Full name: projects.locations.corroborateContent
Given an input text, it returns a score that evaluates the factuality of the text. It also extracts and returns claims from the text and provides supporting facts.
Endpoint
posthttps://{service-endpoint}/v1/{parent}:corroborateContent
Where {service-endpoint} is one of the supported service endpoints.
Path parameters
parentstring
Required. The resource name of the Location from which to corroborate text. The users must have permission to make a call in the project. Format: projects/{project}/locations/{location}.
Request body
The request body contains data with the following structure:
Optional. Facts used to generate the text can also be used to corroborate the text.
Optional. Parameters that can be set to override default settings per request.
Optional. Input content to corroborate, only text format is supported for now.
Response body
Response message for locations.corroborateContent.
If successful, the response body contains data with the following structure:
Claims that are extracted from the input content and facts that support the claims.
corroborationScorenumber
confidence score of corroborating content. value is [0,1] with 1 is the most confidence.
| JSON representation |
|---|
{
"claims": [
{
object ( |
Parameters
Parameters that can be overrided per request.
citationThresholdnumber
Optional. Only return claims with citation score larger than the threshold.
| JSON representation |
|---|
{ "citationThreshold": number } |
Claim
Claim that is extracted from the input text and facts that support it.
factIndexes[]integer
Indexes of the facts supporting this claim.
startIndexinteger
Index in the input text where the claim starts (inclusive).
endIndexinteger
Index in the input text where the claim ends (exclusive).
scorenumber
confidence score of this corroboration.
| JSON representation |
|---|
{ "factIndexes": [ integer ], "startIndex": integer, "endIndex": integer, "score": number } |