LLM Archives - ITFROMZERO - Share tobe shared!

Setting Up Ollama and Open WebUI on Fedora: NVIDIA GPU Optimization Without SELinux Headaches

By IT From Zero October 27, 2026

A guide to self-hosting LLMs on Fedora using a hybrid architecture: run native Ollama for direct NVIDIA GPU access alongside containerized Open WebUI via Podman to bypass SELinux issues.

MetaGPT with Python Guide: Automate Software Development with Multi-Agent Systems

By IT From Zero October 24, 2026

A comprehensive guide to using MetaGPT with Python to automate software development via multi-agent systems. Optimize API costs, implement SOPs, and build MVPs faster.

Artificial Intelligence tutorial - IT technology blog

Installing and Using Portkey AI Gateway: Rate Limiting, Load Balancing, and Multi-LLM Observability

By IT From Zero October 23, 2026

How to self-host Portkey AI Gateway with Docker for load balancing, automated failovers across OpenAI, Claude, and Gemini, and slashing token costs.

A Guide to Controlling LLM Output with Outlines: Enforcing 100% Valid JSON Schema and Regex

By IT From Zero October 11, 2026

A complete guide to using the Outlines library to enforce 100% valid JSON Schema and Regex outputs from LLMs, eliminating JSONDecodeError in backend pipelines.

LightRAG with Python Tutorial: Building Fast, Cost-Optimized Graph RAG

By IT From Zero October 9, 2026

A step-by-step guide to building a Graph RAG system with LightRAG in Python. A dual-level knowledge graph approach that slashes token costs by 90% while solving complex multi-hop synthesis queries.

Getting Started with ScrapeGraphAI: Automating Web Scraping with LLMs and Python

By IT From Zero October 9, 2026

A comprehensive guide on configuring ScrapeGraphAI with OpenAI and Ollama, optimizing token usage, and building self-healing web scraping pipelines for production.

Build Your Own Private AI Search Engine with Perplexica and Docker

By IT From Zero September 10, 2026

A guide to building your own personal AI search engine using Perplexica and Docker. A perfect Perplexity AI alternative supporting Ollama, Groq, and absolute privacy.

Mastering AgentOps: A Professional AI Agent Monitoring and Debugging Solution

By IT From Zero September 5, 2026

Learn how to use AgentOps to monitor, track behavior, and debug AI Agents in Python. Detailed guide from installation to optimizing token costs on the Dashboard.

Groq Cloud + Python: ‘Hack’ LLM Speed to 500 Tokens/Second

By IT From Zero August 20, 2026

Learn to integrate Groq Cloud API with Python to boost AI app speeds to 500 tokens/s. Tips on cost optimization, streaming, and effective rate limit handling.

Build Your Own ‘Google Search’ for AI: Combining SearXNG and LangChain to Break Knowledge Limits

By IT From Zero August 12, 2026

Build your own private, free AI Search Engine with SearXNG and LangChain. Enable LLMs to access real-time data and overcome knowledge limits without expensive API fees.