This blog post will integrate the Spring AI framework into a Java application. We’ll use a simple project that includes a ChatService and a ChatController to demonstrate using the Spring AI framework to generate text & image responses and horoscopes based on user input.
This is part 2 of a humor-inspired take on Monoliths to microservices that I wrote a few years back: https://blogs.justenougharchitecture.com/monos-journey-from-monolith-to-microservices/. If you did not read that, please do so first.
Mikro was serving his consumers as always. He consistently met his promises (SLAs), and his life was good. Suddenly, he felt a stab and excruciating pain. “Damnit, what was that?” he said. To Mikro’s horror, he found himself being sliced and diced into smaller and smaller pieces. “But I thought I was already micro enough!” he wailed as functions were extracted from his very being.
Designing and building robust, scalable, and efficient systems is a fundamental requirement in software engineering. The AWS Well-Architected Framework is an essential resource that can significantly aid this process. Although it originates from Amazon Web Services, the principles and best practices it outlines are universally applicable. This blog aims to provide an understanding of the AWS Well-Architected Framework, its core focus areas, and its value to software engineering practices, regardless of whether you use AWS services.
As an AI and software professional, you’ve likely heard the buzz around large language models (LLMs) like GPT-3, ChatGPT, and their growing capabilities. These powerful models can handle a wide range of natural language tasks, from text generation to question answering. However, effectively leveraging LLMs in your own applications can be a complex challenge. That’s where LangChain comes in.
Welcome to a step-by-step guide on creating an intelligent chatbot powered by OpenAI using Python and Jupyter Notebooks. In this tutorial, we’ll cover the fundamental concepts and guide you through the process of building a simple yet effective chatbot that leverages the power of OpenAI’s language model.
So this is a mix of a couple of howtos. First, we have a simple Spring Boot app that retrieves some data from a MongoDB database that has authentication enabled to access it. Next, we will see how to store secrets in a Vault implementation and then programmatically access it (in our case the user ID and password to access the database).
OpenAI provides us the ability to invoke its features via RESTful APIs. This blog shows how to invoke the API using Spring Boot. There is nothing special here and no OpenAI Java libraries that I use. One can do the same in standard Java (non-spring) or even in more concise code with Nodejs. But here goes a sample with Spring Boot.
So it’s been some time since I wrote a blog. As I was figuring out what my next blog is, how could I ignore ChatGPT, BARD and the AI excitement that it has brought about (or re-awakened among many of us). And then there is GitHub’s Copilot and AWS CodeWhisperer! Code assistants that can make us slightly more efficient developers.
An API Gateway serves as the front-door to your APIs providing features such as route matching and forwarding, rate limiting, path rewriting, circuit breaker patterns, security policy management, throttling, API version management, among other features.
I am really excited about GitHub Copilot, a AI code pair programming capability. While good editors do provide some inbuilt code completion features, this is the first one I used that leans on AI to suggest code completions.