langchain-ladybug

LangChain integration for the Ladybug graph database.

This package provides:

• LadybugGraph — a LangChain graph wrapper for Ladybug that supports schema introspection, Cypher queries, and document ingestion via add_graph_documents.
• LadybugQAChain — a question-answering chain that generates Ladybug-dialect Cypher queries from natural language and returns answers grounded in the graph.
• Prompt templates (LADYBUG_GENERATION_PROMPT, CYPHER_QA_PROMPT) tuned for the Ladybug Cypher dialect.

Installation

uv pip install langchain-ladybug

The ladybug Python package must also be installed:

uv pip install ladybug

Quick Start

import ladybug as lb
from langchain_ladybug import LadybugGraph, LadybugQAChain
from langchain_openai import ChatOpenAI

db = lb.Database("/path/to/my.db")

graph = LadybugGraph(db)

llm = ChatOpenAI(model="gpt-4o", temperature=0)

chain = LadybugQAChain.from_llm(
    llm=llm,
    graph=graph,
)

answer = chain.invoke({"query": "Who acted in The Godfather?"})
print(answer["result"])

Development

# Install dependencies
uv sync

# Run unit tests
make test

# Lint
make lint

# Format
make format

Acknowledgements

Started from the Kuzu → Ladybug LangChain support port by @adsharma (PR #438) — a proposed LadybugDB (formerly Kuzu) integration into the upstream langchain-community repo

Project Structure

langchain_ladybug/
├── graphs/
│   ├── graph_document.py   # Node, Relationship, GraphDocument data classes
│   └── ladybug_graph.py    # LadybugGraph wrapper
└── chains/
    ├── prompts.py           # Ladybug-dialect Cypher prompt templates
    └── ladybug_qa.py        # LadybugQAChain
tests/
├── unit_tests/             # No network calls
└── integration_tests/      # Requires ladybug