Why RAG fails for AI agent memory — and how I fixed it (with benchmarks)
I've been building Pulses — a project where AI personalities need real long-term memory across...
#RAG
942 articles tagged with RAG
I _also_ built a thing! I know, shocker!https://metallapan.se/post/giving-your-ai-a-memory/ #RAG #LLM #python
I _also_ built a thing! I know, shocker!https://metallapan.se/post/giving-your-ai-a-memory/ #RAG #LLM #python
RAG system. Day 3: Indexing.95 years of Oscars data. Now stored as vectors.ChromaDB finds relevant chunks. Claude reads ...
RAG system. Day 3: Indexing.95 years of Oscars data. Now stored as vectors.ChromaDB finds relevant chunks. Claude reads them. Answers grounded in facts.Day 4 tomorrow: the full ret...
🚀 This Week in RAG & Vector Databases: Fastest-Growing Projects — April 14, 2026This week in the RAG & Vector Databases ...
🚀 This Week in RAG & Vector Databases: Fastest-Growing Projects — April 14, 2026This week in the RAG & Vector Databases space, we're seeing a surge in innovative projects that leve...
Как мы перестали мерить качество ответов RAG-поиска «на глаз» и начали нормально сравниватьЕсли вы делаете RAG-поиск по ...
Как мы перестали мерить качество ответов RAG-поиска «на глаз» и начали нормально сравниватьЕсли вы делаете RAG-поиск по документации или базе знаний, то рано или поздно упираетесь ...
Building a Scalable RAG Backend with Cloud Run Jobs and AlloyDB
Building a Retrieval-Augmented Generation (RAG) sounds easy with all the available tutorials. You...
RT @OpenRouter: Neu auf OpenRouter: Reranker-Modelle 🔍 Warum einen Reranker in deine RAG-Pipeline einbauen? Die Embeddin...
RT @OpenRouter: Neu auf OpenRouter: Reranker-Modelle 🔍 Warum einen Reranker in deine RAG-Pipeline einbauen? Die Embedding-Suche findet relevante Textabschnitte, aber Reranker sagen...
🚀 This Week in RAG & Vector Databases: Fastest-Growing Projects — April 14, 2026The RAG & Vector Databases space has see...
🚀 This Week in RAG & Vector Databases: Fastest-Growing Projects — April 14, 2026The RAG & Vector Databases space has seen a surge in innovative projects this week, with a focus on ...
@dbtechyt try some stuff, get your docs on an internal only website and spider with yacy and then rag pipeline with pyda...
@dbtechyt try some stuff, get your docs on an internal only website and spider with yacy and then rag pipeline with pydantic? I think things will keep evolving even in the next 6 m...
https://www.tkhunt.com/2285140/ AIニュースで英語学習 ベクトルデータベース不要でRAG同等の性能を実現――キーワード検索とエージェント型AIの組み合わせに新知見 #AgenticAi #AI #Artifi...
https://www.tkhunt.com/2285140/ AIニュースで英語学習 ベクトルデータベース不要でRAG同等の性能を実現――キーワード検索とエージェント型AIの組み合わせに新知見 #AgenticAi #AI #ArtificialIntelligence #エージェント型AI #人工知能
RAG system. Day 2: Setup.Three tools. One goal.pip install langchain anthropic chromadb→ LangChain: orchestrates the pip...
RAG system. Day 2: Setup.Three tools. One goal.pip install langchain anthropic chromadb→ LangChain: orchestrates the pipeline→ Claude API: generates answers from retrieved context→...
📰 LLM Wiki vs RAG: Build an AI Knowledge System in 2026 (Andrej Karpathy)LLM Wiki is an emerging framework that turns ra...
📰 LLM Wiki vs RAG: Build an AI Knowledge System in 2026 (Andrej Karpathy)LLM Wiki is an emerging framework that turns raw notes and documents into structured, AI-enhanced knowledge...
🚀 I Built a Browser-Local AI Assistant in Next.js with WebLLM, WASM, ONNX Runtime, Web Workers, and RAG
Most AI chat widgets are just frontends for a remote API. This one is different. My assistant runs...
How to Build a PDF RAG Pipeline Without Text Extraction (Using Native PDF Embeddings)
A step-by-step guide to building a PDF RAG pipeline using native PDF embeddings. Avoid text extraction, preserve layout, and improve retrieval with Ge
📰 Missing Context Layer: The 2026 Secret to Stable RAG Systems & LLM ReliabilityThe missing context layer is the critica...
📰 Missing Context Layer: The 2026 Secret to Stable RAG Systems & LLM ReliabilityThe missing context layer is the critical yet overlooked component that transforms RAG from theory i...
🚀 I Built an AI-Powered Fest Assistant with Agents, RAG & Planning (Pragyan @ NITT)
I deleted Instagram more than a year ago, and honestly, it saved me from a lot of distractions. But...
The 5 Levels of RAG Maturity: How to Know When Your RAG Is Actually Production-Ready
I've watched a lot of RAG projects ship in the last eighteen months. They all follow the same...
🚀 This Week in RAG & Vector Databases: Fastest-Growing Projects — April 13, 2026This week in the RAG & Vector Databases ...
🚀 This Week in RAG & Vector Databases: Fastest-Growing Projects — April 13, 2026This week in the RAG & Vector Databases space, we're seeing a surge of interest in tools that facili...
Andrej Karpathy's research organization method drew 16M views: skip RAG pipelines, point an LLM at a folder of markdown ...
Andrej Karpathy's research organization method drew 16M views: skip RAG pipelines, point an LLM at a folder of markdown files instead. His approach generated a 100-article, 400k-wo...
I Built a RAG App That Chats With Any PDF — Here's How
Build a RAG app from scratch with Node.js. Upload PDFs, images, docs and ask questions.
Build Your Own Second Brain: RAG-Powered Knowledge Tools That Never Leave Your Machine
Tags: #ai #python #rag #productivity Every day, we generate an enormous volume of personal knowledge...
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.
I wanted a RAG system that was fast to run and fast to set up for clients. Upload a PDF, ask...
🚀 This Week in RAG & Vector Databases: Fastest-Growing Projects — April 12, 2026This week in the RAG & Vector Databases ...
🚀 This Week in RAG & Vector Databases: Fastest-Growing Projects — April 12, 2026This week in the RAG & Vector Databases space, we're seeing a surge of interest in tools that enable...