Graph All The Things @graph_db

Michael Hunger (@mesirii) of @neo4j, joins @sjmaple to unpack how graph databases inject structure, intent, and traceability into modern AI systems. On the docket: • why relationships in data encode intent • the black-box problem in vector based RAG • why devs should build their own MCP server AI Native Dev, powered by @tessl_io and our global dev community, is your go-to podcast for solutions in software development in the age of AI. Tune in as we engage with engineers, founders, and open-source innovators to talk all things AI, security, and development.

RAG-Anything: An all-in-One RAG System LightRAG + Multi-Modal = RAG-Anything Modern documents increasingly contain diverse multimodal content—text, images, tables, equations, charts, and multimedia—that traditional text-focused RAG systems cannot effectively process. RAG-Anything addresses this challenge as a comprehensive All-in-One Multimodal Document Processing RAG system built on LightRAG. As a unified solution, RAG-Anything eliminates the need for multiple specialized tools. It provides seamless processing and querying across all content modalities within a single integrated framework. Unlike conventional RAG approaches that struggle with non-textual elements, our all-in-one system delivers comprehensive multimodal retrieval capabilities. Users can query documents containing interleaved text, visual diagrams, structured tables, and mathematical formulations through one cohesive interface. This consolidated approach makes RAG-Anything particularly valuable for academic research, technical documentation, financial reports, and enterprise knowledge management where rich, mixed-content documents demand a unified processing framework. 🎯 Key Features 🔄 End-to-End Multimodal Pipeline - Complete workflow from document ingestion and parsing to intelligent multimodal query answering 📄 Universal Document Support - Seamless processing of PDFs, Office documents, images, and diverse file formats 🧠 Specialized Content Analysis - Dedicated processors for images, tables, mathematical equations, and heterogeneous content types 🔗 Multimodal Knowledge Graph - Automatic entity extraction and cross-modal relationship discovery for enhanced understanding ⚡ Adaptive Processing Modes - Flexible MinerU-based parsing or direct multimodal content injection workflows 🎯 Hybrid Intelligent Retrieval - Advanced search capabilities spanning textual and multimodal content with contextual understanding 💡 Well-suited for: 🎓 Academic research with complex documents 📋 Technical documentation processing 💼 Financial report analysis 🏢 Enterprise knowledge management From Chao Huang et.al, creators of LightRAG github.com/HKUDS/RAG-Anyt… #RAG #GraphRAG #GenAI #Opensource #Datascience #EmergingTech #KnowledgeGraph #AI #LLMs -- The Year of the Graph Spring / Summer 2025 edition is out, with the latest news and insights on all things Knowledge Graph, Graph Analytics / Data Science / AI and Semantic Tech 👇 yearofthegraph.xyz/newsletter/202…

RDFox v7.4 is out now and it has a diverse array of incredible new additions! ✔️Apache Lucene™ integration ✔️SQLite integration ✔️Memory Optimisation ✔️Upgraded UI Design ✔️C and C++ APIs Full release notes: hubs.li/Q03wbDhb0 #RDFox #knowledgegraphs #tech #database #AI

keyboard_arrow_left Previous keyboard_arrow_right Next

If I had any kind of following i'd post this as a poll with an option 4. ??? 'cos i wanna know what gets other people's creative juices flowing

Steve Liles @steveliles

12 months ago

I often do my best problem solving / creative thinking while: 1. walking 2. in the bath 3. pacing back and forth by my desk (at home, not disturbing anyone)

0 0 1 36 0

its over, humans are cooked.

Collin Rugg @CollinRugg

12 months ago

NEW: China launches its first humanoid robot soccer league in Beijing. This is way more entertaining than regular soccer. The AI-controlled robots were supplied by Booster Robotics for the tournament and have the skills of 5 to 6 year old children. Robots were seen getting

4K 5K 29K 10.1M 9K

Innovations in Knowledge Graphs, Graph Data Science and AI, Graph Databases, Semantic Technology and Ontology Connected Data London 2025 Call for Submissions Highlight The Connected Data London 2025 Call for Submissions is now open 🚀 connected-data.london/call-for-submi… If you are considering sharing your knowledge with the world's most passionate data community, we are highlighting topics we are interested in, and provide tips and inspiration 🌟 Innovations in Knowledge Graphs, Graph Data Science and AI, Graph Databases and Semantic Technology combined with: * Analytics * Natural Language Processing * Data Governance, Data Quality, Data Observability, Data Mesh, Data Fabric, Metadata * Data Engineering, DataOps, MLOps * Data visualization, Human-computer interaction (HCI), User interfaces and user experience (UI/UX) * Other topics If you are looking for examples of impactful talks others have shared with our community, here's a brief list to get you started: Graph Systems for Data in Motion, by Bogdan Arsintescu and Justin Fine 2024.connected-data.london/talks/graph-sy… Back to the Future of your Data - Wrangling connected data over time, by Dexter Lowe 2024.connected-data.london/talks/back-to-… A Polyglot Domain Model Library, by Veronika H.-Högberg 2024.connected-data.london/talks/a-polygl… Graph Algorithms & Graph Machine Learning: Making Sense of Today's Choices, by Victor Lee youtube.com/watch?v=d1oLRt… Graph Abstractions Matter, by Ora Lassila youtube.com/watch?v=-3fRKa… 📌 Tip: Make sure you think through your target audience, so you can plan and share with us what will the people who attend your talk get from it What we offer: ✅ Platform to reach a global audience ✅ Free access pass for accepted speakers ✅ Expert program committee evaluation ✅ Community that's been connecting data, people & ideas since 2016 Key Dates: 🗓️ Sept 1, 2025: Submission Deadline 🗓️ Sept 19, 2025: Acceptance Notification 🗓️ Nov 20-21, 2025: Event Days in London Submit here 👇 connected-data.london/call-for-submi… #KnowledgeGraphs #GraphAnalytics #ConnectedData #DataScience #SemanticTechnology #ConnectedDataLondon #CDL2025 #CallForSubmissions #TechConference #DataCommunity #ProTips #UseCases #GraphDatabases #EnterpriseAI #DataIntegration #RegulatoryCompliance #TechSpeakers #Innovation #EmergingTech #Ontology

The Geometric Deep Learning textbook: Chapter 5 - Graphs In multiple branches of science, from sociology to particle physics,graphs are a fundamental model of systems of relations and interactions. Graphs give rise to a basic type of symmetry modelled by the group ofpermutations. This is why we start our investigation by studying them. Most other objects of interest to us, such as grids and sets, can beobtained as a particular case of graphs, and many architectures we willdiscuss here will be expressible in the language of graph neural networks. This also includes the modern large language model (LLM) stack, which is presented as a case study in this Chapter. This is part of the Geometric Deep Learning texbook. The Geometric Deep Learning textbook is a resource intended to help students and practitioners enter the field of geometric deep learning, by @mmbronstein, Joan Bruna, @TacoCohen, @PetarV_93 In preparation for releasing their book with MIT Press, the authors make individual draft chapters of the book available. Once published, the chapters will remain online, for free. In addition, they have leveraged the material from the GDL Textbook to support Master’s level courses at both Oxford and Cambridge. Wherever relevant, they also share lecture slides corresponding to individual chapters. geometricdeeplearning.com/book/ #Education #Freebies #Graphs #AI #Analytics #DataScience #Science #Textbook #LLM -- The Year of the Graph Spring / Summer 2025 edition is out, with the latest news and insights on all things Knowledge Graph, Graph Analytics / Data Science / AI and Semantic Tech; check it out and subscribe here 👇 yearofthegraph.xyz/newsletter/202…

Just wanted to write a short 🧵 re: our recent paper on BARQ (vectorized #SPARQL engine in Stardog, link at the end). Vectorized joins for analytical queries are cool, but I'd like to comment a little on the other half of the paper, namely, how we plugged it into the product.

Super-useful! Once built a workflow engine around this exact capability, but this enables many use-cases.

SurrealDB @SurrealDB

a year ago

In our multi-model database, events can be triggered by any change to the data in a record. Each trigger can see the before and after value of the record, enabling advanced custom logic using SurrealQL. Learn more in our docs. 👉 sdb.li/4kOBaAi

0 0 15 494 0

Why are major companies such as Google, Microsoft, Amazon, and others adopting #KnowledgeGraphs? 🤔 💡 Here are the intuitions behind Knowledge Representation & Reasoning, and why they offer more than traditional databases: hubs.li/Q02S1Tj70 #SemanticWeb #AISolutions

📄🔍 GraphRAG Contract Analysis A powerful solution combining GraphRAG and LangGraph agents to analyze legal contracts using Neo4j knowledge graphs, featuring benchmarks across multiple LLMs. Check out the full implementation guide ➡️ towardsdatascience.com/agentic-graphr…

LDBC will hold the next Technical User Community meeting in London on September 6, after the VLDB conference. The call for talks is open – submit your work on graph data management: ldbcouncil.org/event/twentiet…

Attention Devs and Data Scientists! 📢 We are delighted to announce #NODES2025, the annual Neo4j online developer conference for beginners and experts alike!🤩 This free 24-hour online conference features: 🎙️ Live sessions in all timezones ✍️ Hands-on workshops leading up to the event 💡 Lightning talks, as well as deeper technical dives And more! Connect with peers and meet other great graph minds - Save your spot! Psst: Have a graph project to share? The call for papers is also open until June 15. bit.ly/4jhSAEl #CFP #Graphdatabase #developers #DataScience #GenAI #GraphRAG