Core AI

RAG & Vector Search

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

5,267
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

Showing 151 reads from curated sources

Understanding Retrieval-Augmented Generation (RAG): The Future of Smarter AI
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
Understanding Retrieval-Augmented Generation (RAG): The Future of Smarter AI
Artificial Intelligence has evolved rapidly, but one major limitation still exists: models don’t always know everything and sometimes they… Continue reading on
Understanding Retrieval-Augmented Generation (RAG): The Future of Smarter AI
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
Understanding Retrieval-Augmented Generation (RAG): The Future of Smarter AI
Artificial Intelligence has evolved rapidly, but one major limitation still exists: models don’t always know everything and sometimes they… Continue reading on
Dev.to AI 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
Beyond Basic RAG: Architecting a Fault-Tolerant, Agentic AI Platform
<img src="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2F
I built a GraphRAG demo with FalkorDB’s new SDK, then benchmarked it against Neo4j
Dev.to · Dan Shalev 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
I built a GraphRAG demo with FalkorDB’s new SDK, then benchmarked it against Neo4j
FalkorDB shipped graphrag-sdk v1.0.0rc1 and I wanted to see how it feels on real content, not a toy...
How I used Gemini CLI to orchestrate a complex RAG migration
Dev.to · Remigiusz Samborski 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
How I used Gemini CLI to orchestrate a complex RAG migration
Building a complex, multi-phase cloud project like a RAG migration is as much about orchestration as...
I’m an Angular Developer, Not an AI Engineer — A Step-by-Step Guide to Building My First RAG App
Medium · LLM 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
I’m an Angular Developer, Not an AI Engineer — A Step-by-Step Guide to Building My First RAG App
When I first heard about terms like embeddings, vector databases, and retrieval pipelines, I assumed this was not for me. Continue reading on Medium »
RAG Made Simple: How AI Finds the Right Answers
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
RAG Made Simple: How AI Finds the Right Answers
As AI becomes common in enterprises, responses need to be accurate and grounded in business data. Traditional LLMs can be generic or… Continue reading on GoPenA
GraphRAG beyond the demo: Lessons from the trenches
Medium · AI 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
GraphRAG beyond the demo: Lessons from the trenches
When to use it, why it’s hard to ship, and how to make it reliable Continue reading on Data Science + AI at Microsoft »
RAG in Practice — Part 8: RAG in Production — What Breaks After Launch
Dev.to · Gursharan Singh 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
RAG in Practice — Part 8: RAG in Production — What Breaks After Launch
Why production RAG drifts, degrades, and quietly fails — and the patterns and discipline that prevent it.
Dev.to AI 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
I benchmarked RAG vs GraphRAG vs pre-structured knowledge graphs across 45 domains — here's what happened
Three retrieval architectures. Same LLM. Same 7,928 queries across 45 domains. Different structure going in. Here are the results: System F1 Score Tokens/query
DOM Parsing Was Wasting over 40% of My RAG Ingestion Budget.
Medium · AI 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
DOM Parsing Was Wasting over 40% of My RAG Ingestion Budget.
When the first wave of LLM wrappers hit the market, developers quickly realized they had a massive problem: AI models confidently lied. To… Continue reading on
From 0% to 91% Review Coverage: Building and Measuring an AI-Powered Code Review Pipeline with RAG
Medium · AI 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
From 0% to 91% Review Coverage: Building and Measuring an AI-Powered Code Review Pipeline with RAG
Why this problem, why now Continue reading on Medium »
From 0% to 91% Review Coverage: Building and Measuring an AI-Powered Code Review Pipeline with RAG
Medium · DevOps 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
From 0% to 91% Review Coverage: Building and Measuring an AI-Powered Code Review Pipeline with RAG
Why this problem, why now Continue reading on Medium »
Choosing the Right Chunking Strategy for RAG: Why One Size Does Not Fit All
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
Choosing the Right Chunking Strategy for RAG: Why One Size Does Not Fit All
One of the most important design decisions in a RAG system is how you split documents into chunks. Chunking may sound like a small… Continue reading on Medium »
The RAG Quality Wall: Why Your AI Gets 62% Right and What It Takes to Reach 94%
Medium · AI 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
The RAG Quality Wall: Why Your AI Gets 62% Right and What It Takes to Reach 94%
Most teams hit the same ceiling around week three of production. Here’s the architecture pattern that breaks through it. Continue reading on Medium »
RAG With Deterministic Outputs: Hybrid Extraction for Financial Statements
Medium · AI 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
RAG With Deterministic Outputs: Hybrid Extraction for Financial Statements
Solving the hallucination problem in numerical RAG pipelines Continue reading on Medium »
RAG With Deterministic Outputs: Hybrid Extraction for Financial Statements
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
RAG With Deterministic Outputs: Hybrid Extraction for Financial Statements
Solving the hallucination problem in numerical RAG pipelines Continue reading on Medium »
12 patterns that make RAG answers cite-worthy without overquoting
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
12 patterns that make RAG answers cite-worthy without overquoting
How to build retrieval-augmented generation systems that sound grounded, stay legally safer, and earn user trust without turning every… Continue reading on Medi
12 patterns that make RAG answers cite-worthy without overquoting
Medium · LLM 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
12 patterns that make RAG answers cite-worthy without overquoting
How to build retrieval-augmented generation systems that sound grounded, stay legally safer, and earn user trust without turning every… Continue reading on Medi
12 patterns that make RAG answers cite-worthy without overquoting
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
12 patterns that make RAG answers cite-worthy without overquoting
How to build retrieval-augmented generation systems that sound grounded, stay legally safer, and earn user trust without turning every… Continue reading on Medi
Hierarchical Indexed Navigation Tree (HINT)-Proxy RAG
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
Hierarchical Indexed Navigation Tree (HINT)-Proxy RAG
A note before we begin: This article builds on two existing ideas — PageIndex’s Vectorless RAG and Proxy-Pointer RAG by Partha Sarkar —… Continue reading on Med
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
Why RAG in Manufacturing Is an Access Control Problem — Not a Search Problem
A 3-part series summary: Design, Implementation, and Production Operations Continue reading on Medium »
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
Why RAG in Manufacturing Is an Access Control Problem — Not a Search Problem
A 3-part series summary: Design, Implementation, and Production Operations Continue reading on Medium »
Graph RAG in 2026: Why Most Companies Fail — And How to Get It Right
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
Graph RAG in 2026: Why Most Companies Fail — And How to Get It Right
Graph RAG explained for AI engineers: why most knowledge graph projects fail (Cyc, IBM Watson Health), which companies actually succeeded… Continue reading on M
How I Discovered My RAG Was Wrong 29% of the Time
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
How I Discovered My RAG Was Wrong 29% of the Time
Why I evaluate before I optimize — and the framework I built to stop guessing Continue reading on Medium »
The 10-Layer Security System Your RAG Pipeline Is Missing
Dev.to · klement Gunndu 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
The 10-Layer Security System Your RAG Pipeline Is Missing
Your RAG pipeline has a front door and a back door. Both are wide open. The front door lets users...
The Hidden Complexity of RAG — From Beginner Surface to Builder Depth
Medium · LLM 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
The Hidden Complexity of RAG — From Beginner Surface to Builder Depth
There is a version of RAG that takes two hours to build. Embed your documents. Store them in Chroma. Embed the query. Retrieve top-5… Continue reading on Medium
The Hidden Complexity of RAG — From Beginner Surface to Builder Depth
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
The Hidden Complexity of RAG — From Beginner Surface to Builder Depth
There is a version of RAG that takes two hours to build. Embed your documents. Store them in Chroma. Embed the query. Retrieve top-5… Continue reading on Medium
RAG in Practice — Part 7: Your RAG System Is Wrong. Here's How to Find Out Why.
Dev.to · Gursharan Singh 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
RAG in Practice — Part 7: Your RAG System Is Wrong. Here's How to Find Out Why.
Evaluation, metrics, LLM-as-a-judge, and the diagnostic spine. The single most important debugging habit in RAG.
Speaking the Corpus's Language: How Multilingual RAG Stays Coherent Across Turns
Dev.to · HarinezumIgel 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
Speaking the Corpus's Language: How Multilingual RAG Stays Coherent Across Turns
This article assumes you already run a multi-turn RAG pipeline and have query rewriting...
The RAG Identity Crisis: Why Your Vector DB Needs “Folders” to Scale
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 2w ago
The RAG Identity Crisis: Why Your Vector DB Needs “Folders” to Scale
Building a Retrieval-Augmented Generation (RAG) pipeline is easy. Building one that works for production-grade financial data is a… Continue reading on Medium »
10 Chunking Strategies That Make or Break Your RAG Pipeline
Dev.to · klement Gunndu 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
10 Chunking Strategies That Make or Break Your RAG Pipeline
A 2025 peer-reviewed study (Vectara, NAACL 2025) found something most RAG teams get...
Optimizing Web Scraping Data to Reduce RAG Token Costs
Dev.to · AlterLab 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
Optimizing Web Scraping Data to Reduce RAG Token Costs
Feeding raw HTML into a Retrieval-Augmented Generation (RAG) pipeline is a fast way to burn through...
RAG Shorts -Shot#1 -What is RAG — and why should you care?
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
RAG Shorts -Shot#1 -What is RAG — and why should you care?
RAG Shorts is a series that breaks down complex concepts into simple, bite-sized reads — so anyone can quickly understand them. Continue reading on YouCanAutoma
Dev.to AI 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
Memory Grows, Accuracy Drops: The Unseen Consequences of RAG Systems
Memory Grows, Accuracy Drops: The Unseen Consequences of RAG Systems The Silent Failure of RAG Systems: How Memory Growth Affects Accuracy RAG (Reinforcement Le
Enterprise Internal Knowledge Base RAG MCP: POC-to-Production
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
Enterprise Internal Knowledge Base RAG MCP: POC-to-Production
Companion to the public repo at https://github.com/kimsb2429/internal-knowledge-base Continue reading on Medium »
RAG Is Failing in Production — Here’s Why (and What I’m Testing Instead)
Dev.to · Eduardo Borges 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
RAG Is Failing in Production — Here’s Why (and What I’m Testing Instead)
RAG (Retrieval-Augmented Generation) looks great in demos. But in real-world systems, it often fails...
RAG for Customer Support: How Retrieval-Augmented Generation Improves Chatbot Accuracy.
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
RAG for Customer Support: How Retrieval-Augmented Generation Improves Chatbot Accuracy.
A practical guide to building a Retrieval-Augmented Generation (RAG) system for customer support, with real evaluation results and lessons… Continue reading on
The RAG Problem
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
The RAG Problem
Why RAG looks Easy, but is really much Harder Continue reading on Towards AI »
RAG Breaks When Citations Borrow Confidence
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
RAG Breaks When Citations Borrow Confidence
How retrieval systems sound trustworthy long before their citations actually prove anything. Continue reading on Medium »
RAG Breaks When Citations Borrow Confidence
Medium · LLM 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
RAG Breaks When Citations Borrow Confidence
How retrieval systems sound trustworthy long before their citations actually prove anything. Continue reading on Medium »
RAG Breaks When Citations Borrow Confidence
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
RAG Breaks When Citations Borrow Confidence
How retrieval systems sound trustworthy long before their citations actually prove anything. Continue reading on Medium »
FLAMEHAVEN FileSearch: Why This RAG Engine Feels Different from the Usual Stack
Dev.to · Kwansub Yun 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
FLAMEHAVEN FileSearch: Why This RAG Engine Feels Different from the Usual Stack
FLAMEHAVEN FileSearch: Why This RAG Engine Feels Different from the Usual Stack RAG is...
Dev.to AI 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
7 Production RAG Mistakes I Made (And How to Fix Them)
I've shipped RAG systems for healthcare records, financial document search, and real estate databases. The early ones had problems that cost us weeks of debuggi
Dev.to AI 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
Building Production RAG Systems with pgvector: What We Learned After 50 Deployments
We've built over 50 RAG (Retrieval-Augmented Generation) systems in production. Here's what the tutorials don't tell you. The Tutorial Version vs. Reality Every
Production RAG: the six decisions behind every system that works
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
Production RAG: the six decisions behind every system that works
RAG isn’t a system. It’s a pipeline of decisions, and every one of them has a quiet failure mode. Continue reading on Medium »
Beyond Similarity Search: Advanced Relevance Feedback Retrieval in Qdrant for RAG
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
Beyond Similarity Search: Advanced Relevance Feedback Retrieval in Qdrant for RAG
Today we start with an idea that is sixty years old — and somehow still ahead of its time. The idea is simple: when a search system… Continue reading on Medium
Why Your RAG Pipeline Lies to You
Medium · NLP 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
Why Your RAG Pipeline Lies to You
There is a particular kind of confidence that comes from watching your RAG system answer a question correctly during a demo. It retrieves… Continue reading on M