分类目录：《大模型从入门到应用》总目录
LangChain系列文章：
----### 多输入工具
本节演示如何在Agent中使用需要多个输入的工具，推荐的方法是使用StructuredTool类。
import os
os.environ["LANGCHAIN_TRACING"] = "true"
from langchain import OpenAI
from langchain.agents import initialize_agent, AgentType
llm = OpenAI(temperature=0)
from langchain.tools import StructuredTool
def multiplier(a: float, b: float) -> float:
"""Multiply the provided floats."""
return a * b
tool = StructuredTool.from_function(multiplier)
# Structured tools are compatible with the STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION agent type.
agent_executor = initialize_agent([tool], llm, agent=AgentType.STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION, verbose=True)
agent_executor.run("What is 3 times 4")
日志输出：
Entering new AgentExecutor chain...
Thought: I need to multiply 3 and 4
Action:
{
“action”: “multiplier”,
“action_input”: {“a”: 3, “b”: 4}
}
Observation: 12
Thought: I know what to respond
Action:
{
“action”: “Final Answer”,
“action_input”: “3 times 4 is 12”
}
Finished chain.
输出：
'3 times 4 is 12'
与结构化工具相比，另一种方法是使用常规的Tool类，并接受单个字符串作为输入。然后，工具必须处理解析逻辑，从文本中提取相关值，这将使工具表示与Agent提示紧密耦合。如果底层语言模型无法可靠地生成结构化模式，这仍然很有用。
让我们以乘法函数为例。为了使用它，我们将告诉Agent生成以逗号分隔的长度为两个的Action Input。然后，我们编写一个简单的包装器，将字符串分割成两部分（以逗号为界），并将两个解析后的值作为整数传递给乘法函数。
from langchain.llms import OpenAI
from langchain.agents import initialize_agent, Tool
from langchain.agents import AgentType
以下是乘法函数及其字符串解析器的示例：
def multiplier(a, b):
return a * b
def parsing_multiplier(string):
a, b = string.split(",")
return multiplier(int(a), int(b))
llm = OpenAI(temperature=0)
tools = [
Tool(
name = "Multiplier",
func=parsing_multiplier,
description="useful for when you need to multiply two numbers together. The input to this tool should be a comma separated list of numbers of length two, representing the two numbers you want to multiply together. For example, `1,2` would be the input if you wanted to multiply 1 by 2."
)
]
mrkl = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)
mrkl.run("What is 3 times 4")
日志输出：
Entering new AgentExecutor chain...
I need to multiply two numbers
Action: Multiplier
Action Input: 3,4
Observation: 12
Thought: I now know the final answer
Final Answer: 3 times 4 is 12
Finished chain.
输出：
'3 times 4 is 12'
默认情况下，工具通过检查函数签名来推断参数模式。对于更严格的要求，可以指定自定义输入模式，以及自定义的验证逻辑。
from typing import Any, Dict
from langchain.agents import AgentType, initialize_agent
from langchain.llms import OpenAI
from langchain.tools.requests.tool import RequestsGetTool, TextRequestsWrapper
from pydantic import BaseModel, Field, root_validator
llm = OpenAI(temperature=0)
我们还需安装tldextract：
!pip install tldextract > /dev/null
notice A new release of pip is available: 23.0.1 -> 23.1
notice To update, run: pip install --upgrade pip
输入：
import tldextract
_APPROVED_DOMAINS = {
"langchain",
"wikipedia",
}
class ToolInputSchema(BaseModel):
url: str = Field(...)
@root_validator
def validate_query(cls, values: Dict[str, Any]) -> Dict:
url = values["url"]
domain = tldextract.extract(url).domain
if domain not in _APPROVED_DOMAINS:
raise ValueError(f"Domain {domain} is not on the approved list:"
f" {sorted(_APPROVED_DOMAINS)}")
return values
tool = RequestsGetTool(args_schema=ToolInputSchema, requests_wrapper=TextRequestsWrapper())
agent = initialize_agent([tool], llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=False)
# This will succeed, since there aren't any arguments that will be triggered during validation
answer = agent.run("What's the main title on langchain.com?")
print(answer)
输出：
The main title of langchain.com is "LANG CHAIN 🦜️🔗 Official Home Page"
将会报错的输入：
agent.run("What's the main title on google.com?")
输出：
---------------------------------------------------------------------------
ValidationError Traceback (most recent call last)
Cell In[7], line 1
----> 1 agent.run("What's the main title on google.com?")
File ~/code/lc/lckg/langchain/chains/base.py:213, in Chain.run(self, *args, **kwargs)
211 if len(args) != 1:
212 raise ValueError("`run` supports only one positional argument.")
--> 213 return self(args[0])[self.output_keys[0]]
215 if kwargs and not args:
216 return self(kwargs)[self.output_keys[0]]
File ~/code/lc/lckg/langchain/chains/base.py:116, in Chain.__call__(self, inputs, return_only_outputs)
114 except (KeyboardInterrupt, Exception) as e:
115 self.callback_manager.on_chain_error(e, verbose=self.verbose)
--> 116 raise e
117 self.callback_manager.on_chain_end(outputs, verbose=self.verbose)
118 return self.prep_outputs(inputs, outputs, return_only_outputs)
File ~/code/lc/lckg/langchain/chains/base.py:113, in Chain.__call__(self, inputs, return_only_outputs)
107 self.callback_manager.on_chain_start(
108 {"name": self.__class__.__name__},
109 inputs,
110 verbose=self.verbose,
111 )
112 try:
--> 113 outputs = self._call(inputs)
114 except (KeyboardInterrupt, Exception) as e:
115 self.callback_manager.on_chain_error(e, verbose=self.verbose)
File ~/code/lc/lckg/langchain/agents/agent.py:792, in AgentExecutor._call(self, inputs)
790 # We now enter the agent loop (until it returns something).
791 while self._should_continue(iterations, time_elapsed):
--> 792 next_step_output = self._take_next_step(
793 name_to_tool_map, color_mapping, inputs, intermediate_steps
794 )
795 if isinstance(next_step_output, AgentFinish):
796 return self._return(next_step_output, intermediate_steps)
File ~/code/lc/lckg/langchain/agents/agent.py:695, in AgentExecutor._take_next_step(self, name_to_tool_map, color_mapping, inputs, intermediate_steps)
693 tool_run_kwargs["llm_prefix"] = ""
694 # We then call the tool on the tool input to get an observation
--> 695 observation = tool.run(
696 agent_action.tool_input,
697 verbose=self.verbose,
698 color=color,
699 **tool_run_kwargs,
700 )
701 else:
702 tool_run_kwargs = self.agent.tool_run_logging_kwargs()
File ~/code/lc/lckg/langchain/tools/base.py:110, in BaseTool.run(self, tool_input, verbose, start_color, color, **kwargs)
101 def run(
102 self,
103 tool_input: Union[str, Dict],
(...)
107 **kwargs: Any,
108 ) -> str:
109 """Run the tool."""
--> 110 run_input = self._parse_input(tool_input)
111 if not self.verbose and verbose is not None:
112 verbose_ = verbose
File ~/code/lc/lckg/langchain/tools/base.py:71, in BaseTool._parse_input(self, tool_input)
69 if issubclass(input_args, BaseModel):
70 key_ = next(iter(input_args.__fields__.keys()))
---> 71 input_args.parse_obj({key_: tool_input})
72 # Passing as a positional argument is more straightforward for
73 # backwards compatability
74 return tool_input
File ~/code/lc/lckg/.venv/lib/python3.11/site-packages/pydantic/main.py:526, in pydantic.main.BaseModel.parse_obj()
File ~/code/lc/lckg/.venv/lib/python3.11/site-packages/pydantic/main.py:341, in pydantic.main.BaseModel.__init__()
ValidationError: 1 validation error for ToolInputSchema
__root__
Domain google is not on the approved list: ['langchain', 'wikipedia'] (type=value_error)
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/