#RAG

Papers with Code paper Oct 22

Is Complex Agentic Memory Always Needed? Naive RAG Is Stronger Than We Thought

LLM memory is widely used in long-term conversation understanding. Agentic memory systems often use mutation, structural organization, learned retrieval strategies, or other comple...

RAG Agents

21

Mastodon discussion Oct 21

A RAG pipeline retrieved the right documents but lost them during reranking. Here's what went wrong and how to improve r...

A RAG pipeline retrieved the right documents but lost them during reranking. Here's what went wrong and how to improve retrieval quality. https://hackernoon.com/my-rag-pipeline-fou...

RAG

9

Mastodon discussion Oct 20

Understanding Retrieval-Augmented Generation (RAG) with OpenAIhttps://www.codemancers.com/blog/2024-09-17-rag#AI #OpenAI...

Understanding Retrieval-Augmented Generation (RAG) with OpenAIhttps://www.codemancers.com/blog/2024-09-17-rag#AI #OpenAI #LLM

OpenAI RAG

27

Mastodon discussion Oct 20

Agentic RAGとは？従来のRAGとの決定的な違い・導入判断基準まで解説 https://www.yayafa.com/2915591/ #AgenticAi #AI #ArtificialGeneralIntelligence #A...

Agentic RAGとは？従来のRAGとの決定的な違い・導入判断基準まで解説 https://www.yayafa.com/2915591/ #AgenticAi #AI #ArtificialGeneralIntelligence #ArtificialIntelligence #エージェント型AI #人工知能 #汎用人工知能

RAG Agents

9

Dev.to tutorial Oct 20

Inside VOICE-RAG: From Speech to Grounded Answers

Pavan Ganesh Indupudi (Infernix) · Originally published at the-infernix.github.io Ask most RAG demos...

RAG

12

Mastodon discussion Oct 20

RAG после reranker: от корпоративного поиска к агенту, которому можно поручить исследованиеПривет, Хабр! На связи Алекса...

RAG после reranker: от корпоративного поиска к агенту, которому можно поручить исследованиеПривет, Хабр! На связи Александр Михеев, ML-инженер Центра гибридного интеллекта в Рунити...

RAG

9

Dev.to tutorial Oct 20

The 21-case test that decides whether a RAG chatbot ships

Every retrieval-augmented chatbot demo looks the same: paste in a folder of PDFs, ask a question, get...

RAG

12

Mastodon discussion Oct 19

RAGу для программистаВнедрение AI в программные продукты часто сопровождается необходимостью обогатить контекст LLM спец...

RAGу для программистаВнедрение AI в программные продукты часто сопровождается необходимостью обогатить контекст LLM специфичными для ваших задач данными. Для обогащения знаний испо...

LLM RAG

9

Mastodon discussion Oct 19

📝 Neuer Blog-Beitrag: Agentic RAG 2026: Wenn KI-Agenten selbst entscheiden, wie sie Wissen findenKlassisches RAG stößt b...

📝 Neuer Blog-Beitrag: Agentic RAG 2026: Wenn KI-Agenten selbst entscheiden, wie sie Wissen findenKlassisches RAG stößt bei mehrstufigen Fragen an Grenzen. Agentic RAG ersetzt 2026 ...

RAG Agents

9

Mastodon discussion Oct 19

DBのニュースですねベクトルDBを使わない「階層ナビゲーション型RAG」を作って、ベクトルDB版RAGと比較してみた https://zenn.dev/aiforall/articles/8e1803396534de#Apple #LLM ...

DBのニュースですねベクトルDBを使わない「階層ナビゲーション型RAG」を作って、ベクトルDB版RAGと比較してみた https://zenn.dev/aiforall/articles/8e1803396534de#Apple #LLM #news #bot

LLM RAG

24

Mastodon discussion Oct 19

Niektóre elementy #AI budzą wątpliwości wielu osób. Ale akurat lokalny #RAG będący bazą wiedzy w danej organizacji to co...

Niektóre elementy #AI budzą wątpliwości wielu osób. Ale akurat lokalny #RAG będący bazą wiedzy w danej organizacji to coś, na co wiele firm patrzy bardzo chętnie i wręcz z zazdrośc...

RAG

9

Mastodon discussion Oct 19

Uncertainty can measure hallucination risk in retrieval-augmented generation (RAG) when retrieved evidence constrains th...

Uncertainty can measure hallucination risk in retrieval-augmented generation (RAG) when retrieved evidence constrains the answer.Source: arXiv cs.CLhttps://arxiv.org/abs/2610.22615...

RAG

9

Dev.to tutorial Oct 19

RAG Can Retrieve the Right Document and Still Hide the Answer

A document ID can pass a retrieval check while the text sent to the model omits the answer. That...

RAG

12

Dev.to tutorial Oct 18

I Gave a Fraud Agent No Vector Store and No Cypher. It Remembered Anyway.

I Gave a Fraud Agent No Vector Store and No Cypher. It Remembered Anyway. LedgerLens is...

RAG

20

Dev.to tutorial Oct 18

Why Vector RAG Fails in Codebases: Building an Architectural Knowledge Graph with FalkorDB

Before an AI agent or engineer modifies legacy code, what must they know? Discover how we built Argon using FalkorDB, openCypher, and MCP to kill architectural hallucinations.

RAG

12

Dev.to tutorial Oct 18

AI in Practice: RAG, MCP and Multi-Agent Systems in Kotlin, Without Magic Frameworks

AI in Practice: Demystifying RAG, MCP and Multi-Agent Systems in Kotlin, Without "Magic"...

RAG MCP

12

Dev.to tutorial Oct 18

How We Built a Self-Healing Multi-Agent Company Brain on FalkorDB (and Why Vector RAG Failed Us)

How We Built a Self-Healing Multi-Agent Company Brain on FalkorDB (and Why Vector RAG Failed...

RAG

20

Mastodon discussion Oct 18

Синтетическая эмпатия: как RAG, системные промпты и TTS инженерят привязанность к LLM-агентамELIZA в 1966-м заставляла с...

Синтетическая эмпатия: как RAG, системные промпты и TTS инженерят привязанность к LLM-агентамELIZA в 1966-м заставляла секретарш просить не заглядывать в распечатки диалогов. Шесть...

LLM RAG

9

Dev.to tutorial Oct 18

Why Vector Search Guesses and Graphs Prove: What Building ClearPath Taught Me

Let’s talk about something I see over and over in Web3 and AI right now. Everyone wants to build AI...

RAG

12

Dev.to tutorial Oct 18

Why Vector RAG Fails Blast-Radius Questions (and the 4-Hop Cypher Query That Fixes It)

Why Vector RAG Fails Blast-Radius Questions (and the 4-Hop Cypher Query That Fixes It) By...

RAG

12

Dev.to tutorial Oct 18

Beyond Vector Search: Building an Autonomous Enterprise Security Swarm with FalkorDB Graph Memory

Beyond Vector Search: Building an Autonomous Enterprise Security Swarm with FalkorDB Graph...

RAG

12

Dev.to tutorial Oct 18

pgvector vs Pinecone vs Qdrant: Benchmarked for RAG in 2026

pgvector vs Pinecone vs Qdrant for RAG: 100k OpenAI embeddings benchmarked for recall, latency and filtering, plus Pinecone limits and when Postgres is enough.

OpenAI RAG

12

Dev.to tutorial Oct 18

Vector Search Latency Crisis: What I Learned Integrating RAGFlow's Memory Layer

Battle-tested pgvector HNSW tuning and hybrid search implementation after hitting severe concurrency bottlenecks in a production RAG pipeline.

RAG

12

Dev.to tutorial Oct 17

Day 02/90: Chunking Strategies in RAG — Why Splitting Documents Matters

You upload a document, ask a question, and get an incomplete answer. You check the source. The...

RAG

12