ProjectsAgentsModelFactory.AgentOptimizationCandidateEvaluation Method
Definition
Important
Some information relates to prerelease product that may be substantially modified before it’s released. Microsoft makes no warranties, express or implied, with respect to the information provided here.
Comparative evaluation summary for a candidate.
public static Azure.AI.Projects.Agents.AgentOptimizationCandidateEvaluation AgentOptimizationCandidateEvaluation(double? score = default, double? avgTokens = default, TimeSpan? avgLatencyMs = default, string evalId = default, string evalRunId = default, DateTimeOffset? completedOn = default);
static member AgentOptimizationCandidateEvaluation : Nullable<double> * Nullable<double> * Nullable<TimeSpan> * string * string * Nullable<DateTimeOffset> -> Azure.AI.Projects.Agents.AgentOptimizationCandidateEvaluation
Public Shared Function AgentOptimizationCandidateEvaluation (Optional score As Nullable(Of Double) = Nothing, Optional avgTokens As Nullable(Of Double) = Nothing, Optional avgLatencyMs As Nullable(Of TimeSpan) = Nothing, Optional evalId As String = Nothing, Optional evalRunId As String = Nothing, Optional completedOn As Nullable(Of DateTimeOffset) = Nothing) As AgentOptimizationCandidateEvaluation
Parameters
Average composite score across evaluated tasks. Omitted until scoring produces an aggregate score.
Average total tokens consumed per task. Omitted when token usage was not measured.
- evalId
- String
Foundry evaluation identifier used to score this candidate. Omitted when unavailable.
- evalRunId
- String
Foundry evaluation run identifier used to score this candidate. Omitted when unavailable.
- completedOn
- Nullable<DateTimeOffset>
Timestamp when full candidate evaluation completed, represented in Unix time. Omitted when unavailable.
Returns
A new AgentOptimizationCandidateEvaluation instance for mocking.