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

Why Your RAG Pipeline Lies to You
Medium · LLM 🔍 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
Beyond the Hype: Architecting Production-Grade Retrieval-Augmented Generation (RAG)
Medium · NLP 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
Beyond the Hype: Architecting Production-Grade Retrieval-Augmented Generation (RAG)
To provide a truly “long-form” article for Medium (aiming for a 7–10 minute read), we need to expand into technical strategy… Continue reading on Medium »
Retrieval-Augmented Generation (RAG): The Key to Reliable and Accurate AI Systems
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
Retrieval-Augmented Generation (RAG): The Key to Reliable and Accurate AI Systems
Imagine uploading a PDF and asking ChatGPT to summarize it. The response appears confident and structured, but when you actually check the… Continue reading on
Should your RAG use code or documentation? What benchmarks changed my mind about
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
Should your RAG use code or documentation? What benchmarks changed my mind about
A personal look at why benchmark design matters when you build RAG over a codebase. Continue reading on Medium »
RAG Pipeline with LangChain and Pinecone for Production
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
RAG Pipeline with LangChain and Pinecone for Production
Build a RAG pipeline with LangChain and Pinecone that survives real traffic with reliable retrieval, versioned indexing, and measurable… Continue reading on Med
Smarter Search Starts
with Smarter Chunks
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
Smarter Search Starts with Smarter Chunks
A practical guide to document chunking, embeddings, tokenization, and retrieval design for production RAG systems. Continue reading on Medium »
RAG systems were pushed to their limits; this is the startling breakdown that no one warned you…
Medium · Data Science 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
RAG systems were pushed to their limits; this is the startling breakdown that no one warned you…
The unspoken secret? The way you think is not how RAG scales. We discovered the hidden flaws that transform retrieval-augmented generation… Continue reading on
RAG systems were pushed to their limits; this is the startling breakdown that no one warned you…
Medium · LLM 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
RAG systems were pushed to their limits; this is the startling breakdown that no one warned you…
The unspoken secret? The way you think is not how RAG scales. We discovered the hidden flaws that transform retrieval-augmented generation… Continue reading on
RAG systems were pushed to their limits; this is the startling breakdown that no one warned you…
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
RAG systems were pushed to their limits; this is the startling breakdown that no one warned you…
The unspoken secret? The way you think is not how RAG scales. We discovered the hidden flaws that transform retrieval-augmented generation… Continue reading on
Graph RAG and Agentic RAG (Part 2): Where Retrieval Finally Gets Smart
Medium · AI 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
Graph RAG and Agentic RAG (Part 2): Where Retrieval Finally Gets Smart
Flat vector search was a great start, but anyone who has tried to answer multi-hop questions or track entity relationships across a large… Continue reading on M
Graph RAG and Agentic RAG (Part 2): Where Retrieval Finally Gets Smart
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
Graph RAG and Agentic RAG (Part 2): Where Retrieval Finally Gets Smart
Flat vector search was a great start, but anyone who has tried to answer multi-hop questions or track entity relationships across a large… Continue reading on M
Graph RAG and Agentic RAG (Part 2): Where Retrieval Finally Gets Smart
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
Graph RAG and Agentic RAG (Part 2): Where Retrieval Finally Gets Smart
Flat vector search was a great start, but anyone who has tried to answer multi-hop questions or track entity relationships across a large… Continue reading on M
From PDFs to Answers: Understanding RAG (Retrieval-Augmented Generation) Systems
Medium · LLM 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
From PDFs to Answers: Understanding RAG (Retrieval-Augmented Generation) Systems
Introduction Continue reading on Medium »
Towards Data Science 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
Your RAG System Retrieves the Right Data — But Still Produces Wrong Answers. Here’s Why (and How to Fix It).
Your RAG system is retrieving the right documents with perfect scores — yet it still confidently returns the wrong answer. I built a 220 MB local experiment tha
Membangun Hybrid RAG + SQL Agent dari Nol: Panduan Teknik Lengkap
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
Membangun Hybrid RAG + SQL Agent dari Nol: Panduan Teknik Lengkap
Cara membangun sistem AI yang bisa menjawab pertanyaan konseptual dan kueri data real-time dalam satu pipeline yang efisien menggunakan… Continue reading on Med
pgvector vs Qdrant: Why “Selectivity” is the True Decider in Hybrid Vector Search
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
pgvector vs Qdrant: Why “Selectivity” is the True Decider in Hybrid Vector Search
Introduction: The Reality of RAG and Hybrid Search Continue reading on Medium »
I Learned RAG by Building a Q&A System
Medium · Python 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
I Learned RAG by Building a Q&A System
Most RAG tutorials use manufactured data. I wanted to see what happens when I actually use real documents. Continue reading on Data Science Collective »
All About RAG
Medium · LLM 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
All About RAG
AI models know a lot, but they don’t know your stuff. RAG fixes that here’s everything you need to know. Continue reading on Medium »
All About RAG
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
All About RAG
AI models know a lot, but they don’t know your stuff. RAG fixes that here’s everything you need to know. Continue reading on Medium »
Why RAG Systems Fail in Production: The Retrieval Architecture Problem Enterprises Miss
Medium · AI 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
Why RAG Systems Fail in Production: The Retrieval Architecture Problem Enterprises Miss
Retrieval-augmented generation, or RAG, is one of the most practical ways to make AI useful inside a business. It promises something… Continue reading on Medium
RAG Architectures Compared (Part 1): Naive, Advanced, and Modular RAG
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
RAG Architectures Compared (Part 1): Naive, Advanced, and Modular RAG
Part 1 of a 2-part series. Part 2 covers Graph RAG and Agentic RAG. Continue reading on Medium »
Why Your RAG System Costs 10x More Than You Think
Medium · AI 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
Why Your RAG System Costs 10x More Than You Think
The hidden infrastructure tax of Retrieval-Augmented Generation Continue reading on Medium »
Beyond Vector Search: Improving RAG with Hierarchical Document Navigation
Medium · LLM 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
Beyond Vector Search: Improving RAG with Hierarchical Document Navigation
Many RAG systems rely on chunk-based retrieval, which can overlook document structure. This raises an important question: can we improve… Continue reading on Me
I Stopped Using Embeddings for RAG — And My System Got More Accurate
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
I Stopped Using Embeddings for RAG — And My System Got More Accurate
How a vectorless, structure-aware RAG pipeline outperformed traditional embedding-based retrieval in real-world documents Continue reading on Medium »
Why RAG is failing your AI agents (and what trust scoring fixes)
Medium · LLM 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
Why RAG is failing your AI agents (and what trust scoring fixes)
I watched my AI agent waste $5 in API credits yesterday. Continue reading on Medium »
RAG Explained Without the Jargon
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 3w ago
RAG Explained Without the Jargon
Why AI systems hallucinate, what retrieval-augmented generation actually does, and a three-diagram walkthrough that makes the architecture… Continue reading on
The Asymmetric Efficiency Manifesto: Why Vector RAG is a Dead End for Corporate Memory
Medium · AI 🔍 RAG & Vector Search ⚡ AI Lesson 4w ago
The Asymmetric Efficiency Manifesto: Why Vector RAG is a Dead End for Corporate Memory
How we shattered the SOTA memory benchmarks by ditching stochastic vectors for a deterministic graph. Continue reading on Medium »
The Asymmetric Efficiency Manifesto: Why Vector RAG is a Dead End for Corporate Memory
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 4w ago
The Asymmetric Efficiency Manifesto: Why Vector RAG is a Dead End for Corporate Memory
How we shattered the SOTA memory benchmarks by ditching stochastic vectors for a deterministic graph. Continue reading on Medium »
Local RAG: How I Turned My 10-Year PDF Archive into a Private Search Engine
Medium · Programming 🔍 RAG & Vector Search ⚡ AI Lesson 4w ago
Local RAG: How I Turned My 10-Year PDF Archive into a Private Search Engine
I am a digital hoarder. My “Documents” folder is a graveyard of 2014 tax returns, scanned menus from restaurants that closed during the… Continue reading on Med
“RAG Is Dead”: Influencer Fearmongering or Fact? The Enterprise Data Says Otherwise.
Medium · AI 🔍 RAG & Vector Search ⚡ AI Lesson 4w ago
“RAG Is Dead”: Influencer Fearmongering or Fact? The Enterprise Data Says Otherwise.
TL;DR: Karpathy shared a clever personal wiki tool for ~100 documents. The internet declared RAG dead. Enterprise data says the opposite… Continue reading on Me
“RAG Is Dead”: Influencer Fearmongering or Fact? The Enterprise Data Says Otherwise.
Medium · LLM 🔍 RAG & Vector Search ⚡ AI Lesson 4w ago
“RAG Is Dead”: Influencer Fearmongering or Fact? The Enterprise Data Says Otherwise.
TL;DR: Karpathy shared a clever personal wiki tool for ~100 documents. The internet declared RAG dead. Enterprise data says the opposite… Continue reading on Me
RAG Is Not a Memory System. It’s a Policy Engine.
Medium · AI 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
RAG Is Not a Memory System. It’s a Policy Engine.
How to actually use Vector Databases in production AI agent systems Continue reading on Medium »
Why Running RAG Pipelines on Serverless Functions Was Harder Than I Expected
Dev.to · pythonassignmenthelp.com 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Why Running RAG Pipelines on Serverless Functions Was Harder Than I Expected
You know that feeling when you think you’ve nailed a scalable architecture—only to watch your...
Secure RAG: Authorisation-Aware Retrieval and Row-Level Security
Medium · Python 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Secure RAG: Authorisation-Aware Retrieval and Row-Level Security
How enterprise AI systems prevent unauthorised chunk leakage before it becomes a security incident Continue reading on Medium »
Secure RAG: Authorisation-Aware Retrieval and Row-Level Security
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Secure RAG: Authorisation-Aware Retrieval and Row-Level Security
How enterprise AI systems prevent unauthorised chunk leakage before it becomes a security incident Continue reading on Medium »
Production RAG Architecture — Wiring Everything Together
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Production RAG Architecture — Wiring Everything Together
Day 37 of #100DaysOfAgenticAI | By Maneesh Kumar, AI Architect Continue reading on Medium »
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
RAG vs Wiki: A Controlled Benchmark Inspired by Andrej Karpathy’s Retrieval Setup
This experiment starts from an idea shared by Andrej Karpathy — the LLM wiki setup. The shift is simple but important: instead of caching… Continue reading on M
RAG vs GraphRAG: When to Use What (From a Builder’s Perspective)
Dev.to · System Rationale 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
RAG vs GraphRAG: When to Use What (From a Builder’s Perspective)
I wasted time overengineering a GraphRAG system… when a simple RAG pipeline would’ve done the job...
I built a production RAG pipeline. Here's what most tutorials skip.
Dev.to · Anurag Srivastava 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
I built a production RAG pipeline. Here's what most tutorials skip.
I wanted a RAG system that was fast to run and fast to set up for clients. Upload a PDF, ask...
Building RAG Pipelines That Actually Work: Lessons from Microsoft Copilot
Dev.to · Nrk Raju Guthikonda 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Building RAG Pipelines That Actually Work: Lessons from Microsoft Copilot
Most RAG tutorials show you the happy path. You chunk a handful of PDFs, toss them into a vector...
Every RAG Framework I Tested Hallucinated. Here’s What Actually Fixed It
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Every RAG Framework I Tested Hallucinated. Here’s What Actually Fixed It
Most RAG demos show you the happy path. Upload a clean doc, ask a simple question, get a nice answer. Continue reading on Medium »
Every RAG Framework I Tested Hallucinated. Here’s What Actually Fixed It
Medium · LLM 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Every RAG Framework I Tested Hallucinated. Here’s What Actually Fixed It
Most RAG demos show you the happy path. Upload a clean doc, ask a simple question, get a nice answer. Continue reading on Medium »
Every RAG Framework I Tested Hallucinated. Here’s What Actually Fixed It
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Every RAG Framework I Tested Hallucinated. Here’s What Actually Fixed It
Most RAG demos show you the happy path. Upload a clean doc, ask a simple question, get a nice answer. Continue reading on Medium »
Building an Automated AWS Security Advisor: RAG with AWS Bedrock and OpenSearch Serverless
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Building an Automated AWS Security Advisor: RAG with AWS Bedrock and OpenSearch Serverless
The Problem: Security Posture Debt at Scale Continue reading on AWS Tip »
Chunking Methods for RAG
Medium · AI 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Chunking Methods for RAG
If you’re building a RAG pipeline, chunking is the step that quietly decides whether your retrieval works or doesn’t. We will cover 7… Continue reading on Mediu
Chunking Methods for RAG
Medium · Data Science 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Chunking Methods for RAG
If you’re building a RAG pipeline, chunking is the step that quietly decides whether your retrieval works or doesn’t. We will cover 7… Continue reading on Mediu
Chunking Methods for RAG
Medium · Python 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Chunking Methods for RAG
If you’re building a RAG pipeline, chunking is the step that quietly decides whether your retrieval works or doesn’t. We will cover 7… Continue reading on Mediu
Hands-On Evaluation: Best Vector Database for RAG With Metadata Filtering
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1mo ago
Hands-On Evaluation: Best Vector Database for RAG With Metadata Filtering
Why Weaviate’s pre-search filtering architecture makes it the strongest default for production RAG pipelines — and why Pinecone’s… Continue reading on Medium »