Photo credit In the last post, we discussed the basics of Retrieval Augmented Generation (RAG) and how it enhances the capabilities of Large Language Models (LLMs) by integrating them with external knowledge sources. We also introduced the concept of vector embeddings and their role in semantic search. In this post, we’ll dive deeper into the different layers of RAG, including vector RAG, graph RAG, and agents. We’ll explore how these layers can be combined to create more powerful and effective AI systems.

Photo credit Retrieval Augmented Generation (RAG) may sound complex, but it accurately represents the process of the system. RAG is a method that enhances the capabilities of Large Language Models (LLMs) by integrating them with external knowledge sources. Each term represents a piece of the puzzle: Retrieval - data retrieved from some external source outside the LLM (most often a database, but can include files, webpages, etc) Augmented - "augmenting" (or adding to) an LLM’s training data.

Photo credit As someone who is pretty familiar with relational and graph databases, I wanted to dig a little deeper into vector databases and understand the strengths and quirks they bring to the database table. I put together a conference abstract on vector RAG versus GraphRAG which got picked up, so I went to work building a demo and learning all I could. I pivoted a few times along the way, but ended up with a Spring AI application that connects to both Pinecone (vector database) and Neo4j (graph database).

Photo credit I recently had the opportunity to play with the Cypher DSL (domain-specific language) library, and I found it difficult to figure out syntax for some of the queries I was trying to construct. This blog post will hopefully help you understand how to construct your own programmatic queries with Cypher DSL by showing you syntax for nodes, relationships, and filtering. Then see how this in action with some examples for assembling those components into full queries translated from common clauses, functions, and result formats in Cypher.

Photo credit Just when I’m feeling pretty confident about my git skills, I run into a scenario like this one that backpedals my confidence. I keep learning, though, and small improvements are still progress. :) A few weeks ago, I was working on an update to the Graphacademy Spring Data Neo4j course, and things got out of sync. Before I knew it, I was stuck in merge conflict hell and wondering how I got there and if/how I could ever get out.

Photo credit After working on a new online Spring Data Neo4j course, I learned a couple more things about updating an entity. The course required a different set of scenarios than outlined in my previous SDN update blog post, so I wanted to cover those scenarios, as well. Spring save() method First up is the out-of-the-box save() method that is provided by Spring as a default. This method takes an input of the entity object you want to save to the database.

Photo credit The NODES 2024 conference is approaching fast, and we have a lot of exciting activities, including talks, workshops, and more. Here’s what you need to know to get ready for NODES 2024. What is NODES? NODES is a free, virtual conference run by Neo4j for developers, data scientists, and other technical roles who want to learn more about graph databases and how they can be used to solve complex problems.

Photo credit Every year, Neo4j hosts the virtual event NODES 2024 - a free, technical event spanning global timezones and a variety of graph-related topics. This is one of my favorite events of the year, but it doesn’t happen without countless hours of planning and work to make it valuable to the graph community. This year, my colleague and I were put in charge of organizing the schedule, determining how sessions are lined up between the start and end time of the event.

Photo credit Migrating an application always feels a bit daunting, and that was the way I felt when I looked at the Spring AI 1.0 milestone release. However, the upgrade didn’t make as many major shifts as anticipated. This guide will help you upgrade your Spring AI application from version 0.8 to 1.0 and explain why each change is needed. Changes include some naming shifts, configuration options, and more.