推理

概览

Agent 推理是一项让 agents 在执行前先反思任务并制定计划的功能。这有助于 agents 更有条理地处理任务，并确保它们已经准备好执行分配的工作。

使用方法

要为 agent 启用 reasoning，只需在创建 agent 时设置 reasoning=True：

from crewai import Agent

agent = Agent(
    role="Data Analyst",
    goal="Analyze complex datasets and provide insights",
    backstory="You are an experienced data analyst with expertise in finding patterns in complex data.",
    reasoning=True,  # 启用 reasoning
    max_reasoning_attempts=3  # 可选：设置 reasoning 的最大尝试次数
)

工作原理

启用 reasoning 后，在执行 task 之前，agent 会：

反思任务并创建详细计划
评估自己是否已准备好执行任务
根据需要不断优化计划，直到准备就绪或达到 max_reasoning_attempts
在执行前将 reasoning 计划注入 task 描述

这个过程有助于 agent 将复杂任务拆解成可管理的步骤，并在开始前识别潜在挑战。

配置选项

reasoning bool default: False

启用或禁用 reasoning

max_reasoning_attempts int default: None

在开始执行前，用于优化计划的最大尝试次数。如果为 None（默认值），agent 会持续优化，直到准备就绪。

示例

下面是一个完整示例：

from crewai import Agent, Task, Crew

# 创建一个启用了 reasoning 的 agent
analyst = Agent(
    role="Data Analyst",
    goal="Analyze data and provide insights",
    backstory="You are an expert data analyst.",
    reasoning=True,
    max_reasoning_attempts=3  # 可选：设置 reasoning 尝试次数上限
)

# 创建一个 task
analysis_task = Task(
    description="Analyze the provided sales data and identify key trends.",
    expected_output="A report highlighting the top 3 sales trends.",
    agent=analyst
)

# 创建一个 crew 并运行 task
crew = Crew(agents=[analyst], tasks=[analysis_task])
result = crew.kickoff()

print(result)

错误处理

reasoning 流程经过了稳健设计，内置了错误处理。如果 reasoning 过程中发生错误，agent 会直接继续执行 task，而不会使用 reasoning 计划。这确保即使 reasoning 失败，任务仍然可以继续执行。

以下是如何在代码中处理潜在错误：

from crewai import Agent, Task
import logging

# 设置日志，以捕获任何 reasoning 错误
logging.basicConfig(level=logging.INFO)

# 创建一个启用了 reasoning 的 agent
agent = Agent(
    role="Data Analyst",
    goal="Analyze data and provide insights",
    reasoning=True,
    max_reasoning_attempts=3
)

# 创建一个 task
task = Task(
    description="Analyze the provided sales data and identify key trends.",
    expected_output="A report highlighting the top 3 sales trends.",
    agent=agent
)

# 执行 task
# 如果 reasoning 过程中发生错误，它会被记录，执行仍将继续
result = agent.execute_task(task)

reasoning 输出示例

下面是一个用于数据分析任务的 reasoning plan 示例：

Task: Analyze the provided sales data and identify key trends.

Reasoning Plan:
I'll analyze the sales data to identify the top 3 trends.

1. Understanding of the task:
   I need to analyze sales data to identify key trends that would be valuable for business decision-making.

2. Key steps I'll take:
   - First, I'll examine the data structure to understand what fields are available
   - Then I'll perform exploratory data analysis to identify patterns
   - Next, I'll analyze sales by time periods to identify temporal trends
   - I'll also analyze sales by product categories and customer segments
   - Finally, I'll identify the top 3 most significant trends

3. Approach to challenges:
   - If the data has missing values, I'll decide whether to fill or filter them
   - If the data has outliers, I'll investigate whether they're valid data points or errors
   - If trends aren't immediately obvious, I'll apply statistical methods to uncover patterns

4. Use of available tools:
   - I'll use data analysis tools to explore and visualize the data
   - I'll use statistical tools to identify significant patterns
   - I'll use knowledge retrieval to access relevant information about sales analysis

5. Expected outcome:
   A concise report highlighting the top 3 sales trends with supporting evidence from the data.

READY: I am ready to execute the task.

这个 reasoning plan 帮助 agent 组织自己的方法，考虑潜在挑战，并确保它能够交付预期结果。