#RAG

Mastodon discussion Jul 10

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...

RAG API

9

Dev.to tutorial Jul 10

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

12

Mastodon discussion Jul 9

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

RAG

9

Mastodon discussion Jul 9

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...

RAG MCP

9

Mastodon discussion Jul 9

🚀 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 ...

RAG

9

Dev.to tutorial Jul 8

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.

RAG

12

Dev.to tutorial Jul 8

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...

RAG

12

Dev.to tutorial Jul 7

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...

Google RAG Agents

12

Mastodon discussion Jul 7

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...

RAG

9

Mastodon discussion Jul 7

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...

RAG

9

Mastodon discussion Jul 7

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...

Google LLM RAG

9

Dev.to tutorial Jul 7

Building a Four-Tier Parallel RAG Pipeline with Gemini

The Problem When building BotForge, our AI no-code chatbot platform, we needed a retrieval...

Google RAG

20

Mastodon discussion Jul 7

【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...

RAG

9

Dev.to tutorial Jul 7

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...

RAG

12

Mastodon discussion Jul 7

🔥 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

9

Mastodon discussion Jul 7

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...

RAG

18

Mastodon discussion Jul 7

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

RAG

9

Dev.to tutorial Jul 7

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...

RAG

20

Dev.to tutorial Jul 7

Candidate Compliance Agent: Building a Multilingual RAG System for Tamil Nadu Election Affidavits

The Problem Nobody Talks About Every election cycle in India, candidates are not easily...

RAG

12

Mastodon discussion Jul 7

🌗 我們如何訓練一個小型大型語言模型（LLM）刪減 68% 的 RAG 上下文➤ 透過「列表式評估」精準刪減，在成本與準確度間取得最佳平衡✤ https://www.kapa.ai/blog/how-we-prune-rag-context...

🌗 我們如何訓練一個小型大型語言模型（LLM）刪減 68% 的 RAG 上下文➤ 透過「列表式評估」精準刪減，在成本與準確度間取得最佳平衡✤ https://www.kapa.ai/blog/how-we-prune-rag-context在處理大規模技術文件與複雜知識庫時，RAG（檢索增強生成）系統常面臨「檢索過多無效資訊」導致成本高昂且幹擾模型判斷的問題...

LLM RAG

9

NewsData.io news Jul 7

How Retrieval-Augmented Generation (RAG) Improves AI Agent Performance

Retrieval-Augmented Generation boosts Artificial Intelligence with smarter AI Agents. Learn how RAG improves AI Models with accurate, current insights

RAG Agents

21

Mastodon discussion Jul 6

Pruning RAG context down to what the answer actually needshttps://www.kapa.ai/blog/how-we-prune-rag-context#ai

Pruning RAG context down to what the answer actually needshttps://www.kapa.ai/blog/how-we-prune-rag-context#ai

RAG

9

Mastodon discussion Jul 6

Keep hearing the same story from prospects."We used model X, tooling Y, and slapped RAG Z on it. Doesn't work"Yea no shi...

Keep hearing the same story from prospects."We used model X, tooling Y, and slapped RAG Z on it. Doesn't work"Yea no shit.As we speak I know of companies that rejected our offers a...

RAG

18

Mastodon discussion Jul 6

Paula Santamaría and Julia Schröder Langhaeuser of Serenity Star talk about “Production RAG at Scale with Azure Database...

Paula Santamaría and Julia Schröder Langhaeuser of Serenity Star talk about “Production RAG at Scale with Azure Database for PostgreSQL” at POSETTE: An Event for Postgres 2026. 📺Ca...

RAG

9