Core AI

RAG & Vector Search

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

7,099
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 (3,526) Articles (2168)Blog Posts (947)Tutorials (301)Research Papers (103)News (7)
RAG Architecture Explained: What Happens Between a User Question and the Final Answer?
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 11h ago
RAG Architecture Explained: What Happens Between a User Question and the Final Answer?
Retrieval-Augmented Generation, or RAG, is one of the most widely used architectures for building applications with Large Language Models… Continue reading on M
Retrieval: Two Searches, One Answer, and Knowing When to Say No
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 15h ago
Retrieval: Two Searches, One Answer, and Knowing When to Say No
Part 4 of Chanakya: Production RAG at Enterprise Scale. Start with the hub for the map, or Part 3 for how the index gets built. Continue reading on Medium »
Secure RAG for Business: Why Data Governance Matters
Medium · Data Science 🔍 RAG & Vector Search ⚡ AI Lesson 20h ago
Secure RAG for Business: Why Data Governance Matters
Building Secure Retrieval-Augmented Generation (RAG) for Business Continue reading on Medium »
You Think You Know RAG ? You Probably Don’t.
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1d ago
You Think You Know RAG ? You Probably Don’t.
So, today was just a chill day. Randomly, I asked one of my colleagues about RAG. Continue reading on Medium »
Building a Reusable AI Evaluation Platform with Langfuse
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1d ago
Building a Reusable AI Evaluation Platform with Langfuse
Evaluating RAG and document-processing systems through versioned datasets, automated evaluators, experiment tracking, and failure analysis Continue reading on M
The Blindfolded Librarian Problem -And How IBM’s STAIR Finally Solved It
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1d ago
The Blindfolded Librarian Problem -And How IBM’s STAIR Finally Solved It
Picture a consultant. It’s 2am. She’s reviewing a 600-page regulatory document — a government procurement guideline her firm’s AI… Continue reading on Medium »
When The Same Question Needs A Different Answer Depending On Where The Caller Is
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1d ago
When The Same Question Needs A Different Answer Depending On Where The Caller Is
A knowledge base built for a company operating across multiple regions almost always contains information that is correct in one location… Continue reading on M
Evolution of RAG Systems
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1d ago
Evolution of RAG Systems
Naive RAG, RRF, rerankers, agents, graphs, and page trees, explained. Continue reading on Generative AI »
I Built STAIR From Scratch: A Retriever That Returns Section Names, Not Chunk IDs
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 2d ago
I Built STAIR From Scratch: A Retriever That Returns Section Names, Not Chunk IDs
A full STAIR implementation (STructure Aware Information Retriever) rebuilt from the paper after its code went offline: the architecture… Continue reading on Me
Hybrid Search and Reranking: What Actually Moved Our Retrieval Accuracy (And What Didn’t)
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 2d ago
Hybrid Search and Reranking: What Actually Moved Our Retrieval Accuracy (And What Didn’t)
Our support bot had been live for six weeks when a customer asked it a question I still think about. Continue reading on Towards Deep Learning »
Beyond “Toy” RAG (Part 3): Building the AI Serving Layer with Two-Stage Retrieval & MLflow
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 2d ago
Beyond “Toy” RAG (Part 3): Building the AI Serving Layer with Two-Stage Retrieval & MLflow
How to solve the “dumb vector” problem using Cross-Encoders, decouple compute with Spark Connect, and enforce SR 11–7 compliance with… Continue reading on Mediu
RAG at Scale: From Single-Doc to Multimodal Production Pipelines
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 3d ago
RAG at Scale: From Single-Doc to Multimodal Production Pipelines
By Manan Panchal · 10 min read Continue reading on Medium »
RAG at Scale: From Single-Doc to Multimodal Production Pipelines
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 3d ago
RAG at Scale: From Single-Doc to Multimodal Production Pipelines
By Manan Panchal · 10 min read Continue reading on Medium »
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 3d ago
What Is RAG? How AI Can Answer From Your Data Without Retraining the Model
From questions to evidence to answers — and why RAG is much more than a vector database. Continue reading on Medium »
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 3d ago
What Is RAG? How AI Can Answer From Your Data Without Retraining the Model
From questions to evidence to answers — and why RAG is much more than a vector database. Continue reading on Medium »
Battle of Document Parsing RAG: PyMuPDF vs Docling vs LlamaParse vs DPT
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 3d ago
Battle of Document Parsing RAG: PyMuPDF vs Docling vs LlamaParse vs DPT
Membedah kecepatan, ekstraksi tabel, dan struktur grafik menggunakan laporan kompleks IMF World Economic Outlook. Continue reading on Medium »
My RAG Pipeline Would Have Paid for Its Own Attack.I
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 4d ago
My RAG Pipeline Would Have Paid for Its Own Attack.I
What building rails into a financial GraphRAG system taught me about cost ordering Continue reading on Medium »
RIP Vector RAG? An Introduction to Vectorless RAG
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 4d ago
RIP Vector RAG? An Introduction to Vectorless RAG
Before jumping on to Vectorless RAG and saying “RIP RAG”, let’s understand the problem with Normal RAG Continue reading on Medium »
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 4d ago
RAG Systems
Retrieval-Augmented Generation (RAG) systems have evolved significantly from when they were introduced. Initially they were simple keyword… Continue reading on
BUILDING THE COMPLETE RAG SYSTEM — PART 1
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 4d ago
BUILDING THE COMPLETE RAG SYSTEM — PART 1
Complete RAG System: Beyond Vector Search + LLM Continue reading on Medium »
A RAG Pipeline Is Reproducible Only If You Can Explain What Changed
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 4d ago
A RAG Pipeline Is Reproducible Only If You Can Explain What Changed
Suppose a retrieval experiment improves after a pipeline edit. The YAML changed, but so did the document collection, the embedding model… Continue reading on Me
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 4d ago
Beyond “Toy” RAG (Part 2): Building a Compliant Data Engineering Pipeline with PySpark & pgvector
How to ingest, chunk, mask PII, and embed millions of financial documents at scale using PySpark and PostgreSQL. Continue reading on Medium »
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 5d ago
RAG Is Easy Until the Questions Stop Being Easy
Free Agentic RAG Fundamentals 4 practical LangGraph notebooks + more practical patterns… Continue reading on Medium »
AWS Machine Learning 🔍 RAG & Vector Search 5d ago
Selecting a vector store for Amazon Bedrock Knowledge Bases
Choosing the right vector store for your Amazon Bedrock Knowledge Bases RAG application affects performance and cost. This post compares Amazon OpenSearch Servi
I Built an Observability Tool Because I Was Tired of Debugging LLM Apps By Hand
Hackernoon 🔍 RAG & Vector Search 5d ago
I Built an Observability Tool Because I Was Tired of Debugging LLM Apps By Hand
Obyflow is an open-source, CLI-first observability tool for LLM apps, RAG pipelines, agents, vector databases, and LangChain workflows.
Bilgisayar Metnin Anlamını Nasıl Buluyor? Semantic Search ve Embedding’lerin Evrimi- Bölüm 1
Medium · Python 🔍 RAG & Vector Search 6d ago
Bilgisayar Metnin Anlamını Nasıl Buluyor? Semantic Search ve Embedding’lerin Evrimi- Bölüm 1
Bir bilgisayar için metin, bizim gördüğümüz şekilde “anlamlı cümleler” değildir. Bilgisayar doğrudan kelimelerin ne anlama geldiğini, iki… Continue reading on M
Bilgisayar Metnin Anlamını Nasıl Buluyor? Semantic Search ve Embedding’lerin Evrimi- Bölüm 1
Medium · RAG 🔍 RAG & Vector Search 6d ago
Bilgisayar Metnin Anlamını Nasıl Buluyor? Semantic Search ve Embedding’lerin Evrimi- Bölüm 1
Bir bilgisayar için metin, bizim gördüğümüz şekilde “anlamlı cümleler” değildir. Bilgisayar doğrudan kelimelerin ne anlama geldiğini, iki… Continue reading on M
Beyond Basic RAG: Supercharge Retrieval Quality with Hybrid Search, pgvector, BM25, and Reranking…
Medium · RAG 🔍 RAG & Vector Search 6d ago
Beyond Basic RAG: Supercharge Retrieval Quality with Hybrid Search, pgvector, BM25, and Reranking…
If you have spent any time in the Generative AI space recently, you already know about RAG (Retrieval-Augmented Generation). Continue reading on Medium »
My RAG App Said There Was One Employee. There Were Twelve.
Medium · Machine Learning 🔍 RAG & Vector Search ⚡ AI Lesson 6d ago
My RAG App Said There Was One Employee. There Were Twelve.
Building a RAG pipeline for financial PDFs with LangChain, Qdrant and Groq — and the four bugs that made it confidently wrong. Continue reading on Medium »
How BM25, a 30-Year-Old Algorithm, Beats Vector Search
Medium · RAG 🔍 RAG & Vector Search 6d ago
How BM25, a 30-Year-Old Algorithm, Beats Vector Search
Why Claude Code abandoned vector RAG — and how to choose between grep, BM25, embeddings, and hybrid retrieval. Continue reading on Data Science Collective »
Add Semantic Search to Your App Without Rewriting It
Medium · RAG 🔍 RAG & Vector Search 6d ago
Add Semantic Search to Your App Without Rewriting It
How the SearchAI Index Server speaks the API your code already uses — OpenSearch, Elasticsearch, Qdrant, Pinecone, Chroma, or Algolia —… Continue reading on Med
GlucoRef: Building a Book-Grounded RAG Assistant for Diabetes Management
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 6d ago
GlucoRef: Building a Book-Grounded RAG Assistant for Diabetes Management
How Retrieval-Augmented Generation and Clinical Literature Are Reshaping Patient Support Tools Continue reading on Medium »
How Retrieval-Augmented Generation (RAG) Is Transforming Enterprise AI Solutions
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 6d ago
How Retrieval-Augmented Generation (RAG) Is Transforming Enterprise AI Solutions
Most enterprise AI projects fail the same way. The model writes fluent, confident answers about almost everything except the company that… Continue reading on A
Medium · LLM 🔍 RAG & Vector Search ⚡ AI Lesson 6d ago
Challenges in Generative AI projects
Challenges in RAG projects: Continue reading on Medium »
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 6d ago
Challenges in Generative AI projects
Challenges in RAG projects: Continue reading on Medium »
Top 30 RAG & AI Agent Framework Interview Questions and Answers — 2026
Medium · Data Science 🔍 RAG & Vector Search ⚡ AI Lesson 6d ago
Top 30 RAG & AI Agent Framework Interview Questions and Answers — 2026
1. What factors should you consider when selecting a framework for RAG or AI agents? Continue reading on Medium »
Top 30 RAG & AI Agent Framework Interview Questions and Answers — 2026
Medium · LLM 🔍 RAG & Vector Search ⚡ AI Lesson 6d ago
Top 30 RAG & AI Agent Framework Interview Questions and Answers — 2026
1. What factors should you consider when selecting a framework for RAG or AI agents? Continue reading on Medium »
Beyond Naive Vector Search: Engineering Stateful Memory for Enterprise RAG Systems
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Beyond Naive Vector Search: Engineering Stateful Memory for Enterprise RAG Systems
A technical deep dive into UMAP manifold geometry, Hypothetical Document Embeddings, and trainable linear transformation matrices. Continue reading on Medium »
A Framework for Deciding Where Retrieval Work Happens
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
A Framework for Deciding Where Retrieval Work Happens
Profile your corpus and questions, then choose between sending everything, filtering first, indexing ahead or searching in place. Continue reading on LearnWithN
Medium · LLM 🔍 RAG & Vector Search 1w ago
I Fine-Tuned a 7B Medical AI for $0 on Free Kaggle GPUs — Here’s the Full Pipeline
Subtitle: QLoRA + FAISS RAG + hard-coded safety guardrails: how I built “Expert Vaidya,” an offline model that separates Ayurvedic… Continue reading on Medium »
Medium · RAG 🔍 RAG & Vector Search 1w ago
I Fine-Tuned a 7B Medical AI for $0 on Free Kaggle GPUs — Here’s the Full Pipeline
Subtitle: QLoRA + FAISS RAG + hard-coded safety guardrails: how I built “Expert Vaidya,” an offline model that separates Ayurvedic… Continue reading on Medium »
Multi-Tenant RAG on Amazon S3 Vectors - Part 1: The Isolation Model
Medium · RAG 🔍 RAG & Vector Search ⚡ AI Lesson 1w ago
Multi-Tenant RAG on Amazon S3 Vectors - Part 1: The Isolation Model
Part 1 of 3. This part is the requirements and the isolation model. Part 2 is the cost model with the arithmetic. Part 3 is the pipeline… Continue reading on AW
I built an AI that refuses to answer questions about me
Medium · RAG 🔍 RAG & Vector Search 1w ago
I built an AI that refuses to answer questions about me
No RAG, no vector database. Four thousand words of handwritten notes and one sentence: it is not allowed to improvise. Continue reading on Medium »
Building a RAG Pipeline from Scratch: Embeddings, Retrieval, and Claude
Medium · RAG 🔍 RAG & Vector Search 1w ago
Building a RAG Pipeline from Scratch: Embeddings, Retrieval, and Claude
Step-by-step implementation using ChromaDB and the Anthropic API Continue reading on Medium »
Everyone’s Obsessed With Embeddings. BM25 Is Still Doing the Heavy Lifting.
Medium · RAG 🔍 RAG & Vector Search 1w ago
Everyone’s Obsessed With Embeddings. BM25 Is Still Doing the Heavy Lifting.
What TF, IDF, and document length normalization actually mean in plain English and why BM25 remains the go-to first-stage retriever in RAG… Continue reading on
Building a RAG Application with .NET 10 and OpenAI
Medium · LLM 🔍 RAG & Vector Search 1w ago
Building a RAG Application with .NET 10 and OpenAI
A practical, step-by-step introduction to embeddings, vector similarity, retrieval, and grounded LLM responses using C# and .NET 10. Continue reading on Medium
Building My First RAG Pipeline from Scratch with ChromaDB, SentenceTransformers and Ollama
Medium · LLM 🔍 RAG & Vector Search 1w ago
Building My First RAG Pipeline from Scratch with ChromaDB, SentenceTransformers and Ollama
From PDF Documents to an AI Assistant — Understanding What Actually Happens Under the Hood Continue reading on Medium »
Building My First RAG Pipeline from Scratch with ChromaDB, SentenceTransformers and Ollama
Medium · RAG 🔍 RAG & Vector Search 1w ago
Building My First RAG Pipeline from Scratch with ChromaDB, SentenceTransformers and Ollama
From PDF Documents to an AI Assistant — Understanding What Actually Happens Under the Hood Continue reading on Medium »