從 LLMMathChain 遷移

LLMMathChain 能夠評估由 LLM 產生的數學運算式。產生運算式的指示已格式化到提示中，並且在使用 numexpr 程式庫進行評估之前，已從字串回應中剖析出運算式。

透過工具呼叫，可以更自然地實現此目的。我們可以為聊天模型配備一個利用 numexpr 的簡單計算器工具，並使用 LangGraph 圍繞它建構一個簡單的鏈。此方法的一些優點包括

• 利用針對此目的進行微調的聊天模型的工具呼叫功能；
• 減少從字串 LLM 回應中萃取運算式時發生的剖析錯誤；
• 將指示委派給訊息角色（例如，聊天模型可以理解 ToolMessage 代表什麼，而無需額外的提示）；
• 支援串流，包括個別權杖和鏈步驟的串流。

%pip install --upgrade --quiet numexpr

import os
from getpass import getpass

if "OPENAI_API_KEY" not in os.environ:
    os.environ["OPENAI_API_KEY"] = getpass()

舊版

詳細資訊

from langchain.chains import LLMMathChain
from langchain_core.prompts import ChatPromptTemplate
from langchain_openai import ChatOpenAI

llm = ChatOpenAI(model="gpt-4o-mini")

chain = LLMMathChain.from_llm(llm)

chain.invoke("What is 551368 divided by 82?")

API 參考：LLMMathChain | ChatPromptTemplate | ChatOpenAI

{'question': 'What is 551368 divided by 82?', 'answer': 'Answer: 6724.0'}

LangGraph

詳細資訊

import math
from typing import Annotated, Sequence

import numexpr
from langchain_core.messages import BaseMessage
from langchain_core.runnables import RunnableConfig
from langchain_core.tools import tool
from langchain_openai import ChatOpenAI
from langgraph.graph import END, StateGraph
from langgraph.graph.message import add_messages
from langgraph.prebuilt.tool_node import ToolNode
from typing_extensions import TypedDict


@tool
def calculator(expression: str) -> str:
    """Calculate expression using Python's numexpr library.

    Expression should be a single line mathematical expression
    that solves the problem.

    Examples:
        "37593 * 67" for "37593 times 67"
        "37593**(1/5)" for "37593^(1/5)"
    """
    local_dict = {"pi": math.pi, "e": math.e}
    return str(
        numexpr.evaluate(
            expression.strip(),
            global_dict={},  # restrict access to globals
            local_dict=local_dict,  # add common mathematical functions
        )
    )


llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)
tools = [calculator]
llm_with_tools = llm.bind_tools(tools, tool_choice="any")


class ChainState(TypedDict):
    """LangGraph state."""

    messages: Annotated[Sequence[BaseMessage], add_messages]


async def acall_chain(state: ChainState, config: RunnableConfig):
    last_message = state["messages"][-1]
    response = await llm_with_tools.ainvoke(state["messages"], config)
    return {"messages": [response]}


async def acall_model(state: ChainState, config: RunnableConfig):
    response = await llm.ainvoke(state["messages"], config)
    return {"messages": [response]}


graph_builder = StateGraph(ChainState)
graph_builder.add_node("call_tool", acall_chain)
graph_builder.add_node("execute_tool", ToolNode(tools))
graph_builder.add_node("call_model", acall_model)
graph_builder.set_entry_point("call_tool")
graph_builder.add_edge("call_tool", "execute_tool")
graph_builder.add_edge("execute_tool", "call_model")
graph_builder.add_edge("call_model", END)
chain = graph_builder.compile()

API 參考：BaseMessage | RunnableConfig | tool | ChatOpenAI | StateGraph | add_messages | ToolNode

# Visualize chain:

from IPython.display import Image

Image(chain.get_graph().draw_mermaid_png())

# Stream chain steps:

example_query = "What is 551368 divided by 82"

events = chain.astream(
    {"messages": [("user", example_query)]},
    stream_mode="values",
)
async for event in events:
    event["messages"][-1].pretty_print()

================================ Human Message =================================

What is 551368 divided by 82
================================== Ai Message ==================================
Tool Calls:
  calculator (call_1ic3gjuII0Aq9vxlSYiwvjSb)
 Call ID: call_1ic3gjuII0Aq9vxlSYiwvjSb
  Args:
    expression: 551368 / 82
================================= Tool Message =================================
Name: calculator

6724.0
================================== Ai Message ==================================

551368 divided by 82 equals 6724.

後續步驟

請參閱此處有關建立和使用工具的指南。

查看 LangGraph 文件，以了解有關使用 LangGraph 建立的詳細資訊。