Build and Query Knowledge Graphs with LLMs

https://towardsdatascience.com/build-query-knowledge-graphs-with-llms/

 Neo4j — Graph Database + Vector Store

Neo4j powers the knowledge graph layer and also stores vector embeddings for semantic search. The core of Neo4j is Cypher, the query language needed to interact with a Neo4j Database. Some of the key other features from Neo4j that are used in this project are:

• GraphDB: To store structured relationships between entities and concepts.
• VectorDB: Embedding support allows similarity search and hybrid queries.
• Python SDK: Neo4j offers a python driver to interact with its instance and wrap around it. Thanks to the python driver, knowing Cypher is not mandatory to interact with the code in this repo. Thanks to the SDK, we are able to use other python graph data science libraries as well, such as networkx or python-louvain.

 LangChain — Agent Framework for LLM Workflows

LangChain is used to coordinate how LLMs interact with tools like the vector index and the entities in the Knowledge Graphs, and of course with the user input.

• Used to define custom agents and toolchains.
• Integrates with retrievers, memory, and prompt templates.
• Makes it easy to swap in different LLM backends.

 Streamlit — Frontend UI for Interactions & Demos

I have written a small demo app using Streamlit, a python library that allows developers to build minimal frontend layers without writing any HTML or CSS, just pure python.

In this demo app you will see how to

• Ingest your documents into Neo4j under a Graph-based representation.
• Run live demos of the graph-based querying, showcasing key differences between various querying strategies.

Streamlit’s main advantages is that it’s super lightweight, fast to deploy, and doesn’t require a separate frontend framework or backend. Its features make it the perfect fit for demos and prototypes such as this one.

This is what an app looks like in Streamlit

https://github.com/fanqingsong/knowledge-graphs/blob/main/docs/answering-strategies.md

https://microsoft.github.io/graphrag/

https://github.com/microsoft/graphrag

Figure 1: An LLM-generated knowledge graph built using GPT-4 Turbo.

GraphRAG is a structured, hierarchical approach to Retrieval Augmented Generation (RAG), as opposed to naive semantic-search approaches using plain text snippets. The GraphRAG process involves extracting a knowledge graph out of raw text, building a community hierarchy, generating summaries for these communities, and then leveraging these structures when perform RAG-based tasks.