Please read the previous article on Vanilla RAG

For all the excitement around large language models, the latest research from Simona-Vasilica Oprea and Georgiana Stănescu (Electronics 14:1313, 2025) offers a reality check. Automatic ontology generation, even with novel prompting techniques like Memoryless CQ-by-CQ and Ontogenia, remains a partial

Is Graph Data Science a critical, transformative layer for GraphRAG? The field of enterprise Artificial Intelligence (AI) is undergoing a significant architectural evolution. The initial enthusiasm for Large Language Models (LLMs) has matured into a pragmatic recognition of their limitations, partic

I’ve tested countless Retrieval-Augmented Generation (RAG) systems, and they all failed to meet my expectations. I found a simple two-step…

If you’ve ever asked yourself, “Does GraphRAG really outperform vanilla RAG—and by how much?”, you’re not alone.

Welcome back, let’s dive into Chapter 50 of this insightful series!AI Exploration Journey is a reader-supported publication.

Is it worth the hype? How knowledge graphs (KGs) are constructed and queried, and what I learned digging deeper…

𝗙𝗹𝗲𝘅𝗶𝗯𝗹𝗲 𝗚𝗿𝗮𝗽𝗵𝗥𝗔𝗚 𝗼𝗿 𝗥𝗔𝗚 is now flexing to the max using LlamaIndex, supports 𝟳 𝗴𝗿𝗮𝗽𝗵 𝗱𝗮𝘁𝗮𝗯𝗮𝘀𝗲𝘀, 𝟭𝟬 𝘃𝗲𝗰𝘁𝗼𝗿 𝗱𝗮𝘁𝗮𝗯𝗮𝘀𝗲𝘀, 𝟭𝟯 𝗱𝗮𝘁𝗮 𝘀𝗼𝘂𝗿𝗰𝗲𝘀, 𝗟𝗟𝗠𝘀, Docling 𝗱𝗼𝗰 𝗽𝗿𝗼𝗰𝗲𝘀𝘀𝗶𝗻𝗴, 𝗮𝘂𝘁𝗼 𝗰𝗿𝗲𝗮𝘁𝗲 𝗞𝗚𝘀, 𝗚𝗿𝗮𝗽𝗵𝗥𝗔𝗚, 𝗛𝘆𝗯𝗿𝗶𝗱 𝗦𝗲𝗮𝗿𝗰𝗵, 𝗔𝗜 𝗖𝗵𝗮𝘁 (shown Hyland products web page data src) 𝗔𝗽𝗮𝗰𝗵𝗲 𝟮.𝟬 𝗢𝗽𝗲𝗻 𝗦𝗼𝘂𝗿𝗰𝗲 𝗚𝗿𝗮𝗽𝗵: Neo4j ArcadeDB FalkorDB Kuzu NebulaGraph, powered by Vesoft (coming Memgraph and 𝗔𝗺𝗮𝘇𝗼𝗻 𝗡𝗲𝗽𝘁𝘂𝗻𝗲) 𝗩𝗲𝗰𝘁𝗼𝗿: Qdrant, Elastic, OpenSearch Project, Neo4j 𝘃𝗲𝗰𝘁𝗼𝗿, Milvus, created by Zilliz (coming Weaviate, Chroma, Pinecone, 𝗣𝗼𝘀𝘁𝗴𝗿𝗲𝗦𝗤𝗟 + 𝗽𝗴𝘃𝗲𝗰𝘁𝗼𝗿, LanceDB) Docling 𝗱𝗼𝗰𝘂𝗺𝗲𝗻𝘁 𝗽𝗿𝗼𝗰𝗲𝘀𝘀𝗶𝗻𝗴 𝗗𝗮𝘁𝗮 𝗦𝗼𝘂𝗿𝗰𝗲𝘀: using LlamaIndex readers: working: Web Pages, Wikipedia, Youtube, untested: Google Drive, Msft OneDrive, S3, Azure Blob, GCS, Box, SharePoint, previous: filesystem, Alfresco, CMIS. 𝗟𝗟𝗠𝘀: 𝗟𝗹𝗮𝗺𝗮𝗜𝗻𝗱𝗲𝘅 𝗟𝗟𝗠𝘀 (OpenAI, Ollama, Claude, Gemini, etc.) 𝗥𝗲𝗮𝗰𝘁, 𝗩𝘂𝗲, 𝗔𝗻𝗴𝘂𝗹𝗮𝗿 𝗨𝗜𝘀, 𝗠𝗖𝗣 𝘀𝗲𝗿𝘃𝗲𝗿, 𝗙𝗮𝘀𝘁𝗔𝗣𝗜 𝘀𝗲𝗿𝘃𝗲𝗿 𝗚𝗶𝘁𝗛𝘂𝗯 𝘀𝘁𝗲𝘃𝗲𝗿𝗲𝗶𝗻𝗲𝗿/𝗳𝗹𝗲𝘅𝗶𝗯𝗹𝗲-𝗴𝗿𝗮𝗽𝗵𝗿𝗮𝗴: https://lnkd.in/eUEeF2cN 𝗫.𝗰𝗼𝗺 𝗣𝗼𝘀𝘁 𝗼𝗻 𝗙𝗹𝗲𝘅𝗶𝗯𝗹𝗲 𝗚𝗿𝗮𝗽𝗵𝗥𝗔𝗚 𝗼𝗿 𝗥𝗔𝗚 𝗺𝗮𝘅 𝗳𝗹𝗲𝘅𝗶𝗻𝗴 https://lnkd.in/gHpTupAr 𝗜𝗻𝘁𝗲𝗴𝗿𝗮𝘁𝗲𝗱 𝗦𝗲𝗺𝗮𝗻𝘁𝗶𝗰𝘀 𝗕𝗹𝗼𝗴: https://lnkd.in/ehpjTV7d

KG-R1, Why Knowledge Graph RAG Systems Are Too Expensive to Deploy (And How One Team Fixed It) ... What if I told you that most knowledge graph systems require multiple AI models just to answer a single question? That's exactly the problem plaguing current KG-RAG deployments. 👉 The Cost Problem Traditional knowledge graph retrieval systems use a pipeline approach: one model for planning, another for reasoning, a third for reviewing, and a fourth for responding. Each step burns through tokens and compute resources, making deployment prohibitively expensive for most organizations. Even worse? These systems are built for specific knowledge graphs. Change your data source, and you need to retrain everything. 👉 A Single-Agent Solution Researchers from MIT and IBM just published KG-R1, which replaces this entire multi-model pipeline with one lightweight agent that learns through reinforcement learning. Here's the clever part: instead of hardcoding domain-specific logic, the system uses four simple, universal operations: - Get relations from an entity - Get entities from a relation - Navigate forward or backward through connections These operations work on any knowledge graph without modification. 👉 The Results Are Striking Using just a 3B parameter model, KG-R1: - Matches accuracy of much larger foundation models - Uses 60% fewer tokens per query than existing methods - Transfers across different knowledge graphs without retraining - Processes queries in under 7 seconds on a single GPU The system learned to retrieve information strategically through multi-turn interactions, optimized end-to-end rather than stage-by-stage. This matters because knowledge graphs contain some of our most valuable structured data - from scientific databases to legal documents. Making them accessible and affordable could unlock entirely new applications.

Today, I'd like to introduce the GitLab Knowledge Graph. This release includes a code indexing engine, written in Rust, that turns your codebase into a live, embeddable graph database for LLM RAG. You can install it with a simple one-line script, parse local repositories directly in your editor, and connect via MCP to query your workspace and over 50,000 files in under 100 milliseconds. We also saw GKG agents scoring up to 10% higher on the SWE-Bench-lite benchmarks, with just a few tools and a small prompt added to opencode (an open-source coding agent). On average, we observed a 7% accuracy gain across our eval runs, and GKG agents were able to solve new tasks compared to the baseline agents. You can read more from the team's research here https://lnkd.in/egiXXsaE. This release is just the first step: we aim for this local version to serve as the backbone of a Knowledge Graph service that enables you to query the entire GitLab Software Development Life Cycle—from an Issue down to a single line of code. I am incredibly proud of the work the team has done. Thank you, Michael U., Jean-Gabriel Doyon, Bohdan Parkhomchuk, Dmitry Gruzd, Omar Qunsul, and Jonathan Shobrook. You can watch Bill Staples and I present this and more in the GitLab 18.4 release here: https://lnkd.in/epvjrhqB Try today at: https://lnkd.in/eAypneFA Roadmap: https://lnkd.in/eXNYQkEn Watch more below for a complete, in-depth tutorial on what we've built: | 19 comments on LinkedIn

GraphSearch: An Agentic Deep‑Search Workflow for Graph Retrieval‑Augmented Generation ... Why Current AI Search Falls Short When You Need Real Answers What happens when you ask an AI system a complex question that requires connecting multiple pieces of information? Most current approaches retrieve some relevant documents, generate an answer, and call it done. But this single-pass strategy often misses critical evidence. 👉 The Problem with Shallow Retrieval Traditional retrieval-augmented generation (RAG) systems work like a student who only skims the first few search results before writing an essay. They grab what seems relevant on the surface but miss deeper connections that would lead to better answers. When researchers tested these systems on complex multi-hop questions, they found a consistent pattern: the AI would confidently provide answers based on incomplete evidence, leading to logical gaps and missing key facts. 👉 A New Approach: Deep Searching with Dual Channels Researchers from IDEA Research and Hong Kong University of Science and Technology developed GraphSearch, which works more like a thorough investigator than a quick searcher. The system breaks down complex questions into smaller, manageable pieces, then searches through both text documents and structured knowledge graphs. Think of it as having two different research assistants: one excellent at finding descriptive information in documents, another skilled at tracing relationships between entities. 👉 How It Actually Works Instead of one search-and-answer cycle, GraphSearch uses six coordinated modules: Query decomposition splits complex questions into atomic sub-questions Context refinement filters out noise from retrieved information Query grounding fills in missing details from previous searches Logic drafting organizes evidence into coherent reasoning chains Evidence verification checks if the reasoning holds up Query expansion generates new searches to fill identified gaps The system continues this process until it has sufficient evidence to provide a well-grounded answer. 👉 Real Performance Gains Testing across six different question-answering benchmarks showed consistent improvements. On the MuSiQue dataset, for example, answer accuracy jumped from 35% to 51% when GraphSearch was integrated with existing graph-based systems. The approach works particularly well under constrained conditions - when you have limited computational resources for retrieval, the iterative searching strategy maintains performance better than single-pass methods. This research points toward more reliable AI systems that can handle the kind of complex reasoning we actually need in practice. Paper: "GraphSearch: An Agentic Deep Searching Workflow for Graph Retrieval-Augmented Generation" by Yang et al.

In this blog by Alex Gilmore, learn about strategies and methods for ingestion and knowledge graph generation.

This is a very simple post, but if you are confused about LLMs, Knowledge Graphs and Ontologies, if you have questions like "what is a knowledge graph?", "can LLM do all?" or "do we still need ontologies?", I hope this post can bring some simple of fundamental orientation. Warning: this is not a tre

Sign in or join now to see posts like this one and more.

Graph-based Retrieval-Augmented Generation (RAG) methods have significantly enhanced the performance of large language models (LLMs) in domain-specific tasks. However, existing RAG methods do not...

Learn how neurosymbolic frameworks and knowledge graphs are the key to bring structure, context, and flexibility to LLM-powered systems.

Now we can build knowledge graphs without tedious text preprocessing using smaller LLMs on laptops

A framework for measuring retrieval quality in Model Context Protocol agents

Graph retrieval-augmented generation (GraphRAG) has effectively enhanced large language models in complex reasoning by organizing fragmented knowledge into explicitly structured graphs. Prior...

If you could hire the smartest engineers and drop them in your code base would you expect miracles overnight? No, of course not! Because even if they are the best of coders, they don’t have context on your project, engineering processes and culture, security and compliance rules, user personas, business priorities, etc. The same is true of the very best agents.. they may know how to write (mostly) technically correct code, and have the context of your source code, but they’re still missing tons of context. Building agents that can deliver high quality outcomes, faster, is going to require much more than your source code, rules and a few prompts. Agents need the same full lifecyle context your engineers gain after being months and years on the job. LLMs will never have access to your company’s engineering systems to train on, so something has to bridge the knowledge gap and it shouldn’t be you, one prompt at a time. This is why we're building what we call our Knowledge Graph at GitLab. It's not just indexing files and code; it's mapping the relationships across your entire development environment. When an agent understands that a particular code block contains three security vulnerabilities, impacts two downstream services, and connects to a broader epic about performance improvements, it can make smarter recommendations and changes than just technically correct code. This kind of contextual reasoning is what separates valuable AI agents from expensive, slow, LLM driven search tools. We're moving toward a world where institutional knowledge becomes portable and queryable. The context of a veteran engineer who knows "why we built it this way" or "what happened last time we tried this approach" can now be captured, connected, and made available to both human teammates and AI agents. See the awesome demos below and I look forward to sharing more later this month in our 18.4 beta update!

Atomic Facts, Validation, Entity Resolution, KG and more

💡 Graph of Ideas -- LLMs paired with knowledge graphs can be great partners for ideation, exploration, and research. We've all seen the classic detective corkboard, with pinned notes and pictures, all strung together with red twine. 🕵️  The digital version could be a mind-map, but you still have to draw everything by hand. What if you could just build one from a giant pile of documents? Enter GoAI - a fascinating approach that just dropped on arXiv combining knowledge graphs with LLMs for AI research idea generation. While the paper focuses on a graph of research papers, the approach is generalizable. Here's what caught my attention: 🔗 It builds knowledge graphs from AI papers where nodes are papers/concepts and edges capture semantic citation relationships - basically mapping how ideas actually connect and build on each other 🎯 The "Idea Studio" feature gives you feedback on innovation, clarity, and feasibility of your research ideas - like having a research mentor in your pocket 📈 Experiments show it helps produce clearer, more novel, and more impactful research ideas compared to traditional LLM approaches The key insight? Current LLMs miss the semantic structure and prerequisite relationships in academic knowledge. This framework bridges that gap by making the connections explicit. As AI research accelerates, this approach can be be used for any situation where you're looking for what's missing, rather than answering a question about what exists. Read all the details in the paper... https://lnkd.in/ekGtCx9T

Unlock true AI potential with neuro-symbolic AI. Learn how combining LLMs with knowledge graphs solves unreliable and inaccurate outputs for enterprise success.

This post captures the desire for a short cut to #KnowledgeGraphs, the inability of #LLMs to reliably generate #StructuredKnowledge, and the lengths folks will go to realize even basic #semantic queries (the author manually encoded 1,000 #RDF triples, but didn’t use #OWL). https://lnkd.in/eJE_27gS #Ontologists by nature are generally rigorous, if not a tad bit pedantic, as they seek to structure #domain knowledge. 25 years of #SemanticWeb and this is still primarily a manual, tedious, time-consuming and error-prone process. In part, #DeepLearning is a reaction to #structured, #labelled, manually #curated #data (#SymbolicAI). When #GenAI exploded on the scene a couple of years ago, #Ontologist were quick to note the limitations of LLMs. Now some #Ontologists are having a "Road to Damascus" moment - they are aspirationally looking to Language Models as an interface for #Ontologies to lower barrier to ontology creation and use, which are then used for #GraphRAG, but this is a circular firing squad given the LLM weaknesses they have decried. This isn't a solution, it's a Hail Mary. They are lowering the standards on quality and setting up the even more tedious task of identifying non-obvious, low-level LLM errors in an #Ontology (same issue Developers have run into with LLM CodeGen - good for prototypes, not for production code). The answer is not to resign ourselves and subordinate ontologies to LLMs, but to take the high-road using #UpperOntologies to ease and speed the design, use and maintenance of #KGs. An upper ontology is a graph of high-level concepts, types and policies independent of a specific #domain implementation. It provides an abstraction layer with re-usable primitives, building blocks and services that streamline and automate domain modeling tasks (i.e., a #DSL for DSLs). Importantly, an upper ontology drives well-formed and consistent objects and relationships and provides for governance (e.g., security/identity, change management). This is what we do EnterpriseWeb. #Deterministic, reliable, trusted ontologies should be the center of #BusinessArchitecture, not a side-car to an LLM.

Guy van den Broeck (UCLA)https://simons.berkeley.edu/talks/guy-van-den-broeck-ucla-2025-04-29Theoretical Aspects of Trustworthy AIToday, many expect AI to ta...

Blue Morpho: A new solution for building AI apps on top of knowledge bases Blue Morpho helps you build AI agents that understand your business context, using ontologies and knowledge graphs. Knowledge Graphs work great with LLMs. The problem is that building KGs from unstructured data is hard. Blue Morpho promises a system that turns PDFs and text files into knowledge graphs. KGs are then used to augment LLMs with the right context to answer queries, make decisions, produce reports, and automate workflows. How it works: 1. Upload documents (pdf or txt). 2. Define your ontology: concepts, properties, and relationships. (Coming soon: ontology generation via AI assistant.) 3. Extract a knowledge graph from documents based on that ontology. Entities are automatically deduplicated across chunks and documents, so every mention of “Walmart,” for example, resolves to the same node. 4. Build agents on top. Connect external ones via MCP, or use Blue Morpho: Q&A (“text-to-cypher”) and Dashboard Generation agents. Blue Morpho differentiation: - Strong focus on reliability. Guardrails in place to make sure LLMs follow instructions and the ontology.  - Entity deduplication, with AI reviewing edge cases. - Easy to iterate on ontologies: they are versioned, extraction runs are versioned as well with all their parameters, and changes only trigger necessary recomputes.  - Vector embeddings are only used in very special circumstances, coupled with other techniques. Link in comments. Jérémy Thomas #KnowledgeGraph #AI #Agents #MCP #NewRelease #Ontology #LLMs #GenAI #Application -- Connected Data London 2025 is coming! 20-21 November, Leonardo Royal Hotel London Tower Bridge Join us for all things #KnowledgeGraph #Graph #analytics #datascience #AI #graphDB #SemTech #Ontology 🎟️ Ticket sales are open. Benefit from early bird prices with discounts up to 30%. https://lnkd.in/diXHEXNE 📺 Sponsorship opportunities are available. Maximize your exposure with early onboarding. Contact us at info@connected-data.london for more.

Just released a new notebook exploring Semantic Entity Resolution & Extraction using DSPy (Community) and Google's new LangExtract library. Inspired by Russell Jurney’s excellent work on semantic entity resolution, this demo follows his approach of combining: ✅ embeddings, ✅ kNN blocking, ✅ and LLM matching with DSPy (Community). On top of that, I added a general extraction layer to test-drive LangExtract, a Gemini-powered, open-source Python library for reliable structured information extraction. The goal? Detect and merge mentions of the same real-world entities across text. It’s an end-to-end flow tackling one of the most persistent data challenges. Check it out, experiment with your own data, 𝐞𝐧𝐣𝐨𝐲 𝐭𝐡𝐞 𝐬𝐮𝐦𝐦𝐞𝐫 and let me know your thoughts! cc Paco Nathan you might like this 😉 https://wor.ai/8kQ2qa

Stop manually building your company's brain. ❌ Having reviewed the excellent DeepLearning.AI lecture on Agentic Knowledge Graph Construction, by Andreas Kollegger and writing a book on Agentic graph system with Sam Julien, it is clear that the use of agentic systems represents a shift in how we build and maintain knowledge graphs (KGs). Most organizations are sitting on a goldmine of data spread across CSVs, documents, and databases. The dream is to connect it all into a unified Knowledge Graph, an intelligent brain that understands your entire business. The reality? It's a brutal, expensive, and unscalable manual process. But a new approach is changing everything. Here’s the new playbook for building intelligent systems: 🧠 Deploy an AI Agent Workforce Instead of rigid scripts, you use a cognitive assembly line of specialized AI agents. A Proposer agent designs the data model, a Critic refines it, and an Extractor pulls the facts. This modular approach is proven to reduce errors and improve the accuracy and coherence of the final graph. 🎨 Treat AI as a Designer, Not Just a Doer The agents act as data architects. In discovery mode, they analyze unstructured data (like customer reviews) and propose a new logical structure from scratch. In an enterprise with an existing data model, they switch to alignment mode, mapping new information to the established structure. 🏛️ Use a 3-Part Graph Architecture This technique is key to managing data quality and uncertainty. You create three interconnected graphs: The Domain Graph: Your single source of truth, built from trusted, structured data. The Lexical Graph: The raw, original text from your documents, preserving the evidence. The Subject Graph: An AI-generated bridge that connects them. It holds extracted insights that are validated before being linked to your trusted data. Jaro-Winkler is a string comparison algorithm that measures the similarity or edit distance between two strings. It can be used here for entity resolution, the process of identifying and linking entities from the unstructured text (Subject Graph) to the official entities in the structured database (Domain Graph). For example, the algorithm compares a product name extracted from a customer review (e.g., "the gothenburg table") with the official product names in the database. If the Jaro-Winkler similarity score is above a certain threshold, the system automatically creates a CORRESPONDS_TO relationship, effectively linking the customer's comment to the correct product in the supply chain graph. 🤝 Augment Humans, Don't Replace Them The workflow is Propose, then Approve. AI does the heavy lifting, but a human expert makes the final call. This process is made reliable by tools like Pydantic and Outlines, which enforce a rigid contract on the AI's output, ensuring every piece of data is perfectly structured and consistent. And once discovered and validated, a schema can be enforced. | 32 comments on LinkedIn