以编程方式使用文档

使用 Prolog 规则生成答案的 LangChain 工具。

概述

PrologTool 类允许生成使用 Prolog 规则生成答案的 langchain 工具。

设置

让我们使用 family.pl 文件中的以下 Prolog 规则:

parent(john, bianca, mary).\ parent(john, bianca, michael).\ parent(peter, patricia, jennifer).\ partner(X, Y) :- parent(X, Y, _).

#!pip install langchain-prolog

from langchain_prolog import PrologConfig, PrologRunnable, PrologTool

TEST_SCRIPT = "family.pl"

实例化

首先创建 Prolog 工具:

schema = PrologRunnable.create_schema("parent", ["men", "women", "child"])
config = PrologConfig(
    rules_file=TEST_SCRIPT,
    query_schema=schema,
)
prolog_tool = PrologTool(
    prolog_config=config,
    name="family_query",
    description="""
        Query family relationships using Prolog.
        parent(X, Y, Z) implies only that Z is a child of X and Y.
        Input can be a query string like 'parent(john, X, Y)' or 'john, X, Y'"
        You have to specify 3 parameters: men, woman, child. Do not use quotes.
    """,
)

调用

将 Prolog 工具与 LLM 和函数调用结合使用

#!pip install python-dotenv

from dotenv import find_dotenv, load_dotenv

load_dotenv(find_dotenv(), override=True)

#!pip install langchain-openai

from langchain.messages import HumanMessage
from langchain_openai import ChatOpenAI

要使用该工具,请将其绑定到 LLM 模型:

model = ChatOpenAI(model="gpt-5.4-mini")
model_with_tools = model.bind_tools([prolog_tool])

然后查询模型:

query = "Who are John's children?"
messages = [HumanMessage(query)]
response = model_with_tools.invoke(messages)

LLM 将使用工具调用请求进行响应:

messages.append(response)
response.tool_calls[0]
{'name': 'family_query',
 'args': {'men': 'john', 'women': None, 'child': None},
 'id': 'call_gH8rWamYXITrkfvRP2s5pkbF',
 'type': 'tool_call'}

该工具接收此请求并查询 Prolog 数据库:

tool_msg = prolog_tool.invoke(response.tool_calls[0])

该工具返回一个包含查询所有解决方案的列表:

messages.append(tool_msg)
tool_msg
ToolMessage(content='[{"Women": "bianca", "Child": "mary"}, {"Women": "bianca", "Child": "michael"}]', name='family_query', tool_call_id='call_gH8rWamYXITrkfvRP2s5pkbF')

然后我们将结果传递给 LLM,LLM 使用工具响应回答原始查询:

answer = model_with_tools.invoke(messages)
print(answer.content)
John has two children: Mary and Michael, with Bianca as their mother.

链接

将 Prolog 工具与代理结合使用

要使用代理的 Prolog 工具,请将其传递给代理的构造函数:

#!pip install langgraph

from langchain.agents import create_agent


agent_executor = create_agent(model, [prolog_tool])

代理接收查询并在需要时使用 Prolog 工具:

messages = agent_executor.invoke({"messages": [("human", query)]})

然后代理接收工具响应并生成答案:

messages["messages"][-1].pretty_print()
================================== Ai Message ==================================

John has two children: Mary and Michael, with Bianca as their mother.

API 参考

详见 langchain-prolog.readthedocs.io/en/latest/modules.html