RAG Archives - ITNotes

Build a Personal AI Knowledge Base with Obsidian, Ollama and ChromaDB: Offline Semantic Search for Your Notes

July 20, 2026

Keyword search fails when you need it most — 2 AM, 600 notes, and the answer is in there somewhere with a title you don't remember. This guide builds a fully offline personal AI knowledge base using Obsidian, Ollama, and ChromaDB so you can search your notes by meaning, not by exact wording, with no cloud dependency.

Stop Settling for Mediocre RAG: A Practical Guide to Reranking with BGE and Cohere

July 18, 2026

Reranking is the secret to high-accuracy RAG. Learn how to implement a two-stage retrieval pipeline using BGE-Reranker and Cohere's API to eliminate irrelevant AI context.

Advanced RAG: Solving the ‘Broken Table’ Problem with Multi-vector Retrieval

June 7, 2026

Standard RAG fails when tables are split across chunks. This guide shows how to use Multi-vector Retrieval to link searchable summaries to full-context tables and images, boosting accuracy for complex documents.

Stop Feeding Your RAG Garbage: Better Extraction with LlamaParse and LlamaIndex

June 6, 2026

Learn how to build a high-accuracy RAG pipeline using LlamaParse and LlamaIndex. Avoid common PDF parsing traps and extract clean, structured data from complex tables and layouts.

Stop Being a Human Search Engine: Build a RAG-Powered Tech Support Bot

May 31, 2026

Slash your support tickets by 60%. This guide shows you how to build a RAG-powered Telegram bot that answers technical questions using your team's actual documentation.

Build a Private RAG: Secure Document Q&A with LlamaIndex and Ollama

May 26, 2026

Build a secure, high-performance RAG system on your own hardware. This guide shows you how to use LlamaIndex and Ollama to query private documents without cloud risks.

Clean Data, Better RAG: Mastering Microsoft MarkItDown for Python Pipelines

May 9, 2026

Boost your RAG system's accuracy by standardizing data ingestion. Learn how to use Microsoft MarkItDown and Python to convert complex PDFs, Excel, and Word files into clean, LLM-friendly Markdown.

Deploying Dify with Docker: A Professional Guide to Low-code AI Agents and RAG

May 8, 2026

Ditch the complex LangChain boilerplate. Learn how to deploy Dify with Docker and build document-aware AI agents that actually work in production.

Beyond the ‘Vibe Check’: Quantifying RAG Performance with RAGAS

May 2, 2026

Stop relying on 'vibes' to test your AI. Learn how to use RAGAS to quantify Faithfulness, Relevancy, and Recall with automated LLM-based scoring.

Fixing RAG Retrieval Failures: A Practical Guide to BM25 and Hybrid Search

May 1, 2026

Vector search often misses exact technical terms and specific IDs. This guide explains how to combine BM25 and Vector Search using Hybrid Search and RRF to increase RAG accuracy by up to 20%.