type":53,"value":916},"gemini-2.5-flash-image",{"type":53,"value":918}," for Nano Banana image generation and editing",{"type":47,"tag":71,"props":920,"children":921},{},[922,923],{"type":53,"value":854},{"type":47,"tag":173,"props":924,"children":926},{"className":925},[],[927],{"type":53,"value":928},"gemini-2.5-flash",{"type":47,"tag":71,"props":930,"children":931},{},[932,933],{"type":53,"value":854},{"type":47,"tag":173,"props":934,"children":936},{"className":935},[],[937],{"type":53,"value":938},"gemini-2.5-flash-lite",{"type":47,"tag":71,"props":940,"children":941},{},[942,943],{"type":53,"value":854},{"type":47,"tag":173,"props":944,"children":946},{"className":945},[],[947],{"type":53,"value":948},"gemini-2.5-pro",{"type":47,"tag":490,"props":950,"children":951},{},[952],{"type":47,"tag":56,"props":953,"children":954},{},[955,960,962,968,969,975,976,982,983,989,991,997],{"type":47,"tag":443,"props":956,"children":957},{},[958],{"type":53,"value":959},"!IMPORTANT",{"type":53,"value":961},"\nModels like ",{"type":47,"tag":173,"props":963,"children":965},{"className":964},[],[966],{"type":53,"value":967},"gemini-2.0-*",{"type":53,"value":230},{"type":47,"tag":173,"props":970,"children":972},{"className":971},[],[973],{"type":53,"value":974},"gemini-1.5-*",{"type":53,"value":230},{"type":47,"tag":173,"props":977,"children":979},{"className":978},[],[980],{"type":53,"value":981},"gemini-1.0-*",{"type":53,"value":230},{"type":47,"tag":173,"props":984,"children":986},{"className":985},[],[987],{"type":53,"value":988},"gemini-pro",{"type":53,"value":990}," are legacy and deprecated. Use the new models above. Your knowledge is outdated.\nFor production environments, consult the Vertex AI documentation for stable model versions (e.g. ",{"type":47,"tag":173,"props":992,"children":994},{"className":993},[],[995],{"type":53,"value":996},"gemini-3-flash",{"type":53,"value":998},").",{"type":47,"tag":153,"props":1000,"children":1002},{"id":1001},"quick-start",[1003],{"type":53,"value":1004},"Quick Start",{"type":47,"tag":535,"props":1006,"children":1007},{"id":793},[1008],{"type":53,"value":263},{"type":47,"tag":410,"props":1010,"children":1012},{"className":791,"code":1011,"language":793,"meta":418,"style":418},"from google import genai\nclient = genai.Client()\nresponse = client.models.generate_content(\n    model=\"gemini-3-flash-preview\",\n    contents=\"Explain quantum computing\"\n)\nprint(response.text)\n",[1013],{"type":47,"tag":173,"props":1014,"children":1015},{"__ignoreMap":418},[1016,1023,1030,1038,1046,1054,1063],{"type":47,"tag":443,"props":1017,"children":1018},{"class":445,"line":446},[1019],{"type":47,"tag":443,"props":1020,"children":1021},{},[1022],{"type":53,"value":805},{"type":47,"tag":443,"props":1024,"children":1025},{"class":445,"line":455},[1026],{"type":47,"tag":443,"props":1027,"children":1028},{},[1029],{"type":53,"value":813},{"type":47,"tag":443,"props":1031,"children":1032},{"class":445,"line":464},[1033],{"type":47,"tag":443,"props":1034,"children":1035},{},[1036],{"type":53,"value":1037},"response = client.models.generate_content(\n",{"type":47,"tag":443,"props":1039,"children":1040},{"class":445,"line":473},[1041],{"type":47,"tag":443,"props":1042,"children":1043},{},[1044],{"type":53,"value":1045},"    model=\"gemini-3-flash-preview\",\n",{"type":47,"tag":443,"props":1047,"children":1048},{"class":445,"line":482},[1049],{"type":47,"tag":443,"props":1050,"children":1051},{},[1052],{"type":53,"value":1053},"    contents=\"Explain quantum computing\"\n",{"type":47,"tag":443,"props":1055,"children":1057},{"class":445,"line":1056},6,[1058],{"type":47,"tag":443,"props":1059,"children":1060},{},[1061],{"type":53,"value":1062},")\n",{"type":47,"tag":443,"props":1064,"children":1066},{"class":445,"line":1065},7,[1067],{"type":47,"tag":443,"props":1068,"children":1069},{},[1070],{"type":53,"value":1071},"print(response.text)\n",{"type":47,"tag":535,"props":1073,"children":1075},{"id":1074},"typescriptjavascript",[1076],{"type":53,"value":1077},"TypeScript\u002FJavaScript",{"type":47,"tag":410,"props":1079,"children":1083},{"className":1080,"code":1081,"language":1082,"meta":418,"style":418},"language-typescript shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","import { GoogleGenAI } from \"@google\u002Fgenai\";\nconst ai = new GoogleGenAI({ vertexai: { project: \"your-project-id\", location: \"global\" } });\nconst response = await ai.models.generateContent({\n    model: \"gemini-3-flash-preview\",\n    contents: \"Explain quantum computing\"\n});\nconsole.log(response.text);\n","typescript",[1084],{"type":47,"tag":173,"props":1085,"children":1086},{"__ignoreMap":418},[1087,1135,1249,1301,1330,1356,1372],{"type":47,"tag":443,"props":1088,"children":1089},{"class":445,"line":446},[1090,1096,1101,1106,1111,1116,1121,1125,1130],{"type":47,"tag":443,"props":1091,"children":1093},{"style":1092},"--shiki-light:#39ADB5;--shiki-light-font-style:italic;--shiki-default:#89DDFF;--shiki-default-font-style:italic;--shiki-dark:#89DDFF;--shiki-dark-font-style:italic",[1094],{"type":53,"value":1095},"import",{"type":47,"tag":443,"props":1097,"children":1098},{"style":580},[1099],{"type":53,"value":1100}," {",{"type":47,"tag":443,"props":1102,"children":1103},{"style":574},[1104],{"type":53,"value":1105}," GoogleGenAI",{"type":47,"tag":443,"props":1107,"children":1108},{"style":580},[1109],{"type":53,"value":1110}," }",{"type":47,"tag":443,"props":1112,"children":1113},{"style":1092},[1114],{"type":53,"value":1115}," from",{"type":47,"tag":443,"props":1117,"children":1118},{"style":580},[1119],{"type":53,"value":1120}," \"",{"type":47,"tag":443,"props":1122,"children":1123},{"style":591},[1124],{"type":53,"value":186},{"type":47,"tag":443,"props":1126,"children":1127},{"style":580},[1128],{"type":53,"value":1129},"\"",{"type":47,"tag":443,"props":1131,"children":1132},{"style":580},[1133],{"type":53,"value":1134},";\n",{"type":47,"tag":443,"props":1136,"children":1137},{"class":445,"line":455},[1138,1143,1148,1152,1157,1162,1167,1172,1178,1182,1186,1191,1195,1199,1203,1207,1212,1217,1221,1225,1229,1233,1237,1241,1245],{"type":47,"tag":443,"props":1139,"children":1140},{"style":568},[1141],{"type":53,"value":1142},"const",{"type":47,"tag":443,"props":1144,"children":1145},{"style":574},[1146],{"type":53,"value":1147}," ai ",{"type":47,"tag":443,"props":1149,"children":1150},{"style":580},[1151],{"type":53,"value":583},{"type":47,"tag":443,"props":1153,"children":1154},{"style":580},[1155],{"type":53,"value":1156}," new",{"type":47,"tag":443,"props":1158,"children":1160},{"style":1159},"--shiki-light:#6182B8;--shiki-default:#82AAFF;--shiki-dark:#82AAFF",[1161],{"type":53,"value":1105},{"type":47,"tag":443,"props":1163,"children":1164},{"style":574},[1165],{"type":53,"value":1166},"(",{"type":47,"tag":443,"props":1168,"children":1169},{"style":580},[1170],{"type":53,"value":1171},"{",{"type":47,"tag":443,"props":1173,"children":1175},{"style":1174},"--shiki-light:#E53935;--shiki-default:#F07178;--shiki-dark:#F07178",[1176],{"type":53,"value":1177}," vertexai",{"type":47,"tag":443,"props":1179,"children":1180},{"style":580},[1181],{"type":53,"value":408},{"type":47,"tag":443,"props":1183,"children":1184},{"style":580},[1185],{"type":53,"value":1100},{"type":47,"tag":443,"props":1187,"children":1188},{"style":1174},[1189],{"type":53,"value":1190}," project",{"type":47,"tag":443,"props":1192,"children":1193},{"style":580},[1194],{"type":53,"value":408},{"type":47,"tag":443,"props":1196,"children":1197},{"style":580},[1198],{"type":53,"value":1120},{"type":47,"tag":443,"props":1200,"children":1201},{"style":591},[1202],{"type":53,"value":594},{"type":47,"tag":443,"props":1204,"children":1205},{"style":580},[1206],{"type":53,"value":1129},{"type":47,"tag":443,"props":1208,"children":1209},{"style":580},[1210],{"type":53,"value":1211},",",{"type":47,"tag":443,"props":1213,"children":1214},{"style":1174},[1215],{"type":53,"value":1216}," location",{"type":47,"tag":443,"props":1218,"children":1219},{"style":580},[1220],{"type":53,"value":408},{"type":47,"tag":443,"props":1222,"children":1223},{"style":580},[1224],{"type":53,"value":1120},{"type":47,"tag":443,"props":1226,"children":1227},{"style":591},[1228],{"type":53,"value":624},{"type":47,"tag":443,"props":1230,"children":1231},{"style":580},[1232],{"type":53,"value":1129},{"type":47,"tag":443,"props":1234,"children":1235},{"style":580},[1236],{"type":53,"value":1110},{"type":47,"tag":443,"props":1238,"children":1239},{"style":580},[1240],{"type":53,"value":1110},{"type":47,"tag":443,"props":1242,"children":1243},{"style":574},[1244],{"type":53,"value":395},{"type":47,"tag":443,"props":1246,"children":1247},{"style":580},[1248],{"type":53,"value":1134},{"type":47,"tag":443,"props":1250,"children":1251},{"class":445,"line":464},[1252,1256,1261,1265,1270,1275,1279,1283,1287,1292,1296],{"type":47,"tag":443,"props":1253,"children":1254},{"style":568},[1255],{"type":53,"value":1142},{"type":47,"tag":443,"props":1257,"children":1258},{"style":574},[1259],{"type":53,"value":1260}," response ",{"type":47,"tag":443,"props":1262,"children":1263},{"style":580},[1264],{"type":53,"value":583},{"type":47,"tag":443,"props":1266,"children":1267},{"style":1092},[1268],{"type":53,"value":1269}," await",{"type":47,"tag":443,"props":1271,"children":1272},{"style":574},[1273],{"type":53,"value":1274}," ai",{"type":47,"tag":443,"props":1276,"children":1277},{"style":580},[1278],{"type":53,"value":246},{"type":47,"tag":443,"props":1280,"children":1281},{"style":574},[1282],{"type":53,"value":843},{"type":47,"tag":443,"props":1284,"children":1285},{"style":580},[1286],{"type":53,"value":246},{"type":47,"tag":443,"props":1288,"children":1289},{"style":1159},[1290],{"type":53,"value":1291},"generateContent",{"type":47,"tag":443,"props":1293,"children":1294},{"style":574},[1295],{"type":53,"value":1166},{"type":47,"tag":443,"props":1297,"children":1298},{"style":580},[1299],{"type":53,"value":1300},"{\n",{"type":47,"tag":443,"props":1302,"children":1303},{"class":445,"line":473},[1304,1309,1313,1317,1321,1325],{"type":47,"tag":443,"props":1305,"children":1306},{"style":1174},[1307],{"type":53,"value":1308},"    model",{"type":47,"tag":443,"props":1310,"children":1311},{"style":580},[1312],{"type":53,"value":408},{"type":47,"tag":443,"props":1314,"children":1315},{"style":580},[1316],{"type":53,"value":1120},{"type":47,"tag":443,"props":1318,"children":1319},{"style":591},[1320],{"type":53,"value":872},{"type":47,"tag":443,"props":1322,"children":1323},{"style":580},[1324],{"type":53,"value":1129},{"type":47,"tag":443,"props":1326,"children":1327},{"style":580},[1328],{"type":53,"value":1329},",\n",{"type":47,"tag":443,"props":1331,"children":1332},{"class":445,"line":482},[1333,1338,1342,1346,1351],{"type":47,"tag":443,"props":1334,"children":1335},{"style":1174},[1336],{"type":53,"value":1337},"    contents",{"type":47,"tag":443,"props":1339,"children":1340},{"style":580},[1341],{"type":53,"value":408},{"type":47,"tag":443,"props":1343,"children":1344},{"style":580},[1345],{"type":53,"value":1120},{"type":47,"tag":443,"props":1347,"children":1348},{"style":591},[1349],{"type":53,"value":1350},"Explain quantum computing",{"type":47,"tag":443,"props":1352,"children":1353},{"style":580},[1354],{"type":53,"value":1355},"\"\n",{"type":47,"tag":443,"props":1357,"children":1358},{"class":445,"line":1056},[1359,1364,1368],{"type":47,"tag":443,"props":1360,"children":1361},{"style":580},[1362],{"type":53,"value":1363},"}",{"type":47,"tag":443,"props":1365,"children":1366},{"style":574},[1367],{"type":53,"value":395},{"type":47,"tag":443,"props":1369,"children":1370},{"style":580},[1371],{"type":53,"value":1134},{"type":47,"tag":443,"props":1373,"children":1374},{"class":445,"line":1065},[1375,1380,1384,1389,1394,1398,1403],{"type":47,"tag":443,"props":1376,"children":1377},{"style":574},[1378],{"type":53,"value":1379},"console",{"type":47,"tag":443,"props":1381,"children":1382},{"style":580},[1383],{"type":53,"value":246},{"type":47,"tag":443,"props":1385,"children":1386},{"style":1159},[1387],{"type":53,"value":1388},"log",{"type":47,"tag":443,"props":1390,"children":1391},{"style":574},[1392],{"type":53,"value":1393},"(response",{"type":47,"tag":443,"props":1395,"children":1396},{"style":580},[1397],{"type":53,"value":246},{"type":47,"tag":443,"props":1399,"children":1400},{"style":574},[1401],{"type":53,"value":1402},"text)",{"type":47,"tag":443,"props":1404,"children":1405},{"style":580},[1406],{"type":53,"value":1134},{"type":47,"tag":535,"props":1408,"children":1410},{"id":1409},"go",[1411],{"type":53,"value":307},{"type":47,"tag":410,"props":1413,"children":1416},{"className":1414,"code":1415,"language":1409,"meta":418,"style":418},"language-go shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","package main\n\nimport (\n    \"context\"\n    \"fmt\"\n    \"log\"\n    \"google.golang.org\u002Fgenai\"\n)\n\nfunc main() {\n    ctx := context.Background()\n    client, err := genai.NewClient(ctx, &genai.ClientConfig{\n        Backend:  genai.BackendVertexAI,\n        Project:  \"your-project-id\",\n        Location: \"global\",\n    })\n    if err != nil {\n        log.Fatal(err)\n    }\n\n    resp, err := client.Models.GenerateContent(ctx, \"gemini-3-flash-preview\", genai.Text(\"Explain quantum computing\"), nil)\n    if err != nil {\n        log.Fatal(err)\n    }\n\n    fmt.Println(resp.Text)\n}\n",[1417],{"type":47,"tag":173,"props":1418,"children":1419},{"__ignoreMap":418},[1420,1428,1437,1445,1453,1461,1469,1477,1485,1493,1502,1511,1520,1529,1538,1547,1556,1564,1573,1582,1590,1599,1607,1615,1623,1631,1640],{"type":47,"tag":443,"props":1421,"children":1422},{"class":445,"line":446},[1423],{"type":47,"tag":443,"props":1424,"children":1425},{},[1426],{"type":53,"value":1427},"package main\n",{"type":47,"tag":443,"props":1429,"children":1430},{"class":445,"line":455},[1431],{"type":47,"tag":443,"props":1432,"children":1434},{"emptyLinePlaceholder":1433},true,[1435],{"type":53,"value":1436},"\n",{"type":47,"tag":443,"props":1438,"children":1439},{"class":445,"line":464},[1440],{"type":47,"tag":443,"props":1441,"children":1442},{},[1443],{"type":53,"value":1444},"import (\n",{"type":47,"tag":443,"props":1446,"children":1447},{"class":445,"line":473},[1448],{"type":47,"tag":443,"props":1449,"children":1450},{},[1451],{"type":53,"value":1452},"    \"context\"\n",{"type":47,"tag":443,"props":1454,"children":1455},{"class":445,"line":482},[1456],{"type":47,"tag":443,"props":1457,"children":1458},{},[1459],{"type":53,"value":1460},"    \"fmt\"\n",{"type":47,"tag":443,"props":1462,"children":1463},{"class":445,"line":1056},[1464],{"type":47,"tag":443,"props":1465,"children":1466},{},[1467],{"type":53,"value":1468},"    \"log\"\n",{"type":47,"tag":443,"props":1470,"children":1471},{"class":445,"line":1065},[1472],{"type":47,"tag":443,"props":1473,"children":1474},{},[1475],{"type":53,"value":1476},"    \"google.golang.org\u002Fgenai\"\n",{"type":47,"tag":443,"props":1478,"children":1480},{"class":445,"line":1479},8,[1481],{"type":47,"tag":443,"props":1482,"children":1483},{},[1484],{"type":53,"value":1062},{"type":47,"tag":443,"props":1486,"children":1488},{"class":445,"line":1487},9,[1489],{"type":47,"tag":443,"props":1490,"children":1491},{"emptyLinePlaceholder":1433},[1492],{"type":53,"value":1436},{"type":47,"tag":443,"props":1494,"children":1496},{"class":445,"line":1495},10,[1497],{"type":47,"tag":443,"props":1498,"children":1499},{},[1500],{"type":53,"value":1501},"func main() {\n",{"type":47,"tag":443,"props":1503,"children":1505},{"class":445,"line":1504},11,[1506],{"type":47,"tag":443,"props":1507,"children":1508},{},[1509],{"type":53,"value":1510},"    ctx := context.Background()\n",{"type":47,"tag":443,"props":1512,"children":1514},{"class":445,"line":1513},12,[1515],{"type":47,"tag":443,"props":1516,"children":1517},{},[1518],{"type":53,"value":1519},"    client, err := genai.NewClient(ctx, &genai.ClientConfig{\n",{"type":47,"tag":443,"props":1521,"children":1523},{"class":445,"line":1522},13,[1524],{"type":47,"tag":443,"props":1525,"children":1526},{},[1527],{"type":53,"value":1528},"        Backend:  genai.BackendVertexAI,\n",{"type":47,"tag":443,"props":1530,"children":1532},{"class":445,"line":1531},14,[1533],{"type":47,"tag":443,"props":1534,"children":1535},{},[1536],{"type":53,"value":1537},"        Project:  \"your-project-id\",\n",{"type":47,"tag":443,"props":1539,"children":1541},{"class":445,"line":1540},15,[1542],{"type":47,"tag":443,"props":1543,"children":1544},{},[1545],{"type":53,"value":1546},"        Location: \"global\",\n",{"type":47,"tag":443,"props":1548,"children":1550},{"class":445,"line":1549},16,[1551],{"type":47,"tag":443,"props":1552,"children":1553},{},[1554],{"type":53,"value":1555},"    })\n",{"type":47,"tag":443,"props":1557,"children":1558},{"class":445,"line":29},[1559],{"type":47,"tag":443,"props":1560,"children":1561},{},[1562],{"type":53,"value":1563},"    if err != nil {\n",{"type":47,"tag":443,"props":1565,"children":1567},{"class":445,"line":1566},18,[1568],{"type":47,"tag":443,"props":1569,"children":1570},{},[1571],{"type":53,"value":1572},"        log.Fatal(err)\n",{"type":47,"tag":443,"props":1574,"children":1576},{"class":445,"line":1575},19,[1577],{"type":47,"tag":443,"props":1578,"children":1579},{},[1580],{"type":53,"value":1581},"    }\n",{"type":47,"tag":443,"props":1583,"children":1585},{"class":445,"line":1584},20,[1586],{"type":47,"tag":443,"props":1587,"children":1588},{"emptyLinePlaceholder":1433},[1589],{"type":53,"value":1436},{"type":47,"tag":443,"props":1591,"children":1593},{"class":445,"line":1592},21,[1594],{"type":47,"tag":443,"props":1595,"children":1596},{},[1597],{"type":53,"value":1598},"    resp, err := client.Models.GenerateContent(ctx, \"gemini-3-flash-preview\", genai.Text(\"Explain quantum computing\"), nil)\n",{"type":47,"tag":443,"props":1600,"children":1602},{"class":445,"line":1601},22,[1603],{"type":47,"tag":443,"props":1604,"children":1605},{},[1606],{"type":53,"value":1563},{"type":47,"tag":443,"props":1608,"children":1610},{"class":445,"line":1609},23,[1611],{"type":47,"tag":443,"props":1612,"children":1613},{},[1614],{"type":53,"value":1572},{"type":47,"tag":443,"props":1616,"children":1618},{"class":445,"line":1617},24,[1619],{"type":47,"tag":443,"props":1620,"children":1621},{},[1622],{"type":53,"value":1581},{"type":47,"tag":443,"props":1624,"children":1626},{"class":445,"line":1625},25,[1627],{"type":47,"tag":443,"props":1628,"children":1629},{"emptyLinePlaceholder":1433},[1630],{"type":53,"value":1436},{"type":47,"tag":443,"props":1632,"children":1634},{"class":445,"line":1633},26,[1635],{"type":47,"tag":443,"props":1636,"children":1637},{},[1638],{"type":53,"value":1639},"    fmt.Println(resp.Text)\n",{"type":47,"tag":443,"props":1641,"children":1643},{"class":445,"line":1642},27,[1644],{"type":47,"tag":443,"props":1645,"children":1646},{},[1647],{"type":53,"value":1648},"}\n",{"type":47,"tag":535,"props":1650,"children":1652},{"id":1651},"java",[1653],{"type":53,"value":349},{"type":47,"tag":410,"props":1655,"children":1658},{"className":1656,"code":1657,"language":1651,"meta":418,"style":418},"language-java shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","import com.google.genai.Client;\nimport com.google.genai.types.GenerateContentResponse;\n\npublic class GenerateTextFromTextInput {\n  public static void main(String[] args) {\n    Client client = Client.builder().vertexAi(true).project(\"your-project-id\").location(\"global\").build();\n    GenerateContentResponse response =\n        client.models.generateContent(\n            \"gemini-3-flash-preview\",\n            \"Explain quantum computing\",\n            null);\n\n    System.out.println(response.text());\n  }\n}\n",[1659],{"type":47,"tag":173,"props":1660,"children":1661},{"__ignoreMap":418},[1662,1670,1678,1685,1693,1701,1709,1717,1725,1733,1741,1749,1756,1764,1772],{"type":47,"tag":443,"props":1663,"children":1664},{"class":445,"line":446},[1665],{"type":47,"tag":443,"props":1666,"children":1667},{},[1668],{"type":53,"value":1669},"import com.google.genai.Client;\n",{"type":47,"tag":443,"props":1671,"children":1672},{"class":445,"line":455},[1673],{"type":47,"tag":443,"props":1674,"children":1675},{},[1676],{"type":53,"value":1677},"import com.google.genai.types.GenerateContentResponse;\n",{"type":47,"tag":443,"props":1679,"children":1680},{"class":445,"line":464},[1681],{"type":47,"tag":443,"props":1682,"children":1683},{"emptyLinePlaceholder":1433},[1684],{"type":53,"value":1436},{"type":47,"tag":443,"props":1686,"children":1687},{"class":445,"line":473},[1688],{"type":47,"tag":443,"props":1689,"children":1690},{},[1691],{"type":53,"value":1692},"public class GenerateTextFromTextInput {\n",{"type":47,"tag":443,"props":1694,"children":1695},{"class":445,"line":482},[1696],{"type":47,"tag":443,"props":1697,"children":1698},{},[1699],{"type":53,"value":1700},"  public static void main(String[] args) {\n",{"type":47,"tag":443,"props":1702,"children":1703},{"class":445,"line":1056},[1704],{"type":47,"tag":443,"props":1705,"children":1706},{},[1707],{"type":53,"value":1708},"    Client client = Client.builder().vertexAi(true).project(\"your-project-id\").location(\"global\").build();\n",{"type":47,"tag":443,"props":1710,"children":1711},{"class":445,"line":1065},[1712],{"type":47,"tag":443,"props":1713,"children":1714},{},[1715],{"type":53,"value":1716},"    GenerateContentResponse response =\n",{"type":47,"tag":443,"props":1718,"children":1719},{"class":445,"line":1479},[1720],{"type":47,"tag":443,"props":1721,"children":1722},{},[1723],{"type":53,"value":1724},"        client.models.generateContent(\n",{"type":47,"tag":443,"props":1726,"children":1727},{"class":445,"line":1487},[1728],{"type":47,"tag":443,"props":1729,"children":1730},{},[1731],{"type":53,"value":1732},"            \"gemini-3-flash-preview\",\n",{"type":47,"tag":443,"props":1734,"children":1735},{"class":445,"line":1495},[1736],{"type":47,"tag":443,"props":1737,"children":1738},{},[1739],{"type":53,"value":1740},"            \"Explain quantum computing\",\n",{"type":47,"tag":443,"props":1742,"children":1743},{"class":445,"line":1504},[1744],{"type":47,"tag":443,"props":1745,"children":1746},{},[1747],{"type":53,"value":1748},"            null);\n",{"type":47,"tag":443,"props":1750,"children":1751},{"class":445,"line":1513},[1752],{"type":47,"tag":443,"props":1753,"children":1754},{"emptyLinePlaceholder":1433},[1755],{"type":53,"value":1436},{"type":47,"tag":443,"props":1757,"children":1758},{"class":445,"line":1522},[1759],{"type":47,"tag":443,"props":1760,"children":1761},{},[1762],{"type":53,"value":1763},"    System.out.println(response.text());\n",{"type":47,"tag":443,"props":1765,"children":1766},{"class":445,"line":1531},[1767],{"type":47,"tag":443,"props":1768,"children":1769},{},[1770],{"type":53,"value":1771},"  }\n",{"type":47,"tag":443,"props":1773,"children":1774},{"class":445,"line":1540},[1775],{"type":47,"tag":443,"props":1776,"children":1777},{},[1778],{"type":53,"value":1648},{"type":47,"tag":535,"props":1780,"children":1782},{"id":1781},"cnet",[1783],{"type":53,"value":328},{"type":47,"tag":410,"props":1785,"children":1789},{"className":1786,"code":1787,"language":1788,"meta":418,"style":418},"language-csharp shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","using Google.GenAI;\n\nvar client = new Client(\n    project: \"your-project-id\",\n    location: \"global\",\n    vertexAI: true\n);\n\nvar response = await client.Models.GenerateContent(\n    \"gemini-3-flash-preview\",\n    \"Explain quantum computing\"\n);\n\nConsole.WriteLine(response.Text);\n","csharp",[1790],{"type":47,"tag":173,"props":1791,"children":1792},{"__ignoreMap":418},[1793,1801,1808,1816,1824,1832,1840,1848,1855,1863,1871,1879,1886,1893],{"type":47,"tag":443,"props":1794,"children":1795},{"class":445,"line":446},[1796],{"type":47,"tag":443,"props":1797,"children":1798},{},[1799],{"type":53,"value":1800},"using Google.GenAI;\n",{"type":47,"tag":443,"props":1802,"children":1803},{"class":445,"line":455},[1804],{"type":47,"tag":443,"props":1805,"children":1806},{"emptyLinePlaceholder":1433},[1807],{"type":53,"value":1436},{"type":47,"tag":443,"props":1809,"children":1810},{"class":445,"line":464},[1811],{"type":47,"tag":443,"props":1812,"children":1813},{},[1814],{"type":53,"value":1815},"var client = new Client(\n",{"type":47,"tag":443,"props":1817,"children":1818},{"class":445,"line":473},[1819],{"type":47,"tag":443,"props":1820,"children":1821},{},[1822],{"type":53,"value":1823},"    project: \"your-project-id\",\n",{"type":47,"tag":443,"props":1825,"children":1826},{"class":445,"line":482},[1827],{"type":47,"tag":443,"props":1828,"children":1829},{},[1830],{"type":53,"value":1831},"    location: \"global\",\n",{"type":47,"tag":443,"props":1833,"children":1834},{"class":445,"line":1056},[1835],{"type":47,"tag":443,"props":1836,"children":1837},{},[1838],{"type":53,"value":1839},"    vertexAI: true\n",{"type":47,"tag":443,"props":1841,"children":1842},{"class":445,"line":1065},[1843],{"type":47,"tag":443,"props":1844,"children":1845},{},[1846],{"type":53,"value":1847},");\n",{"type":47,"tag":443,"props":1849,"children":1850},{"class":445,"line":1479},[1851],{"type":47,"tag":443,"props":1852,"children":1853},{"emptyLinePlaceholder":1433},[1854],{"type":53,"value":1436},{"type":47,"tag":443,"props":1856,"children":1857},{"class":445,"line":1487},[1858],{"type":47,"tag":443,"props":1859,"children":1860},{},[1861],{"type":53,"value":1862},"var response = await client.Models.GenerateContent(\n",{"type":47,"tag":443,"props":1864,"children":1865},{"class":445,"line":1495},[1866],{"type":47,"tag":443,"props":1867,"children":1868},{},[1869],{"type":53,"value":1870},"    \"gemini-3-flash-preview\",\n",{"type":47,"tag":443,"props":1872,"children":1873},{"class":445,"line":1504},[1874],{"type":47,"tag":443,"props":1875,"children":1876},{},[1877],{"type":53,"value":1878},"    \"Explain quantum computing\"\n",{"type":47,"tag":443,"props":1880,"children":1881},{"class":445,"line":1513},[1882],{"type":47,"tag":443,"props":1883,"children":1884},{},[1885],{"type":53,"value":1847},{"type":47,"tag":443,"props":1887,"children":1888},{"class":445,"line":1522},[1889],{"type":47,"tag":443,"props":1890,"children":1891},{"emptyLinePlaceholder":1433},[1892],{"type":53,"value":1436},{"type":47,"tag":443,"props":1894,"children":1895},{"class":445,"line":1531},[1896],{"type":47,"tag":443,"props":1897,"children":1898},{},[1899],{"type":53,"value":1900},"Console.WriteLine(response.Text);\n",{"type":47,"tag":153,"props":1902,"children":1904},{"id":1903},"api-spec-documentation-source-of-truth",[1905],{"type":53,"value":1906},"API spec & Documentation (source of truth)",{"type":47,"tag":56,"props":1908,"children":1909},{},[1910],{"type":53,"value":1911},"When implementing or debugging API integration for Vertex AI, refer to the official Google Cloud Vertex AI documentation:",{"type":47,"tag":67,"props":1913,"children":1914},{},[1915,1931],{"type":47,"tag":71,"props":1916,"children":1917},{},[1918,1923,1925],{"type":47,"tag":75,"props":1919,"children":1920},{},[1921],{"type":53,"value":1922},"Vertex AI Gemini Documentation",{"type":53,"value":1924},": ",{"type":47,"tag":379,"props":1926,"children":1929},{"href":1927,"rel":1928},"https:\u002F\u002Fcloud.google.com\u002Fvertex-ai\u002Fgenerative-ai\u002Fdocs\u002F",[383],[1930],{"type":53,"value":1927},{"type":47,"tag":71,"props":1932,"children":1933},{},[1934,1939,1940],{"type":47,"tag":75,"props":1935,"children":1936},{},[1937],{"type":53,"value":1938},"REST API Reference",{"type":53,"value":1924},{"type":47,"tag":379,"props":1941,"children":1944},{"href":1942,"rel":1943},"https:\u002F\u002Fcloud.google.com\u002Fvertex-ai\u002Fgenerative-ai\u002Fdocs\u002Freference\u002Frest",[383],[1945],{"type":53,"value":1942},{"type":47,"tag":56,"props":1947,"children":1948},{},[1949,1951,1957,1959,1965,1967,1973],{"type":53,"value":1950},"The Gen AI SDK on Vertex AI uses the ",{"type":47,"tag":173,"props":1952,"children":1954},{"className":1953},[],[1955],{"type":53,"value":1956},"v1beta1",{"type":53,"value":1958}," or ",{"type":47,"tag":173,"props":1960,"children":1962},{"className":1961},[],[1963],{"type":53,"value":1964},"v1",{"type":53,"value":1966}," REST API endpoints (e.g., ",{"type":47,"tag":173,"props":1968,"children":1970},{"className":1969},[],[1971],{"type":53,"value":1972},"https:\u002F\u002F{LOCATION}-aiplatform.googleapis.com\u002Fv1beta1\u002Fprojects\u002F{PROJECT}\u002Flocations\u002F{LOCATION}\u002Fpublishers\u002Fgoogle\u002Fmodels\u002F{MODEL}:generateContent",{"type":53,"value":998},{"type":47,"tag":490,"props":1975,"children":1976},{},[1977],{"type":47,"tag":56,"props":1978,"children":1979},{},[1980,1985,1990,1992,1998,1999,2005],{"type":47,"tag":443,"props":1981,"children":1982},{},[1983],{"type":53,"value":1984},"!TIP",{"type":47,"tag":75,"props":1986,"children":1987},{},[1988],{"type":53,"value":1989},"Use the Developer Knowledge MCP Server",{"type":53,"value":1991},": If the ",{"type":47,"tag":173,"props":1993,"children":1995},{"className":1994},[],[1996],{"type":53,"value":1997},"search_documents",{"type":53,"value":1958},{"type":47,"tag":173,"props":2000,"children":2002},{"className":2001},[],[2003],{"type":53,"value":2004},"get_document",{"type":53,"value":2006}," tools are available, use them to find and retrieve official documentation for Google Cloud and Vertex AI directly within the context. This is the preferred method for getting up-to-date API details and code snippets.",{"type":47,"tag":153,"props":2008,"children":2010},{"id":2009},"workflows-and-code-samples",[2011],{"type":53,"value":2012},"Workflows and Code Samples",{"type":47,"tag":56,"props":2014,"children":2015},{},[2016,2018,2025],{"type":53,"value":2017},"Reference the ",{"type":47,"tag":379,"props":2019,"children":2022},{"href":2020,"rel":2021},"https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fpython-docs-samples\u002Ftree\u002Fmain\u002Fgenai",[383],[2023],{"type":53,"value":2024},"Python Docs Samples repository",{"type":53,"value":2026}," for additional code samples and specific usage scenarios.",{"type":47,"tag":56,"props":2028,"children":2029},{},[2030],{"type":53,"value":2031},"Depending on the specific user request, refer to the following reference files for detailed code samples and usage patterns (Python examples):",{"type":47,"tag":67,"props":2033,"children":2034},{},[2035,2050,2064,2079,2094,2109,2124,2139,2154],{"type":47,"tag":71,"props":2036,"children":2037},{},[2038,2043,2045],{"type":47,"tag":75,"props":2039,"children":2040},{},[2041],{"type":53,"value":2042},"Text & Multimodal",{"type":53,"value":2044},": Chat, Multimodal inputs (Image, Video, Audio), and Streaming. See ",{"type":47,"tag":379,"props":2046,"children":2048},{"href":2047},"references\u002Ftext_and_multimodal.md",[2049],{"type":53,"value":2047},{"type":47,"tag":71,"props":2051,"children":2052},{},[2053,2057,2059],{"type":47,"tag":75,"props":2054,"children":2055},{},[2056],{"type":53,"value":129},{"type":53,"value":2058},": Generate text embeddings for semantic search. See ",{"type":47,"tag":379,"props":2060,"children":2062},{"href":2061},"references\u002Fembeddings.md",[2063],{"type":53,"value":2061},{"type":47,"tag":71,"props":2065,"children":2066},{},[2067,2072,2074],{"type":47,"tag":75,"props":2068,"children":2069},{},[2070],{"type":53,"value":2071},"Structured Output & Tools",{"type":53,"value":2073},": JSON generation, Function Calling, Search Grounding, and Code Execution. See ",{"type":47,"tag":379,"props":2075,"children":2077},{"href":2076},"references\u002Fstructured_and_tools.md",[2078],{"type":53,"value":2076},{"type":47,"tag":71,"props":2080,"children":2081},{},[2082,2087,2089],{"type":47,"tag":75,"props":2083,"children":2084},{},[2085],{"type":53,"value":2086},"Media Generation",{"type":53,"value":2088},": Image generation, Image editing, and Video generation. See ",{"type":47,"tag":379,"props":2090,"children":2092},{"href":2091},"references\u002Fmedia_generation.md",[2093],{"type":53,"value":2091},{"type":47,"tag":71,"props":2095,"children":2096},{},[2097,2102,2104],{"type":47,"tag":75,"props":2098,"children":2099},{},[2100],{"type":53,"value":2101},"Bounding Box Detection",{"type":53,"value":2103},": Object detection and localization within images and video. See ",{"type":47,"tag":379,"props":2105,"children":2107},{"href":2106},"references\u002Fbounding_box.md",[2108],{"type":53,"value":2106},{"type":47,"tag":71,"props":2110,"children":2111},{},[2112,2117,2119],{"type":47,"tag":75,"props":2113,"children":2114},{},[2115],{"type":53,"value":2116},"Live API",{"type":53,"value":2118},": Real-time bidirectional streaming for voice, vision, and text. See ",{"type":47,"tag":379,"props":2120,"children":2122},{"href":2121},"references\u002Flive_api.md",[2123],{"type":53,"value":2121},{"type":47,"tag":71,"props":2125,"children":2126},{},[2127,2132,2134],{"type":47,"tag":75,"props":2128,"children":2129},{},[2130],{"type":53,"value":2131},"Advanced Features",{"type":53,"value":2133},": Content Caching, Batch Prediction, and Thinking\u002FReasoning. See ",{"type":47,"tag":379,"props":2135,"children":2137},{"href":2136},"references\u002Fadvanced_features.md",[2138],{"type":53,"value":2136},{"type":47,"tag":71,"props":2140,"children":2141},{},[2142,2147,2149],{"type":47,"tag":75,"props":2143,"children":2144},{},[2145],{"type":53,"value":2146},"Safety",{"type":53,"value":2148},": Adjusting Responsible AI filters and thresholds. See ",{"type":47,"tag":379,"props":2150,"children":2152},{"href":2151},"references\u002Fsafety.md",[2153],{"type":53,"value":2151},{"type":47,"tag":71,"props":2155,"children":2156},{},[2157,2162,2164],{"type":47,"tag":75,"props":2158,"children":2159},{},[2160],{"type":53,"value":2161},"Model Tuning",{"type":53,"value":2163},": Supervised Fine-Tuning and Preference Tuning. See ",{"type":47,"tag":379,"props":2165,"children":2167},{"href":2166},"references\u002Fmodel_tuning.md",[2168],{"type":53,"value":2166},{"type":47,"tag":2170,"props":2171,"children":2172},"style",{},[2173],{"type":53,"value":2174},"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":2176,"total":2307},[2177,2195,2204,2213,2224,2234,2247,2256,2265,2275,2284,2297],{"slug":2178,"name":2178,"fn":2179,"description":2180,"org":2181,"tags":2182,"stars":2192,"repoUrl":2193,"updatedAt":2194},"mps-aspect-accessories","configure JetBrains MPS module dependencies","Wire MPS module and model dependencies, used languages, used devkits, extended languages, runtime solutions, accessory models, and language\u002Fdependency versions. Use when adding\u002Fremoving module dependencies, importing languages or devkits into a model, declaring runtime solutions, or shipping accessory content visible to consumers without explicit import.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[2183,2186,2189],{"name":2184,"slug":2185,"type":15},"Architecture","architecture",{"name":2187,"slug":2188,"type":15},"Configuration","configuration",{"name":2190,"slug":2191,"type":15},"Engineering","engineering",1650,"https:\u002F\u002Fgithub.com\u002FJetBrains\u002FMPS","2026-07-17T06:06:57.311661",{"slug":2196,"name":2196,"fn":2197,"description":2198,"org":2199,"tags":2200,"stars":2192,"repoUrl":2193,"updatedAt":2203},"mps-aspect-actions","define and edit MPS node factories","Use when defining or editing MPS node factories (the \"actions\" aspect) — `NodeFactories` roots, per-concept `NodeFactory` setup functions that initialize a freshly created node and optionally copy data from a replaced `sampleNode`, plus the actions aspect's `CopyPasteHandlers` and `PasteWrappers` roots. Reach for this skill when a substitution, side transform, completion replacement, or `add new initialized(...)` should preserve fields from the node it is replacing, or when defaults set in a constructor are not enough.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[2201,2202],{"name":2184,"slug":2185,"type":15},{"name":2190,"slug":2191,"type":15},"2026-07-17T06:04:48.066901",{"slug":2205,"name":2205,"fn":2206,"description":2207,"org":2208,"tags":2209,"stars":2192,"repoUrl":2193,"updatedAt":2212},"mps-aspect-behavior","define and edit MPS concept behavior","Use when defining or editing MPS `ConceptBehavior` — per-concept methods (non-virtual \u002F virtual \u002F abstract \u002F static \u002F virtual static), constructors, virtual dispatch (MRO), super and interface-default calls (`super\u003CInterface>.method`), overriding methods from `lang.core.behavior` interfaces such as `ScopeProvider.getScope` \u002F `INamedConcept.getName` \u002F `BaseConcept.getPresentation`, calling sibling methods (`LocalBehaviorMethodCall`) and behavior methods from other aspects via `node.method(...)`. Reach for this skill whenever the task involves authoring or modifying `\u003Clang>\u002FlanguageModels\u002Fbehavior.mps`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[2210,2211],{"name":2184,"slug":2185,"type":15},{"name":2190,"slug":2191,"type":15},"2026-07-13T06:45:21.757084",{"slug":2214,"name":2214,"fn":2215,"description":2216,"org":2217,"tags":2218,"stars":2192,"repoUrl":2193,"updatedAt":2223},"mps-aspect-constraints","define JetBrains MPS language constraints","Use when defining or editing MPS language constraints — property validators \u002F setters \u002F getters, referent search scopes (imperative or inherited via `ScopeProvider.getScope`), `referentSetHandler` side effects, default-scope blocks, `canBeChild` \u002F `canBeParent` \u002F `canBeAncestor` \u002F `canBeRoot` placement rules, `defaultConcreteConcept` for abstract concepts, `set \u003Cread-only>` and `{name}` aliasing, and scope helpers (`SimpleRoleScope`, `ListScope`, `CompositeScope`, `HidingByNameScope`). Reach for this skill whenever the task involves authoring or modifying `\u003Clang>\u002FlanguageModels\u002Fconstraints.mps`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[2219,2220],{"name":2184,"slug":2185,"type":15},{"name":2221,"slug":2222,"type":15},"Code Analysis","code-analysis","2026-07-23T05:41:33.639365",{"slug":2225,"name":2225,"fn":2226,"description":2227,"org":2228,"tags":2229,"stars":2192,"repoUrl":2193,"updatedAt":2233},"mps-aspect-dataflow","define and debug MPS dataflow builders","Use when defining or debugging MPS dataflow builders for a concept — control\u002Fdata flow declarations that drive reachability analysis and variable-use checking. Covers DataFlowBuilderDeclaration, BuilderBlock, emit instructions (code for, jump, ifjump, label, read, write, ret, mayBeUnreachable), positions (AfterPosition, BeforePosition, LabelPosition), the jetbrains.mps.lang.dataFlow language, the NodeParameter implicit, BL+smodel usage inside builder bodies, and IBuilderMode for advanced analyses such as nullable\u002Fnon-null tracking.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[2230],{"name":2231,"slug":2232,"type":15},"Data Analysis","data-analysis","2026-07-13T06:45:19.114674",{"slug":2235,"name":2235,"fn":2236,"description":2237,"org":2238,"tags":2239,"stars":2192,"repoUrl":2193,"updatedAt":2246},"mps-aspect-editor","define MPS editor layouts","Use when creating or changing MPS editor definitions — the overall workflow from scaffolding a `ConceptEditorDeclaration` through componentizing reusable `EditorComponentDeclaration`s, refining cell models and cell layouts, applying style sheets and indent-layout style items, wiring smart references, leveraging inheritance via super-concepts and interfaces, inspecting (`print_node_json`, `show_node_representation`) and validating (`check_root_node_problems`). Covers `jetbrains.mps.lang.editor` cell models (`CellModel_RefNode`\u002F`CellModel_RefNodeList`\u002F`CellModel_RefCell`\u002F`CellModel_Property`\u002F`CellModel_Constant`), layout choices, and JSON blueprints for common editor shapes. For the non-layout side (action maps, keymaps, transformation\u002Fsubstitute menus) use `mps-aspect-editor-menus-and-keymaps`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[2240,2243],{"name":2241,"slug":2242,"type":15},"Design","design",{"name":2244,"slug":2245,"type":15},"UI Components","ui-components","2026-07-23T05:41:56.638151",{"slug":2248,"name":2248,"fn":2249,"description":2250,"org":2251,"tags":2252,"stars":2192,"repoUrl":2193,"updatedAt":2255},"mps-aspect-editor-menus-and-keymaps","author MPS editor menus and keymaps","Use when authoring the **non-layout** parts of the MPS editor aspect — what happens when the user types, presses a key, triggers completion, pastes, or invokes a context action. Covers action maps (`CellActionMapDeclaration`), cell keymaps (`CellKeyMapDeclaration`), transformation menus (`TransformationMenu_Default` \u002F `_Named` \u002F `_Contribution`), substitute menus (`SubstituteMenu_Default` \u002F `SubstituteMenu` \u002F contributions), side transforms (LEFT\u002FRIGHT), legacy cell menus, paste wrappers and copy-paste handlers (in the actions language), completion styling, reference presentation, two-step deletion, and the editor selection API. Trigger terms: `actionMap`, `keyMap`, `delete_action_id`, `transformationMenu`, `substituteMenu`, `Ctrl+Space`, `Ctrl+Alt+B`, side transform, paste wrapper, completion styling, `PasteWrappers`, `CopyPasteHandlers`. For the **layout** side (cells, layouts, style sheets) use `mps-aspect-editor` instead.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[2253,2254],{"name":2190,"slug":2191,"type":15},{"name":2244,"slug":2245,"type":15},"2026-07-23T05:41:49.666535",{"slug":2257,"name":2257,"fn":2258,"description":2259,"org":2260,"tags":2261,"stars":2192,"repoUrl":2193,"updatedAt":2264},"mps-aspect-generation-plan","modify MPS generation plans","Use when defining or modifying an MPS generation plan — explicit ordering of generators, checkpoints for cross-model reference resolution, forks for parallel branches, IncludePlan composition, conditional PlanContribution activation, ParameterEquals\u002FConceptListSelector fork selectors, and InitModelAttributes for targetFacet routing. Apply when working with @genplan models, the jetbrains.mps.lang.generator.plan language, attaching plans via DevKits or the Custom generation facet, or debugging cross-model mapping label resolution.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[2262,2263],{"name":2184,"slug":2185,"type":15},{"name":2190,"slug":2191,"type":15},"2026-07-13T06:44:59.507855",{"slug":2266,"name":2266,"fn":2267,"description":2268,"org":2269,"tags":2270,"stars":2192,"repoUrl":2193,"updatedAt":2274},"mps-aspect-generator","define JetBrains MPS generator rules","Use when defining or modifying MPS generators — author a generator module, add or edit root\u002Freduction\u002Fweaving\u002Fpattern mapping rules, attach template macros ($COPY_SRC, $LOOP, $IF, $PROPERTY, $REF, $SWITCH, $MAP_SRC, $WEAVE, $INSERT, $LABEL, $TRACE, $VAR), wire mapping labels, build template switches, write pre\u002Fpost mapping scripts, navigate `genContext`, or debug \"rule didn't fire\", missing references, empty output, infinite reduction loops, and generated-Java compile failures.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[2271,2272,2273],{"name":2184,"slug":2185,"type":15},{"name":2221,"slug":2222,"type":15},{"name":2190,"slug":2191,"type":15},"2026-07-17T06:06:58.042999",{"slug":2276,"name":2276,"fn":2277,"description":2278,"org":2279,"tags":2280,"stars":2192,"repoUrl":2193,"updatedAt":2283},"mps-aspect-intentions","define and edit MPS intentions","Use when defining or editing MPS intentions (the Alt+Enter context-action aspect) — adding `IntentionDeclaration` roots, parameterized or surround-with variants, description\u002FisApplicable\u002Fexecute blocks, child-filter functions, factory-initialized AST splicing, or debugging why an intention is not offered. Lives in the language's `intentions` model and uses `jetbrains.mps.lang.intentions`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[2281,2282],{"name":2184,"slug":2185,"type":15},{"name":2190,"slug":2191,"type":15},"2026-07-23T05:41:48.692899",{"slug":2285,"name":2285,"fn":2286,"description":2287,"org":2288,"tags":2289,"stars":2192,"repoUrl":2193,"updatedAt":2296},"mps-aspect-migrations","author and debug MPS migration scripts","Use when authoring or debugging MPS migration scripts that upgrade user models after a language definition changes — covers jetbrains.mps.lang.migration (MigrationScript class-based, PureMigrationScript declarative, MoveConcept\u002FMoveContainmentLink\u002FMoveReferenceLink\u002FMoveProperty, ordering via OrderDependency, data exchange via putData\u002FgetData, RefactoringLog, ConceptMigrationReference) and jetbrains.mps.lang.script Enhancement Scripts (MigrationScript with MigrationScriptPart_Instance, ExtractInterfaceMigration, FactoryMigrationScriptPart, CommentMigrationScriptPart) — when a model needs version-gated upgrade, concept rename or removal, link or property rename, instance-level transformation, or composition of migration steps.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[2290,2293],{"name":2291,"slug":2292,"type":15},"Debugging","debugging",{"name":2294,"slug":2295,"type":15},"Migration","migration","2026-07-13T06:45:20.372122",{"slug":2298,"name":2298,"fn":2299,"description":2300,"org":2301,"tags":2302,"stars":2192,"repoUrl":2193,"updatedAt":2306},"mps-aspect-structure-concepts","define concepts in MPS structure aspect","Define concepts, interface concepts, enumerations, and constrained data types in an MPS language's `structure` aspect. Covers smart-reference detection, alias rules, cardinality, INamedConcept usage, bulk creation, and the full `mps_mcp_alter_structure` \u002F `mps_mcp_query_structure` reference. Use when authoring or modifying a language's structure model.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[2303],{"name":2304,"slug":2305,"type":15},"Data Modeling","data-modeling","2026-07-23T05:41:30.705975",188,{"items":2309,"total":2426},[2310,2329,2343,2357,2372,2395,2412],{"slug":2311,"name":2311,"fn":2312,"description":2313,"org":2314,"tags":2315,"stars":25,"repoUrl":26,"updatedAt":2328},"algorithmic-art","create generative art with p5.js","Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[2316,2319,2322,2325],{"name":2317,"slug":2318,"type":15},"Creative","creative",{"name":2320,"slug":2321,"type":15},"Generative Art","generative-art",{"name":2323,"slug":2324,"type":15},"Graphics","graphics",{"name":2326,"slug":2327,"type":15},"JavaScript","javascript","2026-07-13T06:41:35.540127",{"slug":2330,"name":2330,"fn":2331,"description":2332,"org":2333,"tags":2334,"stars":25,"repoUrl":26,"updatedAt":2342},"antfu","configure JavaScript projects with Anthony Fu's tools","Anthony Fu's opinionated tooling and conventions for JavaScript\u002FTypeScript projects. Use when setting up new projects, configuring ESLint\u002FPrettier alternatives, monorepos, library publishing, or when the user mentions Anthony Fu's preferences.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[2335,2338,2339,2340],{"name":2336,"slug":2337,"type":15},"Best Practices","best-practices",{"name":2190,"slug":2191,"type":15},{"name":2326,"slug":2327,"type":15},{"name":2341,"slug":1082,"type":15},"TypeScript","2026-07-13T06:43:13.153309",{"slug":2344,"name":2344,"fn":2345,"description":2346,"org":2347,"tags":2348,"stars":25,"repoUrl":26,"updatedAt":2356},"brand-guidelines","apply Anthropic brand guidelines","Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[2349,2352,2353],{"name":2350,"slug":2351,"type":15},"Branding","branding",{"name":2241,"slug":2242,"type":15},{"name":2354,"slug":2355,"type":15},"Typography","typography","2026-07-13T06:43:06.077629",{"slug":2358,"name":2358,"fn":2359,"description":2360,"org":2361,"tags":2362,"stars":25,"repoUrl":26,"updatedAt":2371},"canvas-design","create visual art and design assets","Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[2363,2364,2365,2368],{"name":2317,"slug":2318,"type":15},{"name":2241,"slug":2242,"type":15},{"name":2366,"slug":2367,"type":15},"Images","images",{"name":2369,"slug":2370,"type":15},"PDF","pdf","2026-07-13T06:39:58.803113",{"slug":2373,"name":2373,"fn":2374,"description":2375,"org":2376,"tags":2377,"stars":25,"repoUrl":26,"updatedAt":2394},"ci-cd-containerization-advisor","design CI\u002FCD pipelines for Kotlin applications","Design reproducible build, image, and deployment pipelines for Kotlin plus Spring applications, including CI verification, layered containers, rollout safety, and deployment-time migration coordination. Use when creating or improving Dockerfiles, CI workflows, image hardening, Kubernetes manifests, release gates, or deployment strategies for Spring Boot services, especially where build reproducibility and operational safety matter.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[2378,2381,2384,2387,2388,2391],{"name":2379,"slug":2380,"type":15},"CI\u002FCD","ci-cd",{"name":2382,"slug":2383,"type":15},"Containers","containers",{"name":2385,"slug":2386,"type":15},"Deployment","deployment",{"name":2190,"slug":2191,"type":15},{"name":2389,"slug":2390,"type":15},"Kotlin","kotlin",{"name":2392,"slug":2393,"type":15},"Spring","spring","2026-07-13T06:41:47.83899",{"slug":2396,"name":2396,"fn":2397,"description":2398,"org":2399,"tags":2400,"stars":25,"repoUrl":26,"updatedAt":2411},"cloudflare-deploy","deploy applications to Cloudflare","Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[2401,2404,2407,2410],{"name":2402,"slug":2403,"type":15},"Cloudflare","cloudflare",{"name":2405,"slug":2406,"type":15},"Cloudflare Pages","cloudflare-pages",{"name":2408,"slug":2409,"type":15},"Cloudflare Workers","cloudflare-workers",{"name":2385,"slug":2386,"type":15},"2026-07-17T06:04:42.853896",{"slug":2413,"name":2413,"fn":2414,"description":2415,"org":2416,"tags":2417,"stars":25,"repoUrl":26,"updatedAt":2425},"compose-ui-control","interact with Compose Desktop applications","Control a running Compose Desktop application via HTTP. Use when you need to interact with UI elements, click buttons, enter text, wait for elements to appear, or capture screenshots in a Compose Desktop app that has compose-ui-test-server enabled.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":9},[2418,2421,2424],{"name":2419,"slug":2420,"type":15},"Automation","automation",{"name":2422,"slug":2423,"type":15},"Desktop","desktop",{"name":2244,"slug":2245,"type":15},"2026-07-13T06:40:38.798626",128]