Grounding overview

In the context of generative AI, grounding refers to the ability to connect model output to verifiable sources of information. By providing models with access to specific data sources, grounding tethers their output to specific data and reduces the chances of inventing content. This is particularly important in situations where accuracy and reliability are significant, for instance with financial reporting and health reporting.

Grounding in Vertex AI Search and Conversation lets you use language models (text-bison, chat-bison) to generate content grounded in your own data corpus. This capability lets the model access information that goes beyond its training data. By linking to designated data stores within Vertex AI Search, the grounded model can produce more accurate and relevant responses.

Grounding provides the following benefits:

  • Reduces model hallucinations, instances where the model generates content that isn't factual.
  • Anchors model responses to specific information.
  • Enhances the trustworthiness and applicability of the generated content.

To get started grounding a model from Vertex AI Search and Conversation, see Grounding in Vertex AI Search and Conversation.

What's next