Will Fuks – Medium

Published in Geek Culture

·Jul 6, 2021

djwto: Django Authentication with JWT

Introducing an alternative implementation for the auth layer using JWTs. — I usually write about data science projects. So it begs the question: “How come this post can be about adding a JWT based auth layer on top of Django?” Well, what I can say is, on each project that we work on, the need to offer customers some sort of…

Django

6 min read

Django

6 min read

Published in Towards Data Science

·Dec 18, 2020

Implementing Causal Impact on Top of TensorFlow Probability

Using structural time series to infer impactful causality between variables. — One day a good friend and coworker of mine came to me and asked a question that would “haunt me” to this day. In fact, this post, written years after that question, is a derivation of that conversation. He asked: -Hey man! We are trying to solve an interesting problem…

Machine Learning

20 min read

Implementing Causal Impact on Top of TensorFlow Probability

Machine Learning

20 min read

Published in Towards Data Science

·Jul 29, 2020

Building a Complete AI Based Search Engine with Elasticsearch, Kubeflow and Katib

Let’s see how to build a complete search engine on top of Kubernetes with AI personalized results — Building search systems is hard. Preparing them to work with machine learning is really hard. Developing a complete search engine framework integrated with AI is really really hard. So let’s make one. ✌️ In this post, we’ll build a search engine from scratch and discuss on how to further optimize…

Elasticsearch

19 min read

Elasticsearch

19 min read

Published in Towards Data Science

·Jul 21, 2020

Solving One of the Biggest Challenges for AI-Based Search Engines: Relevance

Let’s learn how to implement ClickModels in order to extract Relevance from clickstream data. — Building a search engine system usually follows some well-known steps for the most part: Choose an appropriate database for the search operation. Save a set of documents. Apply transformations to the documents fields (remove accents, filter plural, break white spaces…). Create a querying rule for retrieving those documents.

Machine Learning

14 min read

Solving One of the Biggest Challenges for AI-Based Search Engines: Relevance

Machine Learning

14 min read

Published in Google Cloud - Community

·Dec 12, 2017

How We Implemented a Fully Serverless Recommender System Using GCP

Just recently we were faced with a quite exciting challenge by our company and I’d like to take the opportunity to write down about it and what we’ve learned along the way. Our main goal was to work together with our central team at GFG Group to develop a Recommender…

Google Cloud Platform

29 min read

How We Implemented a Fully Serverless Recommender System Using GCP

Google Cloud Platform

29 min read