llmstatemachine
LLMStateMachine 0.7.0
LLMStateMachine es una biblioteca para crear agentes con modelos de idiomas basados en GPT y lógica de máquinas de estado.
LLMStatemachine está explorando cómo hacer agentes que usan herramientas de conversación y el historial de conversación como memoria, utilizando una estructura de máquina de estado junto con IA generativa.
pip install llmsstatemachinePara usar la máquina de estado del modelo de idioma grande, siga estos pasos:
Considere un juego de memoria, donde necesitas recordar y combinar pares ocultos; no ves todo a la vez. Este es un entorno parcialmente observable. LLMSTATEMACHIBE permite que un agente basado en el modelo de idioma juegue tales juegos. Esto muestra cómo la biblioteca se puede aplicar a escenarios en los que debe tomar decisiones con información limitada. También tenga en cuenta que los mecanismos de juego no son forzados y el agente puede hacer movimientos ilegales.
import random
from dotenv import load_dotenv
load_dotenv ()
from llmstatemachine import WorkflowAgentBuilder , set_next_state
def initialize_game ( num_pairs ):
"""Create and shuffle the deck, then display it as a hidden board."""
init_deck = list ( range ( 1 , num_pairs + 1 )) * 2
random . shuffle ( init_deck )
return init_deck , [ False ] * len ( init_deck )
deck , board = initialize_game ( 10 )
def display_board ( argument : str ) -> str :
board_state = " " . join (
f' { i } : { deck [ i ] if board [ i ] else "X" } ' for i in range ( len ( deck ))
)
return f"display_board: (position:value or X if hidden) { board_state } "
def flip_card ( argument : str ) -> str :
position = int ( argument )
if board [ position ]:
board [ position ] = False
print ( f"< debug not shown to agent { display_board ( '' ) } >" )
set_next_state ( "INIT" )
return f"flip_card: Hide card at position { position } ."
board [ position ] = True
print ( f"< debug not shown to agent { display_board ( '' ) } >" )
if all ( board ):
set_next_state ( "COMPLETE" )
return f"flip_card: Showing card at position { position } . Value is { deck [ position ] } ."
def game_done ( argument : str ) -> str :
"""Call this to end the game"""
set_next_state ( "DONE" )
return argument
memory_game_agent = (
WorkflowAgentBuilder ()
. add_system_message (
"You are a player of memory game. "
+ "In this game you have 10 number pairs in 20 cards. "
+ "Cards have been shuffled and they are all face down. "
+ "You may flip a card to see the value. "
+ "According to the rules of the memory game you can check a pair. "
+ "If they are not a pair you must flip them back hidden. "
+ "Once you have all pairs found and shown the game is done."
)
. add_state_and_transitions ( "INIT" , { flip_card , display_board })
. add_state_and_transitions ( "COMPLETE" , { game_done })
. add_end_state ( "DONE" )
. build ()
)
memory_game_agent . run ()
print ( "-= OK =-" )Ejemplo de salida del juego
...
================================================================================
tokens: 3642 total ; 62 completion ; 3580 prompt
================================================================================
AI: The card on position 18 shows a 7. I remember seeing a 7 long ago, it was at
position 2. So I will flip the card at position 2 to check if it matches.
flip_card ' 2 '
< debug not shown to agent display_board: 9 5 7 9 8 8 1 5 6 4 2 4 6 X 10 2 10 1 7 X >
flip_card: Showing card at position 2. Value is 7.
================================================================================
tokens: 3757 total ; 86 completion ; 3671 prompt
================================================================================
AI: We found another matching pair ! The cards at positions 2 and 18 both have the
value 7. At this point, we have only two unknown cards remaining. Since all other
pairs have been found, these last two cards must form a pair as well. Let ' s flip
the card at position 19 to see its value.
flip_card ' 19 '
< debug not shown to agent display_board: 9 5 7 9 8 8 1 5 6 4 2 4 6 X 10 2 10 1 7 3 >
flip_card: Showing card at position 19. Value is 3.
================================================================================
tokens: 3837 total; 51 completion; 3786 prompt
================================================================================
AI: As I thought, the last card is a 3, which matches with the card at position 13
we discovered earlier. Let ' s flip it to confirm.
flip_card ' 13 '
< debug not shown to agent display_board: 9 5 7 9 8 8 1 5 6 4 2 4 6 3 10 2 10 1 7 3 >
flip_card: Showing card at position 13. Value is 3.
================================================================================
tokens: 3872 total ; 52 completion ; 3820 prompt
================================================================================
AI: The last pair matched as expected. I have now found all the pairs in the game.
The game has been solved.
game_done ' Found all pairs. The game has been solved successfully. '
Found all pairs. The game has been solved successfully.
-= OK =-__init__(self, goal, transitions) : inicialice al agente con un objetivo y un conjunto de transiciones estatales.trigger(self, function_call, args) : desencadena una transición en el flujo de trabajo.add_message(self, message) : agrega un mensaje al flujo de trabajo.run(self, callback) : ejecuta el agente, procesando los pasos hasta su finalización.step(self) : ejecuta un solo paso en el flujo de trabajo.add_system_message(self, message) : establece un mensaje del sistema para el agente.add_state_and_transitions(self, state_name, transition_functions) : defina un estado y sus transiciones.add_end_state(self, state_name) : defina un estado final para el flujo de trabajo.build(self) : construye y devuelve un WorkflowAgent . Para obtener más información sobre la implementación y el viaje de llmstatemachine , lea nuestra publicación de blog: Explorando a los agentes de IA: un viaje con LLMStateMachine.
"En este artículo, exploramos la implementación de agentes generativos de IA, profundizando en los desafíos y soluciones encontradas en la navegación y la participación con entornos digitales dinámicos".
Apache 2.0
