Core AI

RAG & Vector Search

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

4,932
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 (1,467) Articles (784)Blog Posts (531)Tutorials (101)Research Papers (49)News (2)
ArXiv cs.AI 🔍 RAG & Vector Search 📄 Paper ⚡ AI Lesson 1w ago
One Retrieval to Cover Them All: Co-occurrence-Aware Knowledge Base Reorganization for Session-Level RAG
arXiv:2606.31156v1 Announce Type: cross Abstract: RAG systems retrieve documents optimized for answering one query at a time. Yet enterprise users arrive with s
Understanding the Limits of Linear RAG — and Why Agentic Workflows Are Catching On
Medium · AI 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Understanding the Limits of Linear RAG — and Why Agentic Workflows Are Catching On
Subtitle: Understanding the fatal flaws of linear Retrieve-and-Generate pipelines — and why the industry is moving to Agentic workflows. Continue reading on Med
Understanding the Limits of Linear RAG — and Why Agentic Workflows Are Catching On
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Understanding the Limits of Linear RAG — and Why Agentic Workflows Are Catching On
Subtitle: Understanding the fatal flaws of linear Retrieve-and-Generate pipelines — and why the industry is moving to Agentic workflows. Continue reading on Med
Understanding the Limits of Linear RAG — and Why Agentic Workflows Are Catching On
Medium · Data Science 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Understanding the Limits of Linear RAG — and Why Agentic Workflows Are Catching On
Subtitle: Understanding the fatal flaws of linear Retrieve-and-Generate pipelines — and why the industry is moving to Agentic workflows. Continue reading on Med
Why you shouldn’t search your documents directly with AI
Medium · Programming 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Why you shouldn’t search your documents directly with AI
Everyone’s first retrieval-augmented system looks the same: chop the documents into pieces, turn each piece into a vector, search the… Continue reading on Mediu
From Traditional RAG to Agentic RAG
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
From Traditional RAG to Agentic RAG
Traditional RAG systems typically rely on a predefined retrieval pipeline. Continue reading on Medium »
Your AI Keeps Making Things Up. RAG Is How You Make It Use Real Facts Instead.
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1w 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
Why Your RAG System Needs Hybrid Search (And How to Actually Implement It)
Dev.to · AlaiKrm 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Why Your RAG System Needs Hybrid Search (And How to Actually Implement It)
Vector similarity search is powerful but it has a well-known weakness: exact term matching. If a user...
ArXiv cs.AI 🔍 RAG & Vector Search 📄 Paper ⚡ AI Lesson 1w ago
Covering the Unseen: Information Demand Coverage Optimization for Retrieval-Augmented Generation
arXiv:2606.29328v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) typically treats context selection as ranking chunks against a single que
Evaluation Metrics for RAG: Measure Retrieval, Generation, and End-to-End Quality With Numbers That…
Medium · AI 🔍 RAG & Vector Search ⚡ AI Lesson 1w 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 »
Evaluation Metrics for RAG: Measure Retrieval, Generation, and End-to-End Quality With Numbers That…
Medium · Data Science 🔍 RAG & Vector Search ⚡ AI Lesson 1w 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 »
I WAS TIRED OF FIVE TABS AT 2AM. SO I BUILT A RAG PIPELINE.
Medium · LLM 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
I WAS TIRED OF FIVE TABS AT 2AM. SO I BUILT A RAG PIPELINE.
It’s 2am. A crash spike just hit production. You’ve got Crashlytics open in one tab, GitHub Issues in another, the release notes doc in a… Continue reading on M
When Does HyDE Help RAG? I Tested 3 Query Types and It Failed on Two
Medium · AI 🔍 RAG & Vector Search ⚡ AI Lesson 1w 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
When Does HyDE Help RAG? I Tested 3 Query Types and It Failed on Two
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 1w 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
When Does HyDE Help RAG? I Tested 3 Query Types and It Failed on Two
Medium · Data Science 🔍 RAG & Vector Search ⚡ AI Lesson 1w 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
3 non-obvious engineering challenges I learned while building my latest RAG application:
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
3 non-obvious engineering challenges I learned while building my latest RAG application:
Chunking isn’t “one size fits all.” Continue reading on Medium »
Self-RAG (Self-Reflective RAG)
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Self-RAG (Self-Reflective RAG)
Problems with Traditional RAG Continue reading on Medium »
“RAG Is Dead!”
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
“RAG Is Dead!”
If you’ve opened LinkedIn or YouTube recently, you’ve probably seen headlines like : Continue reading on Medium »
“RAG Is Dead!”
Medium · LLM 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
“RAG Is Dead!”
If you’ve opened LinkedIn or YouTube recently, you’ve probably seen headlines like : Continue reading on Medium »
Building an AI-Powered RAG Assistant for Monitoring Student Performance
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Building an AI-Powered RAG Assistant for Monitoring Student Performance
Educational institutions are producing more digital learning material than ever before, yet many instructors still struggle to answer a… Continue reading on Med
The Feedback We Collected and Never Read, and How RAG Changed That
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
The Feedback We Collected and Never Read, and How RAG Changed That
I used the idea behind RAG chatbots to make a pile of survey comments actually answer questions. Continue reading on Nothingaholic »
RAG Architecture Deep Dive — The Full Pipeline Explained
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
RAG Architecture Deep Dive — The Full Pipeline Explained
Imagine you’re using an AI assistant at work and ask: Continue reading on Medium »
The Citation Passed. The Evidence Failed.
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
The Citation Passed. The Evidence Failed.
Why grounded RAG answers still need evidence eligibility before they support production decisions Continue reading on Medium »
Your RAG Pipeline Is Probably Useless. Here’s a Better Alternative
KDnuggets 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Your RAG Pipeline Is Probably Useless. Here’s a Better Alternative
Learn what to reach for when retrieval-augmented generation fails in production.
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
The Difference Between RAG, Agents, and Tool Calling — Proven With One Order Cancellation
Let’s Skip the Flowchart Continue reading on Medium »
Why learn RAG?
Medium · NLP 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Why learn RAG?
RAG Explained Simply: Embeddings, Vector Databases, Better Retrieval, Evaluation, and the Basic Components You Need to Know Continue reading on Medium »
Why learn RAG?
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Why learn RAG?
RAG Explained Simply: Embeddings, Vector Databases, Better Retrieval, Evaluation, and the Basic Components You Need to Know Continue reading on Medium »
DCD: The RAG Architecture That Finally Admits Your Knowledge Base Is a Mess
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
DCD: The RAG Architecture That Finally Admits Your Knowledge Base Is a Mess
A new RAG design paper argues that enterprise retrieval should stop searching the whole document swamp at once and start by asking a… Continue reading on Medium
RAG Is not broken but your pipeline is
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
RAG Is not broken but your pipeline is
When the cost conversation hit our Java stack, we started questioning everything about how we were feeding context to our models — and… Continue reading on Arti
Document Strategy in RAG Systems: Which Data, When, and How Should It Be Processed?
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Document Strategy in RAG Systems: Which Data, When, and How Should It Be Processed?
No matter how advanced the AI, the rule stays the same: without data literacy there is no right context, and without right context there… Continue reading on Me
Vector Store Operations: What Keeps RAG Retrieval Correct in Production
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1w 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
Vector Databases — The Missing Piece in the RAG Puzzle
Medium · Programming 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Vector Databases — The Missing Piece in the RAG Puzzle
Vector databases store meaning-numbers and find close matches — the retrieval shelf behind most RAG systems. Continue reading on Medium »
ArXiv cs.AI 🔍 RAG & Vector Search 📄 Paper ⚡ AI Lesson 1w ago
Freshness and the Limits of Heuristic Trend Detection in Temporal RAG
arXiv:2509.19376v2 Announce Type: replace-cross Abstract: We present a lightweight, model-agnostic temporal layer for RAG and use cybersecurity data to separate
The 10,000× Problem Hiding in Every Classical Search Engine
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
The 10,000× Problem Hiding in Every Classical Search Engine
Maximum likelihood ranking has a catastrophic failure mode. The fix is twenty-five years old and modern retrievers keep relearning what it… Continue reading on
I tried to break the three most popular RAG frameworks. GPT-5.1 didn’t save them.
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
I tried to break the three most popular RAG frameworks. GPT-5.1 didn’t save them.
I pointed a red-teaming tool at the default setup of LangChain, LlamaIndex, and Haystack, the three frameworks most teams reach for when… Continue reading on Me
I tried to break the three most popular RAG frameworks. GPT-5.1 didn’t save them.
Medium · LLM 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
I tried to break the three most popular RAG frameworks. GPT-5.1 didn’t save them.
I pointed a red-teaming tool at the default setup of LangChain, LlamaIndex, and Haystack, the three frameworks most teams reach for when… Continue reading on Me
Build Your First RAG Pipeline in Python — The Simplest Way
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Build Your First RAG Pipeline in Python — The Simplest Way
Everyone talks about RAG like it needs a vector database cluster and a retrieval team. The core loop is four steps: embed your data, store… Continue reading on
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Vector Search Alone Is Not Enough: Building Hybrid Search for RAG
Upgrading a baseline FAISS retriever with BM25 keyword search and Reciprocal Rank Fusion Continue reading on Medium »
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Loop Engineering: Why I Stopped Prompting My RAG Pipelines and Started Designing Loops
A few months ago I was building **SketchFlow AI** a tool that takes a photo of a whiteboard sketch and turns it into working Mermaid or… Continue reading on Med
RAG Architectures: Vector Databases, Conversational RAG, Agentic RAG, Graph RAG
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
RAG Architectures: Vector Databases, Conversational RAG, Agentic RAG, Graph RAG
A practical guide to choosing the right RAG architecture for real-world AI applications Continue reading on Medium »
From RAG to Agentic Search: How Retrieval Learned to Think
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
From RAG to Agentic Search: How Retrieval Learned to Think
“It’s not just retrieving; it’s refining its queries using reasoning, turning RAG into a sophisticated tool, and managing information over… Continue reading on
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Advanced RAG Techniques Aren’t Better. They’re Better Sometimes.
I added five retrieval techniques to a RAG pipeline and measured each one. The most useful result was the technique that backfired. Continue reading on Medium »
RAG Is Dead. Context Engineering Is the Future.
Dev.to · Yash Sonawane 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
RAG Is Dead. Context Engineering Is the Future.
For the last year, everyone has been talking about one architecture. RAG. Retrieval-Augmented...
How to know if swapping your RAG model broke anything
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
How to know if swapping your RAG model broke anything
A quantitative framework that tells you whether a model migration is safe — before your customers find out it isn’t. Continue reading on Medium »
Building a RAG System from Scratch — MCP: Exposing pgvector as a Reusable Tool Server
Dev.to · Hiroki Kameyama 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Building a RAG System from Scratch — MCP: Exposing pgvector as a Reusable Tool Server
In the previous article, we built AI Agents that autonomously search our pgvector database. One...
Building a RAG System from Scratch with pgvector and Gemini — Implementation
Dev.to · Hiroki Kameyama 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Building a RAG System from Scratch with pgvector and Gemini — Implementation
In the previous article, we covered the three core concepts behind RAG. Now let's build it. By the...
VisionRAG: Read PDFs Without OCR
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
VisionRAG: Read PDFs Without OCR
Some PDFs are easy for RAG systems. Continue reading on Medium »
Inside RAG : Journey of Words to Vectors
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Inside RAG : Journey of Words to Vectors
Welcome back to Inside RAG. We’ve come a long way. We’ve loaded documents, sliced them into chunks, stored them in a FAISS index, and… Continue reading on Mediu