Leonard Shelby Is a RAG Pipeline
Memento as a two-hour postmortem for retrieval-augmented generation. Leonard Shelby makes...
#RAG
1112 articles tagged with RAG
Google Cloud has released an Always-On Memory Agent that replaces traditional RAG and embeddings with continuous LLM con...
Google Cloud has released an Always-On Memory Agent that replaces traditional RAG and embeddings with continuous LLM consolidation using Gemini 3.1 Flash-Lite. The agent runs 24/7,...
Building a Grounded RAG Assistant: Why Citation Enforcement Matters More Than Retrieval
Most RAG tutorials focus on retrieval quality: better embeddings, better chunking, better reranking....
Why RAG gives wrong answers (and how to fix retrieval failures)
In the previous post, we built a RAG system from scratch. Sixty lines of Python. Six onboarding...
RAG is for finding. Full context is for deciding.
The advice in 2026 is settled: chunk your documents, embed them, retrieve top-k, feed those to the...
FaramarzKowsari/ai-api-playbook: Companion source code for AI APIs in Practice, a visual engineering book on multimodal AI, agents, RAG, evaluation, governance, and production-ready products. Book DOI: 10.5281/zenodo.21431944 · Software DOI: 10.5281/zenodo.21419466
Companion source code for AI APIs in Practice, a visual engineering book on multimodal AI, agents, RAG, evaluation, governance, and production-ready products. Book DOI: 10.5281/zen...
Best Large Language Models (LLM) Course 2026 – Learn RAG, AI Agents, Fine-Tuning & LLM Engineering
Master Large Language Models (LLMs): The Complete AI Course to Build RAG Systems, AI Agents & Multi-Agent Applications in 2026 Artificial Intelligence is transforming every industr...
Retrieval-Augmented Self-Recall: The RAG Problem Nobody Talks About
Part 1 of Retrieval-Augmented Self-Recall — the research track behind Claude Code, Beyond the Prompt....
Beyond Chatbots: Wrapping My RAG Agent in an MCP Server
In my last post, I walked through a RAG pipeline that answers questions from a company policy...
RAG translation system pushes LLMs past sentence-by-sentence limitsA July 2026 arXiv preprint tests PAT, a RAG-based sys...
RAG translation system pushes LLMs past sentence-by-sentence limitsA July 2026 arXiv preprint tests PAT, a RAG-based system that feeds whole-document context to LLMs for English-to...
RAG in Laravel: Embeddings and pgvector for a Knowledge-Base Bot
In the last post we streamed AI responses over SSE. Now let's fix the problem every chatbot hits in...
From RAG to Ragga. The second and last weeks of my residency at Malvina. Vibe coding. Dance codes. Fine-tuning system pr...
From RAG to Ragga. The second and last weeks of my residency at Malvina. Vibe coding. Dance codes. Fine-tuning system prompts and tuning into submolts and the church of molt.#teche...
RAG systems introduce new attack surfaces beyond the prompt layer—ingestion pipelines, vector stores, and retrieval logi...
RAG systems introduce new attack surfaces beyond the prompt layer—ingestion pipelines, vector stores, and retrieval logic each require independent security controls to avoid silent...
Securing RAG: Why the Retrieval Pipeline Is Your New Attack Surface
RAG systems introduce new attack surfaces beyond the prompt layer—ingestion pipelines, vector stores, and retrieval logic each require indep
076. Как работает RAGКак работает RAGГлавное здесь — не сама технология, а то, какую проблему человека или бизнеса она р...
076. Как работает RAGКак работает RAGГлавное здесь — не сама технология, а то, какую проблему человека или бизнеса она решает. RAG сначала находит релевантные источники, а затем пе...
Domain-routed agents vs naive RAG: экономика и риски архитектурного выбораКлассический RAG хорошо ищет отдельные факты, ...
Domain-routed agents vs naive RAG: экономика и риски архитектурного выбораКлассический RAG хорошо ищет отдельные факты, но может пропускать исключения и связи между разными раздела...
LLM-wiki против RAG: Оцениваем и сравниваемПро LLM-wiki здесь уже было несколько хороших статей ( 1 , 2 и 3 ), поэтому п...
LLM-wiki против RAG: Оцениваем и сравниваемПро LLM-wiki здесь уже было несколько хороших статей ( 1 , 2 и 3 ), поэтому подробно останавливаться на идее Andrej Karpathy не буду. В д...
Production RAG at Scale: Lessons from Processing 10,000+ Listings Daily
A practical deep-dive into building a production RAG pipeline that scores thousands of documents daily with LLMs. Chunking, vector stores, cost optimization, and observability.
CyberSunil/LLMVault: An intentionally vulnerable OWASP LLM Top 10 training platform for AI Security, Prompt Injection, RAG Security, Agent Security, and GenAI penetration testing.
An intentionally vulnerable OWASP LLM Top 10 training platform for AI Security, Prompt Injection, RAG Security, Agent Security, and GenAI penetration testing.
Spent the last 2 months building a #RAG engine for cognitive bias detection. Three assumptions completely fell apart: • More knowledge better retrieval • Passing evals production ready • More context better LLM output
Building a RAG Engine: Three Engineering Assumptions I Had to Unlearn ...
🤖 In RAG, retrieval quality is mostly a chunking problem. Common mistakes:🪨 chunks too big → relevant text gets diluted,...
🤖 In RAG, retrieval quality is mostly a chunking problem. Common mistakes:🪨 chunks too big → relevant text gets diluted, retrieval misses🔬 chunks too small → you lose the context t...
#AI #KnowledgeGraph youtu.be/W_s_X_kj3vg?...Claude Opus 4 + RAG: Build an ...
#AI #KnowledgeGraph youtu.be/W_s_X_kj3vg?...Claude Opus 4 + RAG: Build an ...
Chat2Scenic: An Iterative RAG-Based Framework for Scenario Generation in Autonomous Driving
Validating autonomous driving systems requires diverse, regulation-compliant test scenarios. In simulation-based testing, scenarios are defined as executable scripts. Yet automatic...
LLM temperature setting steers ideological bias in RAG answersAn arXiv preprint finds sampling temperature on retrieval-...
LLM temperature setting steers ideological bias in RAG answersAn arXiv preprint finds sampling temperature on retrieval-augmented LLMs controls how strongly ideological framing fro...