在使用语言模型时，通常只需一个优质的提示词和合适的工具就能获得稳定表现。但当处理多个独特流程时，情况可能变得复杂。本指南将介绍一种应对方法。

我们将介绍例行程序和交接的概念，然后逐步讲解实现过程，并展示如何以简单、强大且可控的方式来协调多个智能体。

最后，我们提供了一个示例仓库Swarm，其中实现了这些理念并附有示例。

让我们从设置导入开始。

from openai import OpenAI
from pydantic import BaseModel
from typing import Optional
import json


client = OpenAI()

Routines

"例行程序"的概念并没有严格的定义，而是用来描述一系列步骤的集合。具体来说，我们可以将例行程序定义为用自然语言编写的指令列表（我们将用系统提示来表示），以及完成这些指令所需的工具。

让我们来看一个示例。下面我们定义了一个客户服务智能体的流程，指示其对用户问题进行分级处理，然后要么建议解决方案，要么提供退款。我们还定义了必要的函数execute_refund和look_up_item。我们可以将其称为客户服务流程、智能体、助手等——但核心概念是相同的：一系列步骤及执行这些步骤所需的工具。

# Customer Service Routine

system_message = (
    "You are a customer support agent for ACME Inc."
    "Always answer in a sentence or less."
    "Follow the following routine with the user:"
    "1. First, ask probing questions and understand the user's problem deeper.\n"
    " - unless the user has already provided a reason.\n"
    "2. Propose a fix (make one up).\n"
    "3. ONLY if not satisfied, offer a refund.\n"
    "4. If accepted, search for the ID and then execute refund."
    ""
)

def look_up_item(search_query):
    """Use to find item ID.
    Search query can be a description or keywords."""

    # return hard-coded item ID - in reality would be a lookup
    return "item_132612938"


def execute_refund(item_id, reason="not provided"):

    print("Summary:", item_id, reason) # lazy summary
    return "success"

日常流程的主要优势在于其简单性和鲁棒性。请注意，这些指令包含条件判断，类似于状态机或代码中的分支结构。对于中小型日常流程，LLM实际上可以相当稳健地处理这些情况，并具有"柔性"遵循的额外优势——LLM能够自然地引导对话而不会陷入死胡同。

执行例程

要执行一个例程，让我们实现一个简单的循环：

获取用户输入。
将用户消息追加到messages。
调用模型。
将模型响应追加到messages。

def run_full_turn(system_message, messages):
    response = client.chat.completions.create(
        model="gpt-4o-mini",
        messages=[{"role": "system", "content": system_message}] + messages,
    )
    message = response.choices[0].message
    messages.append(message)

    if message.content: print("Assistant:", message.content)

    return message


messages = []
while True:
    user = input("User: ")
    messages.append({"role": "user", "content": user})

    run_full_turn(system_message, messages)

如你所见，当前忽略了函数调用，让我们添加这部分功能。

模型需要将函数格式化为函数模式。为了方便起见，我们可以定义一个辅助函数，将python函数转换为相应的函数模式。

import inspect

def function_to_schema(func) -> dict:
    type_map = {
        str: "string",
        int: "integer",
        float: "number",
        bool: "boolean",
        list: "array",
        dict: "object",
        type(None): "null",
    }

    try:
        signature = inspect.signature(func)
    except ValueError as e:
        raise ValueError(
            f"Failed to get signature for function {func.__name__}: {str(e)}"
        )

    parameters = {}
    for param in signature.parameters.values():
        try:
            param_type = type_map.get(param.annotation, "string")
        except KeyError as e:
            raise KeyError(
                f"Unknown type annotation {param.annotation} for parameter {param.name}: {str(e)}"
            )
        parameters[param.name] = {"type": param_type}

    required = [
        param.name
        for param in signature.parameters.values()
        if param.default == inspect._empty
    ]

    return {
        "type": "function",
        "function": {
            "name": func.__name__,
            "description": (func.__doc__ or "").strip(),
            "parameters": {
                "type": "object",
                "properties": parameters,
                "required": required,
            },
        },
    }

例如：

def sample_function(param_1, param_2, the_third_one: int, some_optional="John Doe"):
    """
    This is my docstring. Call this function when you want.
    """
    print("Hello, world")

schema =  function_to_schema(sample_function)
print(json.dumps(schema, indent=2))

{
  "type": "function",
  "function": {
    "name": "sample_function",
    "description": "This is my docstring. Call this function when you want.",
    "parameters": {
      "type": "object",
      "properties": {
        "param_1": {
          "type": "string"
        },
        "param_2": {
          "type": "string"
        },
        "the_third_one": {
          "type": "integer"
        },
        "some_optional": {
          "type": "string"
        }
      },
      "required": [
        "param_1",
        "param_2",
        "the_third_one"
      ]
    }
  }
}

现在，我们可以在调用模型时使用此函数来传递工具。

messages = []

tools = [execute_refund, look_up_item]
tool_schemas = [function_to_schema(tool) for tool in tools]

response = client.chat.completions.create(
            model="gpt-4o-mini",
            messages=[{"role": "user", "content": "Look up the black boot."}],
            tools=tool_schemas,
        )
message = response.choices[0].message

message.tool_calls[0].function

Function(arguments='{"search_query":"black boot"}', name='look_up_item')

最后，当模型调用工具时，我们需要执行相应的函数并将结果返回给模型。

我们可以通过在tool_map中将工具名称映射到对应的python函数，然后在execute_tool_call中查找并调用它。最后将结果添加到对话中。

tools_map = {tool.__name__: tool for tool in tools}

def execute_tool_call(tool_call, tools_map):
    name = tool_call.function.name
    args = json.loads(tool_call.function.arguments)

    print(f"Assistant: {name}({args})")

    # call corresponding function with provided arguments
    return tools_map[name](**args)

for tool_call in message.tool_calls:
            result = execute_tool_call(tool_call, tools_map)

            # add result back to conversation 
            result_message = {
                "role": "tool",
                "tool_call_id": tool_call.id,
                "content": result,
            }
            messages.append(result_message)

Assistant: look_up_item({'search_query': 'black boot'})

在实践中，我们还会希望让模型利用该结果生成另一个响应。该响应可能也包含工具调用，因此我们可以直接在循环中运行此过程，直到不再有工具调用为止。

如果我们将所有内容整合在一起，看起来会是这样：

tools = [execute_refund, look_up_item]


def run_full_turn(system_message, tools, messages):

    num_init_messages = len(messages)
    messages = messages.copy()

    while True:

        # turn python functions into tools and save a reverse map
        tool_schemas = [function_to_schema(tool) for tool in tools]
        tools_map = {tool.__name__: tool for tool in tools}

        # === 1. get openai completion ===
        response = client.chat.completions.create(
            model="gpt-4o-mini",
            messages=[{"role": "system", "content": system_message}] + messages,
            tools=tool_schemas or None,
        )
        message = response.choices[0].message
        messages.append(message)

        if message.content:  # print assistant response
            print("Assistant:", message.content)

        if not message.tool_calls:  # if finished handling tool calls, break
            break

        # === 2. handle tool calls ===

        for tool_call in message.tool_calls:
            result = execute_tool_call(tool_call, tools_map)

            result_message = {
                "role": "tool",
                "tool_call_id": tool_call.id,
                "content": result,
            }
            messages.append(result_message)

    # ==== 3. return new messages =====
    return messages[num_init_messages:]


def execute_tool_call(tool_call, tools_map):
    name = tool_call.function.name
    args = json.loads(tool_call.function.arguments)

    print(f"Assistant: {name}({args})")

    # call corresponding function with provided arguments
    return tools_map[name](**args)


messages = []
while True:
    user = input("User: ")
    messages.append({"role": "user", "content": user})

    new_messages = run_full_turn(system_message, tools, messages)
    messages.extend(new_messages)

现在我们有了一个例行程序，假设我们想添加更多步骤和工具。在一定程度上是可以的，但最终如果我们尝试用太多不同的任务扩展这个例行程序，它可能会开始出现问题。这时我们可以利用多个例行程序的概念——根据用户请求，我们可以加载具有适当步骤和工具的正确的例行程序来解决它。

动态切换系统指令和工具可能看起来令人望而生畏。然而，如果我们把"例行程序"视为"智能体"，那么这种交接的概念就能让我们简单地表示这些切换——就像一个智能体将对话移交给另一个智能体。

Handoffs

让我们将转接定义为智能体（或例程）将活跃对话转交给另一个智能体的过程，就像电话通话中被转接给其他人一样。不同之处在于，这里的智能体完全知晓您之前的对话内容！

要查看交接的实际效果，我们首先定义一个基本的智能体类。

class Agent(BaseModel):
    name: str = "Agent"
    model: str = "gpt-4o-mini"
    instructions: str = "You are a helpful Agent"
    tools: list = []

现在要让我们的代码支持它，我们可以将run_full_turn改为接收一个Agent而不是单独的system_message和tools：

def run_full_turn(agent, messages):

    num_init_messages = len(messages)
    messages = messages.copy()

    while True:

        # turn python functions into tools and save a reverse map
        tool_schemas = [function_to_schema(tool) for tool in agent.tools]
        tools_map = {tool.__name__: tool for tool in agent.tools}

        # === 1. get openai completion ===
        response = client.chat.completions.create(
            model=agent.model,
            messages=[{"role": "system", "content": agent.instructions}] + messages,
            tools=tool_schemas or None,
        )
        message = response.choices[0].message
        messages.append(message)

        if message.content:  # print assistant response
            print("Assistant:", message.content)

        if not message.tool_calls:  # if finished handling tool calls, break
            break

        # === 2. handle tool calls ===

        for tool_call in message.tool_calls:
            result = execute_tool_call(tool_call, tools_map)

            result_message = {
                "role": "tool",
                "tool_call_id": tool_call.id,
                "content": result,
            }
            messages.append(result_message)

    # ==== 3. return new messages =====
    return messages[num_init_messages:]


def execute_tool_call(tool_call, tools_map):
    name = tool_call.function.name
    args = json.loads(tool_call.function.arguments)

    print(f"Assistant: {name}({args})")

    # call corresponding function with provided arguments
    return tools_map[name](**args)

我们现在可以轻松运行多个智能体：

def execute_refund(item_name):
    return "success"

refund_agent = Agent(
    name="Refund Agent",
    instructions="You are a refund agent. Help the user with refunds.",
    tools=[execute_refund],
)

def place_order(item_name):
    return "success"

sales_assistant = Agent(
    name="Sales Assistant",
    instructions="You are a sales assistant. Sell the user a product.",
    tools=[place_order],
)


messages = []
user_query = "Place an order for a black boot."
print("User:", user_query)
messages.append({"role": "user", "content": user_query})

response = run_full_turn(sales_assistant, messages) # sales assistant
messages.extend(response)


user_query = "Actually, I want a refund." # implicitly refers to the last item
print("User:", user_query)
messages.append({"role": "user", "content": user_query})
response = run_full_turn(refund_agent, messages) # refund agent

User: Place an order for a black boot.
Assistant: place_order({'item_name': 'black boot'})
Assistant: Your order for a black boot has been successfully placed! If you need anything else, feel free to ask!
User: Actually, I want a refund.
Assistant: execute_refund({'item_name': 'black boot'})
Assistant: Your refund for the black boot has been successfully processed. If you need further assistance, just let me know!

太好了！不过这里我们是手动进行交接的——我们希望智能体能够自行决定何时执行交接。一个简单但出奇有效的方法是给它们一个transfer_to_XXX函数，其中XXX代表某个智能体。模型足够智能，知道在需要交接时调用这个函数！

移交功能

既然智能体能够表达移交的意图，我们就必须让它真正实现。实现方式有很多种，但有一种特别简洁的方法。

对于我们目前定义的智能体函数，比如execute_refund或place_order，它们会返回一个字符串，该字符串将提供给模型。如果我们改为返回一个Agent对象来指示要转移到哪个智能体会怎样？就像这样：

refund_agent = Agent(
    name="Refund Agent",
    instructions="You are a refund agent. Help the user with refunds.",
    tools=[execute_refund],
)

def transfer_to_refunds():
    return refund_agent

sales_assistant = Agent(
    name="Sales Assistant",
    instructions="You are a sales assistant. Sell the user a product.",
    tools=[place_order],
)

然后我们可以更新代码来检查函数响应的返回类型，如果是Agent，就更新当前使用的智能体！此外，现在run_full_turn需要返回最新使用的智能体以防发生交接。（我们可以通过Response类来实现这一点以保持整洁。）

class Response(BaseModel):
    agent: Optional[Agent]
    messages: list

现在来看更新后的 run_full_turn：

def run_full_turn(agent, messages):

    current_agent = agent
    num_init_messages = len(messages)
    messages = messages.copy()

    while True:

        # turn python functions into tools and save a reverse map
        tool_schemas = [function_to_schema(tool) for tool in current_agent.tools]
        tools = {tool.__name__: tool for tool in current_agent.tools}

        # === 1. get openai completion ===
        response = client.chat.completions.create(
            model=agent.model,
            messages=[{"role": "system", "content": current_agent.instructions}]
            + messages,
            tools=tool_schemas or None,
        )
        message = response.choices[0].message
        messages.append(message)

        if message.content:  # print agent response
            print(f"{current_agent.name}:", message.content)

        if not message.tool_calls:  # if finished handling tool calls, break
            break

        # === 2. handle tool calls ===

        for tool_call in message.tool_calls:
            result = execute_tool_call(tool_call, tools, current_agent.name)

            if type(result) is Agent:  # if agent transfer, update current agent
                current_agent = result
                result = (
                    f"Transfered to {current_agent.name}. Adopt persona immediately."
                )

            result_message = {
                "role": "tool",
                "tool_call_id": tool_call.id,
                "content": result,
            }
            messages.append(result_message)

    # ==== 3. return last agent used and new messages =====
    return Response(agent=current_agent, messages=messages[num_init_messages:])


def execute_tool_call(tool_call, tools, agent_name):
    name = tool_call.function.name
    args = json.loads(tool_call.function.arguments)

    print(f"{agent_name}:", f"{name}({args})")

    return tools[name](**args)  # call corresponding function with provided arguments

让我们看一个包含更多智能体的示例。

def escalate_to_human(summary):
    """Only call this if explicitly asked to."""
    print("Escalating to human agent...")
    print("\n=== Escalation Report ===")
    print(f"Summary: {summary}")
    print("=========================\n")
    exit()


def transfer_to_sales_agent():
    """User for anything sales or buying related."""
    return sales_agent


def transfer_to_issues_and_repairs():
    """User for issues, repairs, or refunds."""
    return issues_and_repairs_agent


def transfer_back_to_triage():
    """Call this if the user brings up a topic outside of your purview,
    including escalating to human."""
    return triage_agent


triage_agent = Agent(
    name="Triage Agent",
    instructions=(
        "You are a customer service bot for ACME Inc. "
        "Introduce yourself. Always be very brief. "
        "Gather information to direct the customer to the right department. "
        "But make your questions subtle and natural."
    ),
    tools=[transfer_to_sales_agent, transfer_to_issues_and_repairs, escalate_to_human],
)


def execute_order(product, price: int):
    """Price should be in USD."""
    print("\n\n=== Order Summary ===")
    print(f"Product: {product}")
    print(f"Price: ${price}")
    print("=================\n")
    confirm = input("Confirm order? y/n: ").strip().lower()
    if confirm == "y":
        print("Order execution successful!")
        return "Success"
    else:
        print("Order cancelled!")
        return "User cancelled order."


sales_agent = Agent(
    name="Sales Agent",
    instructions=(
        "You are a sales agent for ACME Inc."
        "Always answer in a sentence or less."
        "Follow the following routine with the user:"
        "1. Ask them about any problems in their life related to catching roadrunners.\n"
        "2. Casually mention one of ACME's crazy made-up products can help.\n"
        " - Don't mention price.\n"
        "3. Once the user is bought in, drop a ridiculous price.\n"
        "4. Only after everything, and if the user says yes, "
        "tell them a crazy caveat and execute their order.\n"
        ""
    ),
    tools=[execute_order, transfer_back_to_triage],
)


def look_up_item(search_query):
    """Use to find item ID.
    Search query can be a description or keywords."""
    item_id = "item_132612938"
    print("Found item:", item_id)
    return item_id


def execute_refund(item_id, reason="not provided"):
    print("\n\n=== Refund Summary ===")
    print(f"Item ID: {item_id}")
    print(f"Reason: {reason}")
    print("=================\n")
    print("Refund execution successful!")
    return "success"


issues_and_repairs_agent = Agent(
    name="Issues and Repairs Agent",
    instructions=(
        "You are a customer support agent for ACME Inc."
        "Always answer in a sentence or less."
        "Follow the following routine with the user:"
        "1. First, ask probing questions and understand the user's problem deeper.\n"
        " - unless the user has already provided a reason.\n"
        "2. Propose a fix (make one up).\n"
        "3. ONLY if not satesfied, offer a refund.\n"
        "4. If accepted, search for the ID and then execute refund."
        ""
    ),
    tools=[execute_refund, look_up_item, transfer_back_to_triage],
)

最后，我们可以在循环中运行这段代码（这不会在Python笔记本中运行，因此你可以在单独的Python文件中尝试）：

agent = triage_agent
messages = []

while True:
    user = input("User: ")
    messages.append({"role": "user", "content": user})

    response = run_full_turn(agent, messages)
    agent = response.agent
    messages.extend(response.messages)

Swarm

作为概念验证，我们已将这些想法打包到一个名为Swarm的示例库中。这仅作为示例用途，不应直接在生产环境中使用。不过，欢迎借鉴这些想法和代码来构建您自己的版本！

2024年10月10日

编排智能体：例程与交接

Routines

执行例程

Handoffs

移交功能

Swarm