CDUser - Ignacio Van Droogenbroeck's Technical Blog
Build your own voice authentication system in Python. Record your voice, train a model, and unlock access with just a phrase. No cloud APIs, just pure open-source ML magic, inspired by spy movies, powered by your mic.
Migrating from InfluxDB 1.x/2.x to 3.0 doesn’t have to mean losing years of data. Historian exports to Parquet, keeps history queryable with DuckDB, and provides a clean path back into InfluxDB 3.0
After years building products across data, AI, and infrastructure, I’m starting a new chapter, one focused on value, not billable hours. This is Basekick.
I built a Python war simulator where GPT, and DeepSeek command real-world armies. The result? Absurd alliances, ruthless economic warfare, and surprising lessons about how AI thinks when its only goal is to win.
In this post, I explore Redis as a time series database using Docker, Python, and RedisInsight. From monitoring my Mac in real time to querying time series data with blazing speed, this hands-on guide walks through the unexpected power of Redis Stack for time series workloads.
Ever wondered why your AI assistant forgets what you just said? Let’s talk about context length, the hidden limit behind LLM memory and what makes some models feel like Dory from Finding Nemo.
A fun dive into hybrid search with Qdrant! From clustering to reranking, see how we built a search app using dense and sparse vectors.
I left AWS after a few months, not because it’s a bad company, but because it wasn’t the right place for me. I thrive in dynamic, flexible environments where culture is lived, not watched in a video. This is my honest take on what I value, and what I’m building next.
Getting too attached to tech tools? After 20 years in the industry, here's why we need to stop falling in love with our tech stack.
How to build a robust speaker recognition system with Python and PyTorch. This guide covers data preprocessing, model training, and feature extraction. Ideal for developers implementing voice recognition and speaker identification in machine learning projects.
Learn how to build a time-series data storage system using blockchain with this fun guide. Explore setting up Ethereum with Ganache, deploying smart contracts with Solidity and Truffle, and using Python to store and retrieve time-series data like temperature and humidity.
Milvus is a powerful open-source vector database that excels at managing unstructured data such as images, video, and audio. This article explores Milvus's capabilities, including an image similarity search use case using Python.