Presentation Building Knowledge Graph-Based Agents with Structured Text Generation and Open-Weights Models

Information about this presentation can be found here.

The video recording of the presentation: coming soon

The slides of the presentation can be found here.

The notebook presented can be found here.

To run the notebook, install the requirements.txt:

pip install -r requirements.txt

You will also need to install llama-cpp-python and the installation will depend if you're using GPUs or not. In the simplest case (without GPUs):

pip install llama-cpp-python

Otherwise, follow these instructions.

This presentation took place on December 5, 2024.

The abstract of this presentation is:

Knowledge graphs are excellent at representing and storing heterogeneous and interconnected information in a structured manner, effectively capturing complex relationships and attributes across different data types. Structured text generation allows for building knowledge graphs by providing neatly structured outputs, making it an ideal method for extracting structured information. Similarly, structured text generation enables the creation of agents by defining which tools are allowed and what action inputs are permitted. In this talk, we first build a graph database from unstructured data and then we create an agent to query the graph database. We will show these capabilities with a demo.