#RAG | AI Hub

Mastodon discussion May 24

Most developers overcomplicate AI agents.My production stack 👇🔀 LangGraph — agent flow control🔍 RAG + Pinecone — searche...

Most developers overcomplicate AI agents.My production stack 👇🔀 LangGraph — agent flow control🔍 RAG + Pinecone — searches your docs 🐍 FastMCP — runs Python code live🧠 PostgreSQL — ...

RAG

24

Dev.to tutorial May 24

Building a RAG Document Q&A System with Hybrid Retrieval (No Embeddings API Needed)

Building a production-quality RAG (Retrieval-Augmented Generation) system taught me one thing: the...

RAG API

12

Mastodon discussion May 24

Most teams reach for fine-tuning when they should be using RAG.The confusion usually comes from one thing people know wh...

Most teams reach for fine-tuning when they should be using RAG.The confusion usually comes from one thing people know what both are, but nobody gives a clear way to decide.Here's t...

RAG

24

Dev.to tutorial May 24

Four production pitfalls that turn RAG demos into broken chatbots

A perfect 50-question demo on Tuesday. By the second week of production, users were filing tickets faster than the team could close them. The model had not changed. The retrieval p...

RAG

12

Dev.to tutorial May 24

Multimodal RAG: when summary-based stops being enough

A founder asked why their AI assistant kept saying 'the chart shows a positive trend' instead of reading the actual numbers. The pipeline was doing exactly what it was designed to ...

Multimodal RAG

12

Mastodon discussion May 24

LMIM OS v2.1 "Tezcat · Sharpened" drops tomorrow.This isn't a patch. It's a different animal:• RAG Lite — drop a PDF, as...

LMIM OS v2.1 "Tezcat · Sharpened" drops tomorrow.This isn't a patch. It's a different animal:• RAG Lite — drop a PDF, ask anything about it• Workspace sandbox — point LMIM at a fol...

RAG

18

Dev.to tutorial May 24

How We Built a Production RAG Chatbot for a Client in 72 Hours (Full Stack Breakdown)

A client messaged us on a Tuesday night. By Friday afternoon, their customer support chatbot was live...

RAG

12

Mastodon discussion May 23

Show HN: I built a RAG and knowledge graph agent that runs locallyhttps://news.ycombinator.com/item?id=48248801#HackerNe...

Show HN: I built a RAG and knowledge graph agent that runs locallyhttps://news.ycombinator.com/item?id=48248801#HackerNews #Tech #AI

RAG

18

Dev.to tutorial May 23

Building a Private RAG System: Lessons from a Local-First AI Journal

Most AI apps quietly send your data to the cloud. DiaryGPT does the opposite — and this is the full...

RAG

12

GitHub Trending repo May 23

study8677/awesome-architecture: 🗺️ Think like a software architect, not just a coder — 21 architecture maps (incl. AI gateway, RAG, agents, inference serving, vector DB) + a language-agnostic system-design tutorial. Every template links to real open-source prototypes. 中英文双语。

🗺️ Think like a software architect, not just a coder — 21 architecture maps (incl. AI gateway, RAG, agents, inference serving, vector DB) + a language-agnostic system-design tutori...

RAG Open Source

62

Dev.to tutorial May 23

From Manual RAG to Real Retrieval — Embedding-Based RAG with NVIDIA NIM

Replace hardcoded context with real retrieval using NVIDIA's nv-embedqa-e5-v5 embedding model. Cosine similarity, the query vs passage input distinction most beginners get wrong, n...

NVIDIA RAG

20

Dev.to tutorial May 22

What Enterprise RAG Is Ready For Today and What Production Deployment Actually Requires

Enterprise RAG — A practitioner's build log | Post 6 of 6 This series has documented a system built...

RAG

12

Mastodon discussion May 22

RAG en PostgreSQL con pgEdge: búsqueda híbrida 2026¿Necesitás una base de datos vectorial o alcanza pgvector? Armá tu pi...

RAG en PostgreSQL con pgEdge: búsqueda híbrida 2026¿Necesitás una base de datos vectorial o alcanza pgvector? Armá tu pipeline RAG en PostgreSQL con búsqueda híbrida y cero infraes...

RAG

18

Mastodon discussion May 22

In RAG, the bottleneck isn’t your app server—it’s vector search, rerankers, and LLM latency.Go is fast glue around slow ...

In RAG, the bottleneck isn’t your app server—it’s vector search, rerankers, and LLM latency.Go is fast glue around slow calls. TypeScript on Bun matches that speed *and* brings bet...

LLM RAG

24

Dev.to tutorial May 22

I Stacked 4 More Context Layers on Top of RAG. Sonnet Got 12% Better. Haiku Got 14% Worse.

I read about Full Context Engineering and added structured output, hierarchical layout, role definition, and few-shot examples to my RAG pipeline. Sonnet got 12% better. Haiku got ...

RAG

12

Dev.to tutorial May 22

I tested 7 vector databases for my RAG stack in 2026, here's the one nobody is talking about (yet)

TL;DR: I spent 1 week benchmarking Pinecone, Weaviate, Qdrant, Milvus, pgvector, SurrealDB, and...

RAG

12

Dev.to tutorial May 22

LLM-Wiki: Multi-Agent Memory Without RAG

How three AI agents can collaborate on a complex task by sharing a folder of markdown files — and...

LLM RAG

25

Dev.to tutorial May 22

Building a P2P 'Wikipedia for Machines': Verifiable RAG with the Holepunch Stack

Current LLMs hallucinate when they lack context. While Retrieval-Augmented Generation (RAG) helps,...

RAG

12

Mastodon discussion May 22

I'm very pleased to release our first work on "RAG and GraphRAG Experiments on MCPs: Perspectives for Historical Researc...

I'm very pleased to release our first work on "RAG and GraphRAG Experiments on MCPs: Perspectives for Historical Research." This work was conducted with historian Caroline Muller (...

RAG

30