Skip to main content

如何将工具转换为 OpenAI 函数

本文介绍如何将 LangChain 工具转换为 OpenAI 函数。

%pip install -qU langchain-community langchain-openai
from langchain_community.tools import MoveFileTool
from langchain_core.messages import HumanMessage
from langchain_core.utils.function_calling import convert_to_openai_function
from langchain_openai import ChatOpenAI
model = ChatOpenAI(model="gpt-3.5-turbo")
tools = [MoveFileTool()]
functions = [convert_to_openai_function(t) for t in tools]
functions[0]
{'name': 'move_file',
'description': 'Move or rename a file from one location to another',
'parameters': {'type': 'object',
'properties': {'source_path': {'description': 'Path of the file to move',
'type': 'string'},
'destination_path': {'description': 'New path for the moved file',
'type': 'string'}},
'required': ['source_path', 'destination_path']}}
message = model.invoke(
[HumanMessage(content="move file foo to bar")], functions=functions
)
message
AIMessage(content='', additional_kwargs={'function_call': {'arguments': '{\n  "source_path": "foo",\n  "destination_path": "bar"\n}', 'name': 'move_file'}})
message.additional_kwargs["function_call"]
{'name': 'move_file',
'arguments': '{\n "source_path": "foo",\n "destination_path": "bar"\n}'}

使用 OpenAI 聊天模型,我们还可以使用 bind_functions 自动绑定和转换类似函数的对象。

model_with_functions = model.bind_functions(tools)
model_with_functions.invoke([HumanMessage(content="move file foo to bar")])
AIMessage(content='', additional_kwargs={'function_call': {'arguments': '{\n  "source_path": "foo",\n  "destination_path": "bar"\n}', 'name': 'move_file'}})

或者,我们可以使用更新的 OpenAI API,该 API 使用 toolstool_choice 而不是 functionsfunction_call,方法是使用 ChatOpenAI.bind_tools

model_with_tools = model.bind_tools(tools)
model_with_tools.invoke([HumanMessage(content="move file foo to bar")])
AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_btkY3xV71cEVAOHnNa5qwo44', 'function': {'arguments': '{\n  "source_path": "foo",\n  "destination_path": "bar"\n}', 'name': 'move_file'}, 'type': 'function'}]})

Was this page helpful?


You can leave detailed feedback on GitHub.