Struct Agent

pub struct Agent<M: CompletionModel> {
    pub tools: ToolSet,
    /* private fields */
}

Struct representing an LLM agent. An agent is an LLM model combined with a preamble (i.e.: system prompt) and a static set of context documents and tools. All context documents and tools are always provided to the agent when prompted.

Example

use rig::{completion::Prompt, providers::openai};

let openai = openai::Client::from_env();

let comedian_agent = openai
    .agent("gpt-4o")
    .preamble("You are a comedian here to entertain the user using humour and jokes.")
    .temperature(0.9)
    .build();

let response = comedian_agent.prompt("Entertain me!")
    .await
    .expect("Failed to prompt the agent");

Fields

tools: ToolSet

Actual tool implementations

Trait Implementations

impl<M: CompletionModel> Chat for Agent<M>

async fn chat( &self, prompt: impl Into<Message> + Send, chat_history: Vec<Message>, ) -> Result<String, PromptError>

Send a prompt with optional chat history to the underlying completion model.

impl<M: CompletionModel> Completion<M> for Agent<M>

async fn completion( &self, prompt: impl Into<Message> + Send, chat_history: Vec<Message>, ) -> Result<CompletionRequestBuilder<M>, CompletionError>

Generates a completion request builder for the given prompt and chat_history. This function is meant to be called by the user to further customize the request at prompt time before sending it.

impl<M: CompletionModel> Prompt for &Agent<M>

async fn prompt( &self, prompt: impl Into<Message> + Send, ) -> Result<String, PromptError>

Send a simple prompt to the underlying completion model.

impl<M: CompletionModel> Prompt for Agent<M>

async fn prompt( &self, prompt: impl Into<Message> + Send, ) -> Result<String, PromptError>

Send a simple prompt to the underlying completion model.

impl<M: StreamingCompletionModel> StreamingChat for Agent<M>

async fn stream_chat( &self, prompt: &str, chat_history: Vec<Message>, ) -> Result<StreamingResult, CompletionError>

Stream a chat with history to the model

impl<M: StreamingCompletionModel> StreamingCompletion<M> for Agent<M>

async fn stream_completion( &self, prompt: impl Into<Message> + Send, chat_history: Vec<Message>, ) -> Result<CompletionRequestBuilder<M>, CompletionError>

Generate a streaming completion from a request

impl<M: StreamingCompletionModel> StreamingPrompt for Agent<M>

async fn stream_prompt( &self, prompt: &str, ) -> Result<StreamingResult, CompletionError>

Stream a simple prompt to the model