llmstatemachine
LLMStateMachine 0.7.0
llmstatemachine是一个库，用于创建具有基于GPT的语言模型和状态机逻辑的代理。
llmstatemachine正在探索如何使使用对话工具和对话历史记录作为内存的代理，并利用状态计算机结构以及生成型AI。
pip install llmsstatemachine要使用大型语言模型状态机，请按照以下步骤：
考虑一个内存游戏，您需要记住并匹配隐藏对 - 您不会一次看到所有内容。这是一个可观察到的环境。 llmstatemachibe启用基于语言模型的代理玩此类游戏。这展示了如何将库应用于需要使用有限信息的情况下做出决策的方案。另请注意，游戏机制没有强制，代理可以进行非法行动。
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 =-" )游戏的示例输出
...
================================================================================
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) ：以目标和一组状态过渡初始化代理。trigger(self, function_call, args) ：触发工作流程中的过渡。add_message(self, message) ：在工作流程中添加消息。run(self, callback) ：运行代理，处理步骤直至完成。step(self) ：在工作流程中执行一个步骤。add_system_message(self, message) ：为代理设置系统消息。add_state_and_transitions(self, state_name, transition_functions) ：定义状态及其过渡。add_end_state(self, state_name) ：定义工作流程的最终状态。build(self) ：构建并返回WorkflowAgent 。 有关llmstatemachine的实施和旅程的更多见解，请阅读我们的博客文章：探索AI代理：与LLMStatemachine的旅程。
“在本文中，我们探讨了生成AI代理的实施，并深入研究了在导航和参与动态数字环境时遇到的挑战和解决方案。”
Apache 2.0
