Building a Production-Ready RAG Evaluation Framework
Evaluating a RAG application is harder than measuring a few metrics. Many existing tools focus on...
#RAG
891 articles tagged with RAG
In-process embeddings for a desktop AI app, or how a missing daemon silently broke my RAG
I'm building a desktop AI app for non-technical users — the kind of person who double-clicks an icon...
Azure AI Search in 2026, how to build a RAG pipeline
Most RAG tutorials online show the same pattern: take a document, split it into chunks, generate...
The AI ecosystem keeps introducing new concepts:• LLMs• AI Agents• RAG• Embeddings• MCP• Vector DatabasesBuilding a clea...
The AI ecosystem keeps introducing new concepts:• LLMs• AI Agents• RAG• Embeddings• MCP• Vector DatabasesBuilding a clear glossary of AI terminology is becoming more important than...
razesoni/Generative-AI-Course-Context-Engine: An offline, AI-powered teaching assistant that uses a local RAG pipeline (Whisper + Ollama) to transcribe educational videos, answer student queries, and generate quizzes.
An offline, AI-powered teaching assistant that uses a local RAG pipeline (Whisper + Ollama) to transcribe educational videos, answer student queries, and generate quizzes.
🚀 Deodat-Lawson/LaunchStackTypeScript engine for AI-native Next.js apps with ingestion, OCR, RAG, and knowledge graph ca...
🚀 Deodat-Lawson/LaunchStackTypeScript engine for AI-native Next.js apps with ingestion, OCR, RAG, and knowledge graph capabilities⭐ Stars: 884📅 Last Update: Jul 01, 2026https://git...
Метод, которого не существовало: как я собрал локальный RAG для CAD APIПоследние годы инжиниринг живёт под одним лозунго...
Метод, которого не существовало: как я собрал локальный RAG для CAD APIПоследние годы инжиниринг живёт под одним лозунгом: то же самое, но дешевле и быстрее. Заказчики сокращают бю...
Architecting an Enterprise RAG Platform: Shifting from AI Hype to Production Trust on AWS
Moving Generative AI from a proof-of-concept sandbox into an enterprise-grade solution requires...
RAG lets AI search your documents and answer questions clearly.#ai #rag #compliance
RAG lets AI search your documents and answer questions clearly.#ai #rag #compliance
Жизнь после RAG: MCP, логи и автоматический анализ тикетов JiraПривет, Хабр! Меня зовут Илья Парамошин, я ведущий инжене...
Жизнь после RAG: MCP, логи и автоматический анализ тикетов JiraПривет, Хабр! Меня зовут Илья Парамошин, я ведущий инженер в МТС Web Services. В прошлый раз я рассказывал об архитек...
🚀 Fastest-growing AI projects today1. LodeDB → a fast, exact, embedded vector database designed for local RAG applicatio...
🚀 Fastest-growing AI projects today1. LodeDB → a fast, exact, embedded vector database designed for local RAG applications (61 stars)2. Rupixel → a Rust port of PixelRAG, focusing ...
You Probably Don't Need a Vector Database for RAG
RAG retrieval strategies without a vector database: BM25, keyword indices, knowledge-in-bundle — and when embeddings earn their cost.
Bigger Context Windows Didn't Make Our RAG Smarter
We stopped measuring retrieval quality by how many tokens we could fit into the prompt. When...
AI Agent Skills migrating worldcup rag app(Gemini and GCP to Qwen and Alibaba)
Disclosure Submission for the Global AI Hackathon Series with Qwen Cloud Blog Post...
Retrieval-Augmented Generation: An Engineer's Guide to Building RAG Systems with Your Own Data by Jeroen Herczeg is the ...
Retrieval-Augmented Generation: An Engineer's Guide to Building RAG Systems with Your Own Data by Jeroen Herczeg is the featured book 📖 on Leanpub!The engineer's guide to RAG syste...
AI isn't just chatbots. It's also helping users find the right document, product, answer or recommendation.Vector search...
AI isn't just chatbots. It's also helping users find the right document, product, answer or recommendation.Vector search is one of the foundational building blocks behind modern AI...
Echtzeit-RAG in Python: Live-Google-Ergebnisse für dein LLM (2026)Was wäre, wenn deine RAG-Pipeline kurz vor der Antwort...
Echtzeit-RAG in Python: Live-Google-Ergebnisse für dein LLM (2026)Was wäre, wenn deine RAG-Pipeline kurz vor der Antwortgenerierung frischen Web-Kontext abrufen könnte? Eine prakti...
Building a Four-Tier Parallel RAG Pipeline with Gemini
The Problem When building BotForge, our AI no-code chatbot platform, we needed a retrieval...
【実測比較】日本語RAGのOCR、結局どれを使う？ glm-ocr / dots.ocr / Unlimited-OCR / MinerU を社内ドライブの実データでガチ評価https://qiita.com/engchina/items/...
【実測比較】日本語RAGのOCR、結局どれを使う？ glm-ocr / dots.ocr / Unlimited-OCR / MinerU を社内ドライブの実データでガチ評価https://qiita.com/engchina/items/6dff7010af1b28e8c30a?utm_campaign=popular_items&utm_medium=f...
Why your RAG accuracy problem is probably stale data (2026)
You picked a model. You built a RAG pipeline or an agent loop. You ran evals, the results looked...
🔥 AI context pruning breakthroughA new technique for pruning RAG context can improve AI performance. By reducing unneces...
🔥 AI context pruning breakthroughA new technique for pruning RAG context can improve AI performance. By reducing unnecessary context, AI models can focus on the most relevant infor...
RAG для закупок: Qdrant и LlamaIndex в локальном контуреПривет Хабр! Меня зовут Владимир, и недавно я решил изучить нову...
RAG для закупок: Qdrant и LlamaIndex в локальном контуреПривет Хабр! Меня зовут Владимир, и недавно я решил изучить новую (для себя) технологию - LlamaIndex . А тут и задачка подве...
Réduire les hallucinations en e-commerce https://www.netguru.com/blog/reduce-ai-hallucinations-ecommerce-rag #ecommerce ...
Réduire les hallucinations en e-commerce https://www.netguru.com/blog/reduce-ai-hallucinations-ecommerce-rag #ecommerce #llm #hallucinations
Your RAG System Is Lying To You About That Table
Retrieval Augmented Generation, or RAG, has become the default way to ask questions about long...