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: i32
The Unix timestamp (in seconds) for when the assistant was created.
description: String
The description of the assistant. The maximum length is 512 characters.
id: String
The identifier, which can be referenced in API endpoints.
instructions: String
The system instructions that the assistant uses. The maximum length is 256,000 characters.
metadata: Metadata
§model: String
ID 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: String
The name of the assistant. The maximum length is 256 characters.
object: String
The 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.