OptimizationOptions Class
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.
Tuning knobs and run-mode for an optimization job.
public class OptimizationOptions : System.ClientModel.Primitives.IJsonModel<Azure.AI.Projects.Agents.OptimizationOptions>, System.ClientModel.Primitives.IPersistableModel<Azure.AI.Projects.Agents.OptimizationOptions>type OptimizationOptions = class
interface IJsonModel<OptimizationOptions>
interface IPersistableModel<OptimizationOptions>Public Class OptimizationOptions
Implements IJsonModel(Of OptimizationOptions), IPersistableModel(Of OptimizationOptions)- Inheritance
-
OptimizationOptions
- Implements
Constructors
| Name | Description |
|---|---|
| OptimizationOptions() |
Initializes a new instance of OptimizationOptions. |
Properties
| Name | Description |
|---|---|
| EvalModel |
Model deployment used for evaluation. Defaults to server config (typically 'gpt-4o'). |
| EvaluationLevel |
Evaluation granularity. Null/omitted means per-item single-turn. Set to 'conversation' for per-conversation multi-turn simulation scoring. |
| MaxIterations |
Maximum optimization iterations per strategy. Must be >= 1. Default: 5. |
| OptimizationConfig |
Per-target-attribute configuration overrides. Contains skills, tools, system_prompt for the agent, plus model space for model optimization. To assign an object to the value of this property use FromObjectAsJson<T>(T, JsonSerializerOptions). To assign an already formatted json string to this property use FromString(String). Examples:
|
| OptimizationModel |
Model deployment for optimization reasoning (must be gpt-5 family). Falls back to the default eval model when not set. |
