DataStoreConnectionSignals

Data store connection feature output signals. Might be only partially field if processing stop before the final answer. Reasons for this can be, but are not limited to: empty UCS search results, positive RAI check outcome, grounding failure, ...

JSON representation
{
  "rewriterModelCallSignals": {
    object (RewriterModelCallSignals)
  },
  "rewrittenQuery": string,
  "searchSnippets": [
    {
      object (SearchSnippet)
    }
  ],
  "answerGenerationModelCallSignals": {
    object (AnswerGenerationModelCallSignals)
  },
  "answer": string,
  "answerParts": [
    {
      object (AnswerPart)
    }
  ],
  "citedSnippets": [
    {
      object (CitedSnippet)
    }
  ],
  "groundingSignals": {
    object (GroundingSignals)
  },
  "safetySignals": {
    object (SafetySignals)
  }
}
Fields
rewriterModelCallSignals

object (RewriterModelCallSignals)

Optional. Diagnostic info related to the rewriter model call.

rewrittenQuery

string

Optional. Rewritten string query used for search.

searchSnippets[]

object (SearchSnippet)

Optional. Search snippets included in the answer generation prompt.

answerGenerationModelCallSignals

object (AnswerGenerationModelCallSignals)

Optional. Diagnostic info related to the answer generation model call.

answer

string

Optional. The final compiled answer.

answerParts[]

object (AnswerPart)

Optional. Answer parts with relevant citations. Concatenation of texts should add up the answer (not counting whitespaces).

citedSnippets[]

object (CitedSnippet)

Optional. Snippets cited by the answer generation model from the most to least relevant.

groundingSignals

object (GroundingSignals)

Optional. Grounding signals.

safetySignals

object (SafetySignals)

Optional. Safety check result.

RewriterModelCallSignals

Diagnostic info related to the rewriter model call.

JSON representation
{
  "renderedPrompt": string,
  "modelOutput": string,
  "model": string
}
Fields
renderedPrompt

string

Prompt as sent to the model.

modelOutput

string

Output of the generative model.

model

string

Name of the generative model. For example, "gemini-ultra", "gemini-pro", "gemini-1.5-flash" etc. Defaults to "Other" if the model is unknown.

SearchSnippet

Search snippet details.

JSON representation
{
  "documentTitle": string,
  "documentUri": string,
  "text": string
}
Fields
documentTitle

string

Title of the enclosing document.

documentUri

string

Uri for the document. Present if specified for the document.

text

string

Text included in the prompt.

AnswerGenerationModelCallSignals

Diagnostic info related to the answer generation model call.

JSON representation
{
  "renderedPrompt": string,
  "modelOutput": string,
  "model": string
}
Fields
renderedPrompt

string

Prompt as sent to the model.

modelOutput

string

Output of the generative model.

model

string

Name of the generative model. For example, "gemini-ultra", "gemini-pro", "gemini-1.5-flash" etc. Defaults to "Other" if the model is unknown.

AnswerPart

Answer part with citation.

JSON representation
{
  "text": string,
  "supportingIndices": [
    integer
  ]
}
Fields
text

string

Substring of the answer.

supportingIndices[]

integer

Citations for this answer part. Indices of searchSnippets.

CitedSnippet

Snippet cited by the answer generation model.

JSON representation
{
  "searchSnippet": {
    object (SearchSnippet)
  },
  "snippetIndex": integer
}
Fields
searchSnippet

object (SearchSnippet)

Details of the snippet.

snippetIndex

integer

Index of the snippet in searchSnippets field.

GroundingSignals

Grounding signals.

JSON representation
{
  "decision": enum (GroundingDecision),
  "score": enum (GroundingScoreBucket)
}
Fields
decision

enum (GroundingDecision)

Represents the decision of the grounding check.

score

enum (GroundingScoreBucket)

Grounding score bucket setting.

GroundingDecision

Represents the decision of the grounding check.

Enums
GROUNDING_DECISION_UNSPECIFIED Decision not specified.
ACCEPTED_BY_GROUNDING Grounding have accepted the answer.
REJECTED_BY_GROUNDING Grounding have rejected the answer.

GroundingScoreBucket

Grounding score buckets.

Enums
GROUNDING_SCORE_BUCKET_UNSPECIFIED Score not specified.
VERY_LOW We have very low confidence that the answer is grounded.
LOW We have low confidence that the answer is grounded.
MEDIUM We have medium confidence that the answer is grounded.
HIGH We have high confidence that the answer is grounded.
VERY_HIGH We have very high confidence that the answer is grounded.

SafetySignals

Safety check results.

JSON representation
{
  "decision": enum (SafetyDecision),
  "bannedPhraseMatch": enum (BannedPhraseMatch),
  "matchedBannedPhrase": string
}
Fields
decision

enum (SafetyDecision)

Safety decision.

bannedPhraseMatch

enum (BannedPhraseMatch)

Specifies banned phrase match subject.

matchedBannedPhrase

string

The matched banned phrase if there was a match.

SafetyDecision

Safety decision. All kinds of check are incorporated into this final decision, including banned phrases check.

Enums
SAFETY_DECISION_UNSPECIFIED Decision not specified.
ACCEPTED_BY_SAFETY_CHECK No manual or automatic safety check fired.
REJECTED_BY_SAFETY_CHECK One ore more safety checks fired.

BannedPhraseMatch

Specifies banned phrase match subject.

Enums
BANNED_PHRASE_MATCH_UNSPECIFIED No banned phrase check was executed.
BANNED_PHRASE_MATCH_NONE All banned phrase checks led to no match.
BANNED_PHRASE_MATCH_QUERY A banned phrase matched the query.
BANNED_PHRASE_MATCH_RESPONSE A banned phrase matched the response.