Skip to main content

BaseAgent

lc_agents::base

Trait BaseAgent 

Source 
pub trait BaseAgent: Send + Sync {
    // Required method
    fn plan<'life0, 'life1, 'life2, 'async_trait>(
        &'life0 self,
        intermediate_steps: &'life1 [AgentStep],
        inputs: &'life2 HashMap<String, String>,
    ) -> Pin<Box<dyn Future<Output = Result<AgentOutput, AgentError>> + Send + 'async_trait>>
       where Self: 'async_trait,
             'life0: 'async_trait,
             'life1: 'async_trait,
             'life2: 'async_trait;

    // Provided methods
    fn input_keys(&self) -> Vec<&str> { ... }
    fn get_allowed_tools(&self) -> Option<Vec<&str>> { ... }
    fn return_stopped_response(
        &self,
        _intermediate_steps: &[AgentStep],
    ) -> AgentFinish { ... }
}
Expand description

Base Agent trait.

Defines the core interface for agents. Agent is responsible for planning, not execution. Execution is handled by AgentExecutor.

Required Methods§

Source

fn plan<'life0, 'life1, 'life2, 'async_trait>( &'life0 self, intermediate_steps: &'life1 [AgentStep], inputs: &'life2 HashMap<String, String>, ) -> Pin<Box<dyn Future<Output = Result<AgentOutput, AgentError>> + Send + 'async_trait>>
where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait, 'life2: 'async_trait,

Plans the next action.

§Arguments
  • intermediate_steps - History of executed steps.
  • inputs - User input.
§Returns
  • AgentOutput::Action - Action to execute.
  • AgentOutput::Finish - Final answer.

Provided Methods§

Source

fn input_keys(&self) -> Vec<&str>

Returns input keys.

Source

fn get_allowed_tools(&self) -> Option<Vec<&str>>

Returns allowed tools list.

Source

fn return_stopped_response( &self, _intermediate_steps: &[AgentStep], ) -> AgentFinish

Returns stopped response when max iterations reached.

Dyn Compatibility§

This trait is dyn compatible.

In older versions of Rust, dyn compatibility was called "object safety".

Implementors§