Intro

Hi, there... I'm Simon

I've been in love with technology since I was knee-high to a grasshopper. Here I'll be posting about my experience with hardware and software... tips and tecnhiques included.

A little bit of history.

I've lived in Brazil since 1979, due to my father (an engineer) being transferred here by a multinational corp, tasked with designing a coffee harvesting machine. He's always loved technology,  and in 1980 he purchased a HP33 (not sure if it was an E or a C) during a trip to the US, along with some application books for it. He spent a week of evenings reading through every manual and trying every single command on the calculator. Around this time he got me a 200 in 1 electronic kit from Radio Shack.

I started playing with computers in 1981 with a TRS80 Pocket computer that an american co-worker of my father owned. He also had a lot of computer magazines (Byte, Kilobaud Microcomputing). I'd stare in awe at computers in a store, and pestered my father to get a ZX81 compatible manufactured here in Brazil, the Microdigital TK-82C. By the time I managed to get him thinking about actually buying one, the newer TK85 had come out, se he got that instead (I still have if, albeit somewhat "patched up"). It looked like a ZX-Spectrum, but was a 16K ZX81 compatible inside. Hi co-worker also got one around the same time. Here in Brazil, software piracy was common, and we'd swap game program tapes.

I'd get up around 6 in the morning, play with the computer until around 7, go to school, and when I got back home at lunch time, eat in a frenzy, and sit in front of the computer until 10 at night, when my parents made me go to bed.

I learned BASIC and Z80 assembly language, and finished an 18-month course on digital electronics and microprocessors. My dad got me a TRS Color Computer compatible (Prológica CP400), so I had to learn 6809E assembly. My brother got a ZX Spectrum clone (TK90X), so I´d play Elite, Gunship, F15 Strike Eagle, Chequered Flag and Highway Encounter when he let me. My dad's friend got an Apple II clone.

Around this time I started working as an apprentice at a consulting company, with the recently introduced, Microtec PC2001, an IBM-PC clone, using and programming dBase II, Wordstar and Lotus 123. In the 35+ years since then I've programmed in a huge variety of languages, operating systems, and technologies. Most recently, I'm working with AI in Python, and Rasa chatbot.

Comments

Post a Comment

Popular posts from this blog

Better report for Rasa chatbot model analysis

Image
Rasa is a very powerful AI Framework for building contextual assistants, but you have to know how to set up your NLU, and improve your intent recognition. You can generate a report that will show what your model looks like using the  rasa test  command. In the results folder, the intent-errors.json will show where intents are getting mixed up, but doesn't show you intents that are nearly  being confused, and an alteration in your NLU examples can cause them to start failing. All of your examples are influencing the neural net that is classifying what the user typed, in one way or another. Imagine a huge spider web connecting all examples with intents... if you "move" one example, all the intents classifications will move, albeit some almost imperceptibly. I'll be showing you how to analyze intent classification and figuring out where to improve your model, and taking you step-by-step through writing a python script to help figure out what's happening. So how do
Read more

Multiple Rasa containers with docker-compose (part 2)

Multiple Rasa containers with docker-compose (part 2) Dockerfiles for our other containers Let's start with the action servers... Rasa normally runs on port 5055. If we want to start two action servers on the same server, we would need to specify different ports for each instance, but in this case, since they will run in separate containers, there's no need. If we want to access them from the host we have to expose different ports, though. We can do that in the docker-compose.yml file. cd  into the chatbot_a/actions folder and let's create this Dockerfile: FROM sscudder/rasabase RUN apt-get update && apt-get -y install locales locales-all RUN locale-gen pt_BR.UTF-8 ENV LANG pt_BR.UTF-8 ENV LANGUAGE pt_BR:pt ENV LC_ALL pt_BR.UTF-8 COPY /actions/actions.ini /actions/actions.ini COPY /actions/actions.py /actions/actions.py WORKDIR /actions The Dockerfile from chatbot_b/actions will be exactly the same. Moving on to the docker file for chat
Read more

Multiple Rasa containers with docker-compose (part 1)

Image
Setting up multiple Rasa instances with docker-compose Our customer has two different chatbots with distinct functions. One is a site support chatbot, with knowledge of the site itself and can open support tickets for the humans that run the site. The other is a general knowledge chatbot that answers questions about the customers business, related to realtors. Here's how we got the chatbots up and running on the same server using docker containers. The setup is under RHEL7 (CentOS). We'll use docker containers and docker-compose to make life easier.  In the end, there will be 5 containers running: Chatbot A Action server A Chatbot B Action server B mongoDB Setting up the file system Create a folder, let's say app , and create a folder for each chatbot (we'll call them chatbot_a and chatbot_b ). Copy your chatbot configuration files into the separate folders, but leave the trained models out for the moment. We want a folder structure li
Read more