Struct LanguageModelInput 

pub struct LanguageModelInput {

    pub system_prompt: Option<String>,
    pub messages: Vec<Message>,
    pub tools: Option<Vec<Tool>>,
    pub tool_choice: Option<ToolChoiceOption>,
    pub response_format: Option<ResponseFormatOption>,
    pub max_tokens: Option<u32>,
    pub temperature: Option<f64>,
    pub top_p: Option<f64>,
    pub top_k: Option<i32>,
    pub presence_penalty: Option<f64>,
    pub frequency_penalty: Option<f64>,
    pub seed: Option<i64>,
    pub modalities: Option<Vec<Modality>>,
    pub metadata: Option<HashMap<String, String>>,
    pub audio: Option<AudioOptions>,
    pub reasoning: Option<ReasoningOptions>,
    pub extra: Option<LanguageModelInputExtra>,
}

Defines the input parameters for the language model completion.

Fields

system_prompt: Option<String>

A system prompt is a way of providing context and instructions to the model

messages: Vec<Message>

A list of messages comprising the conversation so far.

tools: Option<Vec<Tool>>

Definitions of tools that the model may use.

tool_choice: Option<ToolChoiceOption>

response_format: Option<ResponseFormatOption>

max_tokens: Option<u32>

The maximum number of tokens that can be generated in the chat completion.

temperature: Option<f64>

Amount of randomness injected into the response. Ranges from 0.0 to 1.0

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. Ranges from 0.0 to 1.0

top_k: Option<i32>

Only sample from the top K options for each subsequent token. Used to remove ‘long tail’ low probability responses. Must be a non-negative integer.

presence_penalty: Option<f64>

Positive values penalize new tokens based on whether they appear in the text so far, increasing the model’s likelihood to talk about new topics.

frequency_penalty: Option<f64>

Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model’s likelihood to repeat the same line verbatim.

seed: Option<i64>

The seed (integer), if set and supported by the model, to enable deterministic results.

modalities: Option<Vec<Modality>>

The modalities that the model should support.

metadata: Option<HashMap<String, String>>

A set of key/value pairs that store additional information about the request. This is forwarded to the model provider if supported.

audio: Option<AudioOptions>

Options for audio generation.

reasoning: Option<ReasoningOptions>

Options for reasoning generation.

extra: Option<LanguageModelInputExtra>

Extra options that the model may support.

Trait Implementations

impl Clone for LanguageModelInput

fn clone(&self) -> LanguageModelInput

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for LanguageModelInput

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

Formats the value using the given formatter.

impl Default for LanguageModelInput

fn default() -> LanguageModelInput

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for LanguageModelInput

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for LanguageModelInput

fn eq(&self, other: &LanguageModelInput) -> 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 LanguageModelInput

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 LanguageModelInput