Technical Pillar · 14 verified guides

Applied AI

Practical workflows, local LLMs, and AI automation guides.

Lab Tested

Ollama 0.5.7 Local Inference Engine · ChromaDB Semantic Vector Store · Continue.dev VS Code Autocomplete · Open WebUI Docker Deployment · DeepSeek-R1 8B Offline Reasoning Model · Llama 3.2 3B Fast CPU & GPU Inference · Python RAG Offline Document Search · Shell Scripts ShellCheck Compliant · Ollama 0.5.7 Local Inference Engine · ChromaDB Semantic Vector Store · Continue.dev VS Code Autocomplete · Open WebUI Docker Deployment · DeepSeek-R1 8B Offline Reasoning Model · Llama 3.2 3B Fast CPU & GPU Inference · Python RAG Offline Document Search · Shell Scripts ShellCheck Compliant ·

Applied AI

vLLM vs Ollama: Production Serving Throughput and VRAM Benchmarks on Linux

A rigorous performance test evaluating request concurrency, token throughput, and memory offload between vLLM and Ollama on Linux workstations.

Zaisha

Verified 3 min

Applied AI

Fixing vLLM Tool-Call Accuracy on Linux

<p>Tool-call accuracy in vLLM often degrades due to mismatched sampling parameters and parser configurations. This guide walks through a Linux-based fix using guided decoding and prompt tuning.</p>

Zaisha

Verified 10 min

Applied AI

Anthropic S-1 Filing: Build a Local SEC EDGAR Parser

<p>The Anthropic S-1 filing is the top Hacker News story with 973 points, making it a practical dataset for building a local SEC EDGAR parser. This guide shows how to fetch, validate, and extract structured text from the filing on Linux.</p>

Zaisha

Verified 3 min

Applied AI

Building a Production RAG Agent with LangChain, pgvector, and PostgreSQL on Ubuntu

Deploy a high-performance vector search database and connect it to LangChain for accurate, context-aware document question answering.

Zaisha

Verified 3 min

Applied AI

Fine-Tuning Llama 3 with LoRA and Unsloth on Linux GPUs: Step-by-Step Guide

A practical tutorial on fine-tuning open-source LLMs on custom instruction datasets with 2x speed and minimum VRAM overhead on Linux.

Zaisha

Verified 3 min

Applied AI

Complete Setup of Open WebUI with Docker Compose and NVIDIA Container Toolkit

A complete, production-ready guide to running the ChatGPT-like Open WebUI interface on your self-hosted Linux server with hardware acceleration.

Zaisha

Verified 3 min

Applied AI

Running Faster-Whisper Locally on Linux for Fast Audio Transcription with CUDA

Achieve 4x faster speech-to-text transcription locally on Linux using CTranslate2 and Whisper models without cloud fees.

Zaisha

Verified 3 min

Applied AI

How to Quantize Hugging Face Models to GGUF Using llama.cpp on Ubuntu

Convert raw Hugging Face transformer checkpoints into memory-efficient GGUF files ready for zero-latency execution in Ollama and LM Studio.

Zaisha

Verified 3 min

Applied AI

Practical Prompt Templates for Generating Safe Linux Bash Scripts

Learn how to constrain LLM code generation to produce safe Bash scripts with strict error traps, input validation, and dry-run flags.

Zaisha

Verified 3 min

Applied AI

Building a Fast Local Document Search CLI with Python and ChromaDB

A practical guide to building an offline semantic document search CLI using ChromaDB vector database and sentence-transformers on Ubuntu.

Zaisha

Verified 3 min

Applied AI

How to Set Up Continue.dev with Ollama in VS Code on Linux

Configure Continue.dev inside VS Code on Linux to get instant autocomplete and inline code refactoring powered by local open-weight models.

Zaisha

Verified 3 min

Applied AI

Automating Daily Server Log Summaries with Python and Local LLMs

A practical automation guide using Python and Ollama to parse Linux system logs, extract security anomalies, and send concise daily summaries.

Zaisha

Verified 3 min