Struct ChatRequest

pub struct ChatRequest {

    pub messages: Vec<ChatMessage>,
    pub model: String,
    pub store: Option<bool>,
    pub reasoning_effort: Option<ReasoningEffort>,
    pub metadata: Option<Value>,
    pub frequency_penalty: Option<f32>,
    pub logit_bias: Option<HashMap<String, Value>>,
    pub logprobs: Option<bool>,
    pub top_logprobs: Option<u8>,
    pub max_tokens: Option<u32>,
    pub max_completion_tokens: Option<u32>,
    pub n: Option<u8>,
    pub modalities: Option<Vec<Modalities>>,
    pub prediction: Option<PredictionContent>,
    pub audio: Option<ChatAudio>,
    pub presence_penalty: Option<f32>,
    pub response_format: Option<ChatResponseFormat>,
    pub seed: Option<i64>,
    pub service_tier: Option<ServiceTier>,
    pub stop: Option<Stop>,
    pub stream: Option<bool>,
    pub stream_options: Option<StreamOptions>,
    pub temperature: Option<f32>,
    pub top_p: Option<f32>,
    pub tools: Option<Vec<ChatTool>>,
    pub tool_choice: Option<ChatToolChoice>,
    pub parallel_tool_calls: Option<bool>,
    pub user: Option<String>,
    pub function_call: Option<ChatFunctionCall>,
    pub functions: Option<Vec<ChatFunction>>,
}

https://platform.openai.com/docs/api-reference/chat/create

Fields

messages: Vec<ChatMessage>

A list of messages comprising the conversation so far. Depending on the model you use, different message types (modalities) are supported, like text, images, and audio.

model: String

ID of the model to use. See the model endpoint compatibility table for details on which models work with the Chat API.

store: Option<bool>

Whether or not to store the output of this chat completion request for use in our model distillation or evals products.

reasoning_effort: Option<ReasoningEffort>

Constrains effort on reasoning for reasoning models. Currently supported values are low, medium, and high. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.

metadata: Option<Value>

Developer-defined tags and values used for filtering completions in the dashboard.

frequency_penalty: Option<f32>

Number between -2.0 and 2.0. 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.

logit_bias: Option<HashMap<String, Value>>

Modify the likelihood of specified tokens appearing in the completion.

Accepts a JSON object that maps tokens (specified by their token ID in the GPT tokenizer) to an associated bias value from -100 to 100. You can use this tokenizer tool to convert text to token IDs. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token.

As an example, you can pass {“50256”: -100} to prevent the <|endoftext|> token from being generated.

logprobs: Option<bool>

Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the content of message.

top_logprobs: Option<u8>

An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. logprobs must be set to true if this parameter is used.

max_tokens: Option<u32>

👎Deprecated

The maximum number of tokens that can be generated in the chat completion. This value can be used to control costs for text generated via API.

This value is now deprecated in favor of max_completion_tokens, and is not compatible with o1 series models.

max_completion_tokens: Option<u32>

An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.

n: Option<u8>

How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep n as 1 to minimize costs.

modalities: Option<Vec<Modalities>>

Output types that you would like the model to generate for this request. Most models are capable of generating text, which is the default: [“text”] The gpt-4o-audio-preview model can also be used to generate audio. To request that this model generate both text and audio responses, you can use: [“text”, “audio”]

prediction: Option<PredictionContent>

Configuration for a Predicted Output, which can greatly improve response times when large parts of the model response are known ahead of time. This is most common when you are regenerating a file with only minor changes to most of the content.

audio: Option<ChatAudio>

Parameters for audio output. Required when audio output is requested with modalities: [“audio”]. Learn more.

presence_penalty: Option<f32>

Number between -2.0 and 2.0. 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.

See more information about frequency and presence penalties.

response_format: Option<ChatResponseFormat>

seed: Option<i64>

This feature is in Beta. If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.

service_tier: Option<ServiceTier>

Specifies the latency tier to use for processing the request. This parameter is relevant for customers subscribed to the scale tier service:

• If set to ‘auto’, the system will utilize scale tier credits until they are exhausted.
• If set to ‘default’, the request will be processed using the default service tier with a lower uptime SLA and no latency guarentee.
• When not set, the default behavior is ‘auto’.

When this parameter is set, the response body will include the service_tier utilized.

stop: Option<Stop>

Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.

stream: Option<bool>

If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message. Example Python code.

stream_options: Option<StreamOptions>

Options for streaming response. Only set this when you set stream: true.

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.

We generally recommend altering this or top_p but not both.

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.

tools: Option<Vec<ChatTool>>

A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported.

tool_choice: Option<ChatToolChoice>

Controls which (if any) tool is called by the model.

• none means the model will not call any tool and instead generates a message.
• auto means the model can pick between generating a message or calling one or more tools.
• required means the model must call one or more tools.
• Specifying a particular tool via {“type”: “function”, “function”: {“name”: “my_function”}} forces the model to call that tool. none is the default when no tools are present. auto is the default if tools are present.

parallel_tool_calls: Option<bool>

Whether to enable parallel function calling during tool use.

user: Option<String>

A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.

function_call: Option<ChatFunctionCall>

👎Deprecated

Deprecated in favor of tool_choice.

Controls which (if any) function is called by the model.

• none means the model will not call a function and instead generates a message.
• auto means the model can pick between generating a message or calling a function.
• Specifying a particular function via {"name": "my_function"} forces the model to call that function.

none is the default when no functions are present. auto is the default if functions are present.

functions: Option<Vec<ChatFunction>>

👎Deprecated

Deprecated in favor of tools.

A list of functions the model may generate JSON inputs for.

Implementations

impl ChatRequest

pub fn new(model: impl Into<String>, messages: Vec<ChatMessage>) -> Self

pub fn from_system(message: impl Into<Content>) -> Self

pub fn from_model(model: impl Into<String>) -> Self

pub fn iter_messages(&self) -> impl Iterator<Item = &ChatMessage>

pub async fn send(self) -> Result<ChatResponse, Error>

pub async fn send_stream( self, ) -> Result<Pin<Box<dyn Stream<Item = Result<ChatResponseStream, Error>> + Send>>, Error>

impl ChatRequest

Chainable setters

pub fn append_system(self, message: impl Into<Content>) -> Self

pub fn append_user(self, message: impl Into<String>) -> Self

pub fn append_developer(self, message: impl Into<Content>) -> Self

pub fn append_assistant(self, message: impl Into<AssistantContent>) -> Self

pub fn append_tool( self, message: impl Into<Content>, tool_call_id: impl Into<String>, ) -> Self

pub fn with_tool_choice(self, tool_choice: ChatToolChoice) -> Self

pub fn with_model(self, model: impl Into<String>) -> Self

pub fn with_stream(self) -> Self

pub fn with_tools(self, tools: Vec<impl Into<ChatTool>>) -> Self

pub fn with_response_format( self, response_format: impl Into<ChatResponseFormat>, ) -> Self

impl ChatRequest

pub fn to_string_pretty(&self) -> Result<String, Error>

Trait Implementations

impl Clone for ChatRequest

fn clone(&self) -> ChatRequest

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ChatRequest

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

Formats the value using the given formatter.

impl Default for ChatRequest

fn default() -> ChatRequest

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for ChatRequest

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for ChatRequest

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

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

const 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 Printable for ChatRequest

fn to_string_pretty(&self) -> Result<String, Error>

impl Requestable for ChatRequest

fn stream(&self) -> bool

impl Serialize for ChatRequest

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 ChatRequest