Security — Guardrails and Prompt Injection Defense for Production RAG
Introduction In Chapter 3 (Observability), we made system behavior visible. Now we tackle...
#RAG
891 articles tagged with RAG
MADEVAL/FerryAI: Native AI inference for PHP 8.3+ - run ONNX, GGUF (llama.cpp) and RubixML models directly in your PHP process via FFI. Chat, streaming, embeddings, RAG and vector search. No Python, no HTTP microservices, no Docker sidecars.
Native AI inference for PHP 8.3+ - run ONNX, GGUF (llama.cpp) and RubixML models directly in your PHP process via FFI. Chat, streaming, embeddings, RAG and vector search. No Python...
I Ditched Vector Search for My Coding Agent's Memory. FTS5 Won.
Every "give your agent memory" tutorial I've read reaches for the same stack: chunk your docs, embed...
The Best Vector Database in 2026: Qdrant vs Pinecone vs Weaviate vs Milvus vs pgvector
I've run production RAG systems on four of these. Here's the comparison I wish someone had written...
What killed my vector database on a free-tier container
I built a real-time insights dashboard that ingests live public weather data, runs every reading...
I used MariaDB as my vector database and got queries that took 0.001 or 0.002 seconds—crazy ! ⚡EN Use MariaDB como BD Ve...
I used MariaDB as my vector database and got queries that took 0.001 or 0.002 seconds—crazy ! ⚡EN Use MariaDB como BD Vectorial y obtuve consultas rápidas de 0.001 o 0.002 segundos...
Struggling to keep up with AI terminology? This glossary explains the key terms you need to know, from LLMs and RAG to R...
Struggling to keep up with AI terminology? This glossary explains the key terms you need to know, from LLMs and RAG to RLHF and AI agents. A living document for anyone navigating t...
Ahead of Print in BFP: ALIMA, a RAG-based LLM system for subject indexing, is a prototype that assigns GND subject headi...
Ahead of Print in BFP: ALIMA, a RAG-based LLM system for subject indexing, is a prototype that assigns GND subject headings and DK/RVK classes via LLMs, reducing cataloguing worklo...
What a Production RAG System Actually Looks Like After 18 Months
I want to write the post I wish existed when I started building enterprise RAG systems. Not a...
Building RAG-Powered AI Agents with AgentCore: What the Hands-On Tutorials Don't Tell You
Your vector database is returning results. Your retrieval pipeline is clean. But when you connect...
OpenAI-compatible API smoke testBefore moving an SDK, agent, or RAG workflow to an OpenAI-compatible API, run one tiny n...
OpenAI-compatible API smoke testBefore moving an SDK, agent, or RAG workflow to an OpenAI-compatible API, run one tiny non-streaming cURL first.Prove base URL, key, model ID, balan...
A RAG evaluator that admits what it can't judge
Fail-closed groundedness, deterministic corroborators, and a self-test — because an evaluator should...
Why “Please Don’t Make Recommendations” Is Not a Guardrail for RAG
You built a system to surface information so a person could decide. Somewhere it started deciding for...
【ハンズオン】AgentCore最新機能でRAG & AIエージェント構築に入門！https://qiita.com/minorun365/items/7d06434cf830df9c54ff?utm_campaign=popular_it...
【ハンズオン】AgentCore最新機能でRAG & AIエージェント構築に入門！https://qiita.com/minorun365/items/7d06434cf830df9c54ff?utm_campaign=popular_items&utm_medium=feed&utm_source=popular_items#qiita #AWS #AI ...
GraphRAG vs. RAG: When Knowledge Graphs Earn Their Complexity
Vector search tells you which chunks are similar to your query. GraphRAG tells you how entities in...
RAG, or Retrieval-Augmented Generation, is a technique in AI that allows models to read and incorporate information from...
RAG, or Retrieval-Augmented Generation, is a technique in AI that allows models to read and incorporate information from documents when generating responses. This enhances accuracy...
Semantic Observability: Engineering Reliability for Production RAG
It is a noticeable thing when a microservice fails. It is either a null pointer exception in a Java...
Why vector-only RAG is weak for coding agents
Building Droste: a local structural + semantic code-memory engine for MCP agents AI coding agents...
Делюсь опытом: ИИ-агент на Claude без LangChain и RAG — разбор архитектуры и развилокДелюсь опытом: собрал прод-агента н...
Делюсь опытом: ИИ-агент на Claude без LangChain и RAG — разбор архитектуры и развилокДелюсь опытом: собрал прод-агента на Claude для небольшой студии дизайна интерьера. Чат отвечае...
65 бесплатных уроков июля: от LLM и RAG до Kubernetes, Go и QAПрофессиональный рост часто упирается в конкретные слепые ...
65 бесплатных уроков июля: от LLM и RAG до Kubernetes, Go и QAПрофессиональный рост часто упирается в конкретные слепые зоны: где демо AI-агента расходится с продакшеном, как выбир...
1024-token RAG chunks cut my storage cost in half — and nearly doubled my Claude bill
Cloudflare Vectorize에서 청크 크기를 256·512·1024 토큰으로 바꿔가며 지연·품질·비용을 직접 측정한 1인 SaaS 운영자의 실험 기록. 정답은 없고 트레이드오프만 있었다.
Как мы создали внутреннего ИИ-помощника на базе RAG и перестали искать ответы по корпоративной WikiКомпании со временем ...
Как мы создали внутреннего ИИ-помощника на базе RAG и перестали искать ответы по корпоративной WikiКомпании со временем накапливают тысячи страниц документации, и найти нужную инфо...
RAG for Code: Why Chunking by Function Beats Chunking by Lines
I built a retrieval system over a codebase so an LLM could answer questions about it, and my first...
Un bon article d'introduction à propos du RAG (Retrieval-Augmented Generation) : comment obtenir des réponses rapides et...
Un bon article d'introduction à propos du RAG (Retrieval-Augmented Generation) : comment obtenir des réponses rapides et précises sur une base de connaissances spécifiques, en util...