StateMachineInstruction

StateMachineInstruction defines the single instruction used in a state machine protocol. It maps one or more input TokenSets to a state string selected from your samples.

Key characteristics:

• Output is created automatically with a single state token
• Final token is always <NON>
• Samples provide a state string instead of a response snippet

StateMachineInstruction Parameters

class StateMachineInstruction:
    def __init__(self, input: StateMachineInput):

• input: A StateMachineInput instance defining the input TokenSets

Creating a StateMachineInstruction

# Create TokenSets for input patterns
question_tokenset = mtp.TokenSet(tokens=(question, context))

# Create StateMachineInput
state_machine_input = mtp.StateMachineInput(
    tokensets=[question_tokenset]
)

# Create the StateMachineInstruction
state_machine_instruction = mtp.StateMachineInstruction(
    input=state_machine_input
)

# Add samples that map inputs to states
state_machine_instruction.add_sample(
    input_snippets=["Where are you from?"],
    state="WHERE"
)

The list of possible states is derived from these samples and stored in the template states field when state_machine=True. For details, see the State Machines Overview.