PromptAgentDefinition 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.
The prompt agent definition.
public class PromptAgentDefinition : Azure.AI.Projects.OpenAI.AgentDefinition, System.ClientModel.Primitives.IJsonModel<Azure.AI.Projects.OpenAI.PromptAgentDefinition>, System.ClientModel.Primitives.IPersistableModel<Azure.AI.Projects.OpenAI.PromptAgentDefinition>type PromptAgentDefinition = class
inherit AgentDefinition
interface IJsonModel<PromptAgentDefinition>
interface IPersistableModel<PromptAgentDefinition>Public Class PromptAgentDefinition
Inherits AgentDefinition
Implements IJsonModel(Of PromptAgentDefinition), IPersistableModel(Of PromptAgentDefinition)- Inheritance
- Implements
Constructors
| Name | Description |
|---|---|
| PromptAgentDefinition(String) |
Initializes a new instance of PromptAgentDefinition. |
Properties
| Name | Description |
|---|---|
| ContentFilterConfiguration |
Configuration for Responsible AI (RAI) content filtering and safety features. (Inherited from AgentDefinition) |
| Instructions |
A system (or developer) message inserted into the model's context. |
| Model |
The model deployment to use for this agent. |
| ReasoningOptions | |
| StructuredInputs |
Set of structured inputs that can participate in prompt template substitution or tool argument bindings. |
| Temperature |
What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.
We generally recommend altering this or |
| TextOptions | |
| Tools |
An array of tools the model may call while generating a response. You
can specify which tool to use by setting the |
| TopP |
An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or |
