Core AI

RAG & Vector Search

Retrieval-augmented generation, vector databases, embeddings and semantic search

5,269
lessons
Skills in this topic
View full skill map →
RAG Basics
beginner
Chunk documents with LangChain or LlamaIndex
Vector Stores
intermediate
Set up Pinecone, Weaviate, or pgvector
RAG Evaluation
intermediate
Run RAGAS evaluation on a RAG pipeline
Advanced RAG
advanced
Build a hybrid BM25 + dense retrieval pipeline
Videos 5,117 Reads 152

Showing 152 reads from curated sources

Level: All Beginner Intermediate Advanced
Newest Popular Oldest
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 29m ago
Ever Wondered How to Make Your RAG More Effective?
Stop Searching. Start Connecting. Continue reading on Medium »
View lesson → + Playlist
Why StarRocks Is Better Than Elasticsearch for RAG and AI-Powered Vector Search Analytics
Medium · LLM 🔍 RAG & Vector Search ⚡ AI Lesson 22h ago
Why StarRocks Is Better Than Elasticsearch for RAG and AI-Powered Vector Search Analytics
The rise of large language models has made Retrieval-Augmented Generation (RAG) one of the most consequential data architecture patterns… Continue reading on Me
View lesson → + Playlist
Production RAG: Shipping a RAG System Into an Enterprise Product
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1d ago
Production RAG: Shipping a RAG System Into an Enterprise Product
Retrieval, grounding, evaluation, and the operational realities that show up only after the demo is over. Continue reading on Medium »
View lesson → + Playlist
HyDE: Search With the Answer You Wish You Had
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1d ago
HyDE: Search With the Answer You Wish You Had
Why a question is a bad search query Continue reading on Medium »
View lesson → + Playlist
Hierarchical Indices: Find the Section First, Then Find the Sentence
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1d ago
Hierarchical Indices: Find the Section First, Then Find the Sentence
How a human actually searches a long document Continue reading on Medium »
View lesson → + Playlist
Hybrid Search Explained: Why Smart RAG Uses Both Keywords AND Meaning
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 1d ago
Hybrid Search Explained: Why Smart RAG Uses Both Keywords AND Meaning
A beginner-friendly guide to how modern RAG combines keyword search and semantic search for better retrieval accuracy. Continue reading on Medium »
View lesson → + Playlist
RAG Series (15): CRAG — Self-Correcting When Retrieval Falls Short
Dev.to · WonderLab 🔍 RAG & Vector Search ⚡ AI Lesson 1d ago
RAG Series (15): CRAG — Self-Correcting When Retrieval Falls Short
The Knowledge Base Boundary Problem Previous articles optimized retrieval quality — better...
View lesson → + Playlist
Secure RAG on Google Cloud: From Private Data to Safe Answers
Medium · AI 🔍 RAG & Vector Search ⚡ AI Lesson 1d ago
Secure RAG on Google Cloud: From Private Data to Safe Answers
Most RAG demos look safe because they are small. Continue reading on Google Cloud - Community »
View lesson → + Playlist
Secure RAG on Google Cloud: From Private Data to Safe Answers
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1d ago
Secure RAG on Google Cloud: From Private Data to Safe Answers
Most RAG demos look safe because they are small. Continue reading on Google Cloud - Community »
View lesson → + Playlist
RAG Has a Relationship Problem
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1d ago
RAG Has a Relationship Problem
Vector stores are the default starting point for most RAG pipelines. Fast, easy to set up, good enough for factual lookups over a single… Continue reading on Me
View lesson → + Playlist
Production Reranker Layer for RAG in Python: Cross-Encoder, Cohere Fallback, and Reciprocal Rank Fusion (Runnable Code)
Dev.to · Nitin Srivastava 🔍 RAG & Vector Search ⚡ AI Lesson 2d ago
Production Reranker Layer for RAG in Python: Cross-Encoder, Cohere Fallback, and Reciprocal Rank Fusion (Runnable Code)
I shipped my fifth RAG pipeline to production in February. Top-10 recall@10 was 0.94. The team ran a...
View lesson → + Playlist
RAG Series (14): Self-RAG — Let the Model Decide Whether to Retrieve
Dev.to · WonderLab 🔍 RAG & Vector Search ⚡ AI Lesson 2d ago
RAG Series (14): Self-RAG — Let the Model Decide Whether to Retrieve
The Hidden Assumption in Traditional RAG Traditional RAG pipelines never question one...
View lesson → + Playlist
RAG Ki Wiring : Maine Chunk Size 2000 Rakha Tha — Aur Meri RAG Mar Gayi
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 2d ago
RAG Ki Wiring : Maine Chunk Size 2000 Rakha Tha — Aur Meri RAG Mar Gayi
Socha tha bada chunk matlab zyada context, zyada context matlab behtar jawab. Realiity ne thappad maara. Text Splitters ki woh baatein jo… Continue reading on M
View lesson → + Playlist
Building a Production RAG Backend for Enterprise Knowledge Bases: Architecture, Decisions, and…
Medium · AI 🔍 RAG & Vector Search ⚡ AI Lesson 3d ago
Building a Production RAG Backend for Enterprise Knowledge Bases: Architecture, Decisions, and…
How I designed and built a retrieval-augmented generation system that ingests from Document360 and SharePoint, stores embeddings in Aurora… Continue reading on
View lesson → + Playlist
Building a Production RAG Backend for Enterprise Knowledge Bases: Architecture, Decisions, and…
Medium · Data Science 🔍 RAG & Vector Search ⚡ AI Lesson 3d ago
Building a Production RAG Backend for Enterprise Knowledge Bases: Architecture, Decisions, and…
How I designed and built a retrieval-augmented generation system that ingests from Document360 and SharePoint, stores embeddings in Aurora… Continue reading on
View lesson → + Playlist
Chunking Strategy: The Most Underrated Part of RAG
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 4d ago
Chunking Strategy: The Most Underrated Part of RAG
If embeddings are the brain of a retrieval system, chunking is the spine. Continue reading on Medium »
View lesson → + Playlist
Beyond Keywords: Mastering HyDE for Smarter Retrieval 🧠
Dev.to · Rushank Savant 🔍 RAG & Vector Search ⚡ AI Lesson 4d ago
Beyond Keywords: Mastering HyDE for Smarter Retrieval 🧠
If you’ve ever built a RAG system, you’ve likely felt the frustration of the "Mismatch Problem". You...
View lesson → + Playlist
Vectorless RAG vs every flavour of vector RAG: a head-to-head on real 10-Ks.
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 4d ago
Vectorless RAG vs every flavour of vector RAG: a head-to-head on real 10-Ks.
# I asked ten RAG pipelines the same 54 finance questions. Here’s where each one broke. Continue reading on Medium »
View lesson → + Playlist
Vectorless RAG vs every flavour of vector RAG: a head-to-head on real 10-Ks.
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 4d ago
Vectorless RAG vs every flavour of vector RAG: a head-to-head on real 10-Ks.
# I asked ten RAG pipelines the same 54 finance questions. Here’s where each one broke. Continue reading on Medium »
View lesson → + Playlist
When Your AI Has Photographic Memory But No Understanding: Designing Curiosity-Driven Knowledge…
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 4d ago
When Your AI Has Photographic Memory But No Understanding: Designing Curiosity-Driven Knowledge…
How I designed a system that transforms a passive RAG store into a self-aware, autonomously learning knowledge engine, without fine-tuning… Continue reading on
View lesson → + Playlist
Chunking Explained: The Tiny Detail That Makes or Breaks RAG
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 4d ago
Chunking Explained: The Tiny Detail That Makes or Breaks RAG
A beginner-friendly guide to how chunking impacts retrieval quality, context accuracy, and overall RAG performance. Continue reading on Medium »
View lesson → + Playlist
RAG Evaluation with a Local LLM: Comparing Vector Index and Knowledge Graph
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 4d ago
RAG Evaluation with a Local LLM: Comparing Vector Index and Knowledge Graph
A demo to understand RAG evaluation metrics and see Vector Index vs Knowledge Graph retrieval in practice Continue reading on Medium »
View lesson → + Playlist
RAG_First AI Engine: Why RAG Alone Is Not Enough (And How to Build AI That Never Hallucinates)
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 4d ago
RAG_First AI Engine: Why RAG Alone Is Not Enough (And How to Build AI That Never Hallucinates)
The Promise and the Problem Continue reading on Medium »
View lesson → + Playlist
Dev.to AI 🔍 RAG & Vector Search ⚡ AI Lesson 4d ago
Your RAG can't answer 'why' -- GraphRAG finds what vector search misses
The question that broke my RAG pipeline I had a solid RAG setup. Embeddings, vector store, top-k retrieval, the whole thing. It handled factual lookups just fin
View lesson → + Playlist
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 5d ago
Hybrid RAG Isn’t What You Think
Why most teams misunderstand hybrid retrieval, and why “keyword + vector” is only the beginning. Continue reading on Medium »
View lesson → + Playlist
Medium · LLM 🔍 RAG & Vector Search ⚡ AI Lesson 5d ago
Minimal RAG’ı Production’a Taşımak — Proje 2: PostgreSQL, Redis Semantic Cache ve Yapılandırılmış…
Bir sistem çalışıyor olması, güvenilir olduğu anlamına gelmiyor. Continue reading on Medium »
View lesson → + Playlist
Most RAG Systems Don’t Fail Because Retrieval Is Bad — They Fail Because We Destroyed the Context…
Medium · LLM 🔍 RAG & Vector Search ⚡ AI Lesson 5d ago
Most RAG Systems Don’t Fail Because Retrieval Is Bad — They Fail Because We Destroyed the Context…
Why chunking strategy matters more than most teams realize. Continue reading on Medium »
View lesson → + Playlist
Dev.to AI 🔍 RAG & Vector Search ⚡ AI Lesson 6d ago
Building a RAG Agent for Pharmacy Stock Optimization with Gemini, ChromaDB and LangGraph
Introduction FarmaStock AI is an academic Generative AI project focused on a real-world problem: how to make pharmacy stock analysis easier to understand and ex
View lesson → + Playlist
Generative AI: Why the Next Revolution Will Not Be Only About LLMs, but About Agentic RAG Systems
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 6d ago
Generative AI: Why the Next Revolution Will Not Be Only About LLMs, but About Agentic RAG Systems
Since the rise of large language models, generative AI has deeply changed the way we search, summarize, analyze, and produce information… Continue reading on Me
View lesson → + Playlist
10 RAG Architecture Mistakes Fintechs Make in Production
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 6d ago
10 RAG Architecture Mistakes Fintechs Make in Production
This article was originally published on JustSoftLab Insights. Continue reading on Medium »
View lesson → + Playlist
10 RAG Architecture Mistakes Fintechs Make in Production
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 6d ago
10 RAG Architecture Mistakes Fintechs Make in Production
This article was originally published on JustSoftLab Insights. Continue reading on Medium »
View lesson → + Playlist
Vector Index Cold Start: Why Your First Query Takes 8 Seconds
Dev.to · Gabriel Anhaia 🔍 RAG & Vector Search ⚡ AI Lesson 6d ago
Vector Index Cold Start: Why Your First Query Takes 8 Seconds
First-query latency on vector DBs. Why HNSW loads lazy + four warm-up patterns that stop the 8-second cold-start tax.
View lesson → + Playlist
How I solved the riddles of RAG
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
How I solved the riddles of RAG
These past months I have been exploring the domain of RAG and agentic AI. There are a lot of topics being discussed right now and a lot of… Continue reading on
View lesson → + Playlist
I Increased Retrieval From Top-5 to Top-20. My Answers Got Worse
Dev.to · Md Ayan Arshad 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
I Increased Retrieval From Top-5 to Top-20. My Answers Got Worse
The standard advice for improving RAG retrieval quality is: retrieve more candidates, then filter...
View lesson → + Playlist
Graph RAG Isn't a One-Shot Anymore — The Case for Agentic Graph RAG MCPs
Dev.to · Ryosuke Tsuji 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Graph RAG Isn't a One-Shot Anymore — The Case for Agentic Graph RAG MCPs
Hi, I'm Ryan, CTO at airCloset. Over my last few posts, I've introduced internal MCP servers we've...
View lesson → + Playlist
Why I Chose Markdown as the Foundation of my RAG Pipeline
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Why I Chose Markdown as the Foundation of my RAG Pipeline
Markdown is the missing layer in most RAG Pipelines. Continue reading on Artificial Intelligence in Plain English »
View lesson → + Playlist
Built a RAG System From Scratch and Finally Understood Why Everyone Is Talking About It
Medium · Python 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Built a RAG System From Scratch and Finally Understood Why Everyone Is Talking About It
A beginner-friendly walkthrough of Retrieval-Augmented Generation, with real code you can run. Continue reading on Medium »
View lesson → + Playlist
What is RAG and How Does It Work with Modern AI Systems?
Medium · AI 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
What is RAG and How Does It Work with Modern AI Systems?
A practical guide to Retrieval-Augmented Generation — the architecture pattern powering enterprise AI, coding agents, and the next… Continue reading on Jonathan
View lesson → + Playlist
Limits of RAG and implications for self-hosted AI
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Limits of RAG and implications for self-hosted AI
Why scalability isn’t infinite, and Retrieval-Augmented Generation not a panacea Continue reading on Medium »
View lesson → + Playlist
Best Vector Databases for RAG (Free & Paid)
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Best Vector Databases for RAG (Free & Paid)
Let your large language models interact with private, up-to-date, and domain-specific information without expensive model retraining. Continue reading on Medium
View lesson → + Playlist
Retrieval-Augmented Generation: The Architecture That Made AI Actually Useful in Production
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Retrieval-Augmented Generation: The Architecture That Made AI Actually Useful in Production
Every serious AI application I’ve seen ship in the last two years has RAG at its core. Here’s the complete blueprint. Continue reading on Medium »
View lesson → + Playlist
Most RAG Systems Waste 60% of Their Retrieval Calls. Skill-RAG Fixes That.
Medium · AI 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Most RAG Systems Waste 60% of Their Retrieval Calls. Skill-RAG Fixes That.
I audited a RAG pipeline at work last month. 43% of the retrieval calls were for questions the model already knew the answer to. Another… Continue reading on Ar
View lesson → + Playlist
Stop Trusting Your RAG Retriever Blindly — Here’s How to Actually Make It Smart
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Stop Trusting Your RAG Retriever Blindly — Here’s How to Actually Make It Smart
The quiet failure mode nobody talks about Continue reading on Medium »
View lesson → + Playlist
Preparing RAG pipeline for production
Dev.to · Dmytro Levchenko 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
Preparing RAG pipeline for production
Intro Having a working RAG that provides correct semantic answers is a great start, yet,...
View lesson → + Playlist
My RAG System Seemed to Work. That Was the Problem.
Medium · LLM 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
My RAG System Seemed to Work. That Was the Problem.
Building evals for bspQA taught me that “looks right” is not a methodology. Continue reading on Data Science Collective »
View lesson → + Playlist
Document-to-Markdown for RAG: Preparing Documents for Your AI Knowledge Base
Dev.to · Iteration Layer 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
Document-to-Markdown for RAG: Preparing Documents for Your AI Knowledge Base
Your RAG Pipeline Is Only as Good as Its Ingestion Every team building retrieval-augmented...
View lesson → + Playlist
RAG from Public Documentation Websites: Robots.txt, Terms, Retention, and Attribution
Dev.to · Iteration Layer 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
RAG from Public Documentation Websites: Robots.txt, Terms, Retention, and Attribution
Public Docs Are the Easiest RAG Source to Get Wrong Every AI support project eventually...
View lesson → + Playlist
Dev.to AI 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
pdfmux vs LlamaParse vs Docling vs Unstructured: Which PDF extractor for RAG in 2026?
TL;DR : For RAG pipelines in 2026, pick pdfmux if you need free, local, benchmark-proven extraction with per-page confidence scoring (0.905 on opendataloader-be
View lesson → + Playlist