As a first step to having Matilda as a fully open source, micro-serviced AI, I created the first repository on Matilda’s GitHub, it’s small step, as it’s a deadly simple API for weather forecasting, but it will be a keystone for her first meaningful functionality. This will enable me to ask Matilda about the weather and receive a proper response, as described here.
On the above example Matilda is already able to tell me about the weather but she’s limited to two cities, what the API will allow me is to be able to search any city and in a vary scalable manner.
And then I after kicking off the GitHub account with the first repo, I got super excited and created a second one to share what I call the “Broca’s Area”. Well not me exactly, Broca’s area or the Broca area /broʊˈkɑː/ or /ˈbroʊkə/ is a region in the frontal lobe of the dominant hemisphere (usually the left) of the hominid brain with functions linked to speech production. In other words, this is what will allow Matilda to talk. In technical terms, this is a Python micro-service capable of receiving text and turn into speech by using AWS Polly, the artefact generated is a json response with base64 audio embeded. This is awesome because the code I shared here isn’t OS agnostic whereas this one is completely independent to the operational system you’re running, it should just work regardless.
I will also try to always have a Dockerfile in each of the services so that those can be spun up with ease by anyone.
I’m reaaaally looking forward to connecting these two micro-services and watch Matilda give me the weather forecast though them. I’m also really excited about sharing all this open source code, can’t wait to see people being able to leverage from different parts of Matilda’s code on their own projects!