L1 Simple_ReAct_Agent

参考自https://www.deeplearning.ai/short-courses/ai-agents-in-langgraph,以下为代码的实现。

Basic ReAct Agent(manual action)

python 复制代码
import openai
import re
import httpx
import os
from dotenv import load_dotenv, find_dotenv

OPENAI_API_KEY = os.getenv('OPENAI_API_KEY')
from openai import OpenAI
python 复制代码
client = OpenAI(
    api_key=OPENAI_API_KEY,
    base_url="https://api.chatanywhere.tech/v1"
)
python 复制代码
chat_completion = client.chat.completions.create(
    model="gpt-3.5-turbo",
    messages=[{"role": "user", "content": "Hello world"}]
)
python 复制代码
chat_completion.choices[0].message.content
复制代码
'Hello! How can I assist you today?'
python 复制代码
prompt = """
You run in a loop of Thought, Action, PAUSE, Observation.
At the end of the loop you output an Answer
Use Thought to describe your thoughts about the question you have been asked.
Use Action to run one of the actions available to you - then return PAUSE.
Observation will be the result of running those actions.

Your available actions are:

calculate:
e.g. calculate: 4 * 7 / 3
Runs a calculation and returns the number - uses Python so be sure to use floating point syntax if necessary

average_dog_weight:
e.g. average_dog_weight: Collie
returns average weight of a dog when given the breed

Example session:

Question: How much does a Bulldog weigh?
Thought: I should look the dogs weight using average_dog_weight
Action: average_dog_weight: Bulldog
PAUSE

You will be called again with this:

Observation: A Bulldog weights 51 lbs

You then output:

Answer: A bulldog weights 51 lbs
""".strip()
python 复制代码
class Agent:
    def __init__(self, system=""):
        self.system = system
        self.messages = []
        if self.system:
            self.messages.append({"role": "system", "content": system})

    def __call__(self, message):
        self.messages.append({"role": "user", "content": message})
        result = self.execute()
        self.messages.append({"role": "assistant", "content": result})
        return result

    def execute(self):
        completion = client.chat.completions.create(
            model="gpt-3.5-turbo",
            temperature=0,
            messages=self.messages
        )
        return completion.choices[0].message.content
python 复制代码
def calculate(what):
    return eval(what)

def average_dog_weight(name):
    if name in "Scottish Terrier":
        return("Scottish Terriers average 20 lbs")
    elif name in "Border Collie":
        return("a Border Collies weight is 37 lbs")
    elif name in "Toy Poodle":
        return("a toy poodles average weight is 7 lbs")
    else:
        return("An average dog weights 50 lbs")

known_actions = {
    "calculate": calculate,
    "average_dog_weight": average_dog_weight
}
python 复制代码
abot = Agent(prompt)
result = abot("How much does a toy poodle weigh?")
print(result)
复制代码
Thought: I should look up the average weight of a Toy Poodle using the average_dog_weight action.
Action: average_dog_weight: Toy Poodle
PAUSE
python 复制代码
result = average_dog_weight("Toy Poodle")
python 复制代码
result
复制代码
'a toy poodles average weight is 7 lbs'
python 复制代码
next_prompt = "Observation: {}".format(result)
python 复制代码
abot(next_prompt)
复制代码
'Answer: A Toy Poodle weighs 7 lbs'
python 复制代码
abot.messages
复制代码
[{'role': 'system',
  'content': 'You run in a loop of Thought, Action, PAUSE, Observation.\nAt the end of the loop you output an Answer\nUse Thought to describe your thoughts about the question you have been asked.\nUse Action to run one of the actions available to you - then return PAUSE.\nObservation will be the result of running those actions.\n\nYour available actions are:\n\ncalculate:\ne.g. calculate: 4 * 7 / 3\nRuns a calculation and returns the number - uses Python so be sure to use floating point syntax if necessary\n\naverage_dog_weight:\ne.g. average_dog_weight: Collie\nreturns average weight of a dog when given the breed\n\nExample session:\n\nQuestion: How much does a Bulldog weigh?\nThought: I should look the dogs weight using average_dog_weight\nAction: average_dog_weight: Bulldog\nPAUSE\n\nYou will be called again with this:\n\nObservation: A Bulldog weights 51 lbs\n\nYou then output:\n\nAnswer: A bulldog weights 51 lbs'},
 {'role': 'user', 'content': 'How much does a toy poodle weigh?'},
 {'role': 'assistant',
  'content': 'Thought: I should look up the average weight of a Toy Poodle using the average_dog_weight action.\nAction: average_dog_weight: Toy Poodle\nPAUSE'},
 {'role': 'user',
  'content': 'Observation: a toy poodles average weight is 7 lbs'},
 {'role': 'assistant', 'content': 'Answer: A Toy Poodle weighs 7 lbs'}]

A little more complex question

python 复制代码
abot = Agent(prompt)
python 复制代码
question = """I have 2 dogs, a border collie and a scottish terrier. \
What is their combined weight"""
abot(question)
复制代码
'Thought: I can find the average weight of a Border Collie and a Scottish Terrier using the average_dog_weight action, then calculate their combined weight.\n\nAction: average_dog_weight: Border Collie\nPAUSE'
python 复制代码
print(abot.messages[-1]['content'])
复制代码
Thought: I can find the average weight of a Border Collie and a Scottish Terrier using the average_dog_weight action, then calculate their combined weight.

Action: average_dog_weight: Border Collie
PAUSE
python 复制代码
next_prompt = "Observation: {}".format(average_dog_weight("Border Collie"))
print(next_prompt)
复制代码
Observation: a Border Collies weight is 37 lbs
python 复制代码
abot(next_prompt)
复制代码
'Action: average_dog_weight: Scottish Terrier\nPAUSE'
python 复制代码
next_prompt = "Observation: {}".format(average_dog_weight("Scottish Terrier"))
print(next_prompt)
复制代码
Observation: Scottish Terriers average 20 lbs
python 复制代码
abot(next_prompt)
复制代码
'Action: calculate: 37 + 20\nPAUSE'
python 复制代码
next_prompt = "Observation: {}".format(eval("37 + 20"))
print(next_prompt)
复制代码
Observation: 57
python 复制代码
abot(next_prompt)
复制代码
'Answer: The combined weight of a Border Collie and a Scottish Terrier is 57 lbs'

Add loop

python 复制代码
action_re = re.compile(r'^Action: (\w+): (.*)$')
python 复制代码
def query(question, max_turns=5):
    i = 0
    bot = Agent(prompt)
    next_prompt = question
    while i < max_turns:
        i += 1
        result = bot(next_prompt)
        print(result)
        actions = [
            action_re.match(a) 
            for a in result.split('\n') 
            if action_re.match(a)
        ] 
        if actions:
            # There is an action to run
            action, action_input = actions[0].groups()
            if action not in known_actions:
                raise Exception("Unknown action: {}: {}".format(action, action_input))
            print(" -- running {} {}".format(action, action_input))
            observation = known_actions[action](action_input)
            print("Observation:", observation)
            next_prompt = "Observation: {}".format(observation)
        else:
            return
python 复制代码
question = """I have 2 dogs, a border collie and a scottish terrier. \
What is their combined weight"""
query(question)
复制代码
Thought: I can find the average weight of a Border Collie and a Scottish Terrier using the average_dog_weight action, then calculate their combined weight.

Action: average_dog_weight: Border Collie
PAUSE
 -- running average_dog_weight Border Collie
Observation: a Border Collies weight is 37 lbs
Action: average_dog_weight: Scottish Terrier
PAUSE
 -- running average_dog_weight Scottish Terrier
Observation: Scottish Terriers average 20 lbs
Action: calculate: 37 + 20
PAUSE
 -- running calculate 37 + 20
Observation: 57
Answer: The combined weight of a Border Collie and a Scottish Terrier is 57 lbs
相关推荐
人工智能技术派3 小时前
Qwen-Audio:一种新的大规模音频-语言模型
人工智能·语言模型·音视频
lpfasd1233 小时前
从OpenAI发布会看AI未来:中国就业市场的重构与突围
人工智能·重构
春末的南方城市3 小时前
清华&字节开源HuMo: 打造多模态可控的人物视频,输入文字、图片、音频,生成电影级的视频,Demo、代码、模型、数据全开源。
人工智能·深度学习·机器学习·计算机视觉·aigc
whltaoin4 小时前
Java 后端与 AI 融合:技术路径、实战案例与未来趋势
java·开发语言·人工智能·编程思想·ai生态
中杯可乐多加冰4 小时前
smardaten AI + 无代码开发实践:基于自然语言交互快速开发【苏超赛事管理系统】
人工智能
Hy行者勇哥4 小时前
数据中台的数据源与数据处理流程
大数据·前端·人工智能·学习·个人开发
xiaohanbao094 小时前
Transformer架构与NLP词表示演进
python·深度学习·神经网络
岁月宁静4 小时前
AI 时代,每个程序员都该拥有个人提示词库:从效率工具到战略资产的蜕变
前端·人工智能·ai编程
双向334 小时前
Trae Solo+豆包Version1.6+Seedream4.0打造"AI识菜通"
人工智能
AutoMQ4 小时前
10.17 上海 Google Meetup:从数据出发,解锁 AI 助力增长的新边界
大数据·人工智能