The Technician

Sign in Subscribe

Latest — Nov 16, 2024

How to Control the Creativity of LLMs Using the Temperature Parameter

When working with Large Language Models (LLMs), one of the most powerful yet often misunderstood parameters is "temperature". This setting acts as a creativity dial, allowing you to fine-tune the model's output between deterministic precision and creative exploration. Let's dive into what temperature means

More issues

How Computers Generate Random Numbers

Imagine this: you're playing your favorite video game, and an enemy drops a rare item. Or maybe you're shuffling your Spotify playlist, wondering how it picks the next song. Behind these everyday moments lies a fascinating paradox: how do computers, which are fundamentally deterministic machines, create

LeetCode - First Missing Positive

Description: https://leetcode.com/problems/first-missing-positive/description/ This problem requires finding the smallest missing positive integer in an unsorted array. The key challenge is achieving %O(N)% time and %O(1)% space complexity without using extra space for hash tables. Key insights: * Since we're looking for the first

LeetCode - Trapping Rain Water

Description: https://leetcode.com/problems/trapping-rain-water/description/ To solve this problem, the main observation is that at each index i, the amount of water that can be trapped depends on the the highest bars to its left and right elements, minus its own height. Key insights: * Water level at index_

Building a Database From Scratch: Understanding LSM Trees and Storage Engines (Part 1)

Learn core database concepts by implementing a Python key-value store with crash recovery and efficient writes. In this tutorial, we'll build a simple but functional database from scratch with Python. Through this hands-on project, we'll explore core database concepts like Write-Ahead Logging (WAL), Sorted String Tables

The Easiest Way to Add Code Interpreter into Your LLM Apps

Hey mate, I recently tried to add something like the ChatGPT Code Interpreter plugin to my LLM application. I found many libraries and open-source options available, but they seemed a bit complicated to set up, and some required credits for cloud computing. So, I decided to develop my own library

Concurrency Programming in Python: Thread vs. Process

Concurrency is a vital aspect of modern programming, allowing applications to perform multiple tasks simultaneously, thus improving efficiency and responsiveness. In Python, developers often face the choice between using threads or processes to achieve concurrency. This blog explores the differences between these two concurrency models, how they interact with Python&

Stability Patterns in Distributed Systems

In the complex world of distributed systems and microservices, ensuring system stability and reliability is paramount. Stability patterns provide a set of strategies to maintain the robustness of a system under varying conditions. This post will explore essential stability patterns, their principles, and practical examples of implementing them in distributed

Designing APIs for Microservices

In the world of microservices, APIs are the backbone that enables communication and data exchange between different services. Designing robust, scalable, and maintainable APIs is crucial for the success of any microservices architecture. In this post, we'll explore the best practices for designing microservices APIs, covering key aspects

ETL, ELT and Reverse ETL

In the world of data engineering, three acronyms frequently surface: ETL, ELT, and Reverse ETL. Each represents a different approach to data processing, catering to specific needs and scenarios. In this post, we'll break down these concepts, exploring their workflows, benefits, and use cases. What is ETL? ETL