Core AI

RAG & Vector Search

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

4,143
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 3,464 Reads 679
All Reads (679) Articles (192)Blog Posts (418)Tutorials (67)Research Papers (2)
Level: All Beginner Intermediate Advanced
Newest Popular Oldest
Your AI Keeps Making Things Up. RAG Is How You Make It Use Real Facts Instead.
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 7h ago
Your AI Keeps Making Things Up. RAG Is How You Make It Use Real Facts Instead.
You ask an AI a question about your own company’s policy, and it answers — confidently, fluently, and completely wrong. It invented a… Continue reading on Mediu
View lesson → + Playlist
Evaluation Metrics for RAG: Measure Retrieval, Generation, and End-to-End Quality With Numbers That…
Medium · Data Science 🔍 RAG & Vector Search ⚡ AI Lesson 18h ago
Evaluation Metrics for RAG: Measure Retrieval, Generation, and End-to-End Quality With Numbers That…
Last week we compressed retrieved chunks so the model receives only the sentences that matter. Continue reading on Operations Research Bit »
View lesson → + Playlist
When Does HyDE Help RAG? I Tested 3 Query Types and It Failed on Two
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 21h ago
When Does HyDE Help RAG? I Tested 3 Query Types and It Failed on Two
I tested HyDE Retrieval vs Standard vector search on semantic, proprietary, and keyword queries. HyDE won one and quietly made 2 worse. Continue reading on Towa
View lesson → + Playlist
When Does HyDE Help RAG? I Tested 3 Query Types and It Failed on Two
Medium · Data Science 🔍 RAG & Vector Search ⚡ AI Lesson 21h ago
When Does HyDE Help RAG? I Tested 3 Query Types and It Failed on Two
I tested HyDE Retrieval vs Standard vector search on semantic, proprietary, and keyword queries. HyDE won one and quietly made 2 worse. Continue reading on Towa
View lesson → + Playlist
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1d ago
The Difference Between RAG, Agents, and Tool Calling — Proven With One Order Cancellation
Let’s Skip the Flowchart Continue reading on Medium »
View lesson → + Playlist
Vector Store Operations: What Keeps RAG Retrieval Correct in Production
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1d ago
Vector Store Operations: What Keeps RAG Retrieval Correct in Production
Index lifecycle management, embedding refresh, tenant isolation, hybrid retrieval, and metadata controls for production RAG systems. Continue reading on Medium
View lesson → + Playlist
Medium · Python 🔍 RAG & Vector Search ⚡ AI Lesson 5d ago
The New Era of Retrieval: Evaluating Vectorless RAG and Pipeline Resilience
As AI architectures move beyond embedding-based search, the battleground shifts from optimization to data integrity. Here is how to defend… Continue reading on
View lesson → + Playlist
The 5 RAG Architectures and Exactly When to Use Each One in Production
Medium · Python 🔍 RAG & Vector Search ⚡ AI Lesson 5d ago
The 5 RAG Architectures and Exactly When to Use Each One in Production
A deep, practical breakdown of every retrieval pattern worth knowing, with LangGraph and LlamaIndex. Continue reading on Towards AI »
View lesson → + Playlist
Your RAG Pipeline Is Bleeding Memory — TurboVec Might Be the Fix
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Your RAG Pipeline Is Bleeding Memory — TurboVec Might Be the Fix
How a Rust-based open-source project built on Google Research’s TurboQuant is making vector search faster, smaller, and fully local Continue reading on Medium »
View lesson → + Playlist
RAG
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
RAG
Retrieval-Augmented Generation (RAG) confused me at first. Once I learned the concept, I realized the core idea is simple, even if the… Continue reading on Medi
View lesson → + Playlist
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Everyone Keeps Declaring RAG Dead and It Keeps Showing Up to Its Own Funeral
There’s a genre of AI hot take that resurfaces every few months like clockwork: “RAG is dead.” I’ve seen this headline written, in some… Continue reading on Med
View lesson → + Playlist
RAG (Retrieval-Augmented Generation) Nedir? “Açık Kitap Sınavına Giren Yapay Zeka”
Medium · Data Science 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
RAG (Retrieval-Augmented Generation) Nedir? “Açık Kitap Sınavına Giren Yapay Zeka”
Üniversitede beni hem şaşırtan hem çok rahatlatan bir sistemle karşılaşmıştım. Continue reading on Medium »
View lesson → + Playlist
Is ChromaDB Silently Killing Your RAG Accuracy?
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Is ChromaDB Silently Killing Your RAG Accuracy?
You’ve probably seen a dozen “vector database comparison” articles by now. Most of them compare managed cloud services on someone else’s… Continue reading on Me
View lesson → + Playlist
Is ChromaDB Silently Killing Your RAG Accuracy?
Medium · Python 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Is ChromaDB Silently Killing Your RAG Accuracy?
You’ve probably seen a dozen “vector database comparison” articles by now. Most of them compare managed cloud services on someone else’s… Continue reading on Me
View lesson → + Playlist
Scaling RAG Applications in Production: Lessons Beyond the Demo
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Scaling RAG Applications in Production: Lessons Beyond the Demo
Retrieval-Augmented Generation (RAG) has become one of the most popular patterns for building AI applications. A typical RAG pipeline… Continue reading on Mediu
View lesson → + Playlist
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
The RAG Interview Questions Nobody Prepares For (Until It’s Too Late)
Everyone can define retrieval-augmented generation. Far fewer can survive the second question. Here’s the map I built after watching too… Continue reading on Me
View lesson → + Playlist
From Scratch to Agentic: A Hands-On Journey Through Applied RAG Systems
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
From Scratch to Agentic: A Hands-On Journey Through Applied RAG Systems
In the rapidly evolving world of Generative AI, the “Hello World” phase is officially over. Developers are no longer satisfied with basic… Continue reading on M
View lesson → + Playlist
RAG Without the Hype: What Retrieval-Augmented Generation Actually Takes to Work in Production
Medium · NLP 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
RAG Without the Hype: What Retrieval-Augmented Generation Actually Takes to Work in Production
Chunking, embedding, and retrieval each have failure modes that the tutorials skip. Continue reading on Medium »
View lesson → + Playlist
Why Your RAG Pipeline Will Break
Medium · Data Science 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Why Your RAG Pipeline Will Break
I Tested RAG at 10 Million Documents. Here’s What Nobody Tells You About Scale. Continue reading on Medium »
View lesson → + Playlist
Stop Stuffing the Prompt: The Next RAG Debate Is Whether AI Should Search or Think
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Stop Stuffing the Prompt: The Next RAG Debate Is Whether AI Should Search or Think
For the last few years, the default fix for a shaky AI answer has been simple: give the model more context. Continue reading on Medium »
View lesson → + Playlist
My RAG Said We’re Compatible, So I Went on This Date
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
My RAG Said We’re Compatible, So I Went on This Date
It was drizzling steadily one afternoon, and I was dipping my feet in a puddle on my balcony while tapping furiously to a nice gentleman… Continue reading on Me
View lesson → + Playlist
Fixed-Size Chunking Is Killing Your RAG App. Here’s What Actually Works.
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Fixed-Size Chunking Is Killing Your RAG App. Here’s What Actually Works.
You asked your RAG app a question last week, got an answer that sounded confident and polished, and only later realized it was wrong in a… Continue reading on M
View lesson → + Playlist
From Python to C++23: Cutting RAG Retrieval Latency from ~800ms to ~35ms
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
From Python to C++23: Cutting RAG Retrieval Latency from ~800ms to ~35ms
A production story about porting a FastAPI-based legal RAG system to C++23 with Drogon, Qdrant, and llama.cpp, with real benchmark numbers… Continue reading on
View lesson → + Playlist
Entity Resolution in Knowledge Graphs: The Math Behind Clean AI Context
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
Entity Resolution in Knowledge Graphs: The Math Behind Clean AI Context
How similarity scores, graph relationships, and confidence thresholds help build reliable enterprise RAG systems. Continue reading on Medium »
View lesson → + Playlist
I’d never buy a managed RAG service again
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
I’d never buy a managed RAG service again
Eighteen months ago I was the person writing the vendor recommendation. We needed document search across a messy corpus: support tickets… Continue reading on Me
View lesson → + Playlist
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
I Spent a Week Designing the “Perfect” Code-RAG Engine. Then the Research Told Me to Delete It.
A story about building a code-context tool for AI agents — and discovering that the best version of it barely uses the thing I’d centered… Continue reading on M
View lesson → + Playlist
Scaling Enterprise RAG for Business Documents: The Engineering Decisions That Actually Matter
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
Scaling Enterprise RAG for Business Documents: The Engineering Decisions That Actually Matter
A practical guide to building a retrieval system that works — and one that can grow Continue reading on Medium »
View lesson → + Playlist
Scaling Enterprise RAG for Business Documents: The Engineering Decisions That Actually Matter
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
Scaling Enterprise RAG for Business Documents: The Engineering Decisions That Actually Matter
A practical guide to building a retrieval system that works — and one that can grow Continue reading on Medium »
View lesson → + Playlist
Building Production RAG Systems: The Hidden Complexity Behind “Smart” Company Chatbots
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
Building Production RAG Systems: The Hidden Complexity Behind “Smart” Company Chatbots
So you’re building a chatbot. Simple project, right? Just a little popup bubble on your company’s “About Us” page that answers employee… Continue reading on Med
View lesson → + Playlist
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
Day 9: Retrieval-Augmented Generation (RAG) Explained Simply (For DevOps & Cloud Engineers)
 This is part of my 60-Day Agentic AI Series Continue reading on Medium »
View lesson → + Playlist
Medium · DevOps 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
Day 9: Retrieval-Augmented Generation (RAG) Explained Simply (For DevOps & Cloud Engineers)
 This is part of my 60-Day Agentic AI Series Continue reading on Medium »
View lesson → + Playlist
From kubectl to GitOps
Medium · DevOps 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
From kubectl to GitOps
Provisioning and Deploying a RAG System with Terraform and ArgoCD Continue reading on Medium »
View lesson → + Playlist
Spring AI Recipe: Tool-Based RAG
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
Spring AI Recipe: Tool-Based RAG
Traditional RAG retrieves context for every question, whether it’s needed or not. Continue reading on Medium »
View lesson → + Playlist
I Built a Semantic Search Engine from Scratch — No LangChain, No Magic, Just Raw Components
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
I Built a Semantic Search Engine from Scratch — No LangChain, No Magic, Just Raw Components
How I went from “what is pgvector” to a fully deployed two-stage search engine with 11 failures along the way. Continue reading on Medium »
View lesson → + Playlist
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
You Probably Don’t Need a Vector Database - If Your Data Already Lives in BigQuery
How I built an end-to-end RAG proof-of-concept in pure SQL: no new infrastructure, no data movement, and pay-per-query cost. Continue reading on Medium »
View lesson → + Playlist
Not All Knowledge Belongs in the Same Vector Store
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
Not All Knowledge Belongs in the Same Vector Store
An AI engineering lesson from building a peer health community Continue reading on Medium »
View lesson → + Playlist
Do You Really Understand Rerankers in RAG — Or Are You Just Saying I am an expert in RAG?
Medium · Data Science 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
Do You Really Understand Rerankers in RAG — Or Are You Just Saying I am an expert in RAG?
Everyone says they understand RAG. Continue reading on Medium »
View lesson → + Playlist
Do You Really Understand Rerankers in RAG — Or Are You Just Saying I am an expert in RAG?
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
Do You Really Understand Rerankers in RAG — Or Are You Just Saying I am an expert in RAG?
Everyone says they understand RAG. Continue reading on Medium »
View lesson → + Playlist
RAG Evaluation Technical Guide
Medium · LLM 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
RAG Evaluation Technical Guide
Good RAG is not only about better answers. It is about measurable, traceable, and trustworthy answers. Continue reading on Towards AI »
View lesson → + Playlist
The RAG Memory Problem: Why TurboVec Might Be More Important Than Another Bigger LLM
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
The RAG Memory Problem: Why TurboVec Might Be More Important Than Another Bigger LLM
The Rust-powered vector index that skips the “study your data first” phase Continue reading on Medium »
View lesson → + Playlist
I Built a RAG System and Barely Thought About AI
Medium · LLM 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
I Built a RAG System and Barely Thought About AI
When you start working on AI-powered applications, the conversation around you is almost entirely about models. Continue reading on Medium »
View lesson → + Playlist
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
CodeOwner Bot: Building a Production RAG System with Gemini at Scale
An engineer’s deep dive into building an AI-powered code understanding system that answers 2M architectural questions daily, runs at 99.9%… Continue reading on
View lesson → + Playlist
Orchestrating the Machine: Mitigating Vector Drift with Airflow ETL and Dynamic RAG Pipelines
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
Orchestrating the Machine: Mitigating Vector Drift with Airflow ETL and Dynamic RAG Pipelines
A production blueprint for syncing relational state, automating semantic data updates, and monitoring embedding decay at scale. Continue reading on Medium »
View lesson → + Playlist
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
Your RAG App Keeps Missing the Right Answer. Here’s Why.
Part 3 of 10, Becoming an AI Engineer Continue reading on Medium »
View lesson → + Playlist
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
Your RAG App Keeps Missing the Right Answer. Here’s Why.
Part 3 of 10, Becoming an AI Engineer Continue reading on Medium »
View lesson → + Playlist
Financial NL-to-SQL RAG
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
Financial NL-to-SQL RAG
Ask questions about your banking database in plain English — powered by LangGraph, Ollama (Gemma4), and PGVector running entirely on local… Continue reading on
View lesson → + Playlist
Building a Production-Ready RAG Pipeline on AWS: Lessons Learned
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
Building a Production-Ready RAG Pipeline on AWS: Lessons Learned
The demo worked perfectly. Continue reading on AWS in Plain English »
View lesson → + Playlist
Building a RAG Document Q&A Assistant with IBM Granite in Google Colab
Medium · Python 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
Building a RAG Document Q&A Assistant with IBM Granite in Google Colab
Retrieval-Augmented Generation, usually shortened to RAG, is one of the most practical ways to make large language models useful on… Continue reading on Medium
View lesson → + Playlist