Home - News ( United States | United Kingdom | Italy | Germany ) - Football scores

Showing content from https://python.langchain.com/docs/integrations/tools/prolog_tool below:

Prolog | 🦜️🔗 LangChain

LangChain tools that use Prolog rules to generate answers.

The PrologTool class allows the generation of langchain tools that use Prolog rules to generate answers.

Let's use the following Prolog rules in the file family.pl:

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

from langchain_prolog import PrologConfig, PrologRunnable, PrologTool

TEST_SCRIPT = "family.pl"

First create the Prolog tool:

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.
    """,
)

from dotenv import find_dotenv, load_dotenv

load_dotenv(find_dotenv(), override=True)



from langchain_core.messages import HumanMessage
from langchain_openai import ChatOpenAI

To use the tool, bind it to the LLM model:

llm = ChatOpenAI(model="gpt-4o-mini")
llm_with_tools = llm.bind_tools([prolog_tool])

and then query the model:

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

The LLM will respond with a tool call request:

messages.append(response)
response.tool_calls[0]

{'name': 'family_query',
 'args': {'men': 'john', 'women': None, 'child': None},
 'id': 'call_gH8rWamYXITrkfvRP2s5pkbF',
 'type': 'tool_call'}

The tool takes this request and queries the Prolog database:

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

The tool returns a list with all the solutions for the query:

messages.append(tool_msg)
tool_msg

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

That we then pass to the LLM, and the LLM answers the original query using the tool response:

answer = llm_with_tools.invoke(messages)
print(answer.content)

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

To use the prolog tool with an agent, pass it to the agent's constructor:

from langgraph.prebuilt import create_react_agent

agent_executor = create_react_agent(llm, [prolog_tool])

The agent takes the query and use the Prolog tool if needed:

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

Then the agent receives​ the tool response and generates the answer:

messages["messages"][-1].pretty_print()

================================== Ai Message ==================================

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

See https://langchain-prolog.readthedocs.io/en/latest/modules.html for detail.

• Tool conceptual guide
• Tool how-to guides

RetroSearch is an open source project built by @garambo | Open a GitHub Issue

Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo

HTML: 3.2 | Encoding: UTF-8 | Version: 0.7.4