Sign in

With more than 2 million downloads, Rasa is an increasingly relevant open-source framework for the creation of conversation assistants. A conversation assistant can be provided to users as a via Facebook Messenger or Slack. It is also possible to publish the assistant as Alexa Skill. offers both the possibility to implement an assistant without any programming knowledge and to adapt the functional range of the framework to the respective needs via implementing extensions in Python. This article gives an overview of how Rasa makes it possible to easily create assistants. For this purpose, we create a

Event streaming and Apache Kafka

What does e-commerce have to do with event streaming (using Apache Kafka)? For modern e-commerce businesses, the speed of their platform is a crucial factor for their success. How fast can they respond to customers? Can they provide their services quick enough? How fast do their websites load? Maintaining a high speed is now necessary for catering to the demands of impatient customers and for expanding services.

While operating quickly helps in expanding your business and becoming more successful, business expansion, in return, can negatively affect your performance.

This is especially true for online platforms. When traffic and customer interaction…

Explainable Object Detection Human Detection Illustration

Explaining the reasoning going on in models trained with machine learning algorithms, such as object detection models, has become ever more important. This is due to both regulatory standards that demand insight into these models, and the increasing complexity of state-of-the-art models. We have already written about and . This time we want to write about explainable object detection.

In this article we investigate one AI application where explaining the model output is particularly interesting and challenging: Detecting objects in images. Object detection is a task under intense, active development…

TLDR: MicroProfile metrics are awesome and useful,

Those who have already had the pleasure of developing an application with Quarkus are probably aware of its benefits when collecting metrics. The MicroProfile specification offers a range of possibilities for this, which I will briefly introduce here.

However, this article by no means covers all possibilities and aspects concerning MicroProfile metrics and serves rather as an introduction with useful examples. While it is intended for Quarkus, it should apply to other MicroProfile implementations as well. I will not go into the storage and display of metrics with e.g…

A FAQ Chatbot will bring your First-Level Support to a new level!

In this article we will show how to implement a FAQ with Rasa to answer FAQs and fill in forms. For working with forms, the Rasa framework with the offers a simple way to create simple yet user-friendly bots for this task without the need to write extensive dialogs.

In the article “ ” we described how to create a simple with Rasa. We showed how to install Rasa and initialize a first project. We also illustrated how to have a simple dialog with the bot.

To show this use case, we describe…

Customer Churn & Churn Rate

Unhappy customers increasingly change products and service providers. What causes and consequences does this have for companies? How can customer churn and satisfaction be measured? What is the significance of customer churn in this context and what strategies can help to counteract it?

Customer churn refers to the migration of a company’s customers. Gaining new customers is significantly more expensive and time-consuming than retaining existing customers. This makes churn a crucial metric for customer satisfaction and in customer relationship management. For companies it is therefore worthwhile to observe and analyze customer churn carefully. …

Automatic Object Detection based on Deep Learning has the potential to make a significant contribution to areas such as process monitoring in industrial manufacturing, driver assistance systems or health diagnostics support in the future. However, to enable large-scale industrial use, it is necessary to be able to use these methods on resource-limited devices. With the described application we show a possible use which already enables Real Time Object Detection with excellent quality on Android devices.

The advance of Machine learning and Artificial Intelligence brought revolutionary methods in computer vision and text analysis. One of the newer trends is Deep Learning…

Customizeable, real-time Sonar Object Detection for an autonomous survey-robot

Surveying and search operations are carried out worldwide in lakes, canals or coastal waters to detect objects hidden underwater: scrap metal in shipping routes or old military loads, such as aerial bombs or underwater mines. To support these search operations, Evologics developed the Sonobot 5, one of the fastest floating sonar USVs (unmanned surface vessels) in the world. Among other things, it supports the police and coast guard in locating and recovering drowned people.

The Client

EvoLogics is a hightech company based in Berlin with strong maritime bionics and robotics R&D experience. They offer solutions for underwater communication and monitoring, including the…

What is the LAMBADA AI method?

IBM’s LAMBADA AI is a novel data augmentation method for text classification tasks. The acronym LAMBADA stands for “language-model-based data augmentation”. The method’s idea is to finetune pretrained language models to generate synthetic training data for text classification tasks such as intent classification in conversational systems.

Automtically generated training data with the LAMBADA AI method

Chatbots must be able to perform the following three key tasks in general:

  1. understanding what a user is saying and identifying the underlying intent,
  2. managing the conversation, keeping track of previous interactions and deciding which action to take next
  3. responding to the user

For task 1. we face the challenge of identifying all possible…

Better NLG and NLU with Data Augmentation

One of our covered the LAMBADA method that makes use of Natural Language Generation (NLG) to generate training utterances for a Natural Language Understanding (NLU) task, namely intent classification. In this tutorial we walk you through the code to reproduce our PoC implementation of LAMBADA.

Before you go ahead with this tutorial, we suggest having a look at applied by LAMBADA in more detail. In this tutorial we illustrate crucial methods providing an interactive . Overall, we explain some of the key points of the code and demonstrate how…


As strong believers in open-source, microservices & API-based economy, we create digital platforms that solve problems & create business value with technology

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store