AI
Building a Local RAG System with Perl and SQLite
A developer built a local RAG system for text file indexing, transitioning from a Python-based prototype to a Perl-based solution using SQLite and Ollama.
October 4, 2026, 04:44 AM·Хабр
#ollama
AI
Running Local AI Models on Windows with Ollama
A guide to running the DeepSeek language model locally on Windows using Ollama, enabling AI assistance without cloud data transmission.
Хабр
AI
Deploying a Personal LLM Server at Home
A guide to deploying a personal LLM server on home hardware using Ollama and tunneling services for remote access.
Хабр
AI
The Shift in Ollama's Development Strategy
The project Ollama, once the go-to tool for local LLM execution, is facing scrutiny over its shift toward cloud-based models and its reliance on venture capital.
Хабр
Money
DeepSeek vs. Ollama: Optimizing AI Costs Through Scheduling
Choosing between DeepSeek and Ollama for model access requires analyzing peak-hour schedules and concurrency needs rather than just comparing token prices.
Хабр
AI
Local LLM Integration with Codex: Why It Failed to Save Tokens
An experiment connecting local Gemma models to Codex via MCP revealed that delegating routine tasks to a local LLM can double cloud token consumption instead of reducing it.
Хабр
That is everything