Skip to main content

Posts

Showing posts from 2023

Talking to Oracle Database, this time in plain Slovenian

In my previous blog post, Talking to Oracle Database in plain English I am discussing how to query Oracle Database using natural language queries to retrieve data from an Oracle database. From my quick exploration, I can conclude that AI has definitely entered databases and can be applied in very different scenarios. For example, using SELECT AI in chat application where data can be retrieved and presented from Oracle Database by applying natural language query. But that was in plain English. But what about if my primary natural language isn't English. What if your (and, for this matter also mine) isn't English. What if it is Slovenian? Would SELECT AI still work? Let's examine the very same examples that I used in my previous blog post. Let's talk now ... "po slovensko" (Slovenian) Enough said. Let's try the simplest query of all and let's ask my database what is the total revenue recorded. In Slovenian, the question  what is total revenue tra

Talking to Oracle Database in plain English

My SQL beginnings It was approx. 35 years ago (gosh, that long!?) when I first met SQL. Structured Query Language to those who might not be  from that era or are not 100% sure of what I am talking about. It was during the labs at faculty when we went to IBM's training center (we didn't have the capacity at faculty at the time) in Radovljica, Slovenia, to learn and play with this (at least for me) new programming language. The language of the 4th generation, so they said. With its roots in boolean algebra and simple structure, we were told that this was almost the same as natural language (english of course. Who would thought one day you would use Slovenian language to query databases too! With all those SELECTs, FROMs, WHEREs, GROUP BYs, HAVINGs, ORDER BYs, etc. it actually sounded really cool and easy. My Select AI beginnings The other day I finally found some time to invest into something else then just daily work, which is obviously something different than the rest of th

My UKOUG 2023 Report

I recently returned from Reading, UK, where I had the opportunity to attend the UKOUG 2023 conference . This year's event was particularly engaging, commemorating the 40th anniversary of the UK Oracle User Group. My participation at the conference had a dual purpose. Firstly, I attended to present, and while I was there, I had the chance to join several presentations that piqued my interest. I'm genuinely impressed by the innovative solutions showcased and the quality of work demonstrated by the presenters and their teams. My winners My standout presentation was LLMs are the Future of Conversational AI  by Antony Heljula of TPXimpact. Antony shared his experiences in developing chatbots that leverage large language models in conversational AI. Truly groundbreaking! A close second for me was Gianni Ceresa's (DATAlysis) presentation titled ID Please: Did You Already Ask That to Your Data?  Gianni delved into the crucial aspects of data lineage and governance, addressing the

My presentations @ UKOUG 2023

I am more than honoured to share that I am presenting at this year's UKOUG 2023 conference that is taking place on 15th and 16th November at Oracle TVP, Reading. I will deliver the following two presentations: Tuesday, 15th November, 10:00-10:45, Lambourne OCI Vision and Oracle Analytics: Just Like a Box of Chocolates   Oracle Cloud Infrastructure (OCI) is just like a box of chocolates. It is offering a variety of cloud services, including serverless and very user friendly AI services such as Vision, Language, Speach, Document Understanding and Digital Assistant. In this presentationa I am focusing on OCI Vision, which is a self-service AI Service, which applies computer vision for image-based content analysis. It allows developers easily integrate pre-trained models into their applications with APIs or custom training models to meet their specific use cases.  In this presentation we will demonstrate how to train machine learning model for x-ray image classification using OCI Visio

My Presentations @ HrOUG 2023

HrOUG 2023 took place between Tuesday, 17th October, and Friday, 20th October. As usual in a great athmosphere of St. Andrew's Island near Rovinj . This year, 400+ attendees took part in the event organised by Davor and his team.  My part of the event has been focused on two presentations (they will be available to download any day soon), which I had already at SIOUG 2023 in June, however I've added some new facts and new demos since then: My view on Oracle’s position in Gartner Magic Quadrants for Analytics and Business Intelligence Platforms Gartner has published its Magic Quadrants for Analytics and Business Intelligence Platforms (Gartner, 2023) report for 2023, on April 5th. As usually, it presents how various analytics and BI vendors position regarding the completeness of their vision and ability to execute. It is considered as “the go-to resource” when evaluating and comparing these technologies. In their report, Gartner says that the key Oracle’s strengths are in

My Presentations @ Make IT - SIOUG 2023

28th annual event  Make IT 2023  took place in Portorož, Slovenia, between 1st and 2nd June 2023. The conference actually consists of two conferences:            As organisers, we are very pleased with the conference which has grown in terms of the content  presented and also regarding the number of attendees which has surpassed 350.   I've been involved with organisation as a member of the organising committee, however personally, my preference lies of course with  Make IT - SIOUG 2023 , where I delivered two presentations: OCI Vision and Oracle Analytics: Just like a Box of Chocolates OCI Vision is a self-service AI Service, which applies computer vision to analyze image-based content. It allows developers easily integrate pre-trained models into their applications with APIs or custom training models to meet their specific use cases. In our example, I will explore how to use OCI Vision service to create a custom-built model to detect pneumonia infected lungs on a fresh dataset of

Conditional maps formatting in Oracle Analytics

Oracle Analytics Cloud (OAC) is now frequently updated on bi-monthly basis. May Update release has been announced a week or so ago, and I was able to take a look at preview version which brings again several nice new features and functionalities . The one that has drawn my attention was Maps Conditional Formatting , an option to highlight important data events in map visualizations along with other visualization types. So how does this work? Actually, it is very straight forward as the same model is used as with any other conditional formatting. The map above is the starting point and presents profitability by country. Couldn't be more simple, right? In order to implement conditional formatting on the map, click on the traffic light icon ( Manage Conditional Formatting Rules ). This will open Conditional Formatting popup window. Select to what this particular conditional formatting applies to, the whole workbook or just selected visualization. Provide a name for the rule a

Talking to Oracle Analytics

Being able to talk, by using natural language, to computers, especially with the advancements in general AI models like ChatGPT, has become very fashionable in the last couple of months. Everybody does it. It is simple, easy to use and let's be frank, it can be also very useful. Something that has been around for a while, remember Siri or Alexa or TV remote controllers, has been lifted to a new level and has wide spread use in business already. A bit of a secret is also that  Oracle Analytics  can use natural language, query and generation. Here are some of my findings about NLQ and NLG support in  Oracle Analytics . Natural Language Querying (NLQ) In Oracle Analytics , NLQ has already been around for a while, at least for some years now. I remember those early days when Oracle Day by Day mobile application has been introduced. One of the coolest features in Day by Day was actually the ability to ask a question using natural language. Something like What is revenue by region a