RAG – ITFROMZERO – Share tobe shared!

Artificial Intelligence tutorial - IT technology blog

Haystack 2.0: Building Document Processing Pipelines with Document Indexing, Hybrid Retrieval, and Smart Q&A

By admin June 29, 2026

Haystack 2.0 lets you build AI document processing pipelines as directed graphs: each component connected explicitly, making them easy to debug and extend. This guide walks through document indexing, hybrid retrieval combining BM25 and embeddings, and a production-ready Q&A pipeline in Python.

A Guide to Automated LLM Unit Testing with DeepEval

By admin June 25, 2026

DeepEval lets you write unit tests for LLM applications just like regular pytest, with metrics for AnswerRelevancy, Faithfulness, and hallucination detection. A guide from a 5-minute install to CI/CD integration for automatically controlling AI quality before every deployment.

Database

Setting Up Milvus Vector Database with Docker: Building a Knowledge Store for RAG and AI

By admin June 18, 2026

A guide to installing Milvus Vector Database with Docker Compose, creating collections, storing vector embeddings, and building a complete RAG pipeline. Includes tips on choosing index types, chunking strategies, and production optimization from real-world experience.

Database

Getting Started with ChromaDB: The Open-Source Vector Database for Building AI Agent Knowledge Systems

By admin June 13, 2026

ChromaDB is an open-source vector database for semantic storage and search — lightweight enough to run locally, powerful enough to serve as the foundation for RAG systems and AI Agents. This guide walks through installation, document indexing, semantic search queries, and Docker deployment with practical, step-by-step examples.

Installing AnythingLLM on Ubuntu: Build Your Own Ultra-Secure Local AI Knowledge Base

By admin May 11, 2026

Build a secure internal RAG system with AnythingLLM on Ubuntu. Learn how to install via Docker, connect Ollama, and optimize your local AI knowledge base for absolute data privacy.

Docling: Breaking the PDF ‘Curse’ for RAG Systems – From Messy Data to Clean Markdown

By admin May 10, 2026

Complex PDF processing is often the biggest bottleneck in RAG. Discover how IBM's Docling uses AI to understand layouts and convert PDFs into accurate Markdown, helping LLMs understand data deeply and provide smarter answers.

Crawl4AI: Transform Websites into Clean Markdown for RAG with Just a Few Lines of Python Code

By admin May 7, 2026

Eliminate messy web data worries when building RAG systems. A detailed guide on using Crawl4AI to convert websites into standardized Markdown, boosting your AI system's efficiency by 70%.

Database

pgvector Guide: Storing and Searching Vector Embeddings in PostgreSQL for AI and RAG Applications

By admin April 22, 2026

pgvector is a PostgreSQL extension that lets you store and search vector embeddings directly in your existing database — no need to deploy a separate system. This guide covers installation, HNSW index creation, semantic search, and integrating pgvector into a Python RAG pipeline, with practical monitoring tips from real-world experience.

Evaluating RAG with RAGAS: From ‘Gut Feeling’ to Faithfulness, Answer Relevance, and Context Precision Metrics

By admin April 20, 2026

Stop evaluating AI chatbots based on gut feeling. Use RAGAS to accurately measure Faithfulness, Answer Relevance, and Context Precision.

Cleaning PDF/Office Data for RAG with Unstructured.io: Turning ‘Trash’ into Gold

By admin April 6, 2026

Discover how Unstructured.io solves data extraction from PDF and Office files for RAG. Boost accuracy by 35% with smart table processing and text cleaning.