Documentation
¶
Overview ¶
Package agent contains the standard interface all agents must implement, implementations of this interface, and an agent executor.
An Agent is a wrapper around a model, which takes in user input and returns a response corresponding to an “action” to take and a corresponding “action input”. Alternatively the agent can return a finish with the finished answer to the query. This package contains and standard interface for such agents.
Package agents provides and implementation of the agent interface called OneShotZeroAgent. This agent uses the ReAct Framework (based on the descriptions of tools) to decide what action to take. This agent is optimized to be used with LLMs.
To make agents more powerful we need to make them iterative, ie. call the model multiple times until they arrive at the final answer. That's the job of the Executor. The Executor is an Agent and set of Tools. The agent executor is responsible for calling the agent, getting back and action and action input, calling the tool that the action references with the corresponding input, getting the output of the tool, and then passing all that information back into the Agent to get the next action it should take.
Index ¶
- Variables
- type Agent
- type AgentType
- type ConversationalAgent
- type CreationOption
- func WithCallbacksHandler(handler callbacks.Handler) CreationOption
- func WithMaxIterations(iterations int) CreationOption
- func WithMemory(m schema.Memory) CreationOption
- func WithOutputKey(outputKey string) CreationOption
- func WithPrompt(prompt prompts.PromptTemplate) CreationOption
- func WithPromptFormatInstructions(instructions string) CreationOption
- func WithPromptPrefix(prefix string) CreationOption
- func WithPromptSuffix(suffix string) CreationOption
- func WithReturnIntermediateSteps() CreationOption
- type CreationOptions
- type Executor
- func (e Executor) Call(ctx context.Context, inputValues map[string]any, _ ...chains.ChainCallOption) (map[string]any, error)
- func (e Executor) GetCallbackHandler() callbacks.Handler
- func (e Executor) GetInputKeys() []string
- func (e Executor) GetMemory() schema.Memory
- func (e Executor) GetOutputKeys() []string
- type OneShotZeroAgent
Constants ¶
This section is empty.
Variables ¶
var ( // ErrExecutorInputNotString is returned if an input to the executor call function is not a string. ErrExecutorInputNotString = errors.New("input to executor not string") // ErrAgentNoReturn is returned if the agent returns no actions and no finish. ErrAgentNoReturn = errors.New("no actions or finish was returned by the agent") // ErrNotFinished is returned if the agent does not give a finish before the number of iterations // is larger then max iterations. ErrNotFinished = errors.New("agent not finished before max iterations") // ErrUnknownAgentType is returned if the type given to the initializer is invalid. ErrUnknownAgentType = errors.New("unknown agent type") // ErrInvalidOptions is returned if the options given to the initializer is invalid. ErrInvalidOptions = errors.New("invalid options") // ErrUnableToParseOutput is returned if the output of the llm is unparsable. ErrUnableToParseOutput = errors.New("unable to parse agent output") // ErrInvalidChainReturnType is returned if the internal chain of the agent eturns a value in the // "text" filed that is not a string. ErrInvalidChainReturnType = errors.New("agent chain did not return a string") )
Functions ¶
This section is empty.
Types ¶
type Agent ¶
type Agent interface {
// Given an input and previous steps decide what to do next. Returns
// either actions or a finish.
Plan(ctx context.Context, intermediateSteps []schema.AgentStep, inputs map[string]string) ([]schema.AgentAction, *schema.AgentFinish, error) //nolint:lll
GetInputKeys() []string
GetOutputKeys() []string
}
Agent is the interface all agents must implement.
type AgentType ¶
type AgentType string
AgentType is a string type representing the type of agent to create.
const ( // ZeroShotReactDescription is an AgentType constant that represents // the "zeroShotReactDescription" agent type. ZeroShotReactDescription AgentType = "zeroShotReactDescription" // ConversationalReactDescription is an AgentType constant that represents // the "conversationalReactDescription" agent type. ConversationalReactDescription AgentType = "conversationalReactDescription" )
type ConversationalAgent ¶
type ConversationalAgent struct {
// Chain is the chain used to call with the values. The chain should have an
// input called "agent_scratchpad" for the agent to put it's thoughts in.
Chain chains.Chain
// Tools is a list of the tools the agent can use.
Tools []tools.Tool
// Output key is the key where the final output is placed.
OutputKey string
}
ConversationalAgent is a struct that represents an agent responsible for deciding what to do or give the final output if the task is finished given a set of inputs and previous steps taken.
Other agents are often optimized for using tools to figure out the best response, which is not ideal in a conversational setting where you may want the agent to be able to chat with the user as well.
func NewConversationalAgent ¶
func NewConversationalAgent(llm llms.LanguageModel, tools []tools.Tool, opts ...CreationOption) *ConversationalAgent
func (*ConversationalAgent) GetInputKeys ¶
func (a *ConversationalAgent) GetInputKeys() []string
func (*ConversationalAgent) GetOutputKeys ¶
func (a *ConversationalAgent) GetOutputKeys() []string
func (*ConversationalAgent) Plan ¶
func (a *ConversationalAgent) Plan( ctx context.Context, intermediateSteps []schema.AgentStep, inputs map[string]string, ) ([]schema.AgentAction, *schema.AgentFinish, error)
Plan decides what action to take or returns the final result of the input.
type CreationOption ¶
type CreationOption func(*CreationOptions)
CreationOption is a function type that can be used to modify the creation of the agents and executors.
func WithCallbacksHandler ¶
func WithCallbacksHandler(handler callbacks.Handler) CreationOption
func WithMaxIterations ¶
func WithMaxIterations(iterations int) CreationOption
WithMaxIterations is an option for setting the max number of iterations the executor will complete.
func WithMemory ¶
func WithMemory(m schema.Memory) CreationOption
func WithOutputKey ¶
func WithOutputKey(outputKey string) CreationOption
WithOutputKey is an option for setting the output key of the agent.
func WithPrompt ¶
func WithPrompt(prompt prompts.PromptTemplate) CreationOption
WithPrompt is an option for setting the prompt the agent will use.
func WithPromptFormatInstructions ¶
func WithPromptFormatInstructions(instructions string) CreationOption
WithPromptFormatInstructions is an option for setting the format instructions of the prompt used by the agent.
func WithPromptPrefix ¶
func WithPromptPrefix(prefix string) CreationOption
WithPromptPrefix is an option for setting the prefix of the prompt used by the agent.
func WithPromptSuffix ¶
func WithPromptSuffix(suffix string) CreationOption
WithPromptFormatInstructions is an option for setting the suffix of the prompt used by the agent.
func WithReturnIntermediateSteps ¶
func WithReturnIntermediateSteps() CreationOption
WithReturnIntermediateSteps is an option for making the executor return the intermediate steps taken.
type CreationOptions ¶
type CreationOptions struct {
// contains filtered or unexported fields
}
type Executor ¶
type Executor struct {
Agent Agent
Tools []tools.Tool
Memory schema.Memory
CallbacksHandler callbacks.Handler
MaxIterations int
ReturnIntermediateSteps bool
}
Executor is the chain responsible for running agents.
func Initialize ¶
func Initialize( llm llms.LanguageModel, tools []tools.Tool, agentType AgentType, opts ...CreationOption, ) (Executor, error)
Initialize is a function that creates a new executor with the specified LLM model, tools, agent type, and options. It returns an Executor or an error if there is any issues during the creation process.
func NewExecutor ¶
func NewExecutor(agent Agent, tools []tools.Tool, opts ...CreationOption) Executor
NewExecutor creates a new agent executor with a agent and the tools the agent can use.
func (Executor) GetCallbackHandler ¶
func (Executor) GetInputKeys ¶
GetInputKeys gets the input keys the agent of the executor expects. Often "input".
func (Executor) GetOutputKeys ¶
GetOutputKeys gets the output keys the agent of the executor returns.
type OneShotZeroAgent ¶
type OneShotZeroAgent struct {
// Chain is the chain used to call with the values. The chain should have an
// input called "agent_scratchpad" for the agent to put it's thoughts in.
Chain chains.Chain
// Tools is a list of the tools the agent can use.
Tools []tools.Tool
// Output key is the key where the final output is placed.
OutputKey string
}
OneShotZeroAgent is a struct that represents an agent responsible for deciding what to do or give the final output if the task is finished given a set of inputs and previous steps taken.
This agent is optimized to be used with LLMs.
func NewOneShotAgent ¶
func NewOneShotAgent(llm llms.LanguageModel, tools []tools.Tool, opts ...CreationOption) *OneShotZeroAgent
NewOneShotAgent creates a new OneShotZeroAgent with the given LLM model, tools, and options. It returns a pointer to the created agent. The opts parameter represents the options for the agent.
func (*OneShotZeroAgent) GetInputKeys ¶
func (a *OneShotZeroAgent) GetInputKeys() []string
func (*OneShotZeroAgent) GetOutputKeys ¶
func (a *OneShotZeroAgent) GetOutputKeys() []string
func (*OneShotZeroAgent) Plan ¶
func (a *OneShotZeroAgent) Plan( ctx context.Context, intermediateSteps []schema.AgentStep, inputs map[string]string, ) ([]schema.AgentAction, *schema.AgentFinish, error)
Plan decides what action to take or returns the final result of the input.
Source Files