Firebase. AI. GroundingMetadata
Metadata returned to the client when grounding is enabled.
Summary
Important: 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).
Properties |
|
---|---|
GroundingChunks
|
IReadOnlyList< GroundingChunk >
A list of
GroundingChunk structs. |
GroundingSupports
|
IReadOnlyList< GroundingSupport >
A list of
GroundingSupport structs. |
SearchEntryPoint
|
Google Search entry point for web searches.
|
WebSearchQueries
|
IReadOnlyList< string >
A list of web search queries that the model performed to gather the grounding information.
|
Properties
GroundingChunks
IReadOnlyList< GroundingChunk > Firebase::AI::GroundingMetadata::GroundingChunks
A list of GroundingChunk
structs.
Each chunk represents a piece of retrieved content (e.g., from a web page) that the model used to ground its response.
GroundingSupports
IReadOnlyList< GroundingSupport > Firebase::AI::GroundingMetadata::GroundingSupports
A list of GroundingSupport
structs.
Each object details how specific segments of the model's response are supported by the groundingChunks
.
SearchEntryPoint
SearchEntryPoint Firebase::AI::GroundingMetadata::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
IReadOnlyList< string > Firebase::AI::GroundingMetadata::WebSearchQueries
A 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.