First week at Meta complete. Yes, really. This old dog, born long before the iPhone and social media, has joined the Kool Kids and will be “building the future of human connection and the technology that makes it possible.”
Read on for why I made the jump from Docusign and for my first impressions of Meta.
Continue reading “Old Dog Learns New Tricks”
In this article I dig into the question of whether you should use a traditional RDBMS (Postgres, MySQL etc.) or a graph database (Neo4J, AWS Neptune, OrientDB etc.) as you embark on your next data management and knowledge representation project, especially in this era of Knowledge Graphs and LLMs.
Knowing the strengths and weaknesses of each will help you pick the right tool for the job.
Image from: https://www.biconnector.com/blog/knowledge-graph-vs-relational-database-differences/
Continue reading “Knowledge Representation: Graphs or Tables?”There’s been a Cambrian explosion in the number of companies working on orchestration of large language model (LLM) tools, agent-based systems, and exposing enterprise data to LLMs, via retrieval augments generation (RAG), or via graph-based approaches (GraphRAG) or Knowledge Graphs.
In this article I explore LLM agent-based systems, particularly as they will be applied to enterprise systems of record.
Continue reading “Artificial Intelligence Agents and Enterprise Systems of Record”
Confused by people throwing words like ontology, taxonomy and data model around? In this post I explain the differences and give some practical advice for which to adopt.
Continue reading “Ontology vs Taxonomy vs Data Model”
I repeated my experiment with the Miss Manners benchmark using Clause Sonnet (Clause 3.5 Pro). The results were the best I’ve seen so far.
Continue reading “Miss Manners with Claude Sonnet”
All the cool kids are converting natural language text to knowledge graphs, so why not me!? 😊
In this article I show how to use a “1-liner” using Concerto Graph to create nodes and edges in a Knowledge Graph from text, whilst ensuring that the nodes and edges conforms to a Concerto data model (schema).
Continue reading “Text to Knowledge Graph”Over the past few weeks I’ve been researching, and building a framework that combines the power of Large Language Models for text parsing and transformation with the precision of structured data queries over Knowledge Graphs for explainable data retrieval.
In this fourth article of the series (one, two, three) I will show a generic web interface that helps explain how the LLM is using tools and graph queries to answer a wide variety of structured and unstructured questions.
Continue reading “Knowledge Graphs: RAG is NOT all you need”
I repeated my experiment with the Miss Manners benchmark using Clause Opus (Clause Pro). The results were better than GPT4, but inferior to Mistral (Large).
Continue reading “Miss Manners with Claude Opus”
Recently I’ve been evaluating the ability of LLMs to perform simple reasoning, using the Miss Manners benchmark. This article ranks the LLMs on this benchmark and summarises the results.
Continue reading “Miss Manners LLM Benchmark”
Innovation That Matters 