PinnedJérôme DIAZ(Hugging Face) — Text classification, going further than the tutorialHugging Face’s tutorial about text classification train a 2 labels model. This article is about checking if you can go further… (yes)Sep 12Sep 12
PinnedJérôme DIAZRAG: hybrid search based on two indexesThe proposition I will be talking about in this article is something I already have implemented and I am currently testing in a personal…Mar 29Mar 29
Jérôme DIAZ(Python) Why and how to serialize/deserialize objects.Serialization is the process of converting in-memory data into a format, typically text or binary, that can be easily transmitted and…2d ago2d ago
Jérôme DIAZStable-Diffusion simply explained, or how we can create images from textA simple but accurate explanation of how stable diffusion work for generating images from a text. Spoiler alert, it starts with the end…Sep 22Sep 22
Jérôme DIAZA case study about delaying and buffering data transmission to fix performance issuesThis is about an issue that was encountered a few weeks ago in a side project and how it was fixed.Sep 2Sep 2
Jérôme DIAZFrom Text to Knowledge GraphThis short article will start by giving a brief explanation on what is a knowledge graph and how it can be used in the context of RAG. Then…Jul 28Jul 28
Jérôme DIAZPython’s tales from the for-loop: when performance does matterSpoiler alert! We will talk about list construction, memory efficiency, function/variable execution and conditions.Jun 281Jun 281
Jérôme DIAZPython Pandas library: the tricks behind DataFrame filteringSpoiler alert, it is mostly about operator overloading and predicates!Jun 16Jun 16
Jérôme DIAZRAG, Knowledge Bases: transposing programming principlesIn programming, we distinguish compiled and interpreted languages. For RAG it is the same, knowledge can be indexed beforehand… or not!Jun 15Jun 15