#RAG

Mastodon discussion Sep 9

#Gemini #AI refused to be locked down by #RAG #prompt so I will stop using AI and do manual #cataloguing of #library whi...

#Gemini #AI refused to be locked down by #RAG #prompt so I will stop using AI and do manual #cataloguing of #library which is much slower but less error prone

Google RAG

18

Dev.to tutorial Sep 8

Laravel's Native Vector Search Now Speaks MariaDB — Plain MySQL Is Still Left Out

Originally published on my blog. On August 20, PR #61250 was merged into Laravel's 13.x branch,...

RAG

12

Mastodon discussion Sep 8

Как с помощью graph RAG добиться многоходовых рассуждений от LLM с 2B весовПару недель назад YouTube подкинул мне пятими...

Как с помощью graph RAG добиться многоходовых рассуждений от LLM с 2B весовПару недель назад YouTube подкинул мне пятиминутный ролик с небольшого канала, где автор демонстрирует пр...

LLM RAG

9

Mastodon discussion Sep 8

Bundles Ollama, Open WebUI, n8n, ComfyUI, and RAG into a single local stack. Instead of manually stitching together loca...

Bundles Ollama, Open WebUI, n8n, ComfyUI, and RAG into a single local stack. Instead of manually stitching together local AI tools, ODS turns your PC or Mac into a private AI serve...

RAG

18

Mastodon discussion Sep 8

Vector Database Selection Guide: Pinecone, Weaviate, and Chroma ComparedDiscover how to pick the right vector database f...

Vector Database Selection Guide: Pinecone, Weaviate, and Chroma ComparedDiscover how to pick the right vector database for your AI workloads. A deep dive into Pinecone, Weaviate, a...

RAG

9

Mastodon discussion Sep 7

stopped AI from hallucinating by using RAG prompt which requires it to lookup data not generate it; before that I had a ...

stopped AI from hallucinating by using RAG prompt which requires it to lookup data not generate it; before that I had a lot of trouble with AI generating fake Library of Congress C...

RAG

9

Dev.to tutorial Sep 7

RAG Is Not One Problem: Enterprise Search vs. a Voice Agent Mid-Call

Part 1 of a 3-part series on building retrieval-augmented generation for two very different...

RAG

12

Mastodon discussion Sep 7

Как мы научили ИИ читать корпоративные регламенты: от наивного RAG до измеримого pipelineВ статье - практический кейс со...

Как мы научили ИИ читать корпоративные регламенты: от наивного RAG до измеримого pipelineВ статье - практический кейс создания корпоративного RAG-сервиса для поиска по внутренним р...

RAG

9

Dev.to tutorial Sep 7

Building 3 AI Agents on a $0 Budget: What I Learned About Tool-Use, RAG, and Code Execution

Why I built this I'm a CS graduate preparing for a Data Science/AI master's application,...

RAG

20

Dev.to tutorial Sep 7

The Vector Store Question That Changes Your Entire RAG Architecture

I joined a RAG architecture review where the first question was: “Which vector database should we...

RAG

12

Dev.to tutorial Sep 7

Your LLM Trace Is Green. Why Is the RAG Answer Still Wrong?

Most LLM observability stops at the model call. Learn how to trace retrieval, reranking, evidence, and citations to find where RAG systems actually fail.

LLM RAG

31

Dev.to tutorial Sep 6

Securing a RAG Pipeline — The Threats I Designed Against and the Ones I Didn't

Most RAG tutorials end when the pipeline answers a question correctly. That's where the security...

RAG

12

Dev.to tutorial Sep 6

I Built a RAG Pipeline From Scratch Without Using LangChain — Here's Every Decision I Made

Every RAG tutorial starts the same way. from langchain import ... Enter fullscreen mode ...

RAG

12

Dev.to tutorial Sep 6

Multilingual RAG Architecture That Works in Production

A production multilingual RAG architecture across 14 languages: translate at the edges, reason in one base language, and protect entities throughout.

RAG

12

Dev.to tutorial Sep 6

Hybrid Search in Postgres with pgvector: Field Notes on HNSW, tsvector, and Why Pure Vector Search Missed Exact Matches

Headline: pgvector is a Postgres extension that adds vector column types and...

RAG

12

Dev.to tutorial Sep 6

I Rebuilt My RAG Pipeline Without LangChain — What Got Better and What Got Worse

The first time I seriously doubted the framework was not because the model hallucinated. It was...

RAG

38

Dev.to tutorial Sep 6

Building a Production RAG Pipeline with n8n, Qdrant, and Gemini: A Step-by-Step Walkthrough

The first version of a RAG system always looks convincing. You connect a document loader, a vector...

Google RAG

33

Dev.to tutorial Sep 6

We Deleted Our Vector Database. Postgres Was Faster.

We paid for a vector database for a year. It was faster than Postgres at the one thing it does. We...

RAG

20

Dev.to tutorial Sep 6

The Next RAG Problem Isn’t Retrieval — It’s Knowing When Not to Retrieve

The most expensive RAG failure is often not an empty search result. It is a confident answer built...

RAG

33

Dev.to tutorial Sep 6

RAG vs Memory vs Tools: What Information Should an AI Agent Actually Store?

The first time an AI agent remembers something useful, it feels like product magic. The first time...

RAG Agents

33

Dev.to tutorial Sep 6

RAG Poisoning Is a Supply Chain Attack, Not a Prompt Injection Variant

In August 2024, researchers demonstrated a silent attack against Microsoft 365 Copilot. Any user with...

RAG

12

Dev.to tutorial Sep 6

RAG ou MCP? A pergunta errada. Cole o prompt e monte os dois

RAG é a base de conhecimento: Logseq, Notion, Confluence. MCP é o conector: o IDE pede um trecho dessa base. Fine-tuning não grava o doc nos pesos.

RAG MCP

12

Dev.to tutorial Sep 5

RAG Solved the Wrong Problem: What Actually Makes AI Applications Reliable?

Your team ships an internal AI assistant grounded on company documents. The demo is excellent: ask...

RAG

33

Dev.to tutorial Sep 5

RAG Over YouTube Playlists: From Video URLs to Cited Answers in 60 Lines

RAG Over YouTube Playlists: From Video URLs to Cited Answers in 60 Lines In the previous...

RAG

12