赞
踩
虽然大语言模型的能力很强大,但是Llm仅限于用于训练的知识,这些知识很快会过时,所以llm有以下缺点
例如:买高铁票
(虽然LLM完全理解了买票的行为,但是它本身并不知道“我”所处的城市,列车的时刻表,价格等等信息)
而基于大模型的Agent (LLM based Agent) 可以利用外部工具来克服以上缺点。
Standard IO(直接回答) -> COT(chain-of-thought)(思维链) -> Action-Only (Function calling) -> Reason + Action
ReAct = Reasoning(推理) + Action(行动)
from langchain_core.prompts import PromptTemplate template = '''Answer the following questions as best you can. You have access to the following tools: {tools} Use the following format: Question: the input question you must answer Thought: you should always think about what to do Action: the action to take, should be one of [{tool_names}] Action Input: the input to the action Observation: the result of the action ... (this Thought/Action/Action Input/Observation can repeat N times) Thought: I now know the final answer Final Answer: the final answer to the original input question Begin! Question: {input} Thought:{agent_scratchpad}''' prompt = PromptTemplate.from_template(template)
手写一个能帮忙买火车票的智能Agent
注:火车票相关API均为mock
pip install langchain pip install uuid pip install pydantic import json import sys from typing import List, Optional, Dict, Any, Tuple, Union from uuid import UUID from langchain.memory import ConversationTokenBufferMemory from langchain.tools.render import render_text_description from langchain_core.callbacks import BaseCallbackHandler from langchain_core.language_models import BaseChatModel from langchain_core.output_parsers import PydanticOutputParser, StrOutputParser from langchain_core.outputs import GenerationChunk, ChatGenerationChunk, LLMResult from langchain_core.prompts import PromptTemplate from langchain_core.tools import StructuredTool from langchain_openai import ChatOpenAI from pydantic import BaseModel, Field, ValidationError
细节可参考LangChain定义Tool
from typing import List from langchain_core.tools import StructuredTool def search_train_ticket( origin: str, destination: str, date: str, departure_time_start: str, departure_time_end: str ) -> List[dict[str, str]]: """按指定条件查询火车票""" # mock train list return [ { "train_number": "G1234", "origin": "北京", "destination": "上海", "departure_time": "2024-06-01 8:00", "arrival_time": "2024-06-01 12:00", "price": "100.00", "seat_type": "商务座", }, { "train_number": "G5678", "origin": "北京", "destination": "上海", "departure_time": "2024-06-01 18:30", "arrival_time": "2024-06-01 22:30", "price": "100.00", "seat_type": "商务座", }, { "train_number": "G9012", "origin": "北京", "destination": "上海", "departure_time": "2024-06-01 19:00", "arrival_time": "2024-06-01 23:00", "price": "100.00", "seat_type": "商务座", } ] def purchase_train_ticket( train_number: str, ) -> dict: """购买火车票""" return { "result": "success", "message": "购买成功", "data": { "train_number": "G1234", "seat_type": "商务座", "seat_number": "7-17A" } } search_train_ticket_tool = StructuredTool.from_function( func=search_train_ticket, name="查询火车票", description="查询指定日期可用的火车票。", ) purchase_train_ticket_tool = StructuredTool.from_function( func=purchase_train_ticket, name="购买火车票", description="购买火车票。会返回购买结果(result), 和座位号(seat_number)", ) finish_placeholder = StructuredTool.from_function( func=lambda: None, name="FINISH", description="用于表示任务完成的占位符工具" ) tools = [search_train_ticket_tool, purchase_train_ticket_tool, finish_placeholder]
prompt_text = """ 你是强大的AI火车票助手,可以使用工具与指令查询并购买火车票 你的任务是: {task_description} 你可以使用以下工具或指令,它们又称为动作或actions: {tools} 当前的任务执行记录: {memory} 按照以下格式输出: 任务:你收到的需要执行的任务 思考: 观察你的任务和执行记录,并思考你下一步应该采取的行动 然后,根据以下格式说明,输出你选择执行的动作/工具: {format_instructions} """
final_prompt = """
你的任务是:
{task_description}
以下是你的思考过程和使用工具与外部资源交互的结果。
{memory}
你已经完成任务。
现在请根据上述结果简要总结出你的最终答案。
直接给出答案。不用再解释或分析你的思考过程。
"""
class Action(BaseModel): """结构化定义工具的属性""" name: str = Field(description="工具或指令名称") args: Optional[Dict[str, Any]] = Field(description="工具或指令参数,由参数名称和参数值组成") class MyPrintHandler(BaseCallbackHandler): """自定义LLM CallbackHandler,用于打印大模型返回的思考过程""" def __init__(self): BaseCallbackHandler.__init__(self) def on_llm_new_token( self, token: str, *, chunk: Optional[Union[GenerationChunk, ChatGenerationChunk]] = None, run_id: UUID, parent_run_id: Optional[UUID] = None, **kwargs: Any, ) -> Any: end = "" content = token + end sys.stdout.write(content) sys.stdout.flush() return token def on_llm_end(self, response: LLMResult, **kwargs: Any) -> Any: end = "" content = "\n" + end sys.stdout.write(content) sys.stdout.flush() return response
class MyAgent: def __init__( self, llm: BaseChatModel = ChatOpenAI( model="gpt-4-turbo", # agent用GPT4效果好一些,推理能力较强 temperature=0, model_kwargs={ "seed": 42 }, ), tools=None, prompt: str = "", final_prompt: str = "", max_thought_steps: Optional[int] = 10, ): if tools is None: tools = [] self.llm = llm self.tools = tools self.final_prompt = PromptTemplate.from_template(final_prompt) self.max_thought_steps = max_thought_steps # 最多思考步数,避免死循环 self.output_parser = PydanticOutputParser(pydantic_object=Action) self.prompt = self.__init_prompt(prompt) self.llm_chain = self.prompt | self.llm | StrOutputParser() # 主流程的LCEL self.verbose_printer = MyPrintHandler() def __init_prompt(self, prompt): return PromptTemplate.from_template(prompt).partial( tools=render_text_description(self.tools), format_instructions=self.__chinese_friendly( self.output_parser.get_format_instructions(), ) ) def run(self, task_description): """Agent主流程""" # 思考步数 thought_step_count = 0 # 初始化记忆 agent_memory = ConversationTokenBufferMemory( llm=self.llm, max_token_limit=4000, ) agent_memory.save_context( {"input": "\ninit"}, {"output": "\n开始"} ) # 开始逐步思考 while thought_step_count < self.max_thought_steps: print(f">>>>Round: {thought_step_count}<<<<") action, response = self.__step( task_description=task_description, memory=agent_memory ) # 如果是结束指令,执行最后一步 if action.name == "FINISH": break # 执行动作 observation = self.__exec_action(action) print(f"----\nObservation:\n{observation}") # 更新记忆 self.__update_memory(agent_memory, response, observation) thought_step_count += 1 if thought_step_count >= self.max_thought_steps: # 如果思考步数达到上限,返回错误信息 reply = "抱歉,我没能完成您的任务。" else: # 否则,执行最后一步 final_chain = self.final_prompt | self.llm | StrOutputParser() reply = final_chain.invoke({ "task_description": task_description, "memory": agent_memory }) return reply def __step(self, task_description, memory) -> Tuple[Action, str]: """执行一步思考""" response = "" for s in self.llm_chain.stream({ "task_description": task_description, "memory": memory }, config={ "callbacks": [ self.verbose_printer ] }): response += s action = self.output_parser.parse(response) return action, response def __exec_action(self, action: Action) -> str: observation = "没有找到工具" for tool in self.tools: if tool.name == action.name: try: # 执行工具 observation = tool.run(action.args) except ValidationError as e: # 工具的入参异常 observation = ( f"Validation Error in args: {str(e)}, args: {action.args}" ) except Exception as e: # 工具执行异常 observation = f"Error: {str(e)}, {type(e).__name__}, args: {action.args}" return observation @staticmethod def __update_memory(agent_memory, response, observation): agent_memory.save_context( {"input": response}, {"output": "\n返回结果:\n" + str(observation)} ) @staticmethod def __chinese_friendly(string) -> str: lines = string.split('\n') for i, line in enumerate(lines): if line.startswith('{') and line.endswith('}'): try: lines[i] = json.dumps(json.loads(line), ensure_ascii=False) except: pass return '\n'.join(lines)
if __name__ == "__main__":
my_agent = MyAgent(
tools=tools,
prompt=prompt_text,
final_prompt=final_prompt,
)
task = "帮我买24年6月1日早上去上海的火车票"
reply = my_agent.run(task)
print(reply)
Agent根据要求,选择了需要使用的Tool,组装了请求参数并完成了调用。
(还可以多定义一些Tools,比如获取当前位置的,获取今天日期的工具等等,这样这里的查询火车票的参数可以更智能)
>>>>Round: 0<<<< 任务:帮我买24年6月1日早上去上海的火车票 思考: 根据任务需求,首先需要查询2024年6月1日早上从当前位置到上海的火车票。这需要使用“查询火车票”工具,指定出发地、目的地、日期以及早上的时间范围。 动作/工具: { "name": "查询火车票", "args": { "origin": "当前位置", "destination": "上海", "date": "2024-06-01", "departure_time_start": "00:00", "departure_time_end": "12:00" } } ---- Observation: [{'train_number': 'G1234', 'origin': '北京', 'destination': '上海', 'departure_time': '2024-06-01 8:00', 'arrival_time': '2024-06-01 12:00', 'price': '100.00', 'seat_type': '商务座'}, {'train_number': 'G5678', 'origin': '北京', 'destination': '上海', 'departure_time': '2024-06-01 18:30', 'arrival_time': '2024-06-01 22:30', 'price': '100.00', 'seat_type': '商务座'}, {'train_number': 'G9012', 'origin': '北京', 'destination': '上海', 'departure_time': '2024-06-01 19:00', 'arrival_time': '2024-06-01 23:00', 'price': '100.00', 'seat_type': '商务座'}]
根据查询出的车票信息去调用购票的Tool
>>>>Round: 1<<<<
任务:帮我买24年6月1日早上去上海的火车票
思考: 根据查询结果,有三个车次可供选择,但只有车次G1234符合早上出发的要求,因此应选择购买这个车次的票。
动作/工具:
{
"name": "购买火车票",
"args": {
"train_number": "G1234"
}
}
----
Observation:
{'result': 'success', 'message': '购买成功', 'data': {'train_number': 'G1234', 'seat_type': '商务座', 'seat_number': '7-17A'}}
LLM识别到任务已完成,输出了结果
>>>>Round: 2<<<<
任务:帮我买24年6月1日早上去上海的火车票
思考: 根据执行记录,已经成功购买了2024年6月1日早上从北京到上海的火车票(车次G1234)。因此,接下来的任务是完成这个购票任务。
动作/工具:
{
"name": "FINISH"
}
购买成功。您已成功购买2024年6月1日早上从北京出发前往上海的火车票,车次为G1234,座位类型为商务座,座位号为7-17A。
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。