Struct Agent 

#[non_exhaustive]
pub struct Agent<M, P = ()>
where
    M: CompletionModel,
    P: PromptHook<M>,
{

    pub name: Option<String>,
    pub description: Option<String>,
    pub model: Arc<M>,
    pub preamble: Option<String>,
    pub static_context: Vec<Document>,
    pub temperature: Option<f64>,
    pub max_tokens: Option<u64>,
    pub additional_params: Option<Value>,
    pub tool_server_handle: ToolServerHandle,
    pub dynamic_context: Arc<RwLock<Vec<(usize, Box<dyn VectorStoreIndexDyn + Send + Sync>)>>>,
    pub tool_choice: Option<ToolChoice>,
    pub default_max_turns: Option<usize>,
    pub hook: Option<P>,
    pub output_schema: Option<Schema>,
}

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.

The optional type parameter P represents a default hook that will be used for all prompt requests unless overridden via .with_hook() on the request.

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 (Non-exhaustive)

Non-exhaustive structs could have additional fields added in future. Therefore, non-exhaustive structs cannot be constructed in external crates using the traditional Struct { .. } syntax; cannot be matched against without a wildcard ..; and struct update syntax will not work.

name: Option<String>

Name of the agent used for logging and debugging

description: Option<String>

Agent description. Primarily useful when using sub-agents as part of an agent workflow and converting agents to other formats.

model: Arc<M>

Completion model (e.g.: OpenAI’s gpt-3.5-turbo-1106, Cohere’s command-r)

preamble: Option<String>

System prompt

static_context: Vec<Document>

Context documents always available to the agent

temperature: Option<f64>

Temperature of the model

max_tokens: Option<u64>

Maximum number of tokens for the completion

additional_params: Option<Value>

Additional parameters to be passed to the model

tool_server_handle: ToolServerHandle

dynamic_context: Arc<RwLock<Vec<(usize, Box<dyn VectorStoreIndexDyn + Send + Sync>)>>>

List of vector store, with the sample number

tool_choice: Option<ToolChoice>

Whether or not the underlying LLM should be forced to use a tool before providing a response.

default_max_turns: Option<usize>

Default maximum depth for recursive agent calls

hook: Option<P>

Default hook for this agent, used when no per-request hook is provided

output_schema: Option<Schema>

Optional JSON Schema for structured output. When set, providers that support native structured outputs will constrain the model’s response to match this schema.

Trait Implementations

impl<M, P> Chat for Agent<M, P>

where M: CompletionModel, P: PromptHook<M> + 'static,

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

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

impl<M, P> Clone for Agent<M, P>

where M: CompletionModel + Clone, P: PromptHook<M> + Clone,

fn clone(&self) -> Agent<M, P>

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl<M, P> Completion<M> for Agent<M, P>

where M: CompletionModel, P: PromptHook<M>,

async fn completion( &self, prompt: impl Into<Message> + WasmCompatSend, 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> DiscordExt for Agent<M>

where M: CompletionModel + Send + Sync + 'static,

Available on crate feature discord-bot only.

async fn into_discord_bot(self, token: &str) -> Client

fn into_discord_bot_from_env(self) -> impl Future<Output = Client> + Send

impl<M, P> Prompt for &Agent<M, P>

where M: CompletionModel, P: PromptHook<M> + 'static,

fn prompt( &self, prompt: impl Into<Message> + WasmCompatSend, ) -> PromptRequest<'_, Standard, M, P>

Send a simple prompt to the underlying completion model.

impl<M, P> Prompt for Agent<M, P>

where M: CompletionModel, P: PromptHook<M> + 'static,

fn prompt( &self, prompt: impl Into<Message> + WasmCompatSend, ) -> PromptRequest<'_, Standard, M, P>

Send a simple prompt to the underlying completion model.

impl<M, P> StreamingChat<M, <M as CompletionModel>::StreamingResponse> for Agent<M, P>

where M: CompletionModel + 'static, M::StreamingResponse: GetTokenUsage, P: PromptHook<M> + 'static,

type Hook = P

The hook type used by this streaming chat implementation.

fn stream_chat( &self, prompt: impl Into<Message> + WasmCompatSend, chat_history: Vec<Message>, ) -> StreamingPromptRequest<M, P>

Stream a chat with history to the model

impl<M, P> StreamingCompletion<M> for Agent<M, P>

where M: CompletionModel, P: PromptHook<M>,

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

Generate a streaming completion from a request

impl<M, P> StreamingPrompt<M, <M as CompletionModel>::StreamingResponse> for Agent<M, P>

where M: CompletionModel + 'static, M::StreamingResponse: GetTokenUsage, P: PromptHook<M> + 'static,

type Hook = P

The hook type used by this streaming prompt implementation.

fn stream_prompt( &self, prompt: impl Into<Message> + WasmCompatSend, ) -> StreamingPromptRequest<M, P>

Stream a simple prompt to the model

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

const NAME: &'static str = "agent_tool"

The name of the tool. This name should be unique.

type Error = PromptError

The error type of the tool.

type Args = AgentToolArgs

The arguments type of the tool.

type Output = String

The output type of the tool.

async fn definition(&self, _prompt: String) -> ToolDefinition

A method returning the tool definition. The user prompt can be used to tailor the definition to the specific use case.

async fn call(&self, args: Self::Args) -> Result<Self::Output, Self::Error>

The tool execution method. Both the arguments and return value are a String since these values are meant to be the output and input of LLM models (respectively)

fn name(&self) -> String

A method returning the name of the tool.

impl<M, P> TypedPrompt for &Agent<M, P>

where M: CompletionModel, P: PromptHook<M> + 'static,

type TypedRequest<'a, T> = TypedPromptRequest<'a, T, M, P> where Self: 'a, T: JsonSchema + DeserializeOwned + WasmCompatSend + 'a

The type of the typed prompt request returned by prompt_typed.

fn prompt_typed<T>( &self, prompt: impl Into<Message> + WasmCompatSend, ) -> TypedPromptRequest<'_, T, M, P>

where T: JsonSchema + DeserializeOwned + WasmCompatSend,

Send a prompt and receive a typed structured response.

impl<M, P> TypedPrompt for Agent<M, P>

where M: CompletionModel, P: PromptHook<M> + 'static,

fn prompt_typed<T>( &self, prompt: impl Into<Message> + WasmCompatSend, ) -> TypedPromptRequest<'_, T, M, P>

where T: JsonSchema + DeserializeOwned + WasmCompatSend,

Send a prompt and receive a typed structured response.

The JSON schema for T is automatically generated and sent to the provider. Providers that support native structured outputs will constrain the model’s response to match this schema.

Example

use rig::prelude::*;
use schemars::JsonSchema;
use serde::Deserialize;

#[derive(Debug, Deserialize, JsonSchema)]
struct WeatherForecast {
    city: String,
    temperature_f: f64,
    conditions: String,
}

let agent = client.agent("gpt-4o").build();

// Type inferred from variable
let forecast: WeatherForecast = agent
    .prompt_typed("What's the weather in NYC?")
    .await?;

// Or explicit turbofish syntax
let forecast = agent
    .prompt_typed::<WeatherForecast>("What's the weather in NYC?")
    .max_turns(3)
    .await?;

type TypedRequest<'a, T> = TypedPromptRequest<'a, T, M, P> where Self: 'a, T: JsonSchema + DeserializeOwned + WasmCompatSend + 'a

The type of the typed prompt request returned by prompt_typed.