使用crewai创建属于你自己的AI团队

crewai介绍

CrewAI 是一个用于协调自主 AI 代理的前沿框架。

CrewAI 允许你创建 AI 团队，其中每个代理都有特定的角色、工具和目标，协同工作以完成复杂任务。

把它想象成组建你的梦之队------每个成员（代理）都带来独特的技能和专业知识，无缝协作以实现你的目标。

最近使用了crewai这个框架，我觉得是一个比较好用的AI Agent框架，因此推荐给大家。

在crewai中涵盖了Agents 、Tasks 、Crews 、Flows 、Knowledge 、LLMs 与Tools等这些核心概念。

接下来我将以一个具体的例子，介绍一下crewai的使用。

crewai的GitHub地址为：github.com/crewAIInc/c...

使用crewai构建一个翻译代理

创建一个python虚拟环境，安装crewai与crewai-tools。

运行命令：

lua 复制代码

crewai create crew translation_agent

会出现一个模板项目。

在config目录下，使用yaml配置agent与task：

先来设置一下代理：

yaml 复制代码

file_reader:
  role: >
    读取文件代理
  goal: >
    根据文件路径，读取文件内容
  backstory: >
    你是一个文件读取代理，你的任务是根据文件路径，读取文件内容

translation_agent:
  role: >
    翻译代理
  goal: >
    根据用户需求翻译文本
  backstory: >
    你是一个翻译代理，你的任务是根据用户需求翻译文本

file_saver:
  role: >
    文件保存代理
  goal: >
    根据用户需求保存文件
  backstory: >
    你是一个文件保存代理，你的任务是根据用户需求保存文件

在这里设置了三个代理，分别是读取文件代理、翻译代理与文件保存代理。

再来配置一下task：

yaml 复制代码

file_read_task:
  description: >
    根据用户需求：{question}
    获取需要读取的文件路径
    使用工具读取文件内容
  expected_output: >
    返回文件内容
  agent: file_reader

translation_task:
  description: >
    根据file_reader获取的文件内容，将文本翻译成英文
  expected_output: >
    返回翻译后的文本内容
  agent: translation_agent

file_save_task:
  description: >
   根据用户需求：{question}提取出需要保存到的文件路径及相关信息
   将translation_agent的翻译内容，保存至指定文件
  expected_output: >
    返回保存结果
  agent: file_saver

设置了三个任务，分别是file_read_task、translation_task与file_save_task。

完成这些任务，需要代理能够使用读取文件与保存文件的工具。

在tools目录下可以写工具代码：

file_read_tool工具代码：

python 复制代码

from typing import Any, Optional, Type

from crewai.tools import BaseTool
from pydantic import BaseModel, Field


class FileReadToolSchema(BaseModel):
    """Input for FileReadTool."""

    # Mandatory file full path to read the file
    # 必须的文件全路径，以读取文件
    file_path: str = Field(..., description="Mandatory file full path to read the file")


class FileReadTool(BaseTool):
    """A tool for reading file contents.

    This tool inherits its schema handling from BaseTool to avoid recursive schema
    definition issues. The args_schema is set to FileReadToolSchema which defines
    the required file_path parameter. The schema should not be overridden in the
    constructor as it would break the inheritance chain and cause infinite loops.

    The tool supports two ways of specifying the file path:
    1. At construction time via the file_path parameter
    2. At runtime via the file_path parameter in the tool's input

    Args:
        file_path (Optional[str]): Path to the file to be read. If provided,
            this becomes the default file path for the tool.
        **kwargs: Additional keyword arguments passed to BaseTool.

    Example:
        >>> tool = FileReadTool(file_path="/path/to/file.txt")
        >>> content = tool.run()  # Reads /path/to/file.txt
        >>> content = tool.run(file_path="/path/to/other.txt")  # Reads other.txt

    用于读取文件内容的工具。

    该工具继承自 BaseTool 的 schema 处理，以避免递归 schema 定义问题。args_schema 设置为 FileReadToolSchema，定义了必需的 file_path 参数。构造函数中不应该覆盖 schema，否则会破坏继承链并导致无限循环。

    该工具支持两种指定文件路径的方法：

    在构造时通过 file_path 参数
    在运行时通过工具的输入参数 file_path

    参数：
    file_path (可选[str]): 要读取的文件路径。如果提供，则成为工具的默认文件路径。
    **kwargs: 传递给 BaseTool 的其他关键字参数。

    示例：
    >>> tool = FileReadTool(file_path="/path/to/file.txt")
    >>> content = tool.run()  # 读取 /path/to/file.txt
    >>> content = tool.run(file_path="/path/to/other.txt")  # 读取 other.txt
    """

    name: str = "Read a file's content"
    description: str = "A tool that reads the content of a file. To use this tool, provide a 'file_path' parameter with the path to the file you want to read."
    args_schema: Type[BaseModel] = FileReadToolSchema
    file_path: Optional[str] = None

    def __init__(self, file_path: Optional[str] = None, **kwargs: Any) -> None:
        """
        Initialize the FileReadTool.

        Args:
            file_path (Optional[str]): Path to the file to be read. If provided,
                this becomes the default file path for the tool.
            **kwargs: Additional keyword arguments passed to BaseTool.

        初始化 FileReadTool。

        参数：
        file_path（可选[str]）：要读取的文件路径。如果提供，则此路径成为工具的默认文件路径。
        **kwargs：传递给 BaseTool 的其他关键字参数。
        """

        if file_path is not None:
            kwargs['description'] = f"A tool that reads file content. The default file is {file_path}, but you can provide a different 'file_path' parameter to read another file."

        super().__init__(**kwargs)
        self.file_path = file_path

    def _run(
        self,
        **kwargs: Any,
    ) -> str:
        file_path = kwargs.get("file_path", self.file_path)
        if file_path is None:
            return "Error: No file path provided. Please provide a file path either in the constructor or as an argument."

        try:
            with open(file_path, "r",encoding='utf-8') as file:
                return file.read()
        except FileNotFoundError:
            return f"Error: File not found at path: {file_path}"
        except PermissionError:
            return f"Error: Permission denied when trying to read file: {file_path}"
        except Exception as e:
            return f"Error: Failed to read file {file_path}. {str(e)}"

file_writer_tool工具代码：

python 复制代码

import os
from ast import literal_eval
from typing import Any, Optional, Type

from crewai.tools import BaseTool
from pydantic import BaseModel


class FileWriterToolInput(BaseModel):
    filename: str
    directory: Optional[str] = "./"
    overwrite: str = "False"
    content: str


class FileWriterTool(BaseTool):
    name: str = "File Writer Tool"
    description: str = "A tool to write content to a specified file. Accepts filename, content, and optionally a directory path and overwrite flag as input,overwrite flag is True or False."
    args_schema: Type[BaseModel] = FileWriterToolInput

    def _run(self, **kwargs: Any) -> str:
        try:
            # Create the directory if it doesn't exist
            if kwargs.get("directory") and not os.path.exists(kwargs["directory"]):
                os.makedirs(kwargs["directory"])

            # Construct the full path
            filepath = os.path.join(kwargs.get("directory") or "", kwargs["filename"])

            # Convert overwrite to boolean
            kwargs["overwrite"] = bool(literal_eval(kwargs["overwrite"]))

            # Check if file exists and overwrite is not allowed
            if os.path.exists(filepath) and not kwargs["overwrite"]:
                return f"File {filepath} already exists and overwrite option was not passed."

            # Write content to the file
            mode = "w" if kwargs["overwrite"] else "x"
            with open(filepath, mode) as file:
                content = kwargs["content"]
                file.write(content)
            return f"Content successfully written to {filepath}"
        except FileExistsError:
            return (
                f"File {filepath} already exists and overwrite option was not passed."
            )
        except KeyError as e:
            return f"An error occurred while accessing key: {str(e)}"
        except Exception as e:
            return f"An error occurred while writing to the file: {str(e)}"

现在需要构建一个团队。

构建团队的代码：

python 复制代码

from crewai import Agent, Crew, Process, Task,LLM
from crewai.project import CrewBase, agent, crew, task
from translation_agent.tools.file_read_tool import FileReadTool
from translation_agent.tools.file_writer_tool import FileWriterTool
import os
from dotenv import load_dotenv
load_dotenv()

file_read_tool = FileReadTool()
file_writer_tool = FileWriterTool()

api_key = os.getenv('OPENAI_API_KEY')
base_url = os.getenv('OPENAI_API_BASE')
model = os.getenv('OPENAI_MODEL_NAME', 'Qwen/Qwen2.5-72B-Instruct')  # Provide a default model if not set
agent_llm = LLM(
    model=model,
    base_url=base_url,
    api_key=api_key
    )

# If you want to run a snippet of code before or after the crew starts, 
# you can use the @before_kickoff and @after_kickoff decorators
# https://docs.crewai.com/concepts/crews#example-crew-class-with-decorators


@CrewBase
class TranslationAgent():
    """TranslationAgent crew"""

    # Learn more about YAML configuration files here:
    # Agents: https://docs.crewai.com/concepts/agents#yaml-configuration-recommended
    # Tasks: https://docs.crewai.com/concepts/tasks#yaml-configuration-recommended
    agents_config = 'config/agents.yaml'
    tasks_config = 'config/tasks.yaml'
    
    # If you would like to add tools to your agents, you can learn more about it here:
    # https://docs.crewai.com/concepts/agents#agent-tools
    # @agent
    # def researcher(self) -> Agent:
    #   return Agent(
    #       config=self.agents_config['researcher'],
    #       verbose=True
    #   )

    # @agent
    # def reporting_analyst(self) -> Agent:
    #   return Agent(
    #       config=self.agents_config['reporting_analyst'],
    #       verbose=True
    #   )
    
    @agent
    def file_reader(self) -> Agent:     
        return Agent(
            config=self.agents_config['file_reader'],
            verbose=True,
            llm=agent_llm,
            tools=[file_read_tool],
        )
    
    @agent
    def translation_agent(self) -> Agent:       
        return Agent(
            config=self.agents_config['translation_agent'],
            verbose=True,
            llm=agent_llm,      
        )
    
    @agent
    def file_saver(self) -> Agent:      
        return Agent(
            config=self.agents_config['file_saver'],
            verbose=True,
            llm=agent_llm,
            tools=[file_writer_tool],
        )
    
    # To learn more about structured task outputs, 
    # task dependencies, and task callbacks, check out the documentation:
    # https://docs.crewai.com/concepts/tasks#overview-of-a-task
    @task
    def file_read_task(self) -> Task:
        return Task(
            config=self.tasks_config['file_read_task'],
        )

    @task
    def translation_task(self) -> Task:
        return Task(
            config=self.tasks_config['translation_task'],
        )
    
    @task
    def file_save_task(self) -> Task:
        return Task(
            config=self.tasks_config['file_save_task'],
        )

    @crew
    def crew(self) -> Crew:
        """Creates the TranslationAgent crew"""
        # To learn how to add knowledge sources to your crew, check out the documentation:
        # https://docs.crewai.com/concepts/knowledge#what-is-knowledge

        return Crew(
            agents=self.agents, # Automatically created by the @agent decorator
            tasks=self.tasks, # Automatically created by the @task decorator
            process=Process.sequential,
            verbose=True,
            # process=Process.hierarchical, # In case you wanna use that instead https://docs.crewai.com/how-to/Hierarchical/
        )

其中我想让代理使用硅基流动的模型可以这样写：

需要在模型名称前加上openai才行，不如会报错。

如果你还没注册的话，可以点击邀请链接进行注册：cloud.siliconflow.cn/i/Ia3zOSCU。

这里我以具有工具调用能力的meta-llama/Llama-3.3-70B-Instruct为例。

然后可以这样使用：

ini 复制代码

import os
from dotenv import load_dotenv
load_dotenv()

file_read_tool = FileReadTool()
file_writer_tool = FileWriterTool()

api_key = os.getenv('OPENAI_API_KEY')
base_url = os.getenv('OPENAI_API_BASE')
model = os.getenv('OPENAI_MODEL_NAME', 'Qwen/Qwen2.5-72B-Instruct')  # Provide a default model if not set
agent_llm = LLM(
    model=model,
    base_url=base_url,
    api_key=api_key
    )

在创建代理时，记得使用这个大模型，并且记得使用工具：

ini 复制代码

@agent
def file_reader(self) -> Agent:     
        return Agent(
            config=self.agents_config['file_reader'],
            verbose=True,
            llm=agent_llm,
            tools=[file_read_tool],
        )

这样这个团队就构建成功了。

在main.py中这样写：

python 复制代码

#!/usr/bin/env python
import sys
import warnings

from datetime import datetime

from translation_agent.crew import TranslationAgent

warnings.filterwarnings("ignore", category=SyntaxWarning, module="pysbd")

# This main file is intended to be a way for you to run your
# crew locally, so refrain from adding unnecessary logic into this file.
# Replace with inputs you want to test with, it will automatically
# interpolate any tasks and agents information

def run():
    """
    Run the crew.
    """
    inputs = {
        'question': '读取test.txt文件内容，将其翻译为英文，然后写入test4.txt文件',
    }
    
    try:
        TranslationAgent().crew().kickoff(inputs=inputs)
    except Exception as e:
        raise Exception(f"An error occurred while running the crew: {e}")


def train():
    """
    Train the crew for a given number of iterations.
    """
    inputs = {
        "topic": "AI LLMs"
    }
    try:
        TranslationAgent().crew().train(n_iterations=int(sys.argv[1]), filename=sys.argv[2], inputs=inputs)

    except Exception as e:
        raise Exception(f"An error occurred while training the crew: {e}")

def replay():
    """
    Replay the crew execution from a specific task.
    """
    try:
        TranslationAgent().crew().replay(task_id=sys.argv[1])

    except Exception as e:
        raise Exception(f"An error occurred while replaying the crew: {e}")

def test():
    """
    Test the crew execution and returns the results.
    """
    inputs = {
        "topic": "AI LLMs"
    }
    try:
        TranslationAgent().crew().test(n_iterations=int(sys.argv[1]), openai_model_name=sys.argv[2], inputs=inputs)

    except Exception as e:
        raise Exception(f"An error occurred while testing the crew: {e}")

主要关注这里：

python 复制代码

def run():
    """
    Run the crew.
    """
    inputs = {
        'question': '读取test.txt文件内容，将其翻译为英文，然后写入test4.txt文件',
    }
    
    try:
        TranslationAgent().crew().kickoff(inputs=inputs)
    except Exception as e:
        raise Exception(f"An error occurred while running the crew: {e}")

在inputs中输入task中的question占位符的内容。

现在创建一个test.txt，输入内容为：

CrewAI：用于编排复杂 AI 代理系统的生产级框架。从简单的自动化到复杂的现实世界应用，CrewAI 提供精确控制和深度定制。通过灵活的、可投入生产的架构促进协作智能，CrewAI 使代理能够无缝协作，以可预测和一致的结果解决复杂的商业挑战。

现在输入crewai run，看看这个翻译代理的效果。

可以发现读取文件代理做的不够好的地方是多了一些内容。

需要进行改进。

改成这样再试试：

yaml 复制代码

file_reader:
  role: >
    读取文件代理
  goal: >
    根据文件路径，读取文件内容
  backstory: >
    你是一个文件读取代理，你的任务是根据文件路径，读取文件内容,只需返回文件内容即可

现在效果就很好了，如下所示：

翻译代理很好地进行翻译了，如下所示：

文件保存代理将翻译结果进行保存，如下所示：

最后

这就是使用crewai构建一个翻译代理的步骤与效果。在crewai中还有很多很有趣的工具值得探索，下期介绍代码解释器工具的使用。