Class AssistantRequest

Namespace

Glitch9.AIDevKit.OpenAI

Give Assistants access to OpenAI-hosted tools like Issue Interpreter and Knowledge Retrieval, or build your own tools using Function calling. Usage of OpenAI-hosted tools comes at an additional fee — visit our help center article to learn more about how these tools are priced.

public class AssistantRequest : ModelRequest

Inheritance

object

RequestBody

ModelRequest

AssistantRequest

Inherited Members

ModelRequest.Model

ModelRequest.N

ModelRequest.Metadata

ModelRequest.User

Remarks

https://platform.openai.com/docs/Assistants/tools

Properties

Description

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

public string Description { get; set; }

Property Value

string

Instructions

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

public string Instructions { get; set; }

Property Value

string

Name

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

public string Name { get; set; }

Property Value

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.

public ResponseFormat ResponseFormat { get; set; }

Property Value

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

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 top_p but not both.

public float? Temperature { get; set; }

Property Value

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.

public ToolResources ToolResources { get; set; }

Property Value

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.

public List<ToolCall> Tools { get; set; }

Property Value

List<ToolCall>

Remarks

Default: []

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.

public float? TopP { get; set; }

Property Value

float?