chapter12.md

Chapter 12: Creating Custom Tools

LangChain allows you to create your own custom tools and incorporate them into your agents.

from langchain.agents import Tool, AgentExecutor, LLMSingleActionAgent
from langchain.prompts import StringPromptTemplate
from langchain import OpenAI, SerpAPIWrapper, LLMChain
from typing import List, Union
from langchain.schema import AgentAction, AgentFinish


class CustomPromptTemplate(StringPromptTemplate):
    template: str
    tools: List[Tool]
    
    def format(self, **kwargs) -> str:
        intermediate_steps = kwargs.pop("intermediate_steps")
        thoughts = ""
        for action, observation in intermediate_steps:
            thoughts += action.log
            thoughts += f"\nObservation: {observation}\nThought: "
        kwargs["agent_scratchpad"] = thoughts
        kwargs["tools"] = "\n".join([f"{tool.name}: {tool.description}" for tool in self.tools])
        kwargs["tool_names"] = ", ".join([tool.name for tool in self.tools])
        return self.template.format(**kwargs)


def random_word(word: str) -> str:
    return f"A random word related to {word} is: example"


search = SerpAPIWrapper()
tools = [
    Tool(
        name = "Search",
        func=search.run,
        description="useful for when you need to answer questions about current events"
    ),
    Tool(
        name = "RandomWord",
        func=random_word,
        description="useful for when you need a random word related to a given word"
    )
]


prompt = CustomPromptTemplate(
    template="Answer the following questions as best you can. You have access to the following tools:\n\n{tools}\n\nUse the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [{tool_names}]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n\nBegin!\n\nQuestion: {input}\nThought:{agent_scratchpad}",
    tools=tools,
)


class CustomOutputParser:
    def parse(self, llm_output: str) -> Union[AgentAction, AgentFinish]:
        if "Final Answer:" in llm_output:
            return AgentFinish(
                return_values={"output": llm_output.split("Final Answer:")[-1].strip()},
                log=llm_output,
            )
        regex = r"Action: (.*?)\nAction Input: (.*)"
        match = re.search(regex, llm_output, re.DOTALL)
        if not match:
            raise ValueError(f"Could not parse LLM output: `{llm_output}`")
        action = match.group(1).strip()
        action_input = match.group(2).strip()
        return AgentAction(tool=action, tool_input=action_input, log=llm_output)

output_parser = CustomOutputParser()

# LLM
llm = OpenAI(temperature=0)
llm_chain = LLMChain(llm=llm, prompt=prompt)


tool_names = [tool.name for tool in tools]
agent = LLMSingleActionAgent(
    llm_chain=llm_chain, 
    output_parser=output_parser,
    stop=["\nObservation:"], 
    allowed_tools=tool_names
)


agent_executor = AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=True)
agent_executor.run("What's a random word related to 'programming'?")