📌 How to Talk to a PDF File Without Using Proprietary Models: CLI + Streamlit + Ollama

🗂 Category: MACHINE LEARNING

🕒 Date: 2024-08-14 | ⏱️ Read time: 17 min read

A contribution to the creation of a locally executed, free PDF chat app with Streamlit…

📌 Massive Energy for Massive GPU Empowering AI

🗂 Category: MACHINE LEARNING

🕒 Date: 2024-08-18 | ⏱️ Read time: 7 min read

Massive GPUs for AI model training and deployment require significant energy. As AI scales, optimizing…

📌 The Math Behind Keras 3 Optimizers: Deep Understanding and Application

🗂 Category: DATA SCIENCE

🕒 Date: 2024-08-17 | ⏱️ Read time: 9 min read

This is a bit different from what the books say.

📌 Exploring cancer types with neo4j

🗂 Category:

🕒 Date: 2024-08-17 | ⏱️ Read time: 7 min read

How to identify and visualise clusters in knowledge graphs

📌 Adapting the Azure Landing Zone for a Data Platform in the Cloud

🗂 Category: DATA ENGINEERING

🕒 Date: 2024-08-16 | ⏱️ Read time: 8 min read

Working with sensitive data or within a highly regulated environment requires safe and secure cloud…

📌 Writing a Good Job Description for Data Science/Machine Learning

🗂 Category: DATA SCIENCE

🕒 Date: 2024-08-16 | ⏱️ Read time: 16 min read

Things to do and things to avoid in order to find the right candidates for…

📌 How to Build Helpful RAGs with Query Routing.

🗂 Category: ARTIFICIAL INTELLIGENCE

🕒 Date: 2024-08-16 | ⏱️ Read time: 11 min read

An LLM can handle general routing. Semantic search can handle private data better. Which one…

📌 The Missing Piece: Symbolic AI’s Role in Solving Generative AI Hurdles

🗂 Category: ARTIFICIAL INTELLIGENCE

🕒 Date: 2024-08-16 | ⏱️ Read time: 9 min read

Symbolic reasoning may still be alive…

📌 Mastering Data Streaming in Python

🗂 Category: DATA ENGINEERING

🕒 Date: 2024-08-16 | ⏱️ Read time: 13 min read

Best Practices for Real-Time Analytics

📌 Squashing the Average: A Dive into Penalized Quantile Regression for Python

🗂 Category: DATA SCIENCE

🕒 Date: 2024-08-16 | ⏱️ Read time: 5 min read

How to build penalized quantile regression models (with code!)

📌 Bad Assumptions – The Downfall of Even Experienced Data Scientists

🗂 Category: DATA SCIENCE

🕒 Date: 2024-08-16 | ⏱️ Read time: 11 min read

Data can be deceptive, so be on your toes!

📌 This Puzzle Shows Just How Far LLMs Have Progressed in a Little Over a Year

🗂 Category: LARGE LANGUAGE MODELS

🕒 Date: 2025-10-07 | ⏱️ Read time: 10 min read

What took GPT-4o 2 hours to solve, Sonnet 4.5 does in 5 seconds

📌 How to Perform Effective Agentic Context Engineering

🗂 Category: LARGE LANGUAGE MODELS

🕒 Date: 2025-10-07 | ⏱️ Read time: 14 min read

Learn how to optimize the context of your agents, for powerful agentic performance

📌 How to Easily Validate Your Data with Pandera

🗂 Category: DATA ENGINEERING

🕒 Date: 2024-08-14 | ⏱️ Read time: 6 min read

Learn how to build a simple data model that validates your data through type hints

📌 UniFliXsg: AI-Powered Undergraduate Program Recommendations for Singapore Universities

🗂 Category: LARGE LANGUAGE MODELS

🕒 Date: 2024-08-14 | ⏱️ Read time: 8 min read

How could AI suggest your majors?

📌 From insights to impact: leveraging data science to maximize customer value

🗂 Category: DATA SCIENCE

🕒 Date: 2024-08-13 | ⏱️ Read time: 11 min read

Uplift modeling: how causal machine learning transforms customer relationships and revenue

📌 From Data-Informed to Data-Driven Decisions: An Introduction to Tradespace Exploration

🗂 Category: DATA SCIENCE

🕒 Date: 2024-08-13 | ⏱️ Read time: 23 min read

Going beyond Exploratory Data Analysis to find the needle in the haystack

📌 Paper Walkthrough: Vision Transformer (ViT)

🗂 Category: DEEP LEARNING

🕒 Date: 2024-08-13 | ⏱️ Read time: 20 min read

Exploring Vision Transformer (ViT) through PyTorch Implementation from Scratch.

📌 Four Visualisation Libraries That Seamlessly Integrate With Pandas Dataframe

🗂 Category: DATA SCIENCE

🕒 Date: 2024-08-13 | ⏱️ Read time: 5 min read

Make use of Pandas plotting backend for the easiest plotting

📌 Avoid Building a Data Platform in 2024

🗂 Category: DATA ENGINEERING

🕒 Date: 2024-08-13 | ⏱️ Read time: 16 min read

Why articles about ‘Building a Data Platform’ are mostly misleading