GraphNews

The market is obsessed with the sexy stuff, autonomous agents, reasoning engines, sophisticated orchestration. Meanwhile, the unsexy foundation layer is completely broken. ⭕ And that foundation layer? It's the only thing that determines whether your agent actually works. Here's the technical problem killing agentic AI reliability and that a great company like Lettria solves: The document-to-knowledge-graph pipeline is fundamentally broken : Layer 1: Document Parsing Hell You can't feed a 400-page PDF with mixed layouts into a vision-language model and expect consistent structure. Here's why: Reading order detection fails on multi-column layouts, nested tables, and floating elements Vision LLMs hallucinate cell boundaries on complex tables (financial statements, technical specs) You need bbox-level segmentation with preserved coordinate metadata for traceability Traditional CV models (Doctr, Detectron2, YOLO) outperform transformers on layout detection and run on CPU Optimal approach requires model routing: PDF Plumber for text extraction, specialized table parsers for structured data, VLMs only as fallback Without preserving document_id → page_num → bbox_coords → chunk_id mapping, you lose provenance permanently Layer 2: Ontology Generation Collapse RDF/OWL ontology creation isn't prompt engineering. It's semantic modeling: You need 5-6 levels of hierarchical abstraction (not flat entity lists) Object properties require explicit domain/range specifications (rdfs:domain, rdfs:range) Data properties need typed constraints (xsd:string, xsd:integer, xsd:date) Relationships must follow semantic web standards (owl:ObjectProperty, owl:DatatypeProperty) LLM might output syntactically valid Turtle that violates semantic consistency Proper approach: 8-9 specialized LLM calls with constraint validation, reasoner checks, and ontologist-in-the-loop verification Without this, your knowledge graph has edges connecting semantically incompatible nodes Layer 3: Text-to-RDF Extraction Failure Converting natural language to structured triples while maintaining schema compliance is where frontier models crater: GPT-4/Claude achieve ~60-70% F1 on entity extraction, ~50-60% on relation extraction (measured on Text2KGBench) They hallucinate entities not in your ontology They create relations violating domain/range constraints Context window limitations force truncation (32K tokens = ~10-15 pages with full ontology) A specialized 600M parameter model fine-tuned on 14K annotated triples across 19 domain ontologies hits 85%+ F1 Why? Task-specific loss functions, schema-aware training, constrained decoding The compounding effect destroys reliability Your agent's reasoning is irrelevant when it's operating on a knowledge graph where 73% of nodes/edges are wrong, incomplete, or unverifiable. Without bidirectional traceability (SPARQL query → triple → chunk_id → bbox → source PDF), you can't deploy in regulated environments. Period. | 13 comments on LinkedIn

Building AI agents that can synthesize scattered knowledge like expert developers 🧠 I have a tutorial about building intelligent AI memory systems with Cognee in my 'Agents Towards Production' repo that solves a critical problem - developers navigate between documentation, community practices, and personal experience, but traditional approaches treat these as isolated resources. This tutorial shows how to build a unified knowledge graph that connects Python's design philosophy, real-world implementations from its creator, and your specific development patterns. The tutorial covers 3 key capabilities: - Knowledge Graph Construction: Building interconnected networks from Guido van Rossum's actual commits, PEP guidelines, and personal conversations - Temporal Analysis: Understanding how solutions evolved over time with time-aware queries - Dynamic Memory Layer: Inferring implicit rules and discovering non-obvious connections across knowledge domains The cross-domain discovery is particularly impressive - it connects your validation issues from January 2024 with Guido van Rossum's actual solutions from mypy and CPython. Rather than keyword matching, it understands semantic relationships between your type hinting challenges and historical solutions, even when terminology differs. Tech stack: - Cognee for knowledge graph construction - OpenAI GPT-4o-mini for entity extraction - Graph algorithms for pattern recognition - Vector embeddings for semantic search The system uses semantic graph traversal with deep relationship understanding for contextually aware responses. Includes working Python code, complete Jupyter notebook with interactive visualizations, and production-ready patterns. Part of the collection of practical guides for building production-ready AI systems. Direct link to the tutorial: https://lnkd.in/eSsjwbuh Ever wish you could query all your development knowledge as one unified intelligent system? ♻️ Repost to let your network learn about this too!

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

What is your role? I am working in the Publications Office of the European Union as the team leader of the Reference data team. The Publications Office of the European Union is the official provider of publishing services to all EU institutions, bodies and agencies.

This research aims to investigate the roles of ontology and Semantic Web Technologies (SWT) in modern knowledge representation and data management. By analyzing a dataset of 10,037 academic articles from Web of Science (WoS) published in the last 6 years (2019–2024) across several fields, such as computer science, engineering, and telecommunications, our research identifies important trends in the use of ontologies and semantic frameworks. Through bibliometric and semantic analyses, Natural Language Processing (NLP), and topic modeling using Latent Dirichlet Allocation (LDA) and BERT-clustering approach, we map the evolution of semantic technologies, revealing core research themes such as ontology engineering, knowledge graphs, and linked data. Furthermore, we address existing research gaps, including challenges in the semantic web, dynamic ontology updates, and scalability in Big Data environments. By synthesizing insights from the literature, our research provides an overview of the current state of semantic web research and its prospects. With a 0.75 coherence score and perplexity = 48, the topic modeling analysis identifies three distinct thematic clusters: (1) Ontology-Driven Knowledge Representation and Intelligent Systems, which focuses on the use of ontologies for AI integration, machine interpretability, and structured knowledge representation; (2) Bioinformatics, Gene Expression and Biological Data Analysis, highlighting the role of ontologies and semantic frameworks in biomedical research, particularly in gene expression, protein interactions and biological network modeling; and (3) Advanced Bioinformatics, Systems Biology and Ethical-Legal Implications, addressing the intersection of biological data sciences with ethical, legal and regulatory challenges in emerging technologies. The clusters derived from BERT embeddings and clustering show thematic overlap with the LDA-derived topics but with some notable differences in emphasis and granularity. Our contributions extend beyond theoretical discussions, offering practical implications for enhancing data accessibility, semantic search, and automated knowledge discovery.

We are all beginning to appreciate how important #knowledgegraphs are to #RAG for robust #genAi apps. But did you know that KGs can make a significant improvement to #syntheticdata generation? Engineers need to generate synthetic technical data, particularly for industrial maintenance where real datasets (e.g. about failures) are often limited and unbalanced. This research offers a generic approach to extracting legitimate paths from a knowledge graph to ensure that synthetic maintenance/failure data generated are grounded in engineering knowledge while reflecting the style and language of the technicians who write the #maintenanceworkorders. Turing test experiments reveal that subject matter experts could distinguish real from synthetic data only 51% of the time while exhibiting near-zero agreement, indicating random guessing. Statistical hypothesis testing confirms the results from the Turing Test. Check out this paper which includes all code, data and documentation.  https://lnkd.in/gmyiJKtj Huge congrats to our amazing students who did this work Allison Lau and Jadeyn Feng Allison Lau Jadeyn Feng Caitlin Woods Michael Stewart, Tony Seale Vladimir Alexiev Sarah Lukens Tyler Bikaun, PhD Mark Warrener Piero Baraldi Caitlin Woods Milenija Stojkovic Helgesen MSHelgesen Nils Martin Rugsveen Chris McFarlane Jean-Charles Leclerc Adriano Polpo (de Campos) | 10 comments on LinkedIn

A bottom-up approach to knowledge graph development may be in part alike bottom-up ontology development from existing and legacy resources, but for sure also involves other tasks, and perhaps princ…

Moriondo, L., (2025). ArrowSpace: introducing Spectral Indexing for vector search. Journal of Open Source Software, 10(113), 9002, https://doi.org/10.21105/joss.09002

Table of Contents

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…

Knowledge graphs is a powerful concept where we can represent any flow or entity relationships in a structured way.

How can we create general-purpose graph foundation models? (by Dmitry Eremeev) For a long time, we believed that general-purpose graph foundation models were impossible to create. Indeed, graphs are used to represent data across many different domains, and thus graph machine learning must handle tasks on extremely diverse datasets, such as social, information, transportation, and co-purchasing networks, or models of various physical, biological, or engineering systems. Given the vast differences in structure, features, and labels among these datasets, it seemed unlikely that a single model could achieve robust cross-domain generalization and perform well on all of them. However, we noticed that tabular machine learning faces a similar challenge of working with diverse datasets containing different features and labels. And yet, this field has recently witnessed the emergence of first successful foundation models such as TabPFNv2, which are based on the prior-data fitted networks (PFNs) paradigm. Thus, we have…

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

Exploring Network-Knowledge Graph Duality: A Case Study in Agentic Supply Chain Risk Analysis ... What happens when you ask an AI about supply chain vulnerabilities and it misses the most critical dependencies? Most AI systems treat business relationships like isolated facts in a database. They might know Apple uses lithium batteries, but they miss the web of connections that create real risk. 👉 The Core Problem Standard AI retrieval treats every piece of information as a standalone point. But supply chain risk lives in the relationships between companies, products, and locations. When conflict minerals from the DRC affect smartphone production, it's not just about one supplier - it's about cascading effects through interconnected networks. Vector similarity search finds related documents but ignores the structural dependencies that matter most for risk assessment. 👉 A Different Approach New research from UC Berkeley and MSCI demonstrates how to solve this by treating supply chains as both networks and knowledge graphs simultaneously. The key insight: economic relationships like "Company A produces Product B" are both structural network links and semantic knowledge graph triples. This duality lets you use network science to find the most economically important paths. 👉 How It Works Instead of searching for similar text, the system: - Maps supply chains as networks with companies, products, and locations as nodes - Uses centrality measures to identify structurally important paths - Wraps quantitative data in descriptive language so AI can reason about what numbers actually mean - Retrieves specific relationship paths rather than generic similar content When asked about cobalt risks, it doesn't just find articles about cobalt. It traces the actual path from DRC mines through battery manufacturers to final products, revealing hidden dependencies. The system generates risk narratives that connect operational disruptions to financial impacts without requiring specialized training or expensive graph databases. This approach shows how understanding the structure of business relationships - not just their content - can make AI genuinely useful for complex domain problems.

Another awesome Graph RAG paper from February: Agentic Retrieval-Augmented Generation: A Survey ON Agentic RAG by Aditi Singh, Ph.D., Abul E., Saket Kumar and Tala Talaei Khoei, Ph.D.. Section 3 is a complete breakdown of the entire RAG and agentic stack from vector RAG to agentic RAG, that I highly recommend for an introduction... there are lots of figures and plain language, so even useful if you're not that technical. The paper then provides an Agentic RAG taxonomy and gives a thorough, high level overview of different forms of Agentic RAG. It outlines the concepts relating to Agentic RAG, which it refers to as having: - Multiple, autonomous agents - Dynamic decision-making - Iterative refinement and workflow optimization - Adaptable to real-time changes - Scalable for multi-domain tasks - High accuracy What does that mean? Traditional RAG systems, with their static workflows and limited adaptability, often struggle to handle dynamic, multistep reasoning and complex real-world tasks. These limitations have spurred the integration of agentic intelligence, resulting in Agentic RAG. By incorporating autonomous agents capable of dynamic decision-making, iterative reasoning, and adaptive retrieval strategies, Agentic RAG builds on the modularity of earlier paradigms while overcoming their inherent constraints. This evolution enables more complex, multi-domain tasks to be addressed with enhanced precision and contextual understanding, positioning Agentic RAG as a cornerstone for next-generation AI applications. In particular, Agentic RAG systems reduce latency through optimized workflows and refine outputs iteratively, tackling the very challenges that have historically hindered traditional RAG’s scalability and effectiveness. That sounds cool... now how does it work? Agentic RAG is a combination of tool calling agents iteratively accessing different kinds of data stores and APIs in collaboration with other agents that may split tasks in parallel, check one another's work of perform different parts of a chain of prompts. Single Agentic RAG, the simplest form, rocks these features... in summary it can supplement RAG-retrieval by routing queries to different forms of search ("[filesystem, relational DB, graph DB], semantic search, web search"), as well as external APIs such as DuckDuckGo, Serp, Splunk, Wikipedia, Salesforce, Outlook, Dropbox, Google Workspace, Slack, Discord or multiple, iterative tool usage via your favorite MPC servers. The possibilities to craft your own agentic RAG workflows are enormous! The paper is on arXiv here: https://lnkd.in/gZ8ypXYf

Knowledge graphs aren’t magic, and they’re not snake oil. They excel at multi-hop reasoning and explainability, but add complexity that’s…

Construct a knowledge graph and use it to enable your AI agent to find and call the right APIs in the right order.

A head-to-head schema experiment uncovers whether well-implemented structured data gives pages an edge in Google AI Overviews.

Protocols move bits. Semantics move value. The reports on agents are starting to sound samey: go vertical not horizontal; redesign workflows end-to-end; clean your data; stop doing pilots that automate inefficiencies; price for outcomes when the agent does the work. All true. All necessary. All needing repetition ad nauseam. So it’s refreshing to see a switch-up in Bain’s Technology Report 2025: the real leverage now sits with semantics. A shared layer of meaning. Bain notes that protocols are maturing. MCP and A2A let agents pass tool calls, tokens, and results between layers. Useful plumbing. But there’s still no shared vocabulary that says what an invoice, policy, or work order is, how it moves through states, and how it maps to APIs, tables, and approvals. Without that, cross-vendor reliability will keep stalling. They go further: whoever lands a pragmatic semantic layer first gets winner-takes-most network effects. Define the dictionary and you steer the value flow. This isn’t just a feature. It’s a control point. Bain frames the stack clearly: - Systems of record (data, rules, compliance) - Agent operating systems (orchestration, planning, memory) - Outcome interfaces (natural language requests, user-facing actions) The bottleneck is semantics. And there’s a pricing twist. If agents do the work, semantics define what “done” means. That unlocks outcome-based pricing, charging for tasks completed or value delivered, not log-ons. Bain is blunt: the open, any-to-any agent utopia will smash against vendor incentives, messy data, IP, and security. Translation: walled gardens lead first. Start where governance is clear and data is good enough, then use that traction to shape the semantics others will later adopt. This is where I’m seeing convergence. In practice, a knowledge graph can provide that shared meaning, identity, relationships, and policy. One workable pattern: the agent plans with an LLM, resolves entities and checks rules in the graph, then acts through typed APIs, writing back as events the graph can audit. That’s the missing vocabulary and the enforcement that protocols alone can’t cover. Tony Seale puts it well: “Neural and symbolic systems are not rivals; they are complements… a knowledge graph provides the symbolic backbone… to ground AI in shared semantics and enforce consistency.” To me, this is optimistic, because it moves the conversation from “make the model smarter” to “make the system understandable.” Agents don’t need perfection if they are predictable, composable, and auditable. Semantics deliver that. It’s also how smaller players compete with hyperscalers: you don’t need to win the model race to win the meaning race. With semantics, agents become infrastructure. The next few years won’t be won by who builds the biggest model. It’ll be won by who defines the smallest shared meaning. | 27 comments on LinkedIn

Table of Contents

Introducing Microsoft Sentinel graph (Public Preview)

The single most undervalued fact of graph theory: Every board is a graph in disguise. Here’s the 3-step mapping that turns messy “rooms” into clean, countable components. 0/ You’re given a map of walls and floor tiles. By eye, you see there are three rooms. But how do you get a computer to see them too? 1/ Start by modeling the board as a graph. Treat every floor tile as a node. Define valid moves as edges. In our case, moves are the four directions: • Up • Down • Left • Right Walls simply remove edges because you can’t step through them. 2/ Number the floor tiles arbitrarily so you can reference nodes. Now you’ve converted the board to an undirected graph. Why do this? Because two common board questions become standard graph problems. 1. “Shortest path between two tiles?” becomes “shortest path between two nodes.” 2. “How many rooms?” becomes “how many connected components?” That second one is our target. A “room” is just a maximal set of tiles reachable from each other without crossing walls. In graph terms, that’s a connected component. So the count of rooms equals the count of connected components. Here’s the practical recipe I use: • Nodes = all floor tiles. • Edges = pairs of floor tiles one step apart (U/D/L/R). • Walls = missing edges. • Rooms = connected components. • Answer = number of connected components. 3. You can run a DFS or BFS from every unvisited node and mark all reachable tiles. Each fresh start increments the room counter by one. That’s it. No heuristics, no guesswork, just graph structure doing the heavy lifting. Once you see boards as graphs, these problems stop feeling ad hoc. They become repeatable templates you can code in minutes. If this helped, repost so more people learn the “rooms = components” pattern.

G-REASONER: foundation models for unified reasoning over graph-structured knowledge ... Why Graph-Enhanced AI Still Struggles with Complex Reasoning (And How G-REASONER Fixes It) Ever wondered why current AI systems still fail at connecting the dots across complex knowledge domains? The answer lies in how they handle structured information. 👉 The Core Problem Large language models excel at reasoning but hit a wall when dealing with interconnected knowledge. Traditional retrieval systems treat information as isolated fragments, missing the rich relationships that make knowledge truly useful. Current graph-enhanced approaches face three critical limitations: - They're designed for specific graph types only - They rely on expensive agent-based reasoning - They can't generalize across different domains 👉 What G-REASONER Brings to the Table Researchers from Monash University and collaborating institutions introduce G-REASONER, a unified framework that bridges graph and language foundation models. The key innovation is QuadGraph - a standardized four-layer structure that unifies diverse knowledge sources: - Community layer for global context - Document layer for textual information - Knowledge graph layer for factual relationships - Attribute layer for common properties 👉 How It Works in Practice G-REASONER employs a 34M-parameter graph foundation model that jointly processes graph topology and text semantics. Unlike previous approaches, it uses knowledge distillation to learn from large-scale datasets with weak supervision. The system implements distributed message-passing across multiple GPUs, enabling efficient scaling. Mixed-precision training reduces memory usage by 17.5% while doubling training throughput. Testing across six benchmarks shows consistent improvements over state-of-the-art baselines, with particularly strong performance on multi-hop reasoning tasks requiring complex knowledge connections. The framework demonstrates remarkable generalization - the same model works effectively across medical records, legal documents, and encyclopedia data without domain-specific fine-tuning. This represents a significant step toward AI systems that can reason over structured knowledge as fluidly as humans navigate interconnected concepts.

I am excited to announce the formation of a Data Façades W3C Community Group. Façade-X, initially introduced at SEMANTICS 2021 and successfully implemented by the SPARQL Anything project, provides a simple yet powerful, homogeneous view over diverse and heterogeneous data sources (e.g., CSV, JSON, XML, and many others). With the recent v1.0.0 release of SPARQL Anything, the time was right to work on the long-term stability and widespread adoption of this approach by developing an open, vendor-neutral technology. The Façade-X concept was born to allow SPARQL users to query data in any structured format in plain SPARQL. Therefore, the choice of a W3C community group to lead efforts on specifications is just natural. Specifications will enhance its reliability, foster innovation, and encourage various vendors and projects—including graph database developers — to provide their own compatible implementations. The primary goals of the Data Façades Community Group is to: Define the core specification of the Façade-X method. Define Standard Mappings: Formalize the required mappings and profiles for connecting Façade-X to common data formats. Define the specification of the query dialect: Provide a reference for the SPARQL dialect, configuration conventions (like SERVICE IRIs), and the functions/magic properties used. Establish Governance: Create a monitored, robust process for adding support for new data formats. Foster Collaboration: Build connections with relevant W3C groups (e.g., RDF & SPARQL, Data Shapes) and encourage involvement from developers, businesses, and adopters. Join us! With Luigi Asprino Ivo Velitchkov Justin Dowdy Paul Mulholland Andy Seaborne Ryan Shaw ... CG: https://lnkd.in/eSxuqsvn Github: https://lnkd.in/dkHGT8N3 SPARQL Anything #RDF #SPARQL #W3C #FX

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.

Product management makes or breaks AI. That includes 𝐝𝐚𝐭𝐚. The role of 𝐝𝐚𝐭𝐚 𝐏𝐌 is shifting. For years, the focus was BI - dashboards, reports, warehouses. But AI demands more: context, retrieval, real time, and integration into the flow of work. Data PMs who understand AI requirements will define the next generation of enterprise success. Here’s how my team thinks about BI-ready vs AI-ready data 👇