Struct AssistantObject

pub struct AssistantObject {
    pub id: String,
    pub created_at: u64,
    pub name: Option<String>,
    pub description: Option<String>,
    pub model: String,
    pub instructions: Option<String>,
    pub tools: Vec<AssistantObjectTool>,
    pub tool_resources: Option<AssistantObjectToolResources>,
    pub metadata: Option<Metadata>,
    pub temperature: Option<f64>,
    pub top_p: Option<f64>,
    pub response_format: Option<AssistantsApiResponseFormatOption>,
}

Represents an assistant that can call the model and use tools.

Fields

id: String

The identifier, which can be referenced in API endpoints.

created_at: u64

The Unix timestamp (in seconds) for when the assistant was created.

name: Option<String>

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

description: Option<String>

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

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.

instructions: Option<String>

The system instructions that the assistant uses. The maximum length is 256,000 characters.

tools: Vec<AssistantObjectTool>

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.

tool_resources: Option<AssistantObjectToolResources>

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.

metadata: Option<Metadata>

temperature: Option<f64>

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.

top_p: Option<f64>

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.

response_format: Option<AssistantsApiResponseFormatOption>

Implementations

impl AssistantObject

pub fn builder() -> AssistantObjectBuilder<((), (), (), (), (), (), (), (), (), (), (), ())>

Create a builder for building AssistantObject. On the builder, call .id(...), .created_at(...), .name(...)(optional), .description(...)(optional), .model(...), .instructions(...)(optional), .tools(...), .tool_resources(...)(optional), .metadata(...)(optional), .temperature(...)(optional), .top_p(...)(optional), .response_format(...)(optional) to set the values of the fields. Finally, call .build() to create the instance of AssistantObject.

Trait Implementations

impl Clone for AssistantObject

fn clone(&self) -> AssistantObject

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for AssistantObject

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for AssistantObject

fn deserialize<D>(deserializer: D) -> Result<Self, D::Error>

where D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for AssistantObject

fn eq(&self, other: &AssistantObject) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for AssistantObject

fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error>

where S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for AssistantObject