GroundingMetadata
class GroundingMetadata
Metadata returned to the client when grounding is enabled.
If using Grounding with Google Search, you are required to comply with the "Grounding with Google Search" usage requirements for your chosen API provider: Gemini Developer API or Vertex AI Gemini API (see Service Terms section within the Service Specific Terms).
Summary
Public constructors |
|---|
GroundingMetadata( |
Public properties |
|
|---|---|
List<GroundingAttribution> |
This property is deprecated. Use groundingChunks instead |
List<GroundingChunk> |
The list of |
List<GroundingSupport> |
The list of |
List<String> |
|
SearchEntryPoint? |
Google Search entry point for web searches. |
List<String> |
The list of web search queries that the model performed to gather the grounding information. |
Public constructors
GroundingMetadata
GroundingMetadata(
webSearchQueries: List<String>,
searchEntryPoint: SearchEntryPoint?,
retrievalQueries: List<String>,
groundingAttribution: List<GroundingAttribution>,
groundingChunks: List<GroundingChunk>,
groundingSupports: List<GroundingSupport>
)
Public properties
groundingChunks
val groundingChunks: List<GroundingChunk>
The list of GroundingChunk classes. Each chunk represents a piece of retrieved content that the model used to ground its response.
groundingSupports
val groundingSupports: List<GroundingSupport>
The list of GroundingSupport objects. Each object details how specific segments of the model's response are supported by the groundingChunks.
searchEntryPoint
val searchEntryPoint: SearchEntryPoint?
Google Search entry point for web searches. This contains an HTML/CSS snippet that must be embedded in an app to display a Google Search Entry point for follow-up web searches related to the model's "Grounded Response".
webSearchQueries
val webSearchQueries: List<String>
The list of web search queries that the model performed to gather the grounding information. These can be used to allow users to explore the search results themselves.