Class RunCreateRequest

Namespace

OpenAI.ObjectModels.RequestModels

Assembly

AntRunnerLib.dll

public class RunCreateRequest : IOpenAiModels.IModel, IOpenAiModels.IMetaData, IOpenAiModels.ITemperature, IOpenAiModels.IAssistantId

Inheritance

System.Object

RunCreateRequest

Implements

IOpenAiModels.IModel

IOpenAiModels.IMetaData

IOpenAiModels.ITemperature

IOpenAiModels.IAssistantId

Inherited Members

System.Object.Equals(System.Object)

System.Object.Equals(System.Object, System.Object)

System.Object.GetHashCode()

System.Object.GetType()

System.Object.MemberwiseClone()

System.Object.ReferenceEquals(System.Object, System.Object)

System.Object.ToString()

Extension Methods

ModelExtension.ProcessModelId(IOpenAiModels.IModel, String, String, Boolean)

Properties

AdditionalInstructions

Appends additional instructions at the end of the instructions for the run. This is useful for modifying the behavior on a per-run basis without overriding other instructions.

[JsonPropertyName("additional_instructions")]
public string AdditionalInstructions { get; set; }

Property Value

System.String

AdditionalMessages

Adds additional messages to the thread before creating the run.

[JsonPropertyName("additional_messages")]
public List<MessageCreateRequest>? AdditionalMessages { get; set; }

Property Value

System.Nullable<List<MessageCreateRequest>>

AssistantId

The ID of the assistant to use to execute this run.

[JsonPropertyName("assistant_id")]
public string AssistantId { get; set; }

Property Value

System.String

Instructions

Override the default system message of the assistant. This is useful for modifying the behavior on a per-run basis.

[JsonPropertyName("instructions")]
public string Instructions { get; set; }

Property Value

System.String

MaxCompletionTokens

The maximum number of completion tokens that may be used over the course of the run. The run will make a best effort to use only the number of completion tokens specified, across multiple turns of the run. If the run exceeds the number of completion tokens specified, the run will end with status incomplete. See incomplete_details for more info.

[JsonPropertyName("max_completion_tokens")]
public int? MaxCompletionTokens { get; set; }

Property Value

System.Nullable<System.Int32>

MaxPromptTokens

The maximum number of prompt tokens that may be used over the course of the run. The run will make a best effort to use only the number of prompt tokens specified, across multiple turns of the run. If the run exceeds the number of prompt tokens specified, the run will end with status incomplete. See incomplete_details for more info.

[JsonPropertyName("max_prompt_tokens")]
public int? MaxPromptTokens { get; set; }

Property Value

System.Nullable<System.Int32>

Metadata

Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format. Keys can be a maximum of 64 characters long and values can be a maxium of 512 characters long.

[JsonPropertyName("metadata")]
public Dictionary<string, string>? Metadata { get; set; }

Property Value

System.Nullable<Dictionary<System.String, System.String>>

Model

The ID of the Model to be used to execute this run. If a value is provided here, it will override the model associated with the assistant. If not, the model associated with the assistant will be used.

[JsonPropertyName("model")]
public string Model { get; set; }

Property Value

System.String

ResponseFormat

Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.

[JsonPropertyName("response_format")]
public ResponseFormatOneOfType ResponseFormat { get; set; }

Property Value

ResponseFormatOneOfType

Stream

If true, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a data: [DONE] message.

[JsonPropertyName("stream")]
public bool? Stream { get; set; }

Property Value

System.Nullable<System.Boolean>

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.

[JsonPropertyName("temperature")]
public float? Temperature { get; set; }

Property Value

System.Nullable<System.Single>

ToolChoice

Controls which (if any) tool is called by the model.

[JsonPropertyName("tool_choice")]
public ToolChoiceOneOfType ToolChoice { get; set; }

Property Value

ToolChoiceOneOfType

Tools

Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis.

[JsonPropertyName("tools")]
public List<ToolDefinition>? Tools { get; set; }

Property Value

System.Nullable<List<ToolDefinition>>

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 temperature but not both.

[JsonPropertyName("top_p")]
public float? TopP { get; set; }

Property Value

System.Nullable<System.Single>

TruncationStrategy

Controls how a thread will be truncated prior to the run. Use this to control the initial context window of the run.

[JsonPropertyName("truncation_strategy")]
public TruncationStrategy TruncationStrategy { get; set; }

Property Value

TruncationStrategy