跳到主要内容

货币计算器：使用提供工具作为函数的问题解决

Open In Colab Open on GitHub

AutoGen 提供了由LLM、工具或人类驱动的可对话代理，这些代理可以通过自动聊天共同执行任务。该框架允许通过多代理对话使用工具和人类参与。请参阅有关此功能的文档这里。

在本笔记本中，我们演示了如何使用 AssistantAgent 和 UserProxyAgent 来利用 OpenAI 模型的新功能（模型版本 0613）进行函数调用。必须将指定的提示和函数配置 传递给 AssistantAgent 以初始化代理。相应的函数必须传递给 UserProxyAgent，它将 执行由 AssistantAgent 进行的任何函数调用。除了需要确保描述与函数匹配之外，我们建议 检查 AssistantAgent 中的系统消息，以确保指令与函数调用描述一致。

要求​

AutoGen 需要 Python>=3.8。要运行此笔记本示例，请安装 autogen-agentchat：

pip install autogen-agentchat~=0.2
# %pip install "autogen-agentchat~=0.2"

设置您的API端点​

config_list_from_json 函数从环境变量或 JSON 文件加载配置列表。

from typing import Literal

from pydantic import BaseModel, Field
from typing_extensions import Annotated

import autogen
from autogen.cache import Cache

config_list = autogen.config_list_from_json(
    "OAI_CONFIG_LIST",
    filter_dict={"tags": ["tool"]},  # comment out to get all
)

首先，它会查找环境变量“OAI_CONFIG_LIST”，该变量需要是一个有效的JSON字符串。如果未找到该变量，它会接着查找名为“OAI_CONFIG_LIST”的JSON文件。然后，它会根据标签过滤配置（你也可以通过其他键进行过滤）。只有符合过滤条件的配置会被保留在列表中。

配置列表如下所示：

config_list = [
    {
        'model': 'gpt-3.5-turbo',
        'api_key': '<your OpenAI API key here>',
        'tags': ['tool', '3.5-tool'],
    },
    {
        'model': 'gpt-3.5-turbo',
        'api_key': '<your Azure OpenAI API key here>',
        'base_url': '<your Azure OpenAI API base here>',
        'api_type': 'azure',
        'api_version': '2024-02-01',
        'tags': ['tool', '3.5-tool'],
    },
    {
        'model': 'gpt-3.5-turbo-16k',
        'api_key': '<your Azure OpenAI API key here>',
        'base_url': '<your Azure OpenAI API base here>',
        'api_type': 'azure',
        'api_version': '2024-02-01',
        'tags': ['tool', '3.5-tool'],
    },
]

你可以以任何你喜欢的方式设置config_list的值。请参考此 notebook 以获取不同方法的完整代码示例。

进行函数调用​

在这个例子中，我们演示了使用AssistantAgent和UserProxyAgent执行函数调用。通过AssistantAgent的默认系统提示，我们允许LLM助手使用代码执行任务，而UserProxyAgent将从LLM响应中提取代码块并执行它们。通过新的“function_call”功能，我们在OpenAI配置中为AssistantAgent定义了函数并指定了函数的描述。然后我们在UserProxyAgent中注册这些函数。

llm_config = {
    "config_list": config_list,
    "timeout": 120,
}

chatbot = autogen.AssistantAgent(
    name="chatbot",
    system_message="For currency exchange tasks, only use the functions you have been provided with. Reply TERMINATE when the task is done.",
    llm_config=llm_config,
)

# create a UserProxyAgent instance named "user_proxy"
user_proxy = autogen.UserProxyAgent(
    name="user_proxy",
    is_termination_msg=lambda x: x.get("content", "") and x.get("content", "").rstrip().endswith("TERMINATE"),
    human_input_mode="NEVER",
    max_consecutive_auto_reply=10,
)


CurrencySymbol = Literal["USD", "EUR"]


def exchange_rate(base_currency: CurrencySymbol, quote_currency: CurrencySymbol) -> float:
    if base_currency == quote_currency:
        return 1.0
    elif base_currency == "USD" and quote_currency == "EUR":
        return 1 / 1.1
    elif base_currency == "EUR" and quote_currency == "USD":
        return 1.1
    else:
        raise ValueError(f"Unknown currencies {base_currency}, {quote_currency}")


@user_proxy.register_for_execution()
@chatbot.register_for_llm(description="Currency exchange calculator.")
def currency_calculator(
    base_amount: Annotated[float, "Amount of currency in base_currency"],
    base_currency: Annotated[CurrencySymbol, "Base currency"] = "USD",
    quote_currency: Annotated[CurrencySymbol, "Quote currency"] = "EUR",
) -> str:
    quote_amount = exchange_rate(base_currency, quote_currency) * base_amount
    return f"{quote_amount} {quote_currency}"

装饰器 @chatbot.register_for_llm() 读取函数 currency_calculator 的注释签名，并生成以下由OpenAI API用于建议调用该函数的JSON模式。我们可以通过以下方式检查生成的JSON模式：

chatbot.llm_config["tools"]
[{'type': 'function',
  'function': {'description': 'Currency exchange calculator.',
   'name': 'currency_calculator',
   'parameters': {'type': 'object',
    'properties': {'base_amount': {'type': 'number',
      'description': 'Amount of currency in base_currency'},
     'base_currency': {'enum': ['USD', 'EUR'],
      'type': 'string',
      'default': 'USD',
      'description': 'Base currency'},
     'quote_currency': {'enum': ['USD', 'EUR'],
      'type': 'string',
      'default': 'EUR',
      'description': 'Quote currency'}},
    'required': ['base_amount']}}}]

装饰器 @user_proxy.register_for_execution() 将OpenAI API建议的函数名称映射到实际实现。映射的函数被包装，因为我们还自动处理函数的输出序列化，如下所示：

  • 字符串保持不变，并且

  • Pydantic BaseModel类型的对象被序列化为JSON。

我们可以通过使用封装函数的 ._origin 属性来检查函数映射的正确性，如下所示：

assert user_proxy.function_map["currency_calculator"]._origin == currency_calculator

最后，我们可以使用这个函数来准确计算交易金额：

with Cache.disk() as cache:
    # start the conversation
    res = user_proxy.initiate_chat(
        chatbot, message="How much is 123.45 USD in EUR?", summary_method="reflection_with_llm", cache=cache
    )
user_proxy (to chatbot):

How much is 123.45 USD in EUR?

--------------------------------------------------------------------------------
chatbot (to user_proxy):

***** Suggested tool call (call_9ogJS4d40BT1rXfMn7YJb151): currency_calculator *****
Arguments: 
{
  "base_amount": 123.45,
  "base_currency": "USD",
  "quote_currency": "EUR"
}
************************************************************************************

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

>>>>>>>> EXECUTING FUNCTION currency_calculator...
user_proxy (to chatbot):

user_proxy (to chatbot):

***** Response from calling tool (call_9ogJS4d40BT1rXfMn7YJb151) *****
112.22727272727272 EUR
**********************************************************************

--------------------------------------------------------------------------------
chatbot (to user_proxy):

123.45 USD is equivalent to 112.23 EUR.

--------------------------------------------------------------------------------
user_proxy (to chatbot):



--------------------------------------------------------------------------------
chatbot (to user_proxy):

TERMINATE

--------------------------------------------------------------------------------
print("Chat summary:", res.summary)
Chat summary: 123.45 USD is equivalent to 112.23 EUR.

Pydantic 模型​

我们也可以使用Pydantic基础模型来重写该函数，如下所示：

llm_config = {
    "config_list": config_list,
    "timeout": 120,
}

chatbot = autogen.AssistantAgent(
    name="chatbot",
    system_message="For currency exchange tasks, only use the functions you have been provided with. Reply TERMINATE when the task is done.",
    llm_config=llm_config,
)

# create a UserProxyAgent instance named "user_proxy"
user_proxy = autogen.UserProxyAgent(
    name="user_proxy",
    is_termination_msg=lambda x: x.get("content", "") and x.get("content", "").rstrip().endswith("TERMINATE"),
    human_input_mode="NEVER",
    max_consecutive_auto_reply=10,
)


class Currency(BaseModel):
    currency: Annotated[CurrencySymbol, Field(..., description="Currency symbol")]
    amount: Annotated[float, Field(0, description="Amount of currency", ge=0)]


# another way to register a function is to use register_function instead of register_for_execution and register_for_llm decorators
def currency_calculator(
    base: Annotated[Currency, "Base currency: amount and currency symbol"],
    quote_currency: Annotated[CurrencySymbol, "Quote currency symbol"] = "USD",
) -> Currency:
    quote_amount = exchange_rate(base.currency, quote_currency) * base.amount
    return Currency(amount=quote_amount, currency=quote_currency)


autogen.agentchat.register_function(
    currency_calculator,
    caller=chatbot,
    executor=user_proxy,
    description="Currency exchange calculator.",
)
chatbot.llm_config["tools"]
[{'type': 'function',
  'function': {'description': 'Currency exchange calculator.',
   'name': 'currency_calculator',
   'parameters': {'type': 'object',
    'properties': {'base': {'properties': {'currency': {'description': 'Currency symbol',
        'enum': ['USD', 'EUR'],
        'title': 'Currency',
        'type': 'string'},
       'amount': {'default': 0,
        'description': 'Amount of currency',
        'minimum': 0.0,
        'title': 'Amount',
        'type': 'number'}},
      'required': ['currency'],
      'title': 'Currency',
      'type': 'object',
      'description': 'Base currency: amount and currency symbol'},
     'quote_currency': {'enum': ['USD', 'EUR'],
      'type': 'string',
      'default': 'USD',
      'description': 'Quote currency symbol'}},
    'required': ['base']}}}]
with Cache.disk() as cache:
    # start the conversation
    res = user_proxy.initiate_chat(
        chatbot, message="How much is 112.23 Euros in US Dollars?", summary_method="reflection_with_llm", cache=cache
    )
user_proxy (to chatbot):

How much is 112.23 Euros in US Dollars?

--------------------------------------------------------------------------------
chatbot (to user_proxy):

***** Suggested tool call (call_BQkSmdFHsrKvmtDWCk0mY5sF): currency_calculator *****
Arguments: 
{
  "base": {
    "currency": "EUR",
    "amount": 112.23
  },
  "quote_currency": "USD"
}
************************************************************************************

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

>>>>>>>> EXECUTING FUNCTION currency_calculator...
user_proxy (to chatbot):

user_proxy (to chatbot):

***** Response from calling tool (call_BQkSmdFHsrKvmtDWCk0mY5sF) *****
{"currency":"USD","amount":123.45300000000002}
**********************************************************************

--------------------------------------------------------------------------------
chatbot (to user_proxy):

112.23 Euros is equivalent to 123.45 US Dollars.
TERMINATE

--------------------------------------------------------------------------------
print("Chat summary:", res.summary)
Chat summary: 112.23 Euros is equivalent to 123.45 US Dollars.
with Cache.disk() as cache:
    # start the conversation
    res = user_proxy.initiate_chat(
        chatbot,
        message="How much is 123.45 US Dollars in Euros?",
        cache=cache,
    )
user_proxy (to chatbot):

How much is 123.45 US Dollars in Euros?

--------------------------------------------------------------------------------
chatbot (to user_proxy):

***** Suggested tool call (call_Xxol42xTswZHGX60OjvIQRG1): currency_calculator *****
Arguments: 
{
  "base": {
    "currency": "USD",
    "amount": 123.45
  },
  "quote_currency": "EUR"
}
************************************************************************************

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

>>>>>>>> EXECUTING FUNCTION currency_calculator...
user_proxy (to chatbot):

user_proxy (to chatbot):

***** Response from calling tool (call_Xxol42xTswZHGX60OjvIQRG1) *****
{"currency":"EUR","amount":112.22727272727272}
**********************************************************************

--------------------------------------------------------------------------------
chatbot (to user_proxy):

123.45 US Dollars is equivalent to 112.23 Euros.

--------------------------------------------------------------------------------
user_proxy (to chatbot):



--------------------------------------------------------------------------------
chatbot (to user_proxy):

TERMINATE

--------------------------------------------------------------------------------
print("Chat history:", res.chat_history)
Chat history: [{'content': 'How much is 123.45 US Dollars in Euros?', 'role': 'assistant'}, {'tool_calls': [{'id': 'call_Xxol42xTswZHGX60OjvIQRG1', 'function': {'arguments': '{\n  "base": {\n    "currency": "USD",\n    "amount": 123.45\n  },\n  "quote_currency": "EUR"\n}', 'name': 'currency_calculator'}, 'type': 'function'}], 'content': None, 'role': 'assistant'}, {'content': '{"currency":"EUR","amount":112.22727272727272}', 'tool_responses': [{'tool_call_id': 'call_Xxol42xTswZHGX60OjvIQRG1', 'role': 'tool', 'content': '{"currency":"EUR","amount":112.22727272727272}'}], 'role': 'tool'}, {'content': '123.45 US Dollars is equivalent to 112.23 Euros.', 'role': 'user'}, {'content': '', 'role': 'assistant'}, {'content': 'TERMINATE', 'role': 'user'}]