Now that I caught your attention, I hope the image isn't too triggering. I grew up learning to fear these little black monsters that potentially carry a load of Dengue virus that could make you really sick. As recently reported, the disease continues to be an issue in Singapore. During my undergraduate years, I was deeply passionate about viral diseases, and spent a few months in the laboratory learning to characterize the structural components of the virus using cyrogenic electron microscopy. Hence, when Luc Demanche challenged me again to demonstrate retrieval-augmented generation (RAG), I decided to collect and use a few recent articles (PMIDs 38140548, 37478848, 37114191), and use them to create a quick proof-of-concept Oracle APEX application that allows the user to ask questions about the disease. These articles cover topics on the Dengue virus, its genomics and ultrastructure, and progress in vaccine development.

In case you missed it, for the last few blogs posts, I had been using Stability AI's Stable Diffusion model to generate the banner images, and I have been mostly successful. Did I really need to? Perhaps not. For this post, I spent almost 30 minutes trying to figure out the "right" prompt to generate the image I wanted: "A car stopped in front a stop sign."

A new year, a new product! Yesterday, Oracle announced the general availability of the OCI Generative AI (GenAI) service. In my final blog post last year, I briefly looked at the beta information that was available to the public, and suggested how you can quite easily add powerful GenAI capability in Oracle APEX applications by calling the REST APIs using APEX_WEB_SERVICE. With the service in GA, I am now finally able to take a deeper dive and hopefully, help you get started.

In the last one year since OpenAI popularised generative AI, a lot of the excitement and intrigue have been centred on the generative power of large language models (LLMs) or foundational models. Understandably so. However, the generative power of this models only cover a segment of business needs. The underlying promise of these frontier models is in its ability to "understand" natural language, and that to me, is where we will find more utility.

For the last few years at Insum, we've had an almost biannual tradition of reviewing what's been going on in the AI/ML space, in particular, around what Oracle has been doing to provide innovative solutions and tools. If you missed those, I have provided the links below. In the absence of an updated review, I am hoping that this final 2023 blog post would serve somewhat as a stopgap.

In my previous post, you read about how I performed fine-tuning and deployed a large language model (LLM) on the Oracle Cloud Infrastructure (OCI) Data Science service. Here, I was hoping to do the same with the Stable Diffusion XL, a Latent Diffusion Model (LDM), but unfortunately, the platform currently does not support a Hugging Face pipeline using this model. I found an alternative, and you will read about it later in this article.

To demonstrate its utility, I create a simple Oracle APEX application that reads NFC tags using the experimental Web NFC API, and then displays an image generated by the deployed machine learning (ML) model.

In my previous post, I wrote about how a scikit-learn machine learning (ML) could be trained and deployed on the Oracle Cloud Infrastructure (OCI) Data Science service. The model is deployed on the service's managed infrastructure, allowing developers to simply call a HTTP endpoint to perform ML model inference on the submitted data. In my latest adventure, I built an Oracle APEX application that takes product reviews and then automatically ranks the review using a fine-tuned large language model (LLM) available through Hugging Face.

This has been one of those weeks where I couldn't wait to wake up and get to work. Just last week, Luc Demanche threw me a challenge and asked that I help develop an Oracle APEX application that could be used to predict the winner of the Rugby World Cup 2023 (RWC2023). I couldn't resist the challenge!

I hope Joel doesn't mind that I used this image here to commemorate #JoelKallmanDay. This picture was posted by our dear friend, Joel Kallman, in 2019. Shortly after Mike Hichwa was presented with the first coin in the first series of the Oracle APEX Challenge Coin.

One of the key highlights at Oracle Cloudworld 2023 is general availability of Select AI feature that allows anyone to query the Oracle Database using natural language. This is likely made possible with a template wrapping the database metadata with the prompt, and then calling either the OpenAI or Cohere APIs to generate the intended text.

Doug Gault had suggested a while ago that I could bring more awareness to the Oracle APEX Challenge Coin project if I had an Oracle APEX application that plots the location of each sponsored coin on a world map. I agree. However, aside from a lack of time, I had also wanted to find interesting ways for awardees to submit their claim of ownership. Over the last week, I had worked on making this dream of a "claims" map a reality with the use of the Oracle Cloud Infrastructure (OCI) Vision AI service, more specifically, its custom model training feature.

Here's an early preview of the claims process in the Claim My Oracle APEX Challenge Coin application.

I'm finally finding more time, post-conference, to catch up on my writing. In this latest post, I'd like to talk about a presentation that I did at Kscope23, "Solving Everyday Problems with the Oracle Cloud". During the session, I had described and demonstrated how we can use the Oracle Cloud Infrastructure (OCI) AI services and Oracle APEX to build compelling solutions, even for personal life challenges.

In case you missed it, Oracle recently announced the availability of a new feature for the Autonomous Database (ADB) that allows developers and database administrators to send messages using either emails, Slack, or Microsoft Teams (Teams). At Insum, we use teams for internal communications and collaboration, and thus, you can appreciate my excitement when I heard about this feature release. Here's an early guide to getting started with DBMS_CLOUD_NOTIFICATION for those using Teams at their organisation.

When I was first introduced to generative adversarial networks (GANs), I was impressed, but yet not impressed. The concept, performance, and outcomes of these advanced machine learning (ML) algorithms were truly jaw-dropping, but easily abused. And so, when everyone was excitedly chatting about ChatGPT, I was cynical and tried to tune out until I came across a comment by an old acquaintance, following a news article on concerns about ChatGPT and potential plagiarism in school.

It's like someone using a calculator in an arithmetic exam, ChatGPT is just another tool.

-- Sau Sheong Chang

That statement got me rethinking my stance on the technology, and curious about its utility in my day-to-day job.

A few weeks ago, I was fortunate to accompany a group of twenty-four exchange students from a local university. Some of them came from countries as far as Singapore. While up in the North, the Aurora Borealis might be a common sight, for tourists, it is still pretty much a calculated risk that it might be a fruitless journey. The night skies were overcast on the first night that they arrived, and it was bitterly cold for folks used to tropical weather, but they persisted. On their second night, there was a minor emergency that delayed a few of them from heading out to the remote site for viewing the Northern Lights, but again, they were determined. Within minutes of their arrival at the viewing site, there was a sudden break in the cloudy skies that coincided with a display of greens and purples that illuminated in the heavens. What a treat!

As we near the end of 2022, I'd like to reflect on the year's challenges and milestones.

It's been too long since I last posted anything on my blog. Thanks to Tim Hall, I am writing again, after a long pause, to celebrate Joel Kallman Day 2022. My contribution today is about my deep appreciation for the team behind the Oracle Cloud Infrastructure (OCI) AI Services. Below is a quick scoop on how I have used these services to improve on my OCI-powered e-flashcard for learning new words in a different language. I will be doing a quick demonstration (session LRN3673) of this work at the upcoming Oracle CloudWorld 2022.