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

Join our slack and come to the next Graph Learning on Wednesdays (GLOW) session.https://sites.google.com/view/graph-learning-on-wedsOn March 26th, 2025, we h...

It seems the answer on whether an LMM would be able to replace the whole text-to-ontology pipeline is a resounding ‘no’. If you’re one of those who think that should be (or even is?) a ‘yes’: why, and did you do the experiments that show it’s as good as the alternatives (with the results available)? And I mean a proper ontology, not a knowledge graph with numerous duplications and contradictions and lacking constraints. For a few gentle considerations (and pointers to longer arguments) and a summary figure of processes the LLM supposedly would be replacing: see https://lnkd.in/dG_Xsv_6 | 43 comments on LinkedIn

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

Deep stuff! We uncovered a startling link between #entropy, a bedrock concept in #physics, and how #AI can discover new ideas without stagnating. In an era… | 41 comments on LinkedIn

LLMs are taking Graph Neural Networks to the next level: While we've been discussing LLMs for natural language, they're quietly changing how we represent…

This blog post is part of a series that dives into various aspects of SAP’s approach to Generative AI, and its technical underpinnings. In previous blog posts of this series, you learned about how to use large language models (LLMs) for developing AI applications in a trustworthy and reliable manner...

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

Multi-Layer Agentic Reasoning: Connecting Complex Data and Dynamic Insights in Graph-Based RAG Systems 🛜 At the most fundamental level, all approaches rely… | 11 comments on LinkedIn

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

🎁⏳ Zep packs Temporal Knowledge Graphs + Semantic Entity Extraction + Cypher Queries storage—Outperforming MemGPT with 94.8% Accuracy. Build Personalized AI… | 46 comments on LinkedIn

Copyright 2025 Kurt Cagle / The Ontologist

To gain competitive advantage from gen AI, enterprises need to be able to add their own expertise to off-the-shelf systems. Yet standard enterprise data stores aren't a good fit to train large language models.

🎉 We're thrilled to unveil Synalinks (🧠🔗), an open-source framework designed to streamline the creation, evaluation, training, and deployment of…

Breaking LLM Hallucinations in a Smarter Way! (It’s not about feeding more data) Large Language Models (LLMs) still struggle with factual inaccuracies, but…

Build a knowledge graph without an LLM for your RAG applications

KET-RAG: Turbocharging AI Agents with 10x Cheaper, Smarter Knowledge Retrieval This Multi-Granular Graph Framework uses PageRank and Keyword-Chunk Graph to have the Best Cost-Quality Tradeoff ﹌﹌﹌﹌﹌﹌﹌﹌﹌ 》The Problem: Knowledge Graphs Are Expensive (and Clunky) AI agents need context to answer complex questions—like connecting “COVID vaccines” to “myocarditis risks” across research papers. But today’s solutions face two nightmares: ✸ Cost: Building detailed knowledge graphs with LLMs can cost $33,000 for a 5GB legal case. ✸ Quality: Cheap methods (like KNN graphs) miss key relationships, leading to 32% worse answers. ☆ Imagine training an AI doctor that either bankrupts you or misdiagnoses patients. Ouch. ﹌﹌﹌﹌﹌﹌﹌﹌﹌ 》The Fix: KET-RAG’s Two-Layer Brain KET-RAG merges precision (knowledge graphs) and efficiency (keyword-text maps) into one system: ✸ Layer 1: Knowledge Graph Skeleton ☆ Uses PageRank to find core text chunks (like “vaccine side effects” in medical docs). ☆ Builds a sparse graph only on these chunks with LLMs—saving 80% of indexing costs. ✸ Layer 2: Keyword-Chunk Bipartite Graph ☆ Links keywords (e.g., “myocarditis”) to all related text snippets—no LLM needed. ☆ Acts as a “fast lane” for retrieving context without expensive entity extraction. ﹌﹌﹌﹌﹌﹌﹌﹌﹌ 》Results: Beating Microsoft’s Graph-RAG with Pennies On HotpotQA and MuSiQue benchmarks, KET-RAG: ✸ Retrieves 81.6% of critical info vs. Microsoft’s 74.6%—with 10x lower cost. ✸ Boosts answer accuracy (F1 score) by 32.4% while cutting indexing bills by 20%. ✸ Scales to terabytes of data without melting budgets. ☆ Think of it as a Tesla Model 3 outperforming a Lamborghini at 1/10th the price. ﹌﹌﹌﹌﹌﹌﹌﹌﹌ 》Why AI Agents Need This AI agents aren’t just chatbots—they’re problem solvers for medicine, law, and customer service. KET-RAG gives them: ✸ Real-time, multi-hop reasoning: Connecting “drug A → gene B → side effect C” in milliseconds. ✸ Cost-effective scalability: Deploying agents across millions of documents without going broke. ✸ Adaptability: Mixing precise knowledge graphs (for critical data) with keyword maps (for speed). Paper in comments ≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣ 》Build Your Own Supercharged AI Agent? 🔮 Join My 𝐇𝐚𝐧𝐝𝐬-𝐎𝐧 𝐀𝐈 𝐀𝐠𝐞𝐧𝐭𝐬 𝐓𝐫𝐚𝐢𝐧𝐢𝐧𝐠 TODAY! and Learn Building AI Agent with Langgraph/Langchain, CrewAI and OpenAI Swarm + RAG Pipelines 𝐄𝐧𝐫𝐨𝐥𝐥 𝐍𝐎𝐖 [34% discount]: 👉 https://lnkd.in/eGuWr4CH | 10 comments on LinkedIn

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.

LLMs that automatically fill knowledge gaps - too good to be true? Large Language Models (LLMs) often stumble in logical tasks due to hallucinations, especially when relying on incomplete Knowledge Graphs (KGs). Current methods naively trust KGs as exhaustive truth sources - a flawed assumption in real-world domains like healthcare or finance where gaps persist. SymAgent is a new framework that approaches this problem by making KGs active collaborators, not passive databases. Its dual-module design combines symbolic logic with neural flexibility: 1. Agent-Planner extracts implicit rules from KGs (e.g., "If drug X interacts with Y, avoid co-prescription") to decompose complex questions into structured steps. 2. Agent-Executor dynamically pulls external data when KG triples are missing, bypassing the "static repository" limitation. Perhaps most impressively, SymAgent’s self-learning observes failed reasoning paths to iteratively refine its strategy and flag missing KG connections - achieving 20-30% accuracy gains over raw LLMs. Equipped with SymAgent, even 7B models rival their much larger counterparts by leveraging this closed-loop system. It would be great if LLMs were able to autonomously curate knowledge and adapt to domain shifts without costly retraining. But are we there yet? Are hybrid architectures like SymAgent the future? ↓ Liked this post? Join my newsletter with 50k+ readers that breaks down all you need to know about the latest LLM research: llmwatch.com 💡

When (not) to use GraphRAG

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

🌟 Pathway to Artificial General Intelligence (AGI) 🌟 This is my view on the evolutionary steps toward AGI: 1️⃣ Large Language Models (LLMs): Language models…

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

The recently developed retrieval-augmented generation (RAG) technology has enabled the efficient construction of domain-specific applications. However, it also has limitations, including the gap...

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

This study, sponsored by Graphwise, explores LLMs and RAG in enterprises and provides statistics from executives across various industries.

🚀 Knowledge graphs are shaping the future of data and AI, and I’m excited to see them featured in the Data Gang’s predictions for 2025! 🚀 Every year I enjoy… | 10 comments on LinkedIn