Struct MessageRequest 

pub struct MessageRequest {
    pub model: ClaudeModel,
    pub max_tokens: u32,
    pub messages: Vec<Message>,
    pub metadata: Option<MessageMetadata>,
    pub stop_sequences: Option<Vec<String>>,
    pub stream: bool,
    pub system: Option<System>,
    pub temperature: Option<f32>,
    pub top_k: Option<i8>,
    pub top_p: Option<i8>,
}

Fields

model: ClaudeModel

The model that will complete your prompt e.g. Claude 3.5 Sonnet

max_tokens: u32

The maximum number of tokens to generate before stopping.

Defaults to 1000 tokens.

Note that models may stop before reaching this maximum. This parameter only specifies the absolute maximum number of tokens to generate.

messages: Vec<Message>

Input messages.

metadata: Option<MessageMetadata>

An object describing metadata about the request.

stop_sequences: Option<Vec<String>>

Custom text sequences that will cause the model to stop generating.

stream: bool

Whether to incrementally stream the response using server-sent events.

system: Option<System>

System prompt.

A system prompt is a way of providing context and instructions to Claude, such as specifying a particular goal or role.

temperature: Option<f32>

Amount of randomness injected into the response.

Defaults to 1.0. Ranges from 0.0 to 1.0.

Use temperature closer to 0.0 for analytical / multiple choice, and closer to 1.0 for creative and generative tasks. Note that even with temperature of 0.0, the results will not be fully deterministic.

top_k: Option<i8>

Only sample from the top K options for each subsequent token.

Used to remove “long tail” low probability responses. Learn more technical details here.

top_p: Option<i8>

Use nucleus sampling.

In nucleus sampling, we compute the cumulative distribution over all the options for each subsequent token in decreasing probability order and cut it off once it reaches a particular probability specified by top_p. You should either alter temperature or top_p, but not both.

Implementations

impl MessageRequest

pub fn new( model: ClaudeModel, max_tokens: u32, messages: Vec<Message>, ) -> MessageRequest

pub fn with_metadata(self, metadata: MessageMetadata) -> MessageRequest

pub fn with_stop_sequences(self, stop_sequences: Vec<String>) -> MessageRequest

pub fn with_stream(self, stream: bool) -> MessageRequest

pub fn with_system(self, system: System) -> MessageRequest

pub fn with_temperature(self, temperature: f32) -> MessageRequest

pub fn with_top_k(self, top_k: i8) -> MessageRequest

pub fn with_top_p(self, top_p: i8) -> MessageRequest

Trait Implementations

impl Clone for MessageRequest

fn clone(&self) -> MessageRequest

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for MessageRequest

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

Formats the value using the given formatter.

impl Default for MessageRequest

fn default() -> MessageRequest

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for MessageRequest

fn deserialize<__D>( __deserializer: __D, ) -> Result<MessageRequest, <__D as Deserializer<'de>>::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for MessageRequest

fn serialize<__S>( &self, __serializer: __S, ) -> Result<<__S as Serializer>::Ok, <__S as Serializer>::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.