LLMSTATEMACHINE est une bibliothèque pour créer des agents avec des modèles de langage basés sur GPT et une logique de machine d'état.
LLMStateMachine explore comment faire des agents qui utilisent des outils de conversation et l'historique de conversation comme mémoire, en utilisant une structure de machine d'état avec une IA générative.
pip install llmsstatemachinePour utiliser la machine d'état du modèle grand langage, suivez ces étapes:
Considérez un jeu de mémoire, où vous devez vous souvenir et faire correspondre les paires cachées - vous ne voyez pas tout en même temps. Il s'agit d'un environnement partiellement observable. LLMSTATEMACHIBE permet à un agent basé sur un modèle de langue jouer de tels jeux. Cela montre comment la bibliothèque peut être appliquée aux scénarios où vous devez prendre des décisions avec des informations limitées. Notez également que les mécanismes de jeu ne sont pas forcés et que l'agent peut faire des mouvements illégaux.
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 =-" )Exemple de sortie du jeu
...
================================================================================
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) : Initialisez l'agent avec un objectif et un ensemble de transitions d'état.trigger(self, function_call, args) : déclenche une transition dans le flux de travail.add_message(self, message) : ajoute un message au workflow.run(self, callback) : exécute l'agent, les étapes de traitement jusqu'à la fin.step(self) : exécute une seule étape dans le workflow.add_system_message(self, message) : définit un message système pour l'agent.add_state_and_transitions(self, state_name, transition_functions) : définissez un état et ses transitions.add_end_state(self, state_name) : définissez un état final pour le flux de travail.build(self) : construit et renvoie un WorkflowAgent . Pour plus d'informations sur la mise en œuvre et le voyage de llmstatemachine , lisez notre article de blog: Explorer les agents de l'IA: A Journey with LLMStatemachine.
"Dans cet article, nous explorons la mise en œuvre d'agents d'IA génératifs, plongeant dans les défis et solutions rencontrés pour naviguer et s'engager dans des environnements numériques dynamiques."
Apache 2.0