#RAG

Mastodon discussion Mar 26

RAG вместо GPT: как мы сделали внутреннего ассистента для корпоративных данныхВ больших компаниях поиск почти всегда «ра...

RAG вместо GPT: как мы сделали внутреннего ассистента для корпоративных данныхВ больших компаниях поиск почти всегда «работает». Но это не значит, что сотрудники быстро находят нуж...

RAG

9

Dev.to tutorial Mar 26

RAG Architecture

RAG stands for Retrieval-Augmented Generation — a technique used in AI to give more accurate and...

RAG

45

Dev.to tutorial Mar 26

RAG finds chunks. TrailGraph finds answers. Here's the difference.

I built an AI agent that traverses a knowledge graph step by step instead of using vector search. Here's what I learned about structured knowledge retrieval.

RAG

12

Mastodon discussion Mar 26

📰 Bits-Over-Random Metric: The 2026 Breakthrough for RAG and AI Agent ReliabilityThe bits-over-random metric is reshapin...

📰 Bits-Over-Random Metric: The 2026 Breakthrough for RAG and AI Agent ReliabilityThe bits-over-random metric is reshaping how developers evaluate retrieval-augmented generation sys...

RAG Agents

24

Mastodon discussion Mar 26

📰 Bits-over-Random 2026'da RAG ve AI Ajanları İçin Güvenilirlik DevrimiYeni bir metrik olan Bits-over-Random, RAG sistem...

📰 Bits-over-Random 2026'da RAG ve AI Ajanları İçin Güvenilirlik DevrimiYeni bir metrik olan Bits-over-Random, RAG sistemlerinin ve AI ajanlarının güvenilirliğini nasıl yeniden tanı...

RAG

18

Mastodon discussion Mar 26

Text embeddings for RAG and search - Python, Ollama, OpenAI-compatible APIs:https://www.glukhov.org/rag/embeddings/#Embe...

Text embeddings for RAG and search - Python, Ollama, OpenAI-compatible APIs:https://www.glukhov.org/rag/embeddings/#Embeddings #RAG #Python #Ollama #LLM #SelfHosting #VectorDatabas...

OpenAI RAG

30

Mastodon discussion Mar 26

ランスは応答をどう思うかな……文書の内容を学習なしでLLMに反映、Sakana AIの新技術　RAG代替は可能か https://xtech.nikkei.com/atcl/nxt/column/18/00001/11603/#Apple ...

ランスは応答をどう思うかな……文書の内容を学習なしでLLMに反映、Sakana AIの新技術　RAG代替は可能か https://xtech.nikkei.com/atcl/nxt/column/18/00001/11603/#Apple #LLM #news #bot

LLM RAG

27

Mastodon discussion Mar 25

- Google Research: TurboQuant KV cache and vector search compression algorithm: https://research.google/blog/turboquant-...

- Google Research: TurboQuant KV cache and vector search compression algorithm: https://research.google/blog/turboquant-redefining-ai-efficiency-with-extreme-compression/- Serious ...

Google RAG

24

Mastodon discussion Mar 25

Want to learn AI fast? Start with Postgres + RAG.This article dives into how pgEdge’s RAG approach is helping developers...

Want to learn AI fast? Start with Postgres + RAG.This article dives into how pgEdge’s RAG approach is helping developers quickly build and iterate on AI applications.👉 Read more:ht...

RAG

18

ArXiv paper Mar 25

Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA

Retrieval-augmented generation (RAG) systems are increasingly used to analyze complex policy documents, but achieving sufficient reliability for expert usage remains challenging in...

RAG

18

Dev.to tutorial Mar 25

RAG vs Fine-Tuning — What Actually Works in Production (2026)

I've spent the last year building AI systems that actually serve real users — not demos, not proofs...

RAG

12

ArXiv paper Mar 25

Who Benefits from RAG? The Role of Exposure, Utility and Attribution Bias

Large Language Models (LLMs) enhanced with Retrieval-Augmented Generation (RAG) have achieved substantial improvements in accuracy by grounding their responses in external document...

RAG

18

Hacker News discussion Mar 24

From zero to a RAG system: successes and failures

From zero to a RAG system: successes and failures

RAG

67

ArXiv paper Mar 17

Is Conformal Factuality for RAG-based LLMs Robust? Novel Metrics and Systematic Insights

Large language models (LLMs) frequently hallucinate, limiting their reliability in knowledge-intensive applications. Retrieval-augmented generation (RAG) and conformal factuality h...

RAG

18

AI Blogs (RSS) news Mar 12

Retrieval After RAG: Hybrid Search, Agents, and Database Design — Simon Hørup Eskildsen of Turbopuffer

Turbopuffer came out of a reading app.

RAG

24

Papers with Code paper Mar 12

Test-Time Strategies for More Efficient and Accurate Agentic RAG

Retrieval-Augmented Generation (RAG) systems face challenges with complex, multihop questions, and agentic frameworks such as Search-R1 (Jin et al., 2025), which operates iterative...

RAG Agents

21