Citation information for model-generated content.
startIndexinteger
Start of segment of the response that is attributed to this source.
Index indicates the start of the segment, measured in bytes.
endIndexinteger
End of the attributed segment, exclusive.
typeUnion type
type can be only one of the following:NOTE: We use these instead of the Citation message for historical reasons. A URL citation annotation.
A file citation annotation.
A place citation annotation.
word-level ASR annotation with timing and speaker info.
| JSON representation |
|---|
{ "startIndex": integer, "endIndex": integer, // type "urlCitation": { object ( |
UrlCitation
A URL citation annotation.
urlstring
The URL.
titlestring
The title of the URL.
| JSON representation |
|---|
{ "url": string, "title": string } |
FileCitation
A file citation annotation.
documentUristring
The URI of the file.
fileNamestring
The name of the file.
sourcestring
Source attributed for a portion of the text.
user provided metadata about the retrieved context.
pageNumberinteger
Page number of the cited document, if applicable.
mediaIdstring
Media id in-case of image citations, if applicable.
| JSON representation |
|---|
{
"documentUri": string,
"fileName": string,
"source": string,
"customMetadata": {
object ( |
PlaceCitation
A place citation annotation.
placeIdstring
The id of the place, in places/{placeId} format.
namestring
title of the place.
urlstring
URI reference of the place.
Snippets of reviews that are used to generate answers about the features of a given place in Google Maps.
| JSON representation |
|---|
{
"placeId": string,
"name": string,
"url": string,
"reviewSnippets": [
{
object ( |
WordInfo
word-level ASR annotation for transcription output. Carries the word text, optional timing, and optional speaker attribution.
textstring
The transcribed word.
Start offset in time of the word relative to the start of the audio. Present when timestampGranularities contains "word".
A duration in seconds with up to nine fractional digits, ending with 's'. Example: "3.5s".
End offset in time of the word relative to the start of the audio. Present when timestampGranularities contains "word".
A duration in seconds with up to nine fractional digits, ending with 's'. Example: "3.5s".
speakerstring
Optional. Speaker label for this word (e.g. "spk_1", "spk_2"). Present when diarizationMode is set in TranscriptionConfig.
| JSON representation |
|---|
{ "text": string, "startOffset": string, "endOffset": string, "speaker": string } |