Starting April 29, 2025, Gemini 1.5 Pro and Gemini 1.5 Flash models are not available in projects that have no prior usage of these models, including new projects. For details, seeModel versions and lifecycle.
Stay organized with collectionsSave and categorize content based on your preferences.
Preview
Vertex AI Extensions is a Preview offering, subject to the
"Pre-GA Offerings Terms" of theGoogle Cloud Service Specific Terms. Pre-GA products and features
may have limited support, and changes to pre-GA products and features may not be compatible with
other pre-GA versions. For more information, see thelaunch stage descriptions. Further, by using
Vertex AI Extensions, you agree to the Generative AI Previewterms and conditions("Preview Terms").
A Vertex AIextensionis a structured
API wrapper that connects a model to an API for processing real-time data or
performing real-world actions.
The difference between Extensions andFunctionsis in the execution of theTool. Extensions are automatically executed by
Vertex AI. Whereas functions must bemanually executed by the user or
client.
To streamline the extension creation process, we provide prebuiltExtensions by Googlefor common use cases, such ascode
interpretationandVertex AI Search.
If your use case doesn't align with these templates, you can create your owncustom extension.
Use-cases and benefits
The following are some possible extensions use cases:
Generate and run code.
Query websites and synthesize information.
Answer questions based on information within a collection of
enterprise-specific data.
Query and analyze datastores.
Vertex AI extensions provide the following benefits:
Data security: Contractual agreements that your private data won't be
leaked or used in model training
Performance agreements: Contractual agreements that the platform
delivers specific features and uptimes.
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.
Google product integrations: Integration with Google products like
Vertex AI Search, BigQuery and specialized models.
Extensions by Google
Google provides the following prebuilt extensions:
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-09-04 UTC."],[],[],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)."]]
