Parent page for articles explain how to get the most out of Qwiery.

Machine learning: using R to forecast data

The approach in this article works for various types of questions where you need to pull an answer from outside the Qwiery box. NodeJS has a very simple mechanism to invoke inline processes and R or Python are no exception. Let’s assume you have somewhere some data representing a time series (say, sales figures of […]

Add a probing service

A probing service is a service which gathers potential answers to a questions and is different from a pipeline service: it’s activated in parallel together with other probing services. A normal pipeline service is called unless the previous one did not resolve the question. When all probing services are launched in parallel they all potentially […]

Rendering data

This is, strictly speaking, not about Qwiery but about the default client rendering results from the Qwiery backend. The client uses standard ReactJS techniques to inject a component which corresponds to a data type returned from the backend. For example, the question ‘how are you doing?‘ returns a simple string as part of the Output: […]

Generic recipe to integrate Python

NodeJS has plenty of packages you can use and integrate but sometimes you need something out there. If you wish to integrate neural networks then most likely you will want to have a look at Keras or Theano or a combination of Google’s TensorFlow and some other. NodeJS makes it actually incredibly easy to call […]

Dealing with emotions

Details about the way Qwiery processes emotions can be found here. The emotions engine is a dynamical system (a neural network actually) which can quickly give you a world of variations with little efforts. The input for the engine can be diverse: inspecting the smileys as a way to update the social emotions inspecting the […]

What is the weather?

This is an example showing how to make use of workflows. The question ‘What is the weather?’ is somewhat undefined because Qwiery does not necessarily know what your location is. Well, it would not be too difficult to include a service which picks up the IP address and through this the approximate location, but that’s […]