Blog English
Thoughts, news and tutorials about data and artificial intelligence.
- #python#tools#code-qualityDecember 04, 20256 min read
Ruff - The Fastest Python Linter and Formatter: Guide and Configuration
Discover Ruff, the all-in-one tool that replaces Flake8, Black, and isort. Learn how to use it, configure it, and why it is the new standard in Python.
Pedro MedinillaRead article → - #llms#redis#optimizationOctober 30, 20258 min read
How to Save Costs and Improve Latency in LLMs: Semantic Cache with LangChain and Redis
Discover how to save costs using LLM with semantic cache implementing it with LangChain and Redis, comparison, pros and cons and common errors
Pedro MedinillaRead article → - #python#tools#optimizationOctober 21, 20258 min read
UV - Python Package Manager: how to use it, comparisons, and common issues
Learn how to use UV, the Python package manager poised to replace Pip; its advantages, comparisons with other systems, and common issues
Pedro MedinillaRead article → - #docker#llms#langchainMay 07, 20254 min read
How to use Docker Model Runner: Running LLM locally with Docker and LangChain
Learn how to run LLM models locally using Docker Model Runner and LangChain. A beginner-friendly guide to getting started with local LLMs in under 10 minutes, without complex setups or expensive hardware.
Pedro MedinillaRead article → - #llms#ai#deepseekFebruary 03, 202520 min read
How DeepSeek R1 Works: Explaining All Its Key Components and Their Consequences
Learn how the DeepSeek R1 model works and its components such as Chain of Thought, Reinforcement Learning, Reward Modeling, and Distillation
Pedro MedinillaRead article → - #nlp#ai#statisticsJanuary 14, 20254 min read
TF-IDF and Bag of Words: How Statistics Pioneered Natural Language Processing (NLP)
Discover how classic statistical techniques like Bag of Words and TF-IDF laid the foundation for text analysis and natural language understanding in computing.
Pedro MedinillaRead article → - #nlp#ai#embeddingsDecember 05, 20245 min read
From N-grams to Word2Vec: The Early Steps in Language Representation
Explore how traditional approaches like n-grams evolved into more advanced models like Word2Vec to represent human language efficiently.
Pedro MedinillaRead article → - #llms#optimization#cost-savingOctober 17, 20244 min read
Cache Usage in LLMs: LangChain Cache and OpenAI Prompt Caching
Learn what caching for LLMs is and how to implement it with LangChain and OpenAI
Pedro MedinillaRead article → - #llms#ai#promptingOctober 10, 20244 min read
Comparison of Zero-Shot, One-Shot, and Few-Shot in LLMs
Comparison of the zero-shot, one-shot, and few-shot strategies in LLMs.
Pedro MedinillaRead article → - #data#analytics#twitchJune 23, 20213 min read
Marbella Vice Data Report
Analytical summary of the Marbella Vice GTA RP server. General and creator data.
Pedro MedinillaRead article → - #github#tools#code-qualityNovember 10, 20202 min read
How to Create a GitHub Profile README
Tutorial on how to create a profile README on GitHub.
Pedro MedinillaRead article → - #tools#python#code-qualityNovember 10, 20202 min read
Awesome: Resource Lists for Programming
Use the awesome-list of resources to discover and learn new technologies
Pedro MedinillaRead article →
Questions or want to discuss this topic?
I regularly share technical breakdowns, AI architectures, and answer questions. Reach out and let’s chat!
