Systems | Development | Analytics | API | Testing

ODSC East 2023 MLOps Keynote: MLOps in the Era of Generative AI

ChatGPT sparks the imagination and highlights the importance of Generative AI and foundation models as the basis for modern AI applications. However, this also brings a new set of AI operationalization challenges. Challenges like handling massive amounts of data, large scale computation and memory, complex pipelines, transfer learning, extensive testing, monitoring, and so on. In this talk, we explore the new technologies and share MLOps orchestration best practices that will enable you to automate the continuous integration and deployment (CI/CD) of foundation models and transformers, along with the application logic, in production.

How ChatGPT Could Be a Data Security Problem

There’s no doubt in just a short period of time, ChatGPT and other large language models (LLMs) have become so immensely popular, they are now used by millions of people daily. ChatGPT’s ability to provide human-like responses and generate content has shown to be valuable to businesses and people across customer service, education, healthcare, and other industries. However, to get access to OpenAI’s powerful AI-tool, what do these businesses and people give up?

Customer-Centric Test Automation Approach

Some consultant companies will not eliminate all the risks by offering an automagic solution (Perhaps a revolutionary testing tool). However, it could give better possibilities for applications to be evaluated in case of quality gaps and deliver accurate applications for the consumers. We see products/services failing before any launch or retiring a couple of months later.

What are Data Silos and 5 Best Practices to Eliminate Them

Using data to make decisions is actually really hard. Yet nearly every tech company, business, and team touts “data-driven” as the de-facto way that they operate. In practice, this intention to be data-led is often just aspirational—only about a quarter of organizations report that they are actually data-driven, according to Harvard Business Review. It’s easy to see why organizations strive to more effectively use their data.

Creating a Seamless Customer Experience with APIs at Just Eat Takeaway.com

In this Kongcast episode, Danielle Dias, Software Engineer at Just Eat Takeaway.com, talks about how her team creates a seamless customer experience by using Kong Gateway for rate limiting, monitoring, alerting, and more. Check out the transcript and video from our conversation below, and be sure to subscribe to get email alerts for the latest new episodes.

LLM ChatBot Augmented with Enterprise Data

This video demonstrates how to use an open source pre-trained instruction-following LLM (Large Language Model) to build a ChatBot-like web application. The responses of the LLM are enhanced by giving it context from an internal knowledge base. This context is retrieved by using an open source Vector Database to do semantic search.

Test Plan: Ultimate Guide (With Examples)

In software testing, a test plan is a must-have. A well-defined and comprehensive test plan provides all stakeholders involved with necessary information of the testing roadmap. Through it all members gain a shared vision for the testing approaches, strategies, objectives, resources, and timelines. In this article, we will deep-dive into what a test plan is, why it is so important, and how to create a good test plan that truly improves the overall efficiency of your testing activities.

Virtual Scouting with Unreal Engine Multi-User Editor - Perforce U

Learn how virtual scouting works with the Unreal Engine Multi-User Editor (Unreal MUE) in this clip from course 6 of Perforce U. The Unreal Engine Multi-User Editor enables more creative and immersive interaction with a digital environment created for a virtual production. Virtual scouting is one example: MUE eliminates the need for creatives doing virtual (VR) scouting to have a mastery of Unreal and its controls.