[[["易于理解","easyToUnderstand","thumb-up"],["解决了我的问题","solvedMyProblem","thumb-up"],["其他","otherUp","thumb-up"]],[["很难理解","hardToUnderstand","thumb-down"],["信息或示例代码不正确","incorrectInformationOrSampleCode","thumb-down"],["没有我需要的信息/示例","missingTheInformationSamplesINeed","thumb-down"],["翻译问题","translationIssue","thumb-down"],["其他","otherDown","thumb-down"]],["最后更新时间 (UTC):2024-11-25。"],[],[],null,["# Extensions overview\n\n| **Preview**\n|\n| Vertex AI Extensions is a Preview offering, subject to the\n| \"Pre-GA Offerings Terms\" of the\n| [Google Cloud Service Specific Terms](/terms/service-terms). Pre-GA products and features\n| may have limited support, and changes to pre-GA products and features may not be compatible with\n| other pre-GA versions. For more information, see the\n| [launch stage descriptions](/products#product-launch-stages). Further, by using\n| Vertex AI Extensions, you agree to the Generative AI Preview\n| [terms and conditions](/trustedtester/aitos) (\"Preview Terms\").\n\n\u003cbr /\u003e\n\nA Vertex AI\n[`extension`](/vertex-ai/docs/reference/rest/v1beta1/projects.locations.extensions) is a structured\nAPI wrapper that connects a model to an API for processing real-time data or\nperforming real-world actions.\n\nThe difference between Extensions and\n[Functions](/vertex-ai/generative-ai/docs/multimodal/function-calling)\nis in the execution of the *Tool* . Extensions are automatically executed by\nVertex AI. Whereas functions must be [manually executed by the user or\nclient](/vertex-ai/generative-ai/docs/multimodal/function-calling#invoke-api).\n\nTo streamline the extension creation process, we provide prebuilt\n*Extensions by Google* for common use cases, such as [code\ninterpretation](/vertex-ai/generative-ai/docs/extensions/code-interpreter) and\n[Vertex AI Search](/vertex-ai/generative-ai/docs/extensions/vertex-ai-search).\nIf your use case doesn't align with these templates, you can create your own\n[custom extension](/vertex-ai/generative-ai/docs/extensions/create-extension).\n\nUse-cases and benefits\n----------------------\n\nThe following are some possible extensions use cases:\n\n- Generate and run code.\n- Query websites and synthesize information.\n- Answer questions based on information within a collection of enterprise-specific data.\n- Query and analyze datastores.\n\nVertex AI extensions provide the following benefits:\n\n- **Enterprise controls** : [Identity and Access Management (IAM)](https://cloud.google.com/iam) permissions and security controls.\n- **Data security**: Contractual agreements that your private data won't be leaked or used in model training\n- **Performance agreements**: Contractual agreements that the platform delivers specific features and uptimes.\n- **Private extensions**: Authorized users in your organization or a trusted partner can use extensions to access sensitive internal data and actions, such as searching internal knowledge bases or completing HR actions.\n- **Google product integrations**: Integration with Google products like Vertex AI Search, BigQuery and specialized models.\n\nExtensions by Google\n--------------------\n\nGoogle provides the following prebuilt extensions:\n\n- [Code Interpreter](/vertex-ai/generative-ai/docs/extensions/code-interpreter)\n- [Vertex AI Search](/vertex-ai/generative-ai/docs/extensions/vertex-ai-search)\n\nWhat's next\n-----------\n\n- [Create, register, and run\n extensions](/vertex-ai/generative-ai/docs/extensions/create-extension).\n- [Register and use Google-provided extensions](/vertex-ai/generative-ai/docs/extensions/google-extensions)\n- [Use Reasoning Engine](/vertex-ai/generative-ai/docs/reasoning-engine/overview)."]]