Class Run

Represents an execution run on a Thread.

Renamed from RunObject to Run (2024.06.14)

Inheritance
object
OpenAIObject
RunBase
Run
Inherited Members
Namespace: Glitch9.AIDevKit.OpenAI
Assembly: Glitch9.AIDevKit.Provider.OpenAI.dll
Syntax
public class Run : RunBase

Properties

| Edit this page View Source

IncompleteDetails

Details on why the run is incomplete. Will be null if the run is not incomplete.

Declaration
[JsonProperty("incomplete_details")]
public IncompleteDetails IncompleteDetails { get; set; }
Property Value
Type Description
IncompleteDetails
| Edit this page View Source

Instructions

The instructions that the AssistantObject used for this run.

Declaration
[JsonProperty("instructions")]
public string Instructions { get; set; }
Property Value
Type Description
string
| Edit this page View Source

MaxCompletionTokens

The maximum number of completion tokens specified to have been used over the course of the run.

Declaration
[JsonProperty("max_completion_tokens")]
public int? MaxCompletionTokens { get; set; }
Property Value
Type Description
int?
| Edit this page View Source

MaxPromptTokens

The maximum number of prompt tokens specified to have been used over the course of the run.

Declaration
[JsonProperty("max_prompt_tokens")]
public int? MaxPromptTokens { get; set; }
Property Value
Type Description
int?
| Edit this page View Source

Model

ID of the model.

Declaration
[JsonProperty("model")]
public string Model { get; set; }
Property Value
Type Description
string
| Edit this page View Source

RequiredAction

Details on the action required to continue the run. Will be null if no action is required.

Declaration
[JsonProperty("required_action")]
public RequiredAction RequiredAction { get; set; }
Property Value
Type Description
RequiredAction
| Edit this page View Source

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. Setting to { "type": "json_object" } enables JSON mode, which guarantees the message the model generates is valid JSON.

Declaration
[JsonProperty("response_format")]
public ResponseFormat ResponseFormat { get; set; }
Property Value
Type Description
ResponseFormat
| Edit this page View Source

Temperature

The sampling temperature used for this run. If not set, defaults to 1.

Declaration
[JsonProperty("temperature")]
public float? Temperature { get; set; }
Property Value
Type Description
float?
| Edit this page View Source

ToolChoice

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

  • none: the model will not call any tools and instead generates a message.
  • auto: the model can pick between generating a message or calling one or more tools.
  • required: the model must call one or more tools before responding to the user. Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.
Declaration
[JsonProperty("tool_choice")]
public StringOr<ToolChoice> ToolChoice { get; set; }
Property Value
Type Description
StringOr<ToolChoice>
| Edit this page View Source

Tools

The list of tools that the AssistantObject used for this run.

Declaration
[JsonProperty("tools")]
public ToolCall[] Tools { get; set; }
Property Value
Type Description
ToolCall[]
| Edit this page View Source

TopP

The nucleus sampling value used for this run. If not set, defaults to 1.

Declaration
[JsonProperty("top_p")]
public float? TopP { get; set; }
Property Value
Type Description
float?
| Edit this page View Source

TruncationStrategy

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

Declaration
[JsonProperty("truncation_strategy")]
public TruncationStrategy TruncationStrategy { get; set; }
Property Value
Type Description
TruncationStrategy

Extension Methods