Grounding overview
To see an example of grounding, run the "Intro to grounding" notebook in one of the following environments:
Open in Colab |Open in Colab Enterprise |Openin Vertex AI Workbench |View on GitHub
Open in Colab
Open in Colab Enterprise
Openin Vertex AI Workbench
View on GitHubIn generative AI, grounding is the ability to connect model output to verifiablesources of information. If you provide models with access to specific datasources, then grounding tethers their output to these data and reduces thechances of inventing content. This is particularly important in situations whereaccuracy and reliability are significant.
Grounding provides the following benefits:
- Reduces model hallucinations, which are instances where the model generatescontent that isn't factual.
- Anchors model responses to your data sources.
- Provides auditability byproviding grounding support, which are links to sources.
You can ground supported-model output in Vertex AI in the following ways:
| Grounding type | Description |
|---|---|
| Grounding with Google Search | Connect your model to world knowledge and a wide possible range of topics using results from Google's search engine. |
| Grounding with Google Maps | Use Google Maps data with your model to provide more accurate and context-aware responses to your prompts, including geospatial context. |
| Grounding with Vertex AI Search | Use retrieval-augmented generation (RAG) to connect your model to your website data or your sets of documents stored in Vertex AI Search. |
| Grounding with Vertex AI RAG Engine | Ground using your data through Vertex AI RAG Engine, which is a configurable managed RAG service. |
| Grounding with Elasticsearch | Use retrieval-augmented generation with your existing Elasticsearch indexes and Gemini. |
| Grounding with your search API | Connect Gemini to your external data sources by grounding with any search API. |
| Web Grounding for Enterprise | Use a web index suitable for highly-regulated industries to generate grounded responses with compliance controls. |
| Grounding with Parallel web search | Connect Gemini to an LLM-optimized web index to use the most recent information from the web. |
For language support, seeSupported languages for prompts.
What's next
- To learn more about responsible AI best practices and Vertex AI'ssafety filters, seeResponsible AI.
Except as otherwise noted, the content of this page is licensed under theCreative Commons Attribution 4.0 License, and code samples are licensed under theApache 2.0 License. For details, see theGoogle Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2026-02-19 UTC.