This week we feature articles from Dean Allemang, and Daniel Tunkelang.

Additional reading comes from Tim O’Reilly, Bob DuCharme, and Hugo Bowne-Anderson.

News comes from DataStax & Langflow, Vesoft NebulaGraph, Searchspring, and Bridgeline.

All previous issues are available at

Opinion / Analysis

LLMs and knowledge — the study continues

“… if we think that a knowledge graph and an LLM work better together than an LLM alone, we should do a bake-off; set up a problem for the LLM+Knowledge Graph to solve, and let the LLM+Relational Database work on the same problem. Collect the data from a few hundred runs, and see who does better, and by how much.”

Dean Allemang and Juan Sequeda did, and published their benchmark data on GitHub to encourage interested parties to join the effort. Neo4j’s Jesús Barrasa did so. Find out more about both… (10 min)

AI-powered search: embedding-based retrieval and retrieval-augmented generation (RAG)

Daniel Tunkelang: “When search application developers consider replacing a traditional search architecture with AI-powered search, they usually have two things in mind. The first is replacing bag-of-words representations with embeddings. The second is implementing retrieval-augmented generation (RAG), which typically combines embedding-based retrieval with generative AI. This post explains the main ideas of embedding-based retrieval and RAG, with an emphasis on the pitfalls awaiting the unwary.” (9 min)

More Reading

All Gilbane Advisor issues

Content technology news

DataStax acquires Langflow

To enable LangChain-based RAG application development for any developer, with visual workflows, reusable components, and one-click deploy. ■

NebulaGraph Enterprise v3.7.0 simplifies building knowledge graphs

Knowledge Graph Build simplifies knowledge graph construction, reduces costs, and enables the completion of knowledge graphs from data processing through a single platform.

Searchspring acquires Intelligent Reach

Facilitates product discovery with semantic site search, flexible product merchandising, with business rules and AI-driven campaigns.

Smart Search’s concept search, image search & GenAI to enhance online shopping search functionality content creation and customer experience.

All content technology news

The Gilbane Advisor is authored by Frank Gilbane and is ad-free, cost-free, and curated for content, computing, web, data, and digital experience technology and information professionals. We publish recommended articles and content technology news weekly. We do not sell or share personal data.

Subscribe | View online | Editorial policy | Privacy policy | Contact