Overview

Graph-based RAG methods—wherein we integrate RAG techniques with knowledge graphs in various ways—promise greater precision but have been notoriously challenging to implement. Traditionally, constructing, navigating, and maintaining— these “knowledge graphs” was difficult, involving: manual extraction of structured relationships from documents, inflexible static graph databases, and dedicated graph DB infrastructure.

Fortunately, recent advancements—particularly tools like Unstructured and the newly-released Graph Retriever library—have greatly simplified these workflows. Unstructured provides push-button transformation of unstructured documents into structured, graph-ready data, using custom prompting of advanced Large Language Models (LLMs) for automated entity extraction and vector databases for storage. The Graph Retriever library then dynamically constructs graph-based queries over these metadata-rich vector stores, eliminating the need for dedicated graph databases.

Technical Overview

Graph RAG uses many of the same tools and techniques as traditional semantic similarity-based RAG, but also adds some important features:

• Documents are enriched with structured metadata, such as entities (people, locations, organizations).
• A graph is dynamically built based on this structured metadata, capturing explicit relationships between documents.
• Retrieval occurs by traversing these structured connections, enabling more contextually relevant document retrieval.

This structured approach provides superior context navigation, enabling applications to fetch documents related not merely semantically but based explicitly on relationships and entities present in the metadata.

In this session, we discussed:

• Using Unstructured API to load data into Astra DB
• Leveraging the Custom Prompting feature to add named entity metadata to your data
• Using the OSS Graph Retriever library to enable dynamic graph construction from this structured metadata 
• Leveraging the Graph Retriever for dynamic retrieval

BTS

Brian Godsey, Datastax, brian.godsey@datastax.com 
Sara Hardy, Unstructured, sara.hardy@unstructured.io 
Avie Magner, DMP, avie@digitalmarketingpartners.biz 
Marc Lapides, DMP, marc@digitalmarketingpartners.biz