Kay Pacha: a Telegram Weather Chatbot using OpenAI and Open Weather Map APIs

2024-03-23 ML Tutorials OpenAI Joan Gerard

Have you ever tried to ask Chat-GPT about the current weather in your city? Most of the time it answers something like: “It’s impossible for me to give you real time information” and it is because the OpenAI’s models don’t have access to real time information. It only knows the data which was used to train it. Here, I’m going to show you how you can create a Telegram chatbot to ask about today’s weather in any part of the world consuming OpenAI and Open Weather Map APIs. Continue reading

Deploy an MLflow model to local environment and Docker

2024-02-23 Azure ML Tutorials Joan Gerard

Introduction Azure might be very expensive to deploy predictive models into their servers. For that reason I’ll show you how to deploy a predictive model to a local environment and dockerize it using the artifact created by Azure AutoML. Prerequisites You’re going to need to run AutoML in Azure with some dataset and to download the best model into your compute instance environment. Download the artifact locally An "artifact" is a component that results after training a model. Continue reading

JoanGerard