RAG isn't memory. It's Ctrl+F with embeddings.
Part 1 of 3 — "Memory for AI agents" Deconstructing the long-term memory myth in LLM...
#RAG
1136 articles tagged with RAG
🚀 This Week in RAG & Vector Databases: Fastest-Growing Projects — April 30, 2026This week in the RAG & Vector Databases ...
🚀 This Week in RAG & Vector Databases: Fastest-Growing Projects — April 30, 2026This week in the RAG & Vector Databases space, we've seen a surge in innovative projects that combin...
jmerelnyc/rag-forge: Framework for fine-tuning LLMs on retrieval-augmented generation tasks
Framework for fine-tuning LLMs on retrieval-augmented generation tasks
warpdot-dev/composio: typescript python sdk ai-agents anthropic openapi langchain openai-agents llamaindex mastra vercel-ai mcp oauth saas llm integrations agent-tools automation cloudflare google-gemini tooling rag multi-provider developer-sdk composable-actions webhook-triggers
typescript python sdk ai-agents anthropic openapi langchain openai-agents llamaindex mastra vercel-ai mcp oauth saas llm integrations agent-tools automation cloudflare google-gemin...
What I Got Wrong Building a RAG Pipeline from Scratch in TypeScript
Three mistakes I made building a production-grade RAG pipeline in TypeScript with pgvector — fixed-size chunking, pure vector search, and small-model tool calling — and what I repl...
🚀 This Week in RAG & Vector Databases: Fastest-Growing Projects — April 29, 2026This week in the RAG & Vector Databases ...
🚀 This Week in RAG & Vector Databases: Fastest-Growing Projects — April 29, 2026This week in the RAG & Vector Databases space, we've seen a surge in interest around tools that leve...
How I reduced AI codebase context from 100K to 5K tokens using a graph-based RAG
Most AI coding tools lie to you about context. They say "I understand your codebase." What they...
Building a Persistent Knowledge Base RAG System with FastAPI, llama.cpp, Chroma, and Open WebUI
Have you ever wanted to chat with your own PDF collection – textbooks, research papers, internal...
An interesting approach to cultural data access:A local RAG assistant that lets you explore events through natural langu...
An interesting approach to cultural data access:A local RAG assistant that lets you explore events through natural language queries, using OpenAgenda data, FAISS, and Mistral. Runs...
Preparing RAG pipeline for production
Intro Having a working RAG that provides correct semantic answers is a great start, yet,...
Long Context vs RAG: When to Load the Whole Book
AI in Practice, No Fluff — Day 9/10 I have a project where every conversation and decision gets...
What if choosing the wrong AI approach costs you 3x more than necessary?Wrong RAG vs fine-tuning decisions waste million...
What if choosing the wrong AI approach costs you 3x more than necessary?Wrong RAG vs fine-tuning decisions waste millions. It's a strategic business decision impacting cost and tim...
My first “local” Vector Search: MongoDB community edition
This article was written by Darshan Jayarama. Ever since I received an email about the vector...
I built a vector search library in Rust/WASM. Here's what I learned about performance, browser limits, and building in public with AI
I wanted to build a privacy-first RAG app. The kind where your documents never leave the browser. It...
Every embedding model gets deprecated eventually. A practitioner's guide to migrating a production RAG pipeline without ...
Every embedding model gets deprecated eventually. A practitioner's guide to migrating a production RAG pipeline without breaking search quality or your budget. https://hackernoon.c...
Python isn’t the only way to build #AIAgents anymore. With #SpringAI, #Java apps get memory, RAG, tools & model switchin...
Python isn’t the only way to build #AIAgents anymore. With #SpringAI, #Java apps get memory, RAG, tools & model switching—all behind one #API. Same code runs from local Ollama to A...
🚀 This Week in RAG & Vector Databases: Fastest-Growing Projects — April 28, 2026This week in the RAG & Vector Databases ...
🚀 This Week in RAG & Vector Databases: Fastest-Growing Projects — April 28, 2026This week in the RAG & Vector Databases space, we're seeing a surge in innovative projects that leve...
Your AI Agent Isn't Stupid, Your Vector Database Math Is
Hey DEV community, CallmeMiho here. I’ve been auditing AI architectures all week, and I keep seeing...
🚀 This Week in RAG & Vector Databases: Fastest-Growing Projects — April 28, 2026This week, we've seen significant growth...
🚀 This Week in RAG & Vector Databases: Fastest-Growing Projects — April 28, 2026This week, we've seen significant growth in the RAG & Vector Databases space, driven by innovative a...
[Перевод] Пять документов ломают ваш RAG: где реальная уязвимость и что с ней делатьRAG часто воспринимают как аккуратны...
[Перевод] Пять документов ломают ваш RAG: где реальная уязвимость и что с ней делатьRAG часто воспринимают как аккуратный способ «заземлить» LLM на документах и снизить риск галлюц...
Почему ваша LLM-платформа — следующая цель: аудит безопасности AI-сервиса изнутриМы искали уязвимости в RAG-платформе с ...
Почему ваша LLM-платформа — следующая цель: аудит безопасности AI-сервиса изнутриМы искали уязвимости в RAG-платформе с десятками тысяч пользователей — а нашли доступ ко всей инфра...
P-r-e-m-i-u-m/generative-ai-engineering-lab: Hands-on Generative AI engineering lab: RAG, prompt evals, safety, agents, and production patterns from scratch.
Hands-on Generative AI engineering lab: RAG, prompt evals, safety, agents, and production patterns from scratch.
P-r-e-m-i-u-m/ai-outcomes-suite: Generative AI engineering lab plus practical AI MVPs: RAG, evals, agents, safety, SAT tutor, compliance OS, and legal agent.
Generative AI engineering lab plus practical AI MVPs: RAG, evals, agents, safety, SAT tutor, compliance OS, and legal agent.
RAG Without Embeddings: When BM25 Beats Your $0.20-per-1K Vector Index
BEIR still shows BM25 holding its own on exact-match domains. Here is the decision rule, the Postgres setup, and when hybrid actually pays.