Beyond words: How byte pair encoding and Unicode encoding factor into pricing disparities — After publishing my recent article on how to estimate the cost for OpenAI’s API, I received an interesting comment that someone had noticed that the OpenAI API is much more expensive in other languages, such as ones using Chinese, Japanese, or Korean (CJK) characters, than in English.

From Academia to Industry: Finding the best trade-off between predictive performance and inference runtime for sustainability in Machine Learning practices — This article was originally published on Kaggle as an entry to the “2023 Kaggle AI Report” competition on July 5th, 2023, in which it won 1st place in the category “Kaggle competitions”. As it reviews Kaggle competition writeups, it is a special edition of “The Kaggle Blueprints” series.

Count your tokens and avoid going bankrupt from using the OpenAI API — Many people I know are interested in playing with OpenAI’s large language models (LLMs). But hosting LLMs is expensive, and thus, inference services like OpenAI’s application programming interface (API) are not free. …

How to use vector databases for semantic search, question answering, and generative search in Python with OpenAI and Weaviate — If you landed on this article, I assume you have been playing around with building an app with a large language model (LLM) and came across the term vector database. The tool landscape around building apps with LLMs is growing rapidly, with tools such as LangChain or LlamaIndex gaining popularity.

From noob to expert: Demystifying vector databases across different backgrounds — Vector databases have been getting a lot of attention recently, with many vector database startups raising millions in funding. Chances are you have probably already heard of them but didn’t really care about them until now —at least, that’s what I guess why you are here now… If you are…

Recreating lessons learned from Cole Nussbaumer Knaflic’s book in Python using Matplotlib — Being able to communicate effectively with data is a skill that is relevant for anyone working with data – and not only for data scientists and data analysts. One of my favorite books on this topic is Cole Nussbaumer Knaflic‘s „Storytelling with Data“. …

How to reduce inference time on CPU with clever model selection, post-training quantization with ONNX Runtime or OpenVINO, and multithreading with ThreadPoolExecutor — Welcome to another edition of “The Kaggle Blueprints”, where we will analyze Kaggle competitions’ winning solutions for lessons we can apply to our own data science projects. This edition will review the techniques and approaches from the “BirdCLEF 2023” competition, which ended in May 2023.

Learn how to build apps and showcase your skills with large language models (LLMs). Get started today! — One common piece of advice I often hear for job applicants is to have a portfolio showcasing your work. This doesn't only apply to artists or models but also to software developers and data scientists. A portfolio of your projects acts as public evidence of your skills. This public evidence…

Fine-tuning pre-trained Deep Learning models in Python — This practical tutorial shows you how to classify images using a pre-trained Deep Learning model with the PyTorch framework. The difference between this beginner-friendly image classification tutorial to others is that we are not building and training the Deep neural network from scratch. In practice, only a few people train…