pub struct AssistantObject {Show 13 fields
pub created_at: i32,
pub description: String,
pub id: String,
pub instructions: String,
pub metadata: Metadata,
pub model: String,
pub name: String,
pub object: String,
pub response_format: Option<AssistantsApiResponseFormatOption>,
pub temperature: Option<f32>,
pub tool_resources: Option<AssistantObjectToolResources>,
pub tools: Vec<Value>,
pub top_p: Option<f32>,
}Fields§
§created_at: i32The Unix timestamp (in seconds) for when the assistant was created.
description: StringThe description of the assistant. The maximum length is 512 characters.
id: StringThe identifier, which can be referenced in API endpoints.
instructions: StringThe system instructions that the assistant uses. The maximum length is 256,000 characters.
metadata: Metadata§model: StringID of the model to use. You can use the List models API to see all of your available models, or see our Model overview for descriptions of them.
name: StringThe name of the assistant. The maximum length is 256 characters.
object: StringThe object type, which is always assistant.
response_format: Option<AssistantsApiResponseFormatOption>§temperature: Option<f32>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.
tool_resources: Option<AssistantObjectToolResources>§tools: Vec<Value>A list of tool enabled on the assistant. There can be a maximum of 128 tools per assistant. Tools can be of types code_interpreter, file_search, or function.
top_p: Option<f32>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.