All Posts

2025

Beyond Coverage - Building Truly Complete Test Suites with GitHub Copilot
Simple In-Memory Knowledge Graphs for Quick Graph Querying

2024

RankFlow plot for retriever visual evaluation
Open Source LLM Observability Tools and Platforms

2023

Prompt Discovery
Techniques to Boost RAG Performance in Production
Understanding the Differences in Language Models - Transformers vs. Markov Models
How Agile Can Kill Creativity in Data Science team?
From Fixed-Size to NLP Chunking - A Deep Dive into Text Chunking Techniques
Problems with Langchain and how to minimize their impact
Understanding Retrieval-Augmented Generation (RAG) empowering LLMs
Easy Text Vectorization With VectorHub and Sentence Transformers
Harnessing the Power of Dependency Injection for Improved Testability in Python
The Role and Responsibilities of a Forward Deployed Engineer - Bridging the Gap Between Software Products and Customer Needs
The Best Vector Databases for Storing Embeddings
Mastering the Kanban Method - Unveiling the Hidden Gems of Effective Kanban Board Usage
Attacking Differential Privacy Using the Correlation Between the Features
Are LIME Explanations Any Useful?
Intrinsic vs. Extrinsic Evaluation - What's the Best Way to Measure Embedding Quality?
Explaining AI - The Key Differences Between LIME and SHAP Methods
LIME - Understanding How This Method for Explainable AI Works
SHAP - Understanding How This Method for Explainable AI Works
KernelShap and TreeShap - Two Most Popular Variations of the SHAP Method
LIME Tutorial
Zero-Knowledge Explained Like to 5 Years Old
Rethinking the Link Between Speech and Expertise
Understanding AI with ELI5 - Demystifying Decisions (tutorial)
A Guide to Building a Python RPC Server Using Flask
How to Use RPC in Python?
"Comprehensive Guide to Interpreting R\xB2, MSE, and RMSE for Regression Models."
Beyond Airflow - 10 Workflow Tools You Need to Know
Libraries for Automated Exploratory Data Analysis (EDA)
Is the the Game Theory Any Useful for Data Science?
Beat Overfitting in Kaggle Competitions - Proven Techniques
New Cognitive Skills in the Age of AI Tailored Information Presentation
The Impact of Search Engines and AI Generative Models on Mental and Cognitive Capabilities
Leveraging Language Models in Corporate Environments - The Future of Knowledge Management
Top Popular ZSH Plugins on GitHub (2023)
Becoming a Data Wizard - The Benefits of Learning Databricks
Policies in MLOps
MLOps Scorecard - How Advanced Is Your Organization in Implementing MLOps Processes?
Common Types of Data Science Projects
Don't Just Create Backups, Verify Them - How Restic Can Help?
How to Detect ChatGPT-Generated Text?
Maximizing Efficiency in MLOps - How Blue/Green Deployment Can Help?

2022

Grammar of Graphics Explained Like to 5 Years Old Child.
MLOps Certifications - A Comprehensive Guide
Roles in MLOps
50 Questions for MLOps Engineer Job Interview
MLOps Roles of the Future
Is MLOps a Good Career?
Visual Text Exploration as Part of Preprocessing Before Classification
10 Lesser-Known, Yet Powerful Python Plotting Libraries
Automated Signal Segmentation, Trend Detection, and Classification
The Best Self-Hosted, Open Source RSS Feed Readers in 2022
How to Convert Pandas DataFrame to Markdown Table?
Discovering Hidden Gems - Popular and Lesser-Known Dataset Sharing Platforms
Lesser Known Backtesting Libraries
Top 10 Python Libraries for Document Classification
Tutorial on How to Create New Theme for Pelican Static Site Generator
Pro Tips for Diagnosing Regression Model Errors
15 Tools for Document Deskewing and Dewarping
How to Get Most of GitHub Copilot

2021

Understanding Micro and Macro Averages in Multiclass Multilabel Problems
Setup VS Code as NIM IDE
Top Popular ZSH Plugins on GitHub (2021)
Unleashing the Power of T-Sne for Dimensionality Reduction in Python
Kurtosis in Simple Terms, Interpretation and Gotchas
Finding Errors in Data - Data Validation
Pandas Schema Validation

2020

Evaluation of Interpretability for Explainable AI
Metrics Used to Compare Histograms

2019

Interactive plots for blogging
Data Science Command-Line Tools
Finding the Spy - Post on Markov Chains and Stochastic Matrices
Top Popular ZSH Plugins on GitHub (2019)
Learn Bayesian Methods in 4 Steps - By Reading and by Doing
Kaggle Evaluation Metrics Used for Regression Problems
How to Install TensorFlow and Keras on Windows 10
Darwin Approach to Traveling Salesman
How to Organize Data Science Project Based on Jupyter Notebook

2018

What's Cooking
Blockchain Implementation
Top Popular ZSH Plugins on GitHub