Documenting how to map relationship entities from a database to an application. Then, delving into one author’s viewpoint on software project estimates and some ideas to adapt this inaccurate process for better results.

The term GraphRAG has recently popped up in the current AI industry, so I review a blog post on what it is and how it fits into the current landscape. I also read an article on ways to improve software development.

I’m always refreshing my memory and learning new things. How to explain technical concepts to broader audiences, then a question from the community took me into the Java driver docs and entity mapping/OGMs.

Happy Fall! This week, we talk about confusion around GraphQL, GQL, and graph query languages. Then, I am excited to gear up for NODES 2024 by showcasing pre-conference workshops called Road to NODES!

This week, we discuss retrieval augmented generation (RAG) and how it’s being used to improve responses (or prevent hallucinations) from an LLM. We also chat about an article on how tech conferences have changed and how you can still find value in speaking or attending, plus how to justify the benefits at your organization.

A recent blog post defines "knowledge graph", a term that has been around awhile and is part of many recent AI conversations. And then we chat about the DevUp conference I attended last week. Hopefully my thoughts will help you decide how to choose the best event for you.

With the amount of new information, sometimes it’s hard to review earlier concepts. In this episode, we explain what an embedding is and talk about aligning your prompt with your use case for improving LLM answers (example app code repository).

In preparing for the NODES 2024 conference, I’ll talk about how my colleague and I made scheduling easier by using Neo4j (a database). Spring AI also moved to a 1.0 milestone, and I’ll talk about the easier-than-expected migration (more in my related blog post).

Do you ever feel like some people have all the luck? Sometimes we need to see things in a new light to break through the barrier or overcome the obstacle. Plus, I took a look at a new-ish tool from Neo4j called the LLM Graph Builder. I’ll give a quick intro on that, plus what I’m doing with it and how it’s going.

I now have a code repository and blog post for Neo4j+Kubernetes. We also chat about another blog post on how to solve a deadlock with parallel relationship loading.