Graph Data Modeling Without Graph Databases: PostgreSQL and Hybrid Approaches for Agentic Systems 🖇️ Organizations implementing AI systems today face a practical challenge: maintaining multiple specialized databases (vector stores, graph databases, relational systems) creates significant operational complexity, increases costs, and introduces synchronization headaches. Companies like Writer (insight from a recent Waseem Alshikh interview with Harrison Chase) have tackled this problem by implementing graph-like structures directly within PostgreSQL, eliminating the need for separate graph databases while maintaining the necessary functionality. This approach dramatically simplifies infrastructure management, reduces the number of systems to monitor, and eliminates error-prone synchronization processes that can cost thousands of dollars in wasted resources. For enterprises focused on delivering business value rather than managing technical complexity, these PostgreSQL-based implementations offer a pragmatic path forward, though with important trade-offs when considering more sophisticated agentic systems. Writer implemented a subject-predicate-object triple structure directly in PostgreSQL tables rather than using dedicated graph databases. This approach maintains the semantic richness of knowledge graphs while leveraging PostgreSQL's maturity and scalability. Writer kept the conceptual structure of triples that underpin knowledge graphs implemented through a relational schema design. Instead of relying on native graph traversals, Writer developed a fusion decoder that reconstructs graph-like relationships at query time. This component serves as the bridge between the storage layer (PostgreSQL with its triple-inspired structure) and the language model, enabling sophisticated information retrieval without requiring a dedicated graph database's traversal capabilities. The approach focuses on query translation and result combination rather than storage structure optimization. Complementing the triple-based approach, PostgreSQL with extensions (PG Vector and PG Vector Scale) can function effectively as a vector database. This challenges the notion that specialized vector databases are necessary, Treating embeddings as derived data leads to a more natural and maintainable architecture. This reframes the database's role from storing independent vector embeddings to managing derived data that automatically synchronizes with its source. But a critical distinction between retrieval systems and agentic systems need to be made. While PostgreSQL-based approaches excel at knowledge retrieval tasks where the focus is on precision and relevance, agentic systems operate in dynamic environments where context evolves over time, previous actions influence future decisions, and contradictions need to be resolved. This distinction drives different architectural requirements and suggests potential complementary roles for different database approaches. | 15 comments on LinkedIn

Learn how to use Spanner Graph with LangChain workflows to build advanced, relationship-aware RAG systems, a.k.a. GraphRAG.

Read about how our partners from Semantic Partners explore the latest iteration of the GraphDB's Talk To Your Graph feature

Build a graph for RAG application for a price of a chocolate bar! What is GraphRAG for you? What is GraphRAG? What does GraphRAG mean from your perspective? What if you could have a standard RAG and a GraphRAG as a combi-package, with just a query switch? The fact is, there is no concrete, universal

Bridge the gap and unlock hidden potential within your unstructured data

New features include community summaries, local and global retrievers, running retrievers in parallel, and custom prompt instructions.

When (not) to use GraphRAG

Imagine you’re solving a complex puzzle with scattered pieces of information.

Explore its functionality and how it leverages the power of LLMs and Neo4j graph databases to improve data analysis and knowledge discovery.

David Hughes presented “Unleashing the Power of Multimodal GraphRAG: Integrating Image Features for Deeper Insights” at Data Day Texas 2025.

Discover Neo4j's 2024 product innovations in cloud-native graph technology, enhancing performance, scalability, AI innovation, and developer productivity.

As technology advances, large language models (LLMs) and information retrieval/management methods evolve at breakneck speed. Knowledge…

A RAG System Built for Both Semantic Search and Structured Data Queries

Authors: Makbule Gulcin Ozsoy, Leila Messallem, Jon Besga

Authors: Makbule Gulcin Ozsoy, Leila Messallem, Jon Besga

A deep dive into LangChain’s implementation of graph construction with LLMs

Elevating RAG accuracy and performance by structuring long documents into explorable graphs and implementing graph-based agent systems

😎 Pretty proud to see Ontotext mentioned in more than 10 Gartner Hype Cycle reports over the last couple months! This demonstrates the success of our…

Using SPARQL and the Knowledge Graph for RAG

Retrieval Augmented Generation (RAG) is an innovative approach that combines the power of large language models with external knowledge sources, enabling more accurate and informative generation of content. Using knowledge graphs as sources for RAG (GraphRAG) yields numerous advantages. These knowledge bases encapsulate a vast wealth of curated and interconnected information, enabling the generation of responses that are grounded in factual knowledge. In this post, we show you how to build GraphRAG applications using Amazon Bedrock and Amazon Neptune with LlamaIndex framework.

Many people have asked about loading Microsoft Research #GraphRAG data into Neo4j. I wrote a quick notebook last night to import Documents, Chunks (TextUnit)… | 27 comments on LinkedIn

The Programmable Neuro-Symbolic AGI that lets you program its behavior using Graph-based Prompt Programming: for people who want AI to behave as expected - SynaLinks/HybridAGI

Learn how to build a technical support chatbot with deeper, more relevant retrieval.

End to end solution for migrating CSV data into a Neo4j graph using an LLM for the data discovery and graph data modeling stages. - a-s-g93/neo4j-runway

This notebook converts CSV data into a Neo4j Graph Database. All you do is describe your data. Have you wanted to see what your data looked like as a graph…

How SP used Ontotext GraphDB’s vector capabilities to build a simple RAG retriever over a Knowledge Graph, using open, offline LLM models

How we used Ontotext GraphDB’s vector capabilities to build a simple RAG retriever over a Knowledge Graph, using open, offline LLM models

At Semantic Partners, we wanted to build our informed opinion over the strengths and weaknesses of graph RAG for RDF triple stores. We considered a simple use case: matching a job opening with Curriculum Vitae. We show how we used Ontotext GraphDB to build a simple graph RAG retriever using open, offline LLM models – the graph acting like a domain expert for improving search accuracy.

Another once specialized database technology from the previous big data era might find its way into AI products thanks to retrieval augmented generation.

When to use graph data models, such as parent-child, question-based, and topic-summary, for RAG applications powered by knowledge graphs.