DEV Community

# rag

Retrieval augmented generation, or RAG, is an architectural approach that can improve the efficacy of large language model (LLM) applications by leveraging custom data.

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Building a Perplexity Clone for Local LLMs in 50 Lines of Python

Building a Perplexity Clone for Local LLMs in 50 Lines of Python

1
Comments 1
6 min read
Scaling LLMs at the Edge: A journey through distillation, routers, and embeddings

Scaling LLMs at the Edge: A journey through distillation, routers, and embeddings

1
Comments
20 min read
15 Engineering Decisions Behind RAG Hybrid Search

15 Engineering Decisions Behind RAG Hybrid Search

11
Comments
9 min read
RAG + FastAPI in Action: Creating a Smart Business Analytics Dashboard in Python

RAG + FastAPI in Action: Creating a Smart Business Analytics Dashboard in Python

Comments
9 min read
Your AI Memory System Can't Tell a River Bank from a Savings Account

Your AI Memory System Can't Tell a River Bank from a Savings Account

21
Comments 4
5 min read
I Built a Fully Local Paper RAG on an RTX 4060 8GB — BGE-M3 + Qwen2.5-32B + ChromaDB

I Built a Fully Local Paper RAG on an RTX 4060 8GB — BGE-M3 + Qwen2.5-32B + ChromaDB

Comments
10 min read
RAG in Practice — Part 6: RAG, Fine-Tuning, or Long Context?

RAG in Practice — Part 6: RAG, Fine-Tuning, or Long Context?

2
Comments
9 min read
How CodiLay Reads a Codebase the Way a Detective Reads a Crime Scene

How CodiLay Reads a Codebase the Way a Detective Reads a Crime Scene

2
Comments
9 min read
Anatomy of a RAG System Architecture

Anatomy of a RAG System Architecture

Comments
5 min read
Qu'est-ce qu'OpenViking ?

Qu'est-ce qu'OpenViking ?

Comments
15 min read
OpenViking คืออะไร

OpenViking คืออะไร

Comments
3 min read
¿Qué es OpenViking?

¿Qué es OpenViking?

Comments
11 min read
Beyond Vector Search: Building a Personal Health Knowledge Graph with GraphRAG and Neo4j 🧬📊

Beyond Vector Search: Building a Personal Health Knowledge Graph with GraphRAG and Neo4j 🧬📊

1
Comments
4 min read
Introducing Recursive Memory Harness: RLM For Agentic Memory

Introducing Recursive Memory Harness: RLM For Agentic Memory

2
Comments
5 min read
I Built Beans — A Semantic News & Blogs API & MCP for AI Agents and RAG

I Built Beans — A Semantic News & Blogs API & MCP for AI Agents and RAG

Comments
2 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.