Struct ChatRequest

pub struct ChatRequest<'input> {
    pub message: &'input str,
    pub model: Option<GenerateModel>,
    pub prompt_truncation: Option<PromptTruncation>,
    pub temperature: Option<f64>,
    pub conversation_id: Option<String>,
    pub chat_history: Option<&'input Vec<ChatMessage>>,
    pub preamble: Option<String>,
    pub max_tokens: Option<u64>,
    pub k: Option<u64>,
}

Fields

message: &'input str

The chat message from the user to the model.

model: Option<GenerateModel>

optional - The model to use for text generation. Custom models can also be supplied with their full ID. Defaults to ‘command’.

prompt_truncation: Option<PromptTruncation>

optional - Dictates how the prompt will be constructed. When set to ‘AUTO’ some parts of chat history and documents will be dropped to construct a prompt that fits within the model’s context length limit.

temperature: Option<f64>

optional - A non-negative float that tunes the degree of randomness in generation.

conversation_id: Option<String>

optional - Previous conversations can be stored and resumed by providing the conversation’s identifier. If a conversation with this id does not already exist, a new conversation will be created.

chat_history: Option<&'input Vec<ChatMessage>>

optional - A list of previous messages between the user and the model, meant to give the model conversational context for responding to the user’s message.

preamble: Option<String>

max_tokens: Option<u64>

k: Option<u64>

Trait Implementations

impl<'input> Debug for ChatRequest<'input>

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

Formats the value using the given formatter.

impl<'input> Default for ChatRequest<'input>

fn default() -> ChatRequest<'input>

Returns the “default value” for a type.

impl<'input> Serialize for ChatRequest<'input>

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

where __S: Serializer,

Serialize this value into the given Serde serializer.