20 Jul 2024
Making an API out of a Hugging Face model — deployment: Closing
In the previous four posts, we have been demonstrating how you can grab a preconfigured Hugging Face model and create an API from it. The API we made can read in a CV (or any PDF document) and recommend skills that are implied or stated in there from a predefined list. Now it’s time to wrap that project up.
13 Feb 2024
Making an API out of a Hugging Face model — deployment: part 3
We will use Docker to package the Python application and Flask API into a container, ensuring consistent execution across environments. This allows easy deployment and scaling on Cloud Run or other platforms, providing seamless access to the API.
18 Dec 2023
Making an API out of a Hugging Face model — the code: part 2
In the last post we showed you how to match sections of a CV to a list of skill names without turning it into an API. Here we will add the code that will turn that code into an API and serve it on Cloud Run.
27 Oct 2023
Making an API out of a Hugging Face model — the code: part 1
In the previous blog post, we have set the stage for a deep dive into the practical aspects of AI deployment using an API served on Cloud Run. In this installment, we will demonstrate how to recommend skills from a CV without turning your code into an API.
25 Jul 2023
Making an API out of a Hugging Face model — Introduction
This is the introduction to a blog series that shows how to create an API out of one of the Transformer models from Hugging Face. Currently, all the AI-related blog posts out there explain how to create an AI system, but few talk about how to actually deploy it.
2 May 2023
Are you paying enough attention to the EU AI-ACT? | Part 2
While most organisations are only just coming to terms with the EU’s General Data Protection Regulation (GDPR), the next big thing is already looming on the horizon: The EU AI-Act, or AIA.
2 May 2023
Are you paying enough attention to the EU AI-ACT? | Part 1
While most organisations are only just coming to terms with the EU’s General Data Protection Regulation (GDPR), the next big thing is already looming on the horizon: The EU AI-Act, or AIA.
17 Apr 2023
How to test Databricks’ Dolly 2.0?
We had our first look at the recently released Dolly 2.0, an open-source instruction-following Large Language Model (LLM). This model is similar to ChatGPT’s but with a free license for research and commercial use.
22 Feb 2023
Break the cycle: How to develop AI solutions that really work for government
Are you tired of hearing about the next major wave of digital transformation that will revolutionize government; only to see it fall short of expectations?
22 Feb 2023
Creating a long running job in GCP’s new Batch service
TLDR. You can run long-running jobs on a fully configurable virtual machine using Google Cloud Platform’s (GCP) new Batch service. You can find the link to Github with our working sample here.
11 Aug 2022
Predicting vaccine uptake with publicly available data
Tim Sanderse did this research as part of his master in Data Science and Society at Tilburg University. I tried to predict vaccine coverage rates in sub-national areas based on socio-demographic variables using machine learning models.