Core AI

RAG & Vector Search

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

4,144
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 (680) Articles (192)Blog Posts (418)Tutorials (68)Research Papers (2)
Why you shouldn’t search your documents directly with AI
Medium · Programming 🔍 RAG & Vector Search ⚡ AI Lesson 2h 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
Your AI Keeps Making Things Up. RAG Is How You Make It Use Real Facts Instead.
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 10h 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
Evaluation Metrics for RAG: Measure Retrieval, Generation, and End-to-End Quality With Numbers That…
Medium · AI 🔍 RAG & Vector Search ⚡ AI Lesson 20h 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 20h 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 »
When Does HyDE Help RAG? I Tested 3 Query Types and It Failed on Two
Medium · AI 🔍 RAG & Vector Search ⚡ AI Lesson 1d 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 1d 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 1d 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
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 »
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
RAG Is Dead. Context Engineering Is the Future.
Dev.to · Yash Sonawane 🔍 RAG & Vector Search ⚡ AI Lesson 2d ago
RAG Is Dead. Context Engineering Is the Future.
For the last year, everyone has been talking about one architecture. RAG. Retrieval-Augmented...
Building a RAG System from Scratch — MCP: Exposing pgvector as a Reusable Tool Server
Dev.to · Hiroki Kameyama 🔍 RAG & Vector Search ⚡ AI Lesson 3d 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 3d 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...
I Got Tired of Debugging Haystack RAG Pipelines Blind, So I Built a Diagnostics Engine
Dev.to · Aditya Raut 🔍 RAG & Vector Search ⚡ AI Lesson 3d ago
I Got Tired of Debugging Haystack RAG Pipelines Blind, So I Built a Diagnostics Engine
RAG pipelines fail in quiet ways. Retrieval drops. Documents go missing. Metadata gets corrupted...
Build a Simple RAG App with Telnyx AI Inference
Dev.to · Sonam 🔍 RAG & Vector Search ⚡ AI Lesson 4d ago
Build a Simple RAG App with Telnyx AI Inference
RAG is one of those patterns that sounds more complicated than it has to be. At its core,...
10 GenAI Techniques for Integrating a RAG Pipeline with Enterprise Data Warehouses
Medium · AI 🔍 RAG & Vector Search ⚡ AI Lesson 4d ago
10 GenAI Techniques for Integrating a RAG Pipeline with Enterprise Data Warehouses
Practical GenAI patterns for connecting RAG systems with enterprise-scale data platforms Continue reading on Medium »
I Let My AI Agent Build a Bedrock RAG Knowledge Base, Here Are the 2 Mistakes the AWS Agent Toolkit Caught
Dev.to · Saurabh "Rob" Dahal 🔍 RAG & Vector Search ⚡ AI Lesson 5d ago
I Let My AI Agent Build a Bedrock RAG Knowledge Base, Here Are the 2 Mistakes the AWS Agent Toolkit Caught
Provisioning a Bedrock RAG knowledge base with S3 Vectors, without the hallucinated API calls. If...
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
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 »
Towards Data Science 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Retrieval Is Filtering, Not Search: A Mental Model for Enterprise RAG
Enterprise Document Intelligence [Vol.1 #7A] - Stop searching strings. Filter line_df and toc_df. Pick anchors small, expand context large The post Retrieval Is
I added a reranker to my RAG pipeline — it broke everything, then I fixed it
Dev.to · Santanu Mohanta 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
I added a reranker to my RAG pipeline — it broke everything, then I fixed it
In v2 I added hybrid retrieval (FAISS + BM25) to fix keyword blindspots. All 19 test questions...
I built research - Document 04 ? RAG and Knowledge Retrieval in 2 months. Zero cloud. Zero compromise.
Dev.to · Lois-Kleinner 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
I built research - Document 04 ? RAG and Knowledge Retrieval in 2 months. Zero cloud. Zero compromise.
**research - Document 04 ? RAG and Knowledge Retrieval** --- ## The Problem This document presents the design and evaluation of the Retrieval-Augmented Generati
Towards Data Science 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
When RAG Users Ask Vague Questions: Clarify Once, Learn the Default
Enterprise Document Intelligence [Vol.1 #6bis] - Ask one focused clarification, learn the default from the answer, stay silent next time The post When RAG Users
Phase 1: Document Ingestion - The Hidden Complexity Before Embeddings
Dev.to · surajrkhonde 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Phase 1: Document Ingestion - The Hidden Complexity Before Embeddings
The Complete Story: Why Most RAG Systems Fail Before They Start The Story...
Towards Data Science 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Reconstructing the Table of Contents a PDF Forgot to Ship, So RAG Can Scope by Section
Enterprise Document Intelligence [Vol.1 #5septies] - When a PDF prints a contents page but exposes no outline, two ways to turn it back into structure, plus the
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 »
Knowledge Graphs: The Missing Piece in Most RAG Systems
Dev.to · Vishwajeet Kondi 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Knowledge Graphs: The Missing Piece in Most RAG Systems
If you've been exploring AI agents recently, chances are you've come across RAG (Retrieval-Augmented...
I built a code Q&A bot with RAG – what worked and what failed
Dev.to · zhongqiyue 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
I built a code Q&A bot with RAG – what worked and what failed
A few months ago, our team had a problem: every new developer spent days digging through scattered...
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
Dev.to AI 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
I Spent $500 on RAG Infrastructure Before Realizing These 7 Mistakes Were Killing My Results
I Spent $500 on RAG Infrastructure Before Realizing These 7 Mistakes Were Killing My Results I built a RAG pipeline for private document search. It cost me $500
Choosing a Vector Database in 2026: pgvector vs Pinecone vs Qdrant vs Weaviate
Dev.to · DatanestDigital 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Choosing a Vector Database in 2026: pgvector vs Pinecone vs Qdrant vs Weaviate
A practical comparison of the main vector database options for RAG and semantic search — pgvector, Pinecone, Qdrant, and Weaviate — with the trade-offs that act
RAG Pipeline: The Uncle-Nephew Complete Learning Guide
Dev.to · surajrkhonde 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
RAG Pipeline: The Uncle-Nephew Complete Learning Guide
How to Build Systems That Actually Know Your Data (Not Hallucinate About It) ...
How Japan’s Research Labs Are Building RAG Systems That Actually Work — And What Western Teams Keep Getting Wrong
Dev.to · xu xu 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
How Japan’s Research Labs Are Building RAG Systems That Actually Work — And What Western Teams Keep Getting Wrong
Your vector database is returning relevant chunks. Your embedding model scores 0.89 on retrieval...
Dev.to AI 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Amazon Bedrock AgentCore Web Search: Why RAG Agents Fail and How to Ship Live-Grounded Agents
Originally published at twarx.com - read the full interactive version there. Last Updated: June 20, 2026 Every RAG pipeline your team shipped in 2023 is silentl
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
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 »
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
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
Your RAG Retrieved the Right Documents but Still Gave the Wrong Answer
Dev.to · mofuteq 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Your RAG Retrieved the Right Documents but Still Gave the Wrong Answer
Your retriever returned the right documents. The similarity scores look fine. The answer is still...
Building a RAG Pipeline from Scratch: WorldWar-II Edition
Medium · AI 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Building a RAG Pipeline from Scratch: WorldWar-II Edition
Or: How I taught an LLM to read Wikipedia and answer questions without hallucinating Continue reading on Medium »
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
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
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
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 »
Demystifying RAG in Telecom: A Deep Dive into Graph, Vector, and Hybrid Pipelines for O-RAN
Medium · AI 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Demystifying RAG in Telecom: A Deep Dive into Graph, Vector, and Hybrid Pipelines for O-RAN
There is no one-size-fits-all “best” RAG pipeline for O-RAN; the ideal architecture depends entirely on your specific operational… Continue reading on Medium »
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 »
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 »
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
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