Photo credit There are so many options when it comes to languages, frameworks, and tools for building generative AI (GenAI) applications. When you are just getting started, these decisions and figuring out how to integrate everything can be overwhelming. My team has been working on some pre-packaged solutions to make this process easier by providing starter kit projects with a few key technologies. One of those is the topic of today’s post - building a GenAI application with Spring AI in Java.

Photo credit There is no shortage of technical events such as conferences, meetups, trainings, hackathons, and so on. These events are a great way to learn new things, connect with people, and share knowledge with others. One of the most valuable and exciting ways to share knowledge is by giving a technical presentation. Today, we will look at how to submit a technical presentation for an event and get some personal recommendations from me, as well.

Photo credit Generative AI (GenAI) is currently a hot topic in the tech world. It’s a subset of artificial intelligence that focuses on creating new content, such as text, images, or music. One popular type of GenAI component is the Large Language Model (LLM), which can generate human-like text based on a prompt. Retrieval-Augmented Generation (RAG) is a technique that enhances the accuracy and reliability of generative AI models by grounding them in external knowledge sources.

Photo credit It’s been awhile since I wrote a Cypher Sleuthing post, but I’m back with a new one! This time, I’m going to show you how to find the data types of properties in Neo4j. I frequently want to find out the data type of a property so that I can map it in an application (in Java). I can never remember off the top of my head, and when I Google the question, the results are often outdated (here’s the answer post, but the syntax is old).

Photo credit What is RAG? This term is used a lot in today’s technical landscape, but what does it actually mean? Here are a few definitions from various sources: "Retrieval-Augmented Generation (RAG) is the process of optimizing the output of a large language model, so it references an authoritative knowledge base outside of its training data sources before generating a response." - Amazon Web Services "Retrieval-augmented generation (RAG) is a technique for enhancing the accuracy and reliability of generative AI models with facts fetched from external sources.

Photo credit Just before the holidays, I was working on writing some more lesson content for a Spring Data Neo4j course. To save an entity to the database, I needed to pass a JSON object containing the entity’s properties to a Spring Boot controller method. Each time I wanted to test the code, I had to manually create the JSON object and pass it to the controller method on the command line.

Photo credit I have been using an Apple M1 laptop since autumn of 2021, but I just recently came across an issue that surprised me. It seems I hadn’t converted Homebrew (a package manager for macOS) for compatibility with Apple Silicon. I mostly use Homebrew to install packages I rarely use (such as Ruby or Python libraries), so perhaps that’s why I hadn’t noticed. However, this issue surfaced because I tried to install a Python package (Poetry) to work on a generative AI project, and it was looking for Python in the wrong place.

Photo credit It’s right in the middle of busy conference season, and I was prepping for an upcoming conference talk. As I often do, I went to Neo4j Aura to spin up a free database and use Cypher with APOC to import data from an API, but this API requires a header, and the APOC procedure that adds headers to a request is blocked by security in Aura. Hm, I needed a new route.

Photo credit I have recently been working on a self-paced learning course for Spring Data Neo4j and wanted users to be able to test the database connection. Typically, in a Spring Boot application with Spring Data, you set the database credentials as properties in the application.properties file. You can run the application with just these details, but it only fails when the database URI has improper syntax. The application does not actually test the connection to see if it is valid and successfully connects.