For the past few months I’ve been working with Pinecone on a series of articles and videos covering the essentials of vector similarity search.
The course introduces the idea and theory behind vector search, how to implement several algorithms in plain Python, and how to implement everything we learn efficiently…
Building that first API is for many of us, a significant step towards creating impactful tools that may one day be used by many developers. But often those APIs don’t make it out of our local machines.
Fortunately, it’s incredibly easy to deploy APIs. Assuming you have no idea what…
Question-answering (Q&A) transformers are widely applicable, insanely cool applications of modern-NLP.
At first glance, most of us would view building something like this as a feat of great difficulty. Fortunately, most of us would be wrong.
Transformers are — despite their incredible performance — surprisingly straightforward to train or fine-tune…
Taking those first steps into interacting with the web using Python can seem daunting — but it need not be. It is a surprisingly simple process, with well established rules and guidelines.
We’ll cover the absolute essentials for getting started, including:
- Application Program Interfaces (APIs)
- Javascript Object Notation (JSON)
…
HF Datasets is an essential tool for NLP practitioners — hosting over 1.4K (mainly) high-quality language-focused datasets and an easy-to-use treasure trove of functions for building efficient pre-processing pipelines.
This article will look at the massive repository of datasets available and explore some of the library's brilliant data processing capabilities.
Building a transformer model from scratch can often be the only option for many more specific use cases. Although BERT and other transformer models have been pre-trained for many languages and domains, they do not cover everything.
Often, these less common use cases stand to gain the most from having…
Facebook AI Similarity Search (Faiss) is one of the most popular implementations of efficient similarity search, but what is it — and how can we use it?
What is it that makes Faiss special? How do we make the best use of this incredible tool?
Fortunately, it’s a brilliantly simple…
HuggingFace’s transformers library is the de-facto standard for NLP — used by practitioners worldwide, it’s powerful, flexible, and easy to use. It achieves this through a fairly large (and complex) code-base, which has resulted in the question:
Why are there so many tokenization methods in HuggingFace transformers?
Tokenization is the…
Many of my articles have been focused on BERT — the model that came and dominated the world of natural language processing (NLP) and marked a new age for language models.
For those of you that may not have used transformers models (eg what BERT is) before, the process looks…
Similarity search is one of the fastest-growing domains in AI and machine learning. At its core, it is the process of matching relevant pieces of information together.
There’s a strong chance that you found this article through a search engine — most likely Google. Maybe you searched something like “what…
