AI DevKit
Search Results for

    Show / Hide Table of Contents

    Class Assistant

    Renamed from AssistantObject to Assistant (2024.06.14)

    Inheritance
    object
    OpenAIModelBase
    Assistant
    Inherited Members
    OpenAIModelBase.Id
    OpenAIModelBase.Object
    OpenAIModelBase.Model
    OpenAIModelBase.CreatedAt
    OpenAIModelBase.Metadata
    OpenAIModelBase.Usage
    Namespace: Glitch9.AIDevKit.OpenAI
    Assembly: .dll
    Syntax
    public class Assistant : OpenAIModelBase

    Properties

    CodeInterpreterEnabled

    Declaration
    public bool CodeInterpreterEnabled { get; set; }
    Property Value
    Type Description
    bool

    Description

    The description of the AssistantObject. The maximum length is 512 characters.

    Declaration
    public string Description { get; set; }
    Property Value
    Type Description
    string

    FileSearchEnabled

    Declaration
    public bool FileSearchEnabled { get; set; }
    Property Value
    Type Description
    bool

    Instructions

    The System instructions that the AssistantObject uses. The maximum length is 32768 characters.

    Declaration
    public string Instructions { get; set; }
    Property Value
    Type Description
    string

    Name

    The name of the AssistantObject. The maximum length is 256 characters.

    Declaration
    public string Name { get; set; }
    Property Value
    Type Description
    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. Setting to { "type": "json_object" } enables JSON mode, which guarantees the message the model generates is valid JSON.

    Declaration
    public ResponseFormat ResponseFormat { get; set; }
    Property Value
    Type Description
    ResponseFormat
    Remarks

    Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.

    Temperature

    [Legacy] A list of file IDs attached to this AssistantObject. There can be a maximum of 20 files attached to the AssistantObject. Files are ordered by their creation date in ascending order.

    Declaration
    public float? Temperature { get; set; }
    Property Value
    Type Description
    float?

    ToolResources

    A set of resources that are used by the assistant's tools. The resources are specific to the type of tool. For example, the code_interpreter tool requires a list of file IDs, while the file_search tool requires a list of vector store IDs.

    Declaration
    public ToolResources ToolResources { get; set; }
    Property Value
    Type Description
    ToolResources

    Tools

    A list of Tool enabled on the AssistantObject. There can be a maximum of 128 tools per AssistantObject. Tools can be of types code_interpreter, retrieval, or Function.

    Declaration
    public List<ToolCall> Tools { get; set; }
    Property Value
    Type Description
    List<ToolCall>

    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.

    Declaration
    public float? TopP { get; set; }
    Property Value
    Type Description
    float?
    In this article
    Back to top Generated by DocFX