Evaluation and tracking of your LLM experiments with TruLens — The development of a Large Language Model application involves many iterations of experimentation. As a developer, your objective is to ensure that the model’s answers align with your specific requirements like informativeness and appropriateness. This process of retesting and evaluation can be quite time-consuming. This article will show you step-by-step…

Use LangChain and IPyWidgets to run conversational sessions with ChatGPT about custom documents in Jupyter Notebook — In March 2023, OpenAI released its API for developers to access ChatGPT and its Whisper models. Since then, developers can integrate these services and models into their applications and products via their API. Many great tutorials have then been published on how to create your own ChatGPT Chat web app…

Use prompt engineering to analyze your documents with langchain and openai in a ChatGPT-like way — ChatGPT is definitely one of the most popular Large Language Models (LLMs). Since the release of its beta version at the end of 2022, everyone can use the convenient chat function to ask questions or interact with the language model. But what if we would like to ask ChatGPT questions…

One of the most popular evaluation metrics for recommender or ranking problems step by step explained — Mean Average Precision at K (MAP@K) is one of the most commonly used evaluation metrics for recommender systems and other ranking related classification tasks. Since this metric is a composition of different error metrics or layers, it may not be that easy to understand at first glance. This article explains…

Using BERTopic to identify the most important ML topics — Topic modeling has become a popular technique in the field of Machine Learning (ML), particularly in the area of Natural Language Processing (NLP). This article shows how to leverage topic modeling to identify trending ML topics in science. Since 2022 has just passed, let’s use this opportunity to apply topic…

Transcription of audio files with OpenAI’s Whisper — OpenAI recently open-sourced a neural network called Whisper. It allows you to transcribe (large) audio files like mp3 offline. OpenAI claims Whisper approaches human-level robustness and accuracy in English speech recognition. Since there are already existing (open-source) models or packages like Vosk or NVIDIA NeMo out there, I was wondering…

Insights from comparing widely used customer churn prediction approaches — This article shows the results and findings from my previous (more technical) article, “A pipeline for benchmarking churn prediction approaches” where I explained how to build a generic pipeline to benchmark churn prediction approaches. The motivation behind this article is a paper from Geiler et al. …

How to benchmark multiple sampling strategies and models on different data sets using a scikit-learn pipeline — Customer churn prediction is a very common Data Science use case in Marketing. The idea is to estimate which customers are likely to cancel a subscription or stop using your service. Within the past years many competitions have been held and new approaches were developed to better predict customer churn…

Integrate modules from imblearn, feature-engine in your pipeline, and extract feature importance plots — Using pipelines in your machine learning project helps you bring more structure to your workflow. They make your different process steps easier to understand, reproducible and prevent data leakage. Scikit-learn pipeline(s) work great with its transformers, models, and other modules. However, it can be (very) challenging when one tries to…