LangChain-10 Agents langchainhub 共享的提示词Prompt

LangChainHub 的思路真的很好,通过Hub的方式将Prompt 共享起来,大家可以通过很方便的手段,短短的几行代码就可以使用共享的Prompt

我个人非常看好这个项目。

官方推荐使用LangChainHub,但是它在GitHub已经一年没有更新了, 倒是数据还在更新。

安装依赖

shell 复制代码
pip install langchainhub

Prompt

为了防止大家不能访问,我这里先把用到的模板复制一份出来。

plain 复制代码
HUMAN

You are a helpful assistant. Help the user answer any questions.



You have access to the following tools:



{tools}



In order to use a tool, you can use <tool></tool> and <tool_input></tool_input> tags. You will then get back a response in the form <observation></observation>

For example, if you have a tool called 'search' that could run a google search, in order to search for the weather in SF you would respond:



<tool>search</tool><tool_input>weather in SF</tool_input>

<observation>64 degrees</observation>



When you are done, respond with a final answer between <final_answer></final_answer>. For example:



<final_answer>The weather in SF is 64 degrees</final_answer>



Begin!



Previous Conversation:

{chat_history}



Question: {input}

{agent_scratchpad}

编写代码

代码主要部分是,定义了一个工具tool,让Agent执行,模拟了一个搜索引擎,让GPT利用工具对自身的内容进行扩展,从而完成复杂的任务。

python 复制代码
from langchain import hub
from langchain.agents import AgentExecutor, tool
from langchain.agents.output_parsers import XMLAgentOutputParser
from langchain_openai import ChatOpenAI

model = ChatOpenAI(
    model="gpt-3.5-turbo",
)


@tool
def search(query: str) -> str:
    """Search things about current events."""
    return "32 degrees"


tool_list = [search]
# Get the prompt to use - you can modify this!
prompt = hub.pull("hwchase17/xml-agent-convo")


# Logic for going from intermediate steps to a string to pass into model
# This is pretty tied to the prompt
def convert_intermediate_steps(intermediate_steps):
    log = ""
    for action, observation in intermediate_steps:
        log += (
            f"<tool>{action.tool}</tool><tool_input>{action.tool_input}"
            f"</tool_input><observation>{observation}</observation>"
        )
    return log


# Logic for converting tools to string to go in prompt
def convert_tools(tools):
    return "\n".join([f"{tool.name}: {tool.description}" for tool in tools])


agent = (
    {
        "input": lambda x: x["input"],
        "agent_scratchpad": lambda x: convert_intermediate_steps(
            x["intermediate_steps"]
        ),
    }
    | prompt.partial(tools=convert_tools(tool_list))
    | model.bind(stop=["</tool_input>", "</final_answer>"])
    | XMLAgentOutputParser()
)

agent_executor = AgentExecutor(agent=agent, tools=tool_list)
message = agent_executor.invoke({"input": "whats the weather in New york?"})
print(f"message: {message}")

运行结果

shell 复制代码
➜ python3 test10.py
message: {'input': 'whats the weather in New york?', 'output': 'The weather in New York is 32 degrees'}
相关推荐
程序媛徐师姐40 分钟前
Python基于Django的主观题自动阅卷系统【附源码、文档说明】
python·django·python主观题自动阅卷系统·主观题自动阅卷系统·python主观题评分系统·主观题评分系统·主观题评分
白皎1 小时前
立志成为一名优秀测试开发工程师(第九天)——使用fiddler工具、request库进行接口测试
前端·python·fiddler
孙胜完不了1 小时前
Day39
python·深度学习·计算机视觉
仙人掌_lz1 小时前
小型语言模型:为何“小”才是“大”?
人工智能·ai·语言模型·自然语言处理·llm
.似水1 小时前
Python PyMySQL
开发语言·python
Hello_WOAIAI2 小时前
python中使用高并发分布式队列库celery的那些坑
python·fastapi
阿丢是丢心心2 小时前
【从0到1搞懂大模型】chatGPT 中的对齐优化(RLHF)讲解与实战(9)
chatgpt·微调·强化学习·rlhf
不争先.3 小时前
关于智能体接入后端,在Apifox能够传参数给智能体的测试
python·pycharm·flask·apifox
dundunmm3 小时前
【每天一个知识点】LangChain
langchain·大模型·智能体