I want to share my experience in the cloud, AI, and agents development areas.
This blog post is about a simple example to use the Watson Assistant API v2 with the Node.js SDK to get a Watson Assistant sessionID and send a message to Watson Assistant using this sessionID. Here is the GitHub project watson-assistant-simple-node-js-server-example.
This blog post is about how export an example development realm using the Keycloak in version 20. I wanted to ensure that the export contains all information including users. You can find the relevant information in the Keycloak documentation ‘Exporting a realm to a file.’. I did some demo configurations in the new version and I can’t reuse my older exported examples from Keycloak.
My last blog post was about Watson Speech to Text language model customization and this blog post is about IBM Cloud Watson Text to Speech (TTS) custom voice model configuration. Because, now it's time to have some fun with the Watson TTS service. I created a fun customisation of the service that the German pronunciation sounds a little bit like the palatinate dialect. Here are the differences with two wav file I created with a custom Watson to Text to Speech voice model.
This blog post is about IBM Cloud Watson Speech to Text (STT) language model customization. Currently I took a look at the IBM Cloud Watson Assistant service used to build conversational assistants. A conversation leads potentially to speech input of users, which needs to be converted to text to be processed using AI for example the NLU.
IBM Watson Assistant is a SaaS offering from IBM to build conversational assistants. IBM Watson Assistant is using artificial intelligence which helps to understand users in context, to provide them easy and fast, consistent, and accurate answers across various applications, devices, or channels. IBM Watson Assistant is built on natural language understanding (NLU), natural language processing (NLP) and machine learning (ML). The first version was already very good, and IBM clients and partners were starting to take these advantages; for example Watson Assistant was used at the International Space Station. Here you can find some more details: CIMON brings AI to the International Space Station. Based on the feedback from clients, the IBM development and design team has created a brand new experience and added new functionalities to the service for example they expanded the integration possibilities with extensions. In this blog post I focus especially on custom extensions development and setup.
Infrastructure as Code and GitOps are ongoing big topics related to DevOps and CI/CD which needs effective automation to shorter the Software Development Lifecycle and simplify production deployments. In this blog post we don't talk much about these processes and methodologies. The blog post is more about how to reduce efforts to build an automation by using the IBM Accelerator Toolkit.
In this blog post we use an existing template file, that we created for a custom resource to insert the needed value for an URL to point to a container image in a container registry, to create custom resource yaml file we use to deploy that custom resource . The template file contains a string which we will replace with the content of URL to the container image. We haven't used helm, kustomize to do that in this situation.
That blog post is a short cheat sheet to deploy a pure UBI image as a container with Helm. With the values.yaml in the Helm chart we can configure replica count of the pods. The deployed containers are only a basic UBI operating system (Red Hat Universal Base Image).
This blog post is a small cheat sheet to deploy and delete the vend application example with a Helm chart in an OpenShift cluster. The related GitHub repository is vend-helm.
This blog post is a short cheat sheet related to the setup of a supported environment when you use a tools virtual machine in context for the usage with iascable and the Terraform output.
Thomas Suedbroecker's Blog 