如何将 LangGraph (函数式 API) 与 AutoGen、CrewAI 及其他框架集成¶

LangGraph 是一个用于构建代理和多代理应用程序的框架。LangGraph 可以轻松地与其他代理框架集成。

您可能希望将 LangGraph 与其他代理框架集成的主要原因

创建多代理系统，其中每个代理都使用不同的框架构建
利用 LangGraph 添加诸如持久化、流式传输、短期和长期记忆等功能

集成来自其他框架的代理最简单的方法是在 LangGraph 节点内部调用这些代理

import autogen
from langgraph.func import entrypoint, task

autogen_agent = autogen.AssistantAgent(name="assistant", ...)
user_proxy = autogen.UserProxyAgent(name="user_proxy", ...)

@task
def call_autogen_agent(messages):
    response = user_proxy.initiate_chat(
        autogen_agent,
        message=messages[-1],
        ...
    )
    ...


@entrypoint()
def workflow(messages):
    response = call_autogen_agent(messages).result()
    return response


workflow.invoke(
    [
        {
            "role": "user",
            "content": "Find numbers between 10 and 30 in fibonacci sequence",
        }
    ]
)

在本指南中，我们将展示如何构建一个与 AutoGen 集成的 LangGraph 聊天机器人，但您可以使用相同的方法与其他框架集成。

设置¶

%pip install autogen langgraph

import getpass
import os


def _set_env(var: str):
    if not os.environ.get(var):
        os.environ[var] = getpass.getpass(f"{var}: ")


_set_env("OPENAI_API_KEY")

OPENAI_API_KEY:  ········

定义 AutoGen 代理¶

在这里我们定义我们的 AutoGen 代理。改编自官方教程此处。

import autogen
import os

config_list = [{"model": "gpt-4o", "api_key": os.environ["OPENAI_API_KEY"]}]

llm_config = {
    "timeout": 600,
    "cache_seed": 42,
    "config_list": config_list,
    "temperature": 0,
}

autogen_agent = autogen.AssistantAgent(
    name="assistant",
    llm_config=llm_config,
)

user_proxy = autogen.UserProxyAgent(
    name="user_proxy",
    human_input_mode="NEVER",
    max_consecutive_auto_reply=10,
    is_termination_msg=lambda x: x.get("content", "").rstrip().endswith("TERMINATE"),
    code_execution_config={
        "work_dir": "web",
        "use_docker": False,
    },  # Please set use_docker=True if docker is available to run the generated code. Using docker is safer than running the generated code directly.
    llm_config=llm_config,
    system_message="Reply TERMINATE if the task has been solved at full satisfaction. Otherwise, reply CONTINUE, or the reason why the task is not solved yet.",
)

创建工作流¶

我们现在将创建一个调用 AutoGen 代理的 LangGraph 聊天机器人图。

^{API 参考: convert_to_openai_messages | BaseMessage | entrypoint | task | add_messages | MemorySaver}

from langchain_core.messages import convert_to_openai_messages, BaseMessage
from langgraph.func import entrypoint, task
from langgraph.graph import add_messages
from langgraph.checkpoint.memory import MemorySaver


@task
def call_autogen_agent(messages: list[BaseMessage]):
    # convert to openai-style messages
    messages = convert_to_openai_messages(messages)
    response = user_proxy.initiate_chat(
        autogen_agent,
        message=messages[-1],
        # pass previous message history as context
        carryover=messages[:-1],
    )
    # get the final response from the agent
    content = response.chat_history[-1]["content"]
    return {"role": "assistant", "content": content}


# add short-term memory for storing conversation history
checkpointer = MemorySaver()


@entrypoint(checkpointer=checkpointer)
def workflow(messages: list[BaseMessage], previous: list[BaseMessage]):
    messages = add_messages(previous or [], messages)
    response = call_autogen_agent(messages).result()
    return entrypoint.final(value=response, save=add_messages(messages, response))

运行图¶

我们现在可以运行该图。

# pass the thread ID to persist agent outputs for future interactions
config = {"configurable": {"thread_id": "1"}}

for chunk in workflow.stream(
    [
        {
            "role": "user",
            "content": "Find numbers between 10 and 30 in fibonacci sequence",
        }
    ],
    config,
):
    print(chunk)

user_proxy (to assistant):

Find numbers between 10 and 30 in fibonacci sequence

--------------------------------------------------------------------------------
assistant (to user_proxy):

To find numbers between 10 and 30 in the Fibonacci sequence, we can generate the Fibonacci sequence and check which numbers fall within this range. Here's a plan:

1. Generate Fibonacci numbers starting from 0.
2. Continue generating until the numbers exceed 30.
3. Collect and print the numbers that are between 10 and 30.

Let's implement this in Python:

\`\`\`python
# filename: fibonacci_range.py

def fibonacci_sequence():
    a, b = 0, 1
    while a <= 30:
        if 10 <= a <= 30:
            print(a)
        a, b = b, a + b

fibonacci_sequence()
\`\`\`

This script will print the Fibonacci numbers between 10 and 30. Please execute the code to see the result.

--------------------------------------------------------------------------------

>>>>>>>> EXECUTING CODE BLOCK 0 (inferred language is python)...
user_proxy (to assistant):

exitcode: 0 (execution succeeded)
Code output: 
13
21


--------------------------------------------------------------------------------
assistant (to user_proxy):

The Fibonacci numbers between 10 and 30 are 13 and 21. 

These numbers are part of the Fibonacci sequence, which is generated by adding the two preceding numbers to get the next number, starting from 0 and 1. 

The sequence goes: 0, 1, 1, 2, 3, 5, 8, 13, 21, 34, ...

As you can see, 13 and 21 are the only numbers in this sequence that fall between 10 and 30.

TERMINATE

--------------------------------------------------------------------------------
{'call_autogen_agent': {'role': 'assistant', 'content': 'The Fibonacci numbers between 10 and 30 are 13 and 21. \n\nThese numbers are part of the Fibonacci sequence, which is generated by adding the two preceding numbers to get the next number, starting from 0 and 1. \n\nThe sequence goes: 0, 1, 1, 2, 3, 5, 8, 13, 21, 34, ...\n\nAs you can see, 13 and 21 are the only numbers in this sequence that fall between 10 and 30.\n\nTERMINATE'}}
{'workflow': {'role': 'assistant', 'content': 'The Fibonacci numbers between 10 and 30 are 13 and 21. \n\nThese numbers are part of the Fibonacci sequence, which is generated by adding the two preceding numbers to get the next number, starting from 0 and 1. \n\nThe sequence goes: 0, 1, 1, 2, 3, 5, 8, 13, 21, 34, ...\n\nAs you can see, 13 and 21 are the only numbers in this sequence that fall between 10 and 30.\n\nTERMINATE'}}

由于我们正在利用 LangGraph 的持久化功能，我们现在可以使用相同的线程 ID 继续对话——LangGraph 将自动把之前的历史记录传递给 AutoGen 代理

for chunk in workflow.stream(
    [
        {
            "role": "user",
            "content": "Multiply the last number by 3",
        }
    ],
    config,
):
    print(chunk)

user_proxy (to assistant):

Multiply the last number by 3
Context: 
Find numbers between 10 and 30 in fibonacci sequence
The Fibonacci numbers between 10 and 30 are 13 and 21. 

These numbers are part of the Fibonacci sequence, which is generated by adding the two preceding numbers to get the next number, starting from 0 and 1. 

The sequence goes: 0, 1, 1, 2, 3, 5, 8, 13, 21, 34, ...

As you can see, 13 and 21 are the only numbers in this sequence that fall between 10 and 30.

TERMINATE

--------------------------------------------------------------------------------
assistant (to user_proxy):

The last number in the Fibonacci sequence between 10 and 30 is 21. Multiplying 21 by 3 gives:

21 * 3 = 63

TERMINATE

--------------------------------------------------------------------------------
{'call_autogen_agent': {'role': 'assistant', 'content': 'The last number in the Fibonacci sequence between 10 and 30 is 21. Multiplying 21 by 3 gives:\n\n21 * 3 = 63\n\nTERMINATE'}}
{'workflow': {'role': 'assistant', 'content': 'The last number in the Fibonacci sequence between 10 and 30 is 21. Multiplying 21 by 3 gives:\n\n21 * 3 = 63\n\nTERMINATE'}}