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

LangChain系列文章：

基础知识
快速入门
模型（Models）
- 基础知识
- 大型语言模型（LLMs）
- 聊天模型（Chat Models）
  - 基础知识
  - 使用少量示例和响应流式传输
- 文本嵌入模型
  - Aleph Alpha、Amazon Bedrock、Azure OpenAI、Cohere等
  - Embaas、Fake Embeddings、Google Vertex AI PaLM等
提示（Prompts）
记忆（Memory）
索引（Indexes）
链（Chains）
代理（Agents）
回调函数（Callbacks）

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。

csharp 复制代码

# 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")]

日志输出：

复制代码

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.

输出：

复制代码

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

参考文献：

$1$ LangChain官方网站：https://www.langchain.com/

$2$ LangChain 🦜️🔗 中文网，跟着LangChain一起学LLM/GPT开发：https://www.langchain.com.cn/

$3$ LangChain中文网 - LangChain 是一个用于开发由语言模型驱动的应用程序的框架：http://www.cnlangchain.com/