Response message for [PredictionService.GenerateContent].
candidates[]
object (Candidate
)
Output only. Generated candidates.
promptFeedback
object (PromptFeedback
)
Output only. Content filter results for a prompt sent in the request. Note: Sent only in the first stream chunk. Only happens when no candidates were generated due to content violations.
usageMetadata
object (UsageMetadata
)
Usage metadata about the response(s).
JSON representation |
---|
{ "candidates": [ { object ( |
Candidate
A response candidate generated from the model.
index
integer
Output only. Index of the candidate.
content
object (Content
)
Output only. Content parts of the candidate.
avgLogprobs
number
Output only. Average log probability score of the candidate.
finishReason
enum (FinishReason
)
Output only. The reason why the model stopped generating tokens. If empty, the model has not stopped generating the tokens.
safetyRatings[]
object (SafetyRating
)
Output only. List of ratings for the safety of a response candidate.
There is at most one rating per category.
citationMetadata
object (CitationMetadata
)
Output only. Source attribution of the generated content.
groundingMetadata
object (GroundingMetadata
)
Output only. metadata specifies sources used to ground generated content.
finishMessage
string
Output only. Describes the reason the mode stopped generating tokens in more detail. This is only filled when finishReason
is set.
JSON representation |
---|
{ "index": integer, "content": { object ( |
FinishReason
The reason why the model stopped generating tokens. If empty, the model has not stopped generating the tokens.
Enums | |
---|---|
FINISH_REASON_UNSPECIFIED |
The finish reason is unspecified. |
STOP |
token generation reached a natural stopping point or a configured stop sequence. |
MAX_TOKENS |
token generation reached the configured maximum output tokens. |
SAFETY |
token generation stopped because the content potentially contains safety violations. NOTE: When streaming, Candidate.content is empty if content filters blocks the output. |
RECITATION |
token generation stopped because the content potentially contains copyright violations. |
OTHER |
All other reasons that stopped the token generation. |
BLOCKLIST |
token generation stopped because the content contains forbidden terms. |
PROHIBITED_CONTENT |
token generation stopped for potentially containing prohibited content. |
SPII |
token generation stopped because the content potentially contains Sensitive Personally Identifiable Information (SPII). |
MALFORMED_FUNCTION_CALL |
The function call generated by the model is invalid. |
SafetyRating
Safety rating corresponding to the generated content.
category
enum (HarmCategory
)
Output only. Harm category.
probability
enum (HarmProbability
)
Output only. Harm probability levels in the content.
probabilityScore
number
Output only. Harm probability score.
severity
enum (HarmSeverity
)
Output only. Harm severity levels in the content.
severityScore
number
Output only. Harm severity score.
blocked
boolean
Output only. Indicates whether the content was filtered out because of this rating.
JSON representation |
---|
{ "category": enum ( |
HarmProbability
Harm probability levels in the content.
Enums | |
---|---|
HARM_PROBABILITY_UNSPECIFIED |
Harm probability unspecified. |
NEGLIGIBLE |
Negligible level of harm. |
LOW |
Low level of harm. |
MEDIUM |
Medium level of harm. |
HIGH |
High level of harm. |
HarmSeverity
Harm severity levels.
Enums | |
---|---|
HARM_SEVERITY_UNSPECIFIED |
Harm severity unspecified. |
HARM_SEVERITY_NEGLIGIBLE |
Negligible level of harm severity. |
HARM_SEVERITY_LOW |
Low level of harm severity. |
HARM_SEVERITY_MEDIUM |
Medium level of harm severity. |
HARM_SEVERITY_HIGH |
High level of harm severity. |
CitationMetadata
A collection of source attributions for a piece of content.
citations[]
object (Citation
)
Output only. List of citations.
JSON representation |
---|
{
"citations": [
{
object ( |
Citation
Source attributions for content.
startIndex
integer
Output only. Start index into the content.
endIndex
integer
Output only. End index into the content.
uri
string
Output only. url reference of the attribution.
title
string
Output only. title of the attribution.
license
string
Output only. License of the attribution.
publicationDate
object (Date
)
Output only. Publication date of the attribution.
JSON representation |
---|
{
"startIndex": integer,
"endIndex": integer,
"uri": string,
"title": string,
"license": string,
"publicationDate": {
object ( |
GroundingMetadata
metadata returned to client when grounding is enabled.
webSearchQueries[]
string
Optional. Web search queries for the following-up web search.
retrievalQueries[]
string
Optional. Queries executed by the retrieval tools.
groundingChunks[]
object (GroundingChunk
)
List of supporting references retrieved from specified grounding source.
groundingSupports[]
object (GroundingSupport
)
Optional. List of grounding support.
searchEntryPoint
object (SearchEntryPoint
)
Optional. Google search entry for the following-up web searches.
JSON representation |
---|
{ "webSearchQueries": [ string ], "retrievalQueries": [ string ], "groundingChunks": [ { object ( |
SearchEntryPoint
Google search entry point.
renderedContent
string
Optional. Web content snippet that can be embedded in a web page or an app webview.
sdkBlob
string (bytes format)
Optional. Base64 encoded JSON representing array of <search term, search url> tuple.
A base64-encoded string.
JSON representation |
---|
{ "renderedContent": string, "sdkBlob": string } |
GroundingChunk
Grounding chunk.
chunk_type
. Chunk type. chunk_type
can be only one of the following:
web
object (Web
)
Grounding chunk from the web.
retrievedContext
object (RetrievedContext
)
Grounding chunk from context retrieved by the retrieval tools.
JSON representation |
---|
{ // Union field |
Web
Chunk from the web.
uri
string
URI reference of the chunk.
title
string
title of the chunk.
JSON representation |
---|
{ "uri": string, "title": string } |
RetrievedContext
Chunk from context retrieved by the retrieval tools.
uri
string
URI reference of the attribution.
title
string
title of the attribution.
JSON representation |
---|
{ "uri": string, "title": string } |
GroundingSupport
Grounding support.
groundingChunkIndices[]
integer
A list of indices (into 'grounding_chunk') specifying the citations associated with the claim. For instance [1,3,4] means that grounding_chunk[1], grounding_chunk[3], grounding_chunk[4] are the retrieved content attributed to the claim.
confidenceScores[]
number
confidence score of the support references. Ranges from 0 to 1. 1 is the most confident. This list must have the same size as the groundingChunkIndices.
segment
object (Segment
)
Segment of the content this support belongs to.
JSON representation |
---|
{
"groundingChunkIndices": [
integer
],
"confidenceScores": [
number
],
"segment": {
object ( |
Segment
Segment of the content.
partIndex
integer
Output only. The index of a Part object within its parent Content object.
startIndex
integer
Output only. Start index in the given Part, measured in bytes. offset from the start of the Part, inclusive, starting at zero.
endIndex
integer
Output only. End index in the given Part, measured in bytes. offset from the start of the Part, exclusive, starting at zero.
text
string
Output only. The text corresponding to the segment from the response.
JSON representation |
---|
{ "partIndex": integer, "startIndex": integer, "endIndex": integer, "text": string } |
PromptFeedback
Content filter results for a prompt sent in the request.
blockReason
enum (BlockedReason
)
Output only. Blocked reason.
safetyRatings[]
object (SafetyRating
)
Output only. Safety ratings.
blockReasonMessage
string
Output only. A readable block reason message.
JSON representation |
---|
{ "blockReason": enum ( |
BlockedReason
Blocked reason enumeration.
Enums | |
---|---|
BLOCKED_REASON_UNSPECIFIED |
Unspecified blocked reason. |
SAFETY |
Candidates blocked due to safety. |
OTHER |
Candidates blocked due to other reason. |
BLOCKLIST |
Candidates blocked due to the terms which are included from the terminology blocklist. |
PROHIBITED_CONTENT |
Candidates blocked due to prohibited content. |
UsageMetadata
Usage metadata about response(s).
promptTokenCount
integer
Number of tokens in the request. When cachedContent
is set, this is still the total effective prompt size meaning this includes the number of tokens in the cached content.
candidatesTokenCount
integer
Number of tokens in the response(s).
totalTokenCount
integer
JSON representation |
---|
{ "promptTokenCount": integer, "candidatesTokenCount": integer, "totalTokenCount": integer } |