Talk to Your Graph (TTYG)

TTYG is a Python module that enables Natural Language Querying (NLQ) using GraphDB and LangGraph Agents. It includes a lightweight GraphDB client and a collection of tools designed for integration with large language model (LLM) agents.

License

Apache-2.0 License. See LICENSE file for details.

Installation

pip install ttyg

Maintainers

Developed and maintained by Graphwise. For issues or feature requests, please open a GitHub issue.

Usage

A sample usage is provided in the Jupyter Notebook, which demonstrates natural language querying using the Star Wars dataset.

Run Jupyter Notebook

Prerequisites

• Install conda. miniconda will suffice.
• Install Docker. The documentation is created using Docker version 28.3.3 which bundles Docker Compose. For earlier Docker versions you may need to install Docker Compose separately.

Create and activate the Conda environment

conda create --name ttyg --file conda-linux-64.lock
conda activate ttyg

Install dependencies with Poetry

Depending on the LLM provider you want to use, run one of the following:

poetry install --with llm-openai --with jupyter
# or
poetry install --with llm-anthropic --with jupyter
# or
poetry install --with llm-databricks --with jupyter

Run the Notebook

jupyter notebook