Struct rig::agent::Agent

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

Struct reprensenting 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_client = openai::Client::from_env();

let comedian_agent = client
    .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 GPT-4");

Implementations

impl<M: CompletionModel> Agent<M>

pub fn new( model: M, preamble: String, static_context: Vec<String>, static_tools: Vec<impl Tool + 'static>, temperature: Option<f64>, additional_params: Option<Value>, ) -> Self

Create a new Agent

Trait Implementations

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

async fn chat( &self, prompt: &str, chat_history: Vec<Message>, ) -> Result<String, PromptError>

Send a one-shot prompt to the completion endpoint. If the response is a message, then it is returned as a string. If the response is a tool call, then the tool is called and the result is returned as a string.

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

async fn completion( &self, prompt: &str, 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: &str) -> Result<String, PromptError>