LLMSTATEMACHINE ist eine Bibliothek für die Erstellung von Agenten mit GPT-basierten Sprachmodellen und staatlicher Maschinenlogik.
LLMStatemachine untersucht, wie Agenten, die Konversationstools und den Gesprächsgeschichte als Speicher verwenden, zusammen mit generativen KI verwenden.
pip install llmsstatemachineFolgen Sie die folgenden Schritte, um die große Sprachmodellmaschine zu verwenden:
Betrachten Sie ein Memory -Spiel, bei dem Sie sich erinnern und verborgene Paare anpassen müssen - Sie sehen nicht alles auf einmal. Dies ist eine teilweise beobachtbare Umgebung. LLMSTATEMACHIBE ermöglicht einem sprachmodellbasierten Agenten, der solche Spiele abspielt. Dies zeigt, wie die Bibliothek auf Szenarien angewendet werden kann, in denen Sie Entscheidungen mit begrenzten Informationen treffen müssen. Beachten Sie auch, dass die Spielmechanismen nicht erzwungen werden und Agent illegale Bewegungen ausführen kann.
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 =-" )Beispielausgabe vom Spielspiel
...
================================================================================
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) : Initialisieren Sie den Agenten mit einem Ziel und einer Reihe von staatlichen Übergängen.trigger(self, function_call, args) : löst einen Übergang im Workflow aus.add_message(self, message) : Fügt dem Workflow eine Nachricht hinzu.run(self, callback) : Führen Sie den Agenten bis zur Fertigstellung von Verarbeitungsschritten aus.step(self) : Führen Sie einen einzelnen Schritt im Workflow aus.add_system_message(self, message) : Legt eine Systemnachricht für den Agenten fest.add_state_and_transitions(self, state_name, transition_functions) : Definieren Sie einen Status und seine Übergänge.add_end_state(self, state_name) : Definieren Sie einen Endstatus für den Workflow.build(self) : Erstellt und gibt einen WorkflowAgent zurück. Weitere Einblicke in die Umsetzung und Reise von llmstatemachine finden Sie in unserem Blog -Beitrag: Erkundung von AI -Agenten: Eine Reise mit LLMstatemachine.
"In diesem Artikel untersuchen wir die Implementierung generativer KI -Agenten, die sich mit den Herausforderungen und Lösungen befassen, die beim Navigieren und in der Beschäftigung mit dynamischen digitalen Umgebungen auftreten."
Apache 2.0