Core AI

RAG & Vector Search

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

5,062
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
All Reads (1,593) Articles (881)Blog Posts (549)Tutorials (111)Research Papers (50)News (2)
The DevTools AI Deserves: Debugging RAG & Memory Systems at Scale
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
The DevTools AI Deserves: Debugging RAG & Memory Systems at Scale
Chrome DevTools for AI Memory. See what your RAG pipeline remembered, what it forgot, and exactly why it hallucinated. Continue reading on Medium »
ArXiv cs.AI 🔍 RAG & Vector Search 📄 Paper ⚡ AI Lesson 1mo ago
Cordon-MAS: Defending RAG against Knowledge Poisoning via Information-Flow Control
arXiv:2605.26754v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) increasingly underpins high-stakes applications, yet remains vulnerable t
RAG - Sparse Embedding
Dev.to · Ramya Perumal 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
RAG - Sparse Embedding
Sparse means thinly spread, scattered, or not dense. In sparse embeddings, chunks are converted into...
Why Your RAG Demo Doesn’t Survive Production
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Why Your RAG Demo Doesn’t Survive Production
The data-readiness gap that nobody talks about — and the methodology that fixed our 40% accuracy drop Continue reading on Medium »
Why Your RAG Demo Doesn’t Survive Production
Medium · LLM 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Why Your RAG Demo Doesn’t Survive Production
The data-readiness gap that nobody talks about — and the methodology that fixed our 40% accuracy drop Continue reading on Medium »
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Stop Using a Single Retrieval Method: Build a Smarter RAG Pipeline
A deep dive into seven retrieval strategies: dense, BM25, hybrid, HyDE, RRF, MMR and re-ranking. Continue reading on Medium »
98. RAG: Give Your AI Access to Your Documents
Dev.to · Akhilesh 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
98. RAG: Give Your AI Access to Your Documents
You ask ChatGPT about your company's internal policies. It makes something up. It sounds confident....
Production RAG with Gemini: Five Things the Tutorials Skip
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Production RAG with Gemini: Five Things the Tutorials Skip
Chunking, reranking, cost control, hallucination defenses, and the evaluation loop — five lessons from running a customer-facing RAG… Continue reading on Medium
Why Naive RAG Fails in Production — Building an Agentic LangGraph Assistant for SAP
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Why Naive RAG Fails in Production — Building an Agentic LangGraph Assistant for SAP
A deep-dive into building a 7-node agentic RAG assistant for SAP S/4HANA procurement, with every design decision explained. Continue reading on Medium »
Medium · AI 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Building RAG Systems That Don’t Lie: What I Learned the Hard Way at Work
My data engineering background made me confident going into RAG. That confidence lasted about two weeks. Continue reading on Medium »
Medium · LLM 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Building RAG Systems That Don’t Lie: What I Learned the Hard Way at Work
My data engineering background made me confident going into RAG. That confidence lasted about two weeks. Continue reading on Medium »
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
DocuMind: Building a Production-Grade RAG System That Actually Works
Most RAG systems work perfectly in tutorials. Very few survive first contact with production. Continue reading on Medium »
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Top 5 Mistakes Developers Make While Building RAG Apps
The rise of Retrieval-Augmented Generation has completely changed how modern AI applications are built. Continue reading on Medium »
From PDFs to AI‑Ready Data: Docling vs OpenDataLoader Explained
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
From PDFs to AI‑Ready Data: Docling vs OpenDataLoader Explained
Estimated Reading Time: 25 minutes Continue reading on Medium »
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Building a Production-Grade Multi-Agent RAG Architecture: A Complete Blueprint
8 Axes, 7 Layers, 33 Components: A Production-Grade Multi-Agent RAG Architecture Continue reading on Medium »
Stop Settling for AI “hallucinations”
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Stop Settling for AI “hallucinations”
If your firm is exploring GenAI, the term you need to know is RAG (Retrieval-Augmented Generation). I’ve been testing various systems for… Continue reading on A
ArXiv cs.AI 🔍 RAG & Vector Search 📄 Paper ⚡ AI Lesson 1mo ago
Leveraging Spreading Activation for Improved Document Retrieval in Knowledge-Graph-Based RAG Systems
arXiv:2512.15922v3 Announce Type: replace Abstract: Despite initial successes and a variety of architectures, retrieval-augmented generation systems still strug
Backpressure, Cancellation, and Channels in WorkIt
Hackernoon 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Backpressure, Cancellation, and Channels in WorkIt
A naive RAG pipeline pulls 281 docs to deliver 25. Real backpressure pulls 40. How WorkIt paces the producer to consumer demand in Node.js & TypeScript.
One Article, One Maggi, The Entire RAG Pipeline — Everything In One Go
Medium · LLM 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
One Article, One Maggi, The Entire RAG Pipeline — Everything In One Go
Maggi takes 2 minutes, RAG takes one article. Water boiled — hallucination understood. Masala dropped — documents loaded. Noodles in —… Continue reading on Medi
My RAG system slowly got worse for three months and nobody noticed.
Dev.to · Mukunda Rao Katta 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
My RAG system slowly got worse for three months and nobody noticed.
A composable drift detector for RAG and agent systems. Five orthogonal dimensions, one DriftReport, bring your own embedder and time-series store.
Medium · Data Science 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Weaviate is a powerful open-source vector database with a rich feature set that goes well beyond…
ChromaDB: The Developer’s Local-First ChoiceVector Databases Compared: Pinecone vs. Weaviate vs. ChromaDB for RAG Continue reading on Medium »
Meet the Writer: Hacker Noon's Contributor Vineet Vijay, Lead AI Engineer
Hackernoon 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Meet the Writer: Hacker Noon's Contributor Vineet Vijay, Lead AI Engineer
Vineet Vijay found 40 K-mismatched vectors silently breaking his RAG system. Here's what he learned, and what he's writing about next.
turbovec: Local RAG Without the 60 GB Tax
Dev.to · Lars 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
turbovec: Local RAG Without the 60 GB Tax
A 1536-dimensional float32 embedding is 6 KB. A corpus of 10 million documents is roughly 60 GB of...
I Built RAG Systems for Enterprises — Here’s the Learning Path I Wish I Had
Medium · Data Science 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
I Built RAG Systems for Enterprises — Here’s the Learning Path I Wish I Had
A complete guide to moving from toy demos to production-ready RAG systems Continue reading on CodeX »
Your AI Didn’t Hallucinate. It Just Looked in the Wrong Place First.
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Your AI Didn’t Hallucinate. It Just Looked in the Wrong Place First.
The unglamorous machinery that decides whether your RAG app is brilliant or useless and why almost everyone blames the wrong component. Continue reading on Medi
Don’t let a billion RAG docs drown your 25-result pipeline
Medium · JavaScript 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Don’t let a billion RAG docs drown your 25-result pipeline
Last time we showed how to terminate non-cooperative CPU work at the worker boundary. This article stays cooperative but adds the missing… Continue reading on M
Retrieval Strategies in RAG: Beyond Basic Similarity Search
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Retrieval Strategies in RAG: Beyond Basic Similarity Search
Your RAG system finds documents. But is it finding the RIGHT documents? Here’s how to make retrieval actually work. Continue reading on Medium »
Don't let a billion RAG docs drown your 25-result pipeline
Dev.to · AdmilsonCossa 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Don't let a billion RAG docs drown your 25-result pipeline
Backpressure For Streaming Pipelines Last time we showed how to terminate non-cooperative...
RAPTOR: A Tree of Summaries So Queries Find Their Right Level
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
RAPTOR: A Tree of Summaries So Queries Find Their Right Level
Two queries, two different needs Continue reading on Medium »
ArXiv cs.AI 🔍 RAG & Vector Search 📄 Paper ⚡ AI Lesson 1mo ago
Through the Stealth Lens: Attention-Aware Defenses Against Poisoning in RAG
arXiv:2506.04390v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) systems are vulnerable to attacks that inject poisoned passages i
Building a RAG Platform on AWS- Offline Ingestion + GenAI Deployment
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Building a RAG Platform on AWS- Offline Ingestion + GenAI Deployment
In this article, I’ll walk through a production-oriented AWS architecture for building an end-to-end RAG ingestion and retrieval platform… Continue reading on M
Document Parsing for Production RAG: Architecture, Tradeoffs, and When to Use What
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Document Parsing for Production RAG: Architecture, Tradeoffs, and When to Use What
Text extraction is a solved problem. But enterprise documents aren’t just text — they are visual hierarchies. They contain nested lists… Continue reading on Med
Production RAG Is Not a Vector Search Problem
Medium · NLP 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Production RAG Is Not a Vector Search Problem
Why vector search alone quietly fails — and how hybrid retrieval, re-ranking, and real evaluation fixed it. Continue reading on Medium »
A Tiny RAG Security Test: What Happens When the Knowledge Base Is Poisoned
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
A Tiny RAG Security Test: What Happens When the Knowledge Base Is Poisoned
It was not just mine; everyone’s feed was filled with screenshots where people noticed something interesting in Google search- search for… Continue reading on M
A Tiny RAG Security Test: What Happens When the Knowledge Base Is Poisoned
Medium · Cybersecurity 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
A Tiny RAG Security Test: What Happens When the Knowledge Base Is Poisoned
It was not just mine; everyone’s feed was filled with screenshots where people noticed something interesting in Google search- search for… Continue reading on M
The Two Speeds of AI in ODC: Why RAG and Agent Development Are Not the Same Build
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
The Two Speeds of AI in ODC: Why RAG and Agent Development Are Not the Same Build
I have been building applications with the OutSystems platform for almost 10 years now. Continue reading on Medium »
SQLite FTS5 won't tokenize Chinese — here's the 7-line bigram fix that did
Dev.to · foxck016077 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
SQLite FTS5 won't tokenize Chinese — here's the 7-line bigram fix that did
I shipped a personal RAG bot spike in 25 minutes. SQLite FTS5 with unicode61 returned 0 hits for every Chinese query. Bigram preprocessing made it work without
How to Evaluate Your RAG Pipeline
Dev.to · Dave Graham 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
How to Evaluate Your RAG Pipeline
RAG has two places to fail: retrieval and generation. Most teams only catch one. Here's the complete...
Building a RAG Document Q&A System with Hybrid Retrieval (No Embeddings API Needed)
Dev.to · Haji Rufai 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Building a RAG Document Q&A System with Hybrid Retrieval (No Embeddings API Needed)
Building a production-quality RAG (Retrieval-Augmented Generation) system taught me one thing: the...
From Zero to RAG: How I Built My First AI Pipeline with FAISS, Groq & FastAPI
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
From Zero to RAG: How I Built My First AI Pipeline with FAISS, Groq & FastAPI
A hands-on builder’s account of designing a Retrieval-Augmented Generation system from scratch — the architecture, the decisions, and the… Continue reading on M
Designing RAG for Financial Documents: When a Single Wrong Number Can Cost Millions
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Designing RAG for Financial Documents: When a Single Wrong Number Can Cost Millions
In most AI demos, hallucinations are amusing. Continue reading on Medium »
Why RAG Pipelines Silently Hallucinate — And The Decay Score That Catches It Before The LLM Does
Dev.to · VLSiddarth 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Why RAG Pipelines Silently Hallucinate — And The Decay Score That Catches It Before The LLM Does
Your RAG pipeline has a blind spot. It is not your embeddings. It is not your retrieval algorithm. It...
Why hybrid search is the boring default we keep recommending
Dev.to · SapotaCorp 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Why hybrid search is the boring default we keep recommending
A team came to us frustrated that their semantic search was missing exact product codes like 'GPT-4o' even though those tokens appeared in the indexed content.
What Is Reciprocal Rank Fusion and Why I Used It in My RAG System
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
What Is Reciprocal Rank Fusion and Why I Used It in My RAG System
When you build a system that retrieves information before generating an answer, your first real problem is not the generation — it is the… Continue reading on M
Four production pitfalls that turn RAG demos into broken chatbots
Dev.to · SapotaCorp 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Four production pitfalls that turn RAG demos into broken chatbots
A perfect 50-question demo on Tuesday. By the second week of production, users were filing tickets faster than the team could close them. The model had not chan
I tried hybrid retrieval on my RAG. It made things worse.
Medium · Python 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
I tried hybrid retrieval on my RAG. It made things worse.
I built a semantic retrieval system over Australian federal tax law. ~1,400 legal documents, 38,000 chunks, embedded with… Continue reading on Medium »
Building a Production RAG Ingestion Pipeline on AWS: Unstructured.io, S3 Vectors, and a Private VPC
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Building a Production RAG Ingestion Pipeline on AWS: Unstructured.io, S3 Vectors, and a Private VPC
When Bedrock Knowledge Bases hit its production limits, I built a private, self-hosted alternative that actually scales. Continue reading on Towards AWS »
Building a Production Hybrid RAG: Why I Threw Out the LangChain Recipe
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Building a Production Hybrid RAG: Why I Threw Out the LangChain Recipe
19 components, 274 tests, an evaluation framework with actual math, and a hallucination rate that dropped from 12% to 3%. Here’s the… Continue reading on Medium