GraphNews

An exploration

First experience of building a knowledge graph from a document using Docling!

The quest to build truly intelligent systems hinges on our ability to represent, manage, and reason over complex knowledge. Knowledge…

Integrating Large Language Models (LLMs) with Knowledge Graphs (KGs) results in complex systems with numerous hyperparameters that directly affect performance. While such systems are increasingly...

Picture an AI agent that seamlessly traverses knowledge graphs while performing semantic vector searches, applies probabilistic predictions alongside deterministic rules, reasons about temporal evolution and spatial relationships, and resolves contradictions between multiple data sources—all within a single atomic transaction. It is PostgreSQL-based architecture that consolidates traditionally distributed data systems into a single, coherent platform. This architecture doesn't just store different data types; it enables every conceivable form of reasoning—deductive, inductive, abductive, analogical, causal, and spatial—transforming isolated data modalities into a coherent intelligence substrate where graph algorithms, embeddings, tabular predictions, and ontological inference work in perfect harmony. It changes how agentic systems operate by eliminating the complexity and inconsistencies inherent in multi-database architectures while enabling sophisticated multi-modal reasoning capabilities. Conventional approaches typically distribute agent knowledge across multiple specialized systems: vector databases for semantic search, graph databases for relationship reasoning, relational databases for structured data, and separate ML platforms for predictions. This fragmentation creates synchronization nightmares, latency penalties, and operational complexity that can cripple agent performance and reliability. Apache AGE brings native graph database capabilities to PostgreSQL, enabling complex relationship traversal and graph algorithms without requiring a separate graph database. Similarly, pgvector enables semantic search through vector embeddings, while extensions like TabICL provide zero-shot machine learning predictions directly within the database. This extensibility allows PostgreSQL to serve as a unified substrate for all data modalities that agents require. While AGE may not match the pure performance of dedicated graph databases like Neo4j for certain specialized operations, it excels in the hybrid queries that agents typically require. An agent rarely needs just graph traversal or just vector search; it needs to combine these operations with structured queries and ML predictions in coherent reasoning chains. The ability to perform these operations within single ACID transactions eliminates entire classes of consistency bugs that plague distributed systems. Foundational models eliminate traditional ML complexity. TabICL and TabSTAR enable instant predictions on new data patterns without training, deployment, or complex MLOps pipelines. This capability is particularly crucial for agentic systems that must adapt quickly to new situations and data types without human intervention or retraining cycles. The unified architecture simplifies every aspect of system management: one backup strategy instead of multiple, unified security through PostgreSQL's mature RBAC system, consistent monitoring, and simplified debugging. | 21 comments on LinkedIn

Want to Fix LLM Hallucination? Neurosymbolic Alone Won’t Cut It The Conversation’s new piece makes a clear case for neurosymbolic AI—integrating symbolic logic with statistical learning—as the long-term fix for LLM hallucinations. It’s a timely and necessary argument: “No matter how large a language model gets, it can’t escape its fundamental lack of grounding in rules, logic, or real-world structure. Hallucination isn’t a bug, it’s the default.” But what’s crucial—and often glossed over—is that symbolic logic alone isn’t enough. The real leap comes from adding formal ontologies and semantic constraints that make meaning machine-computable. OWL, Shapes Constraint Language (SHACL), and frameworks like BFO, Descriptive Ontology for Linguistic and Cognitive Engineering (DOLCE), the Suggested Upper Merged Ontology (SUMO), and the Common Core Ontologies (CCO) don’t just “represent rules”—they define what exists, what can relate, and under what conditions inference is valid. That’s the difference between “decorating” a knowledge graph and engineering one that can detect, explain, and prevent hallucinations in practice. I’d go further: • Most enterprise LLM hallucinations are just semantic errors—mislabeling, misattribution, or class confusion that only formal ontologies can prevent. • Neurosymbolic systems only deliver if their symbolic half is grounded in ontological reality, not just handcrafted rules or taxonomies. The upshot: We need to move beyond mere integration of symbols and neurons. We need semantic scaffolding—ontologies as infrastructure—to ensure AI isn’t just fluent, but actually right. Curious if others are layering formal ontologies (BFO, DOLCE, SUMO) into their AI stacks yet? Or are we still hoping that more compute and prompt engineering will do the trick? #NeuroSymbolicAI #SemanticAI #Ontology #LLMs #AIHallucination #KnowledgeGraphs #AITrust #AIReasoning

AutoSchemaKG: Building Billion-Node Knowledge Graphs Without Human Schemas 👉 Why This Matters Traditional knowledge graphs face a paradox: they require expert-crafted schemas to organize information, creating bottlenecks for scalability and adaptability. This limits their ability to handle dynamic real-world knowledge or cross-domain applications effectively. 👉 What Changed AutoSchemaKG eliminates manual schema design through three innovations: 1. Dynamic schema induction: LLMs automatically create conceptual hierarchies while extracting entities/events 2. Event-aware modeling: Captures temporal relationships and procedural knowledge missed by entity-only approaches 3. Multi-level conceptualization: Organizes instances into semantic categories through abstraction layers The system processed 50M+ documents to build ATLAS - a family of KGs with: - 900M+ nodes (entities/events/concepts) - 5.9B+ relationships - 95% alignment with human-created schemas (zero manual intervention) 👉 How It Works 1. Triple extraction pipeline:   - LLMs identify entity-entity, entity-event, and event-event relationships   - Processes text at document level rather than sentence level for context preservation 2. Schema induction:   - Automatically groups instances into conceptual categories   - Creates hierarchical relationships between specific facts and abstract concepts 3. Scale optimization:   - Handles web-scale corpora through GPU-accelerated batch processing   - Maintains semantic consistency across 3 distinct domains (Wikipedia, academic papers, Common Crawl) 👉 Proven Impact - Boosts multi-hop QA accuracy by 12-18% over state-of-the-art baselines - Improves LLM factuality by up to 9% on specialized domains like medicine and law - Enables complex reasoning through conceptual bridges between disparate facts 👉 Key Insight The research demonstrates that billion-scale KGs with dynamic schemas can effectively complement parametric knowledge in LLMs when they reach critical mass (1B+ facts). This challenges the assumption that retrieval augmentation needs domain-specific tuning to be effective. Question for Discussion As autonomous KG construction becomes viable, how should we rethink the role of human expertise in knowledge representation? Should curation shift from schema design to validation and ethical oversight? | 15 comments on LinkedIn

Small Models, Big Knowledge: How DRAG Bridges the AI Efficiency-Accuracy Gap 👉 Why This Matters Modern AI systems face a critical tension: large language models (LLMs) deliver impressive knowledge recall but demand massive computational resources, while smaller models (SLMs) struggle with factual accuracy and "hallucinations." Traditional retrieval-augmented generation (RAG) systems amplify this problem by requiring constant updates to vast knowledge bases. 👉 The Innovation DRAG introduces a novel distillation framework that transfers RAG capabilities from LLMs to SLMs through two key mechanisms: 1. Evidence-based distillation: Filters and ranks factual snippets from teacher LLMs 2. Graph-based structuring: Converts retrieved knowledge into relational graphs to preserve critical connections This dual approach reduces model size requirements by 10-100x while improving factual accuracy by up to 27.7% compared to prior methods like MiniRAG. 👉 How It Works 1. Evidence generation: A large teacher LLM produces multiple context-relevant facts 2. Semantic filtering: Combines cosine similarity and LLM scoring to retain top evidence 3. Knowledge graph creation: Extracts entity relationships to form structured context 4. Distilled inference: SLMs generate answers using both filtered text and graph data The process mimics how humans combine raw information with conceptual understanding, enabling smaller models to "think" like their larger counterparts without the computational overhead. 👉 Privacy Bonus DRAG adds a privacy layer by: - Local query sanitization before cloud processing - Returning only de-identified knowledge graphs Tests show 95.7% reduction in potential personal data leakage while maintaining answer quality. 👉 Why It’s Significant This work addresses three critical challenges simultaneously: - Makes advanced RAG capabilities accessible on edge devices - Reduces hallucination rates through structured knowledge grounding - Preserves user privacy in cloud-based AI interactions The GitHub repository provides full implementation details, enabling immediate application in domains like healthcare diagnostics, legal analysis, and educational tools where accuracy and efficiency are non-negotiable.

Graph database optimized for fast analysis and real-time data processing. It is provided as an extension to PostgreSQL. - apache/age

Your agents, multi-agent systems and LMs apps are still failing with basic logic? We got you covered. Today we're excited to announce Synalinks 0.3 our Keras-based neuro-symbolic framework that bridges the gap between neural networks and symbolic reasoning. Our latest release focuses entirely on the Knowledge Graph layer, delivering production-ready solutions for real-world applications: - Fully constrained KG extraction powered by Pydantic: ensuring that relations connect to the correct entity types. - Seamless integration with our Agents/Chain-of-Thought and Self-Critique modules. - Automatic entity alignment with HSWN. - KG extraction and retrieval optimizable with OPRO and RandomFewShot algorithms. - 100% reliable Cypher query generation through logic-enhanced hybrid triplet retrieval (works with local models too!). - We took extra care to avoid Cypher injection vulnerabilities (yes, we're looking at you, LangGraph 👀) - The retriever don't need the graph schema, as it is included in the way we constrain the generation, avoiding context pollution (hence better accuracy). - We also fixed Synalinks CLI for Windows users along with some minor bug fixes. Our technology combine constrained structured output with in-context reinforcement learning, making enterprise-grade reasoning both highly efficient and cost-effective. Currently supporting Neo4j with plans to expand to other graph databases. Built this initially for a client project, but the results were too good not to share with the community. Want to add support for your preferred graph database? It's just one file to implement! Drop a comment and let's make it happen! #AI #MachineLearning #KnowledgeGraphs #NeuralNetworks #Keras #Neo4j #AIAgents #TechInnovation #OpenSource | 10 comments on LinkedIn

In the long tradition of dictionaries, the essence of meaning has always relied on two elements: a symbol (usually a word or a phrase) and a definition—an intelligible explanation composed using other known terms. This recursive practice builds a web of meanings, where each term is explained using o

In complex engineering systems, how can we ensure that design knowledge doesn’t get lost in spreadsheets, silos, or forgotten documents? One of the greatest challenges in design domain and product development isn’t a lack of data, but a lack of meaningful, connected knowledge. This is where ontologies come in. An ontology is more than just a taxonomy or glossary. It’s a formal representation of concepts and relationships that enables shared understanding across teams, tools, and disciplines. In the design domain, ontologies serve as a semantic backbone, helping engineers and systems interpret, reuse, and reason over knowledge that would otherwise remain trapped in silos. Why does this matter? Because design decisions are rarely made in isolation. Whether it’s integrating functional models, analysing field failures, or updating risk assessment documents, we need a way to bridge data across multiple sources and domains. Ontologies enable that integration by creating a common language and structured relationships, allowing information to flow intelligently from design to deployment. Ontology-driven systems also support human decision-making by enhancing traceability, contextualising feedback, and enabling AI-powered insights. It’s not about replacing designers, it’s about augmenting their intuition with structured, reusable knowledge. As we move towards more data-driven and model-based approaches in engineering, ontologies are key to unlocking collaboration, innovation, and resilience in product development. #Ontology #KnowledgeEngineering #SystemsThinking #DesignThinking #SystemEngineering #AI #DigitalEngineering #MBSE #KnowledgeSharing #DecisionSupport #AugmentedIntelligence | 16 comments on LinkedIn

Stop wondering about changes to your graph data model and start exploring your up-to-date database schema with only a couple of clicks when you use G.V().

I'm happy to share the draft of the "Semantically Composable Architectures" mini-paper. It is the culmination of approximately four years' work, which began with Coreless Architectures and has now evolved into something much bigger. LLMs are impressive, but a real breakthrough will occur once we surpass the cognitive capabilities of a single human brain. Enabling autonomous large-scale system reverse engineering and large-scale autonomous transformation with minimal to no human involvement, while still making it understandable to humans if they choose to, is a central pillar of making truly groundbreaking changes. We hope the ideas we shared will be beneficial to humanity and advance our civilization further. It is not final and will require some clarification and improvements, but the key concepts are present. Happy to hear your thoughts and feedback. Some of these concepts underpin the design of the Product X system. Part of the core team + external contribution: Andrew Barsukov Andrey Kolodnitsky Sapta Girisa N Keith E. Glendon Gurpreet Sachdeva Saurav Chandra Mike Diachenko Oleh Sinkevych | 13 comments on LinkedIn

The number of published scholarly articles is growing at a significant rate, making scholarly knowledge organization increasingly important. Various approaches have been proposed to organize...

Unlocking graph insights with Raphtory, an advanced in-memory graph tool designed to facilitate efficient exploration of evolving networks. 🔹 Scalability & Performance: Handles large-scale graph data seamlessly, enabling fast computations. 🔹 Temporal Analysis: Investigate how networks change over time, identifying trends and key shifts. 🔹 Multi-layer Modeling: Incorporate diverse data sources into a unified, structured framework for deeper insights. 🔹 Integration: Works easily with existing pipelines via **Python APIs**, ensuring a smooth workflow for professionals. #Graphs #GraphDB #NetworkAnalysis #TemporalData https://www.raphtory.com/

In our GraphGeeks Talk with Max De Marzi , we unpack what makes a graph model solid, what tends to break things, and how to design with both your data and your queries in mind.

Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.

Want to explore the Anthropic Transformer-Circuit's as a queryable graph? Wrote a script to import the graph json into Neo4j - code in Gist. https://lnkd.in/eT4NjQgY https://lnkd.in/e38TfQpF Next step - write directly from the circuit-tracer library to the graph db. https://lnkd.in/eVU_t6mS

Spacetime and information both have the basics of a geometry

SAP Knowledge Graph is now generally available (Q1 2025) and is poised to fundamentally change how data relationships are mapped and queried. With grounded intelligence, knowledge graphs are crucial in enabling AI agents for reasoning and retrieval with context and high accuracy. SAP Knowledge Graph...

A few challenges We keep redoing what has already been done elsewhere in the company. We don’t learn from our mistakes.

Introducing FACT: Fast Augmented Context Tools (3.2x faster, 90% cost reduction vs RAG) RAG had its run, but it’s not built for agentic systems. Vectors are fuzzy, slow, and blind to context. They work fine for static data, but once you enter recursive, real-time workflows, where agents need to reason, act, and reflect. RAG collapses under its own ambiguity. That’s why I built FACT: Fast Augmented Context Tools. Traditional Approach: User Query → Database → Processing → Response (2-5 seconds) FACT Approach: User Query → Intelligent Cache → [If Miss] → Optimized Processing → Response (50ms) It replaces vector search in RAG pipelines with a combination of intelligent prompt caching and deterministic tool execution via MCP. Instead of guessing which chunk is relevant, FACT explicitly retrieves structured data, SQL queries, live APIs, internal tools, then intelligently caches the result if it’s useful downstream. The prompt caching isn’t just basic storage. It’s intelligent using the prompt cache from Anthropic and other LLM providers, tuned for feedback-driven loops: static elements get reused, transient ones expire, and the system adapts in real time. Some things you always want cached, schemas, domain prompts. Others, like live data, need freshness. Traditional RAG is particularly bad at this. Ask anyone force to frequently update vector DBs. I'm also using Arcade.dev to handle secure, scalable execution across both local and cloud environments, giving FACT hybrid intelligence for complex pipelines and automatic tool selection. If you're building serious agents, skip the embeddings. RAG is a workaround. FACT is a foundation. It’s cheaper, faster, and designed for how agents actually work: with tools, memory, and intent. To get started point your favorite coding agent at: https://lnkd.in/gek_akem | 38 comments on LinkedIn

🏯🏇 A-MEM Transforms AI Agent Memory with Zettelkasten Method, Atomic Notes, Dynamic Linking & Continuous Evolution! This Novel Memory fixes rigid structures with adaptable, evolving, and interconnected knowledge networks, delivering 2x performance in complex reasoning tasks. 𝗧𝗵𝗶𝘀 𝗶𝘀 𝘄𝗵𝗮𝘁 𝗜 𝗹𝗲𝗮𝗿𝗻𝗲𝗱: ﹌﹌﹌﹌﹌﹌﹌﹌﹌ 》 𝗪𝗵𝘆 𝗧𝗿𝗮𝗱𝗶𝘁𝗶𝗼𝗻𝗮𝗹 𝗠𝗲𝗺𝗼𝗿𝘆 𝗙𝗮𝗹𝗹 𝗦𝗵𝗼𝗿𝘁 Most AI agents today rely on simplistic storage and retrieval but break down when faced with complex, multi-step reasoning tasks. ✸ Common Limitations: ☆ Fixed schemas: Conventional memory systems require predefined structures that limit flexibility. ☆ Limited adaptability: When new information arises, old memories remain static and disconnected, reducing an agent’s ability to build on past experiences. ☆ Ineffective long-term retention: AI agents often struggle to recall relevant past interactions, leading to redundant processing and inefficiencies. ﹌﹌﹌﹌﹌﹌﹌﹌﹌ 》𝗔-𝗠𝗘𝗠: 𝗔𝘁𝗼𝗺𝗶𝗰 𝗻𝗼𝘁𝗲𝘀 𝗮𝗻𝗱 𝗗𝘆𝗻𝗮𝗺𝗶𝗰 𝗹𝗶𝗻𝗸𝗶𝗻𝗴 A-MEM organizes knowledge in a way that mirrors how humans create and refine ideas over time. ✸ How it Works: ☆ Atomic notes: Information is broken down into small, self-contained knowledge units, ensuring clarity and easy integration with future knowledge. ☆ Dynamic linking: Instead of relying on static categories, A-MEM automatically creates connections between related knowledge, forming a network of interrelated ideas. ﹌﹌﹌﹌﹌﹌﹌﹌﹌ 》 𝗣𝗿𝗼𝘃𝗲𝗻 𝗣𝗲𝗿𝗳𝗼𝗿𝗺𝗮𝗻𝗰𝗲 𝗔𝗱𝘃𝗮𝗻𝘁𝗮𝗴𝗲 A-MEM delivers measurable improvements. ✸ Empirical results demonstrate: ☆ Over 2x performance improvement in complex reasoning tasks, where AI must synthesize multiple pieces of information across different timeframes. ☆ Superior efficiency across top foundation models, including GPT, Llama, and Qwen—proving its versatility and broad applicability. ﹌﹌﹌﹌﹌﹌﹌﹌﹌ 》 𝗜𝗻𝘀𝗶𝗱𝗲 𝗔-𝗠𝗘𝗠 ✸ Note Construction: ☆ AI-generated structured notes that capture essential details and contextual insights. ☆ Each memory is assigned metadata, including keywords and summaries, for faster retrieval. ✸ Link Generation: ☆ The system autonomously connects new memories to relevant past knowledge. ☆ Relationships between concepts emerge naturally, allowing AI to recognize patterns over time. ✸ Memory Evolution: ☆ Older memories are continuously updated as new insights emerge. ☆ The system dynamically refines knowledge structures, mimicking the way human memory strengthens connections over time. ≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣ ⫸ꆛ Want to build Real-World AI agents? Join My 𝗛𝗮𝗻𝗱𝘀-𝗼𝗻 𝗔𝗜 𝗔𝗴𝗲𝗻𝘁 𝟰-𝗶𝗻-𝟭 𝗧𝗿𝗮𝗶𝗻𝗶𝗻𝗴 TODAY! 𝟰𝟴𝟬+ already Enrolled. ➠ Build Real-World AI Agents for Healthcare, Finance,Smart Cities,Sales ➠ Learn 4 Framework: LangGraph | PydanticAI | CrewAI | OpenAI Swarm ➠ Work with Text, Audio, Video and Tabular Data 👉𝗘𝗻𝗿𝗼𝗹𝗹 𝗡𝗢𝗪 (𝟰𝟱% 𝗱𝗶𝘀𝗰𝗼𝘂𝗻𝘁): https://lnkd.in/eGuWr4CH | 27 comments on LinkedIn

RAG vs Graph RAG, explained visually. (it's a popular LLM interview question) Imagine you have a long document, say a biography, about an individual (X) who has accomplished several things in this life. ↳ Chapter 1: Talks about Accomplishment-1. ↳ Chapter 2: Talks about Accomplishment-2. ... ↳ Chapter 10: Talks about Accomplishment-10. Summarizing all these accomplishments via RAG might never be possible since... ...it must require the entire context... ...but one might only be fetching the top-k relevant chunks from the vector db. Moreover, since traditional RAG systems retrieve each chunk independently, this can often leave the LLM to infer the connections between them (provided the chunks are retrieved). Graph RAG solves this. The idea is to first create a graph (entities & relationships) from the documents and then do traversal over that graph during the retrieval phase. See how Graph RAG solves the above problems. - First, a system (typically an LLM) will create the graph by understanding the biography. - This will produce a full graph of nodes entities & relationships, and a subgraph will look like this: ↳ X → → Accomplishment-1. ↳ X → → Accomplishment-2. ... ↳ X → → Accomplishment-N. When summarizing these accomplishments, the retrieval phase can do a graph traversal to fetch all the relevant context related to X's accomplishments. This context, when passed to the LLM, will produce a more coherent and complete answer as opposed to traditional RAG. Another reason why Graph RAG systems are so effective is because LLMs are inherently adept at reasoning with structured data. Graph RAG instills that structure into them with their retrieval mechanism. 👉 Over to you: What are some other issues with traditional RAG systems that Graph RAG solves? ____ Find me → Avi Chawla Every day, I share tutorials and insights on DS, ML, LLMs, and RAGs. | 24 comments on LinkedIn

In the age of AI-driven applications, the ability to ground large language models (LLMs) with trustworthy, contextual information is more…

The integration of Knowledge Graphs (KGs) into the Retrieval Augmented Generation (RAG) framework has attracted significant interest, with early studies showing promise in mitigating...

Retrieval-Augmented Generation (RAG) has significantly enhanced large language models (LLMs) in knowledge-intensive tasks by incorporating external knowledge retrieval. However, existing RAG...

Join the discussion on this paper page

Join the discussion on this paper page