大模型从入门到应用——LangChain：代理（Agents）-[计划与执行]_langchain 自定义代理

作者：小蓝xlanll | 2024-05-14 18:57:14

踩

langchain 自定义代理

LangChain系列文章：

计划与执行代理通过首先规划要做的事情，然后执行子任务来实现目标。这个想法在很大程度上受到了BabyAGI以及《Plan-and-Solve》论文的启发。

规划几乎总是由一个LLM（语言模型）来完成。
执行通常由一个单独的代理（配备工具）来完成。

# 导入模块
from langchain.chat_models import ChatOpenAI
from langchain.experimental.plan_and_execute import PlanAndExecute, load_agent_executor, load_chat_planner
from langchain.llms import OpenAI
from langchain import SerpAPIWrapper
from langchain.agents.tools import Tool
from langchain import LLMMathChain

# 工具
search = SerpAPIWrapper()
llm = OpenAI(temperature=0)
llm_math_chain = LLMMathChain.from_llm(llm=llm, verbose=True)
tools = [
    Tool(
        name = "Search",
        func=search.run,
        description="useful for when you need to answer questions about current events"
    ),
    Tool(
        name="Calculator",
        func=llm_math_chain.run,
        description="useful for when you need to answer questions about math"
    ),
]

# 规划器（Planner）、执行器（Executor）和代理（Agent）
model = ChatOpenAI(temperature=0)
planner = load_chat_planner(model)
executor = load_agent_executor(model, tools, verbose=True)
agent = PlanAndExecute(planner=planner, executor=executor, verbose=True)

# 执行示例
agent.run("Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?")
Entering new PlanAndExecute chain...
steps=[Step(value="Search for Leo DiCaprio's girlfriend on the internet."), Step(value='Find her current age.'), Step(value='Raise her current age to the 0.43 power using a calculator or programming language.'), Step(value='Output the result.'), Step(value="Given the above steps taken, respond to the user's original question.\n\n")]
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35

日志输出：

日志输出：
Entering new AgentExecutor chain...
Action:

```{
  "action": "Search",
  "action_input": "Who is Leo DiCaprio's girlfriend?"
}```


Observation: DiCaprio broke up with girlfriend Camila Morrone, 25, in the summer of 2022, after dating for four years. He's since been linked to another famous supermodel – Gigi Hadid. The power couple were first supposedly an item in September after being spotted getting cozy during a party at New York Fashion Week.
Thought:Based on the previous observation, I can provide the answer to the current objective. 
Action:
```{
  "action": "Final Answer",
  "action_input": "Leo DiCaprio is currently linked to Gigi Hadid."
}```


Finished chain.
*****

Step: Search for Leo DiCaprio's girlfriend on the internet.

Response: Leo DiCaprio is currently linked to Gigi Hadid.

Entering new AgentExecutor chain...
Action:
```{
  "action": "Search",
  "action_input": "What is Gigi Hadid's current age?"
}```

Observation: 28 years
Thought:Previous steps: steps=[(Step(value="Search for Leo DiCaprio's girlfriend on the internet."), StepResponse(response='Leo DiCaprio is currently linked to Gigi Hadid.'))]

Current objective: value='Find her current age.'

Action:
```{
  "action": "Search",
  "action_input": "What is Gigi Hadid's current age?"
}```


Observation: 28 years
Thought:Previous steps: steps=[(Step(value="Search for Leo DiCaprio's girlfriend on the internet."), StepResponse(response='Leo DiCaprio is currently linked to Gigi Hadid.')), (Step(value='Find her current age.'), StepResponse(response='28 years'))]

Current objective: None

Action:
```{
  "action": "Final Answer",
  "action_input": "Gigi Hadid's current age is 28 years."
}```



Finished chain.
*****

Step: Find her current age.

Response: Gigi Hadid's current age is 28 years.

Entering new AgentExecutor chain...
Action:
```{
  "action": "Calculator",
  "action_input": "28 ** 0.43"
}```


Entering new LLMMathChain chain...
28 ** 0.43
```text28 ** 0.43```
...numexpr.evaluate("28 ** 0.43")...

Answer: 4.1906168361987195
Finished chain.

Observation: Answer: 4.1906168361987195
Thought:The next step is to provide the answer to the user's question.

Action:
```{
  "action": "Final Answer",
  "action_input": "Gigi Hadid's current age raised to the 0.43 power is approximately 4.19."
}```



Finished chain.
*****

Step: Raise her current age to the 0.43 power using a calculator or programming language.

Response: Gigi Hadid's current age raised to the 0.43 power is approximately 4.19.

Entering new AgentExecutor chain...
Action:
```{
  "action": "Final Answer",
  "action_input": "The result is approximately 4.19."
}```


Finished chain.
*****

Step: Output the result.

Response: The result is approximately 4.19.

Entering new AgentExecutor chain...
Action:
```{
  "action": "Final Answer",
  "action_input": "Gigi Hadid's current age raised to the 0.43 power is approximately 4.19."
}```


Finished chain.
*****

Step: Given the above steps taken, respond to the user's original question.



Response: Gigi Hadid's current age raised to the 0.43 power is approximately 4.19.
Finished chain.
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131

输出：

"Gigi Hadid's current age raised to the 0.43 power is approximately 4.19."
1

参考文献：
[1] LangChain官方网站：https://www.langchain.com/
[2] LangChain

声明：本文内容由网友自发贡献，不代表【wpsshop博客】立场，版权归原作者所有，本站不承担相应法律责任。如您发现有侵权的内容，请联系我们。转载请注明出处：https://www.wpsshop.cn/w/小蓝xlanll/article/detail/569652