- JSON representation
- AggregatedMetrics.MetricsByAppVersion
- AggregatedMetrics.ToolMetrics
- AggregatedMetrics.SemanticSimilarityMetrics
- AggregatedMetrics.HallucinationMetrics
- AggregatedMetrics.ToolCallLatencyMetrics
- AggregatedMetrics.TurnLatencyMetrics
- AggregatedMetrics.MetricsByTurn
Aggregated metrics for an evaluation or evaluation dataset.
| JSON representation |
|---|
{
"metricsByAppVersion": [
{
object ( |
| Fields | |
|---|---|
metricsByAppVersion[] |
Output only. Aggregated metrics, grouped by app version ID. |
AggregatedMetrics.MetricsByAppVersion
Metrics aggregated per app version.
| JSON representation |
|---|
{ "appVersionId": string, "toolMetrics": [ { object ( |
| Fields | |
|---|---|
appVersionId |
Output only. The app version ID. |
toolMetrics[] |
Output only. Metrics for each tool within this app version. |
semanticSimilarityMetrics[] |
Output only. Metrics for semantic similarity within this app version. |
hallucinationMetrics[] |
Output only. Metrics for hallucination within this app version. |
toolCallLatencyMetrics[] |
Output only. Metrics for tool call latency within this app version. |
turnLatencyMetrics[] |
Output only. Metrics for turn latency within this app version. |
passCount |
Output only. The number of times the evaluation passed. |
failCount |
Output only. The number of times the evaluation failed. |
metricsByTurn[] |
Output only. Metrics aggregated per turn within this app version. |
AggregatedMetrics.ToolMetrics
Metrics for a single tool.
| JSON representation |
|---|
{ "tool": string, "passCount": integer, "failCount": integer } |
| Fields | |
|---|---|
tool |
Output only. The name of the tool. |
passCount |
Output only. The number of times the tool passed. |
failCount |
Output only. The number of times the tool failed. |
AggregatedMetrics.SemanticSimilarityMetrics
Metrics for semantic similarity results.
| JSON representation |
|---|
{ "score": number } |
| Fields | |
|---|---|
score |
Output only. The average semantic similarity score (0-4). |
AggregatedMetrics.HallucinationMetrics
Metrics for hallucination results.
| JSON representation |
|---|
{ "score": number } |
| Fields | |
|---|---|
score |
Output only. The average hallucination score (0 to 1). |
AggregatedMetrics.ToolCallLatencyMetrics
Metrics for tool call latency.
| JSON representation |
|---|
{ "tool": string, "averageLatency": string } |
| Fields | |
|---|---|
tool |
Output only. The name of the tool. |
averageLatency |
Output only. The average latency of the tool calls. A duration in seconds with up to nine fractional digits, ending with ' |
AggregatedMetrics.TurnLatencyMetrics
Metrics for turn latency.
| JSON representation |
|---|
{ "averageLatency": string } |
| Fields | |
|---|---|
averageLatency |
Output only. The average latency of the turns. A duration in seconds with up to nine fractional digits, ending with ' |
AggregatedMetrics.MetricsByTurn
Metrics aggregated per turn.
| JSON representation |
|---|
{ "turnIndex": integer, "toolMetrics": [ { object ( |
| Fields | |
|---|---|
turnIndex |
Output only. The turn index (0-based). |
toolMetrics[] |
Output only. Metrics for each tool within this turn. |
semanticSimilarityMetrics[] |
Output only. Metrics for semantic similarity within this turn. |
hallucinationMetrics[] |
Output only. Metrics for hallucination within this turn. |
toolCallLatencyMetrics[] |
Output only. Metrics for tool call latency within this turn. |
turnLatencyMetrics[] |
Output only. Metrics for turn latency within this turn. |