AI Engineering Archives - ITFROMZERO

Getting Started with LanceDB: A Lightweight Embedded Vector Database for AI and Multimodal Search

By IT From Zero October 12, 2026

Struggling with high RAM usage and the operational overhead of complex vector database clusters? Discover LanceDB: an embedded, in-process, zero-server vector database that enables resource-efficient AI applications and multimodal search.

Python

LiteLLM Python Guide: Standardize 100+ AI Models Through a Single Interface

By IT From Zero October 12, 2026

Compare LLM integration strategies and learn how to use LiteLLM in Python to connect OpenAI, Claude, and Gemini via a unified interface, complete with fallback handling and real-time cost tracking.

Artificial Intelligence tutorial - IT technology blog

Setting Up and Managing Milvus with Attu: Deploying a Vector Database for Large-Scale RAG

By IT From Zero October 4, 2026

Step-by-step guide to deploying Milvus Vector Database and the Attu GUI with Docker Compose for large-scale RAG. Learn schema design, HNSW indexing, and RAM sizing.

Database

Deploying Weaviate with Docker: Building Optimized Hybrid Search for RAG Systems

By IT From Zero September 13, 2026

A detailed guide on deploying Weaviate with Docker and optimizing Hybrid Search. Includes real-world experience on RAM management and search weighting for RAG systems.

Optimizing LLM Costs: Smart Request Routing with Semantic Router

By IT From Zero August 14, 2026

Semantic Router allows you to classify user intent at the gateway, saving up to 45% in API costs and significantly reducing response latency for AI applications.