Updated tutorial: Database-driven chatbot

If you want to build a chatbot that gets its content from a database, there is a good news. The existing tutorial “Build a database-driven Slackbot” was just updated to adapt to latest features of IBM Watson Assistant. First, define a skill that reaches out to a database service like Db2. Thereafter, use the built-in integrations to easily tie in the assistant with Slack, Facebook Messenger, embed the chatbot into your own application or use the WordPress plugin.

Architecture of database-driven chatbot

Running Db2 Developer-C as Docker container

Container: Db2 the easy way

Last week I wanted to start testing some new Db2 features without going through the steps of installing that Db2 version. I turned to my local Docker installation, issued a single command and had Db2 up and running. Quite interesting, that command downloaded Db2, installed it, created a sample database. Here are the details.

Db2 Developer-C Edition as Docker Image

IBM provides a free Db2 edition, Db2 Developer-C Edition. It can be installed and used as Docker container, see here the Db2 Developer-C Edition in the Docker store. Once you have added it to your basket and checked out, you can download it and get information about how to configure it. Basically, only few values need to be set in an environment file (see db2_env_list below).

After adapting the environment file, I invoke the script (with a single command) to run Db2 on docker. If not downloaded yet, it obtains the container image, starts it, sets it up:

docker run -h db2server_ --name db2server --detach \
--privileged=true \
-p 50000:50000 -p 55000:55000 \
--env-file db2_env_list \
-v /home/hloeser/progs/db2:/database \
store/ibmcorp/db2_developer_c:11.1.4.4-x86_64

Thereafter, I can connect to Db2 using the usual tools and SDKs.

If you have feedback, suggestions, or questions about this post, please reach out to me on Twitter (@data_henrik) or LinkedIn.

Digital ethics, trusted AI and IBM

Last week I gave a talk followed by a discussion at a university. The presentation was about the current state of Artificial Intelligence (AI) and AI research topics. A good chunk of the discussion was dedicated to fairness, trust and digital ethics. In the following, I am sharing some of the related links.

IBM Research has a site dedicated to  AI. On that, a section provides insight into topics on what they call Trusted AI. On the main IBM site is also a portal Trusted AI for Business, providing an introduction and overview for the non-research crowd. If you are interested and want to try out and learn about few problems hands-on, I recommend these links:

• AI Fairness 360 Open Source Toolkit: http://aif360.mybluemix.net/
• Detect the bias - a game and survey: http://biasreduction.mybluemix.net/
• Old, but still great: MIT Moral Machine:  http://moralmachine.mit.edu/

IBM experts are part of many public panels, workgroups and commissions. In Germany, there is the Enquete-Kommission "Künstliche Intelligenz - Gesellschaftliche Verantwortung und wirtschafliche, soziale und ökologische Potenziale". On the European level, it is the EU High-Level Expert Group on Artificial Intelligence.

Finally, as a showcase of current AI capabilities, I recommend this video of IBM Project Debater and the live debate at Think 2019. A short video explains how Project Debater works:


If you have feedback, suggestions, or questions about this post, please reach out to me on Twitter (@data_henrik) or LinkedIn.

Startup lessons from a Fuckup Night

Last Wednesday, I attended the Fuckup Night Friedrichshafen Vol. II. If you don't know, Fuckup Nights is a global movement and event series dedicated to professional failures. That is, usually founders of failed startups tell their stories. Typically, it is a mix of funny adventures into the world of business, some sad parts and most importantly some lessons learned. So what were the lessons I took away? Read on...