Fixed Entity Architecture and Cypherouting: GraphRAG made uncomplicated and nearly LLM-free
We often hear that GraphRAG is too expensive, too complicated, and requires highly trained ontologists, making it unappealing for most organizations. But what if we could simplify things and drastically improve our RAG applications using graphs, without such effort?
Fixed Entity Architecture offers a solution by building graphs based on a limited and usually predefined business domain ontology. A layered lexical graph, constructed without the help of LLMs and with a limited number of logically separated layers, can be a viable alternative to the well-known Microsoft GraphRAG.
Cypherouting is a method of querying this graph by leveraging its fixed structure, thereby avoiding the error-prone LLM-based text-to-cypher methods. In this presentation, I will introduce both methodologies and provide examples of their implementations.
Link to talk:
2025.connected-data.london/?…
--
Irina Adamchic. Knowledge Graphs expert, Accenture
Dr. Irina Adamchic is a GenAI and Knowledge Graphs expert at Accenture, driving Graph AI innovation across the company. She created the Fixed Entity Architecture (FEA) methodology, a cost- and effort-effective approach to building graphs for GraphRAG applications.
--
Welcome to Connected Data London's
#TeaserTuesday
Every Tuesday, we share teasers from
#CDL25 on our channels
Connected Data London 2025 brought together leaders and innovators. Were you there?
🎥 Watch the sessions:
2025.connected-data.london/
📩 Join the community:
connected-data.london?utm_so…
Tune in and learn from leaders and innovators; subscribe and watch premieres as they are released!
Join community legends and new voices in
#CDL25 for all things
#KnowledgeGraph #Graph #analytics #datascience #AI #graphDB #SemTech #Ontology