虽然大语言模型具备完成很多任务的能力，但是在专业细分领域并不擅长。此外，大模型本身的幻觉问题也很难通过模型自身的能力来解决，需要引入额外的组件。

因此，我们需要通过一些工具辅助来帮助大模型来完成相关任务。

在DB-GPT所支持的模型列表中，绝大多数都具备工具调用的能力。在开源模型中也有相当一部分模型表现出色，比如glm-4-9b-chat、 Yi-1.5-34B-Chat、Qwen2-72B-Instruct等

工具编写

在有些情况下，大模型没有能力直接完成任务的计算，所以我们需要编写一些计算工具，来辅助大模型完成对应的目标。

from dbgpt.agent.resource import tool
@tool
def simple_calculator(first_number: int, second_number: int, operator: str) -> float:
    """Simple calculator tool. Just support +, -, *, /."""
    if isinstance(first_number, str):
        first_number = int(first_number)
    if isinstance(second_number, str):
        second_number = int(second_number)
    if operator == "+":
        return first_number + second_number
    elif operator == "-":
        return first_number - second_number
    elif operator == "*":
        return first_number * second_number
    elif operator == "/":
        return first_number / second_number
    else:
        raise ValueError(f"Invalid operator: {operator}")

为了测试多工具使用，我们继续编写一个工具来帮助LLM计算目录中的文件数量。

import os
from typing_extensions import Annotated, Doc
@tool
def count_directory_files(path: Annotated[str, Doc("The directory path")]) -> int:
    """Count the number of files in a directory."""
    if not os.path.isdir(path):
        raise ValueError(f"Invalid directory path: {path}")
    return len(os.listdir(path))

将工具打包到ToolPack中

绝大多数情况下，尤其是在生产使用中。我们我要具备多工具的能力，所以需要由ToolPack来进行工具的管理。 ToolPack是一组工具的集合，你可以使用它来进行工具管理。智能体可以根据具体的任务从工具包中选择对应的工具来完成任务。

from dbgpt.agent.resource import ToolPack
tools = ToolPack([simple_calculator, count_directory_files])

在Agent中使用工具

import asyncio
import os
from dbgpt.agent import AgentContext, AgentMemory, LLMConfig, UserProxyAgent
from dbgpt.agent.expand.tool_assistant_agent import ToolAssistantAgent
from dbgpt.model.proxy import OpenAILLMClient
async def main():
    llm_client = OpenAILLMClient(
        model_alias="gpt-3.5-turbo",  # or other models, eg. "gpt-4o"
        api_base=os.getenv("OPENAI_API_BASE"),
        api_key=os.getenv("OPENAI_API_KEY"),
    )
    context: AgentContext = AgentContext(
        conv_id="test123", language="en", temperature=0.5, max_new_tokens=2048
    )
    agent_memory = AgentMemory()
    user_proxy = await UserProxyAgent().bind(agent_memory).bind(context).build()
    tool_man = (
        await ToolAssistantAgent()
        .bind(context)
        .bind(LLMConfig(llm_client=llm_client))
        .bind(agent_memory)
        .bind(tools)
        .build()
    )
    await user_proxy.initiate_chat(
        recipient=tool_man,
        reviewer=user_proxy,
        message="Calculate the product of 10 and 99",
    )
    await user_proxy.initiate_chat(
        recipient=tool_man,
        reviewer=user_proxy,
        message="Count the number of files in /tmp",
    )
    # dbgpt-vis message infos
    print(await agent_memory.gpts_memory.one_chat_completions("test123"))
if __name__ == "__main__":
    asyncio.run(main())

输出如下

--------------------------------------------------------------------------------
User (to LuBan)-[]:
"Calculate the product of 10 and 99"
--------------------------------------------------------------------------------
un_stream ai response: {
  "thought": "To calculate the product of 10 and 99, we need to use a tool that can perform multiplication operation.",
  "tool_name": "simple_calculator",
  "args": {
    "first_number": 10,
    "second_number": 99,
    "operator": "*"
  }
}
--------------------------------------------------------------------------------
LuBan (to User)-[gpt-3.5-turbo]:
"{\n  \"thought\": \"To calculate the product of 10 and 99, we need to use a tool that can perform multiplication operation.\",\n  \"tool_name\": \"simple_calculator\",\n  \"args\": {\n    \"first_number\": 10,\n    \"second_number\": 99,\n    \"operator\": \"*\"\n  }\n}"
>>>>>>>>LuBan Review info: 
Pass(None)
>>>>>>>>LuBan Action report: 
execution succeeded,
990
--------------------------------------------------------------------------------
--------------------------------------------------------------------------------
User (to LuBan)-[]:
"Count the number of files in /tmp"
--------------------------------------------------------------------------------
un_stream ai response: {
  "thought": "To count the number of files in /tmp directory, we should use a tool that can perform this operation.",
  "tool_name": "count_directory_files",
  "args": {
    "path": "/tmp"
  }
}
--------------------------------------------------------------------------------
LuBan (to User)-[gpt-3.5-turbo]:
"{\n  \"thought\": \"To count the number of files in /tmp directory, we should use a tool that can perform this operation.\",\n  \"tool_name\": \"count_directory_files\",\n  \"args\": {\n    \"path\": \"/tmp\"\n  }\n}"
>>>>>>>>LuBan Review info: 
Pass(None)
>>>>>>>>LuBan Action report: 
execution succeeded,
19
--------------------------------------------------------------------------------

在上面的代码中，我们使用了ToolAssistantAgent 工具助手智能体来选择并且调用工具，你可以将相关的能力应用到自己的业务当中。

附录

英文文档

DB-GPT 使用文档 - 帮助手册 - 教程

工具调用

工具编写

将工具打包到ToolPack中

在Agent中使用工具

更多细节

附录