Struct ChatCompletionRequest 

pub struct ChatCompletionRequest {
    pub model: String,
    pub messages: Vec<Message>,
    pub temperature: Option<f32>,
    pub max_tokens: Option<u32>,
    pub top_p: Option<f32>,
    pub frequency_penalty: Option<f32>,
    pub presence_penalty: Option<f32>,
    pub stream: Option<bool>,
    pub tools: Option<Vec<Tool>>,
}

Request to create a chat completion.

This is the primary request type for the chat completions endpoint. Uses the Former builder pattern for fluent construction.

Required Fields

• model: Model ID (e.g., “grok-2-1212”)
• messages: Conversation messages

Optional Fields

• temperature: Randomness (0.0-2.0, default varies by model)
• max_tokens: Maximum tokens to generate
• top_p: Nucleus sampling threshold
• frequency_penalty: Repetition reduction
• presence_penalty: Topic diversity
• stream: Enable SSE streaming
• tools: Available functions for tool calling

Examples

use api_xai::{ ChatCompletionRequest, Message };

let request = ChatCompletionRequest::former()
  .model( "grok-2-1212".to_string() )
  .messages( vec![ Message::user( "Hello!" ) ] )
  .temperature( 0.7 )
  .max_tokens( 100u32 )
  .form();

Fields

model: String

Model ID (e.g., “grok-2-1212”, “grok-4”).

messages: Vec<Message>

Conversation messages.

temperature: Option<f32>

Sampling temperature (0.0-2.0).

Higher values (0.8-2.0) make output more random. Lower values (0.0-0.4) make output more focused and deterministic.

max_tokens: Option<u32>

Maximum tokens to generate.

Limits the length of the completion. Does not include prompt tokens.

top_p: Option<f32>

Nucleus sampling threshold (0.0-1.0).

Only tokens with cumulative probability up to top_p are considered. Recommended : 0.1-0.9. Do not use with temperature.

frequency_penalty: Option<f32>

Frequency penalty (0.0-2.0).

Reduces repetition of tokens based on their frequency. Typical range : 0.1-0.8.

presence_penalty: Option<f32>

Presence penalty (0.0-2.0).

Encourages the model to talk about new topics. Typical range : 0.1-0.8.

stream: Option<bool>

Enable Server-Sent Events streaming.

When true, the response is streamed as SSE chunks.

tools: Option<Vec<Tool>>

Tools (functions) available for the model to call.

Implementations

impl ChatCompletionRequest

pub fn former() -> ChatCompletionRequestFormer<ChatCompletionRequestFormerDefinition<(), ChatCompletionRequest, ReturnPreformed>>

Provides a mechanism to initiate the formation process with a default completion behavior.

Trait Implementations

impl Clone for ChatCompletionRequest

fn clone(&self) -> ChatCompletionRequest

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ChatCompletionRequest

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for ChatCompletionRequest

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl<__Context, __Formed, __End> EntityToDefinition<__Context, __Formed, __End> for ChatCompletionRequest

where __End: FormingEnd<ChatCompletionRequestFormerDefinitionTypes<__Context, __Formed>>,

type Definition = ChatCompletionRequestFormerDefinition<__Context, __Formed, __End>

The specific FormerDefinition associated with this entity.

type Types = ChatCompletionRequestFormerDefinitionTypes<__Context, __Formed>

The specific FormerDefinitionTypes associated with this entity.

impl<__Context, __Formed> EntityToDefinitionTypes<__Context, __Formed> for ChatCompletionRequest

type Types = ChatCompletionRequestFormerDefinitionTypes<__Context, __Formed>

Specifies the FormerDefinitionTypes that define the storage, formed entity, and context types used during formation.

impl<Definition> EntityToFormer<Definition> for ChatCompletionRequest

where Definition: FormerDefinition<Storage = ChatCompletionRequestFormerStorage>,

type Former = ChatCompletionRequestFormer<Definition>

The type of the former (builder) used for constructing the entity.

fn __f(_: &Definition)

A placeholder function to reference the definition without operational logic.

impl EntityToStorage for ChatCompletionRequest

type Storage = ChatCompletionRequestFormerStorage

The storage type used for forming the entity.

impl PartialEq for ChatCompletionRequest

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

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 ChatCompletionRequest