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

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Mathematically Optimal Chunking Strategy

Mathematically Optimal Chunking Strategy

Comments
8 min read
How I Built a GraphRAG System That Saves 70-85% LLM Tokens Using TigerGraph

How I Built a GraphRAG System That Saves 70-85% LLM Tokens Using TigerGraph

1
Comments
1 min read
Documents are records waiting to exist

Documents are records waiting to exist

Comments
2 min read
Reranker Fine-Tuning on Click Data: When Off-the-Shelf Stops Winning

Reranker Fine-Tuning on Click Data: When Off-the-Shelf Stops Winning

Comments
8 min read
RAG in Rust, Multi-Agent Orchestration with Hermes, and Arm Metis AI Security Framework

RAG in Rust, Multi-Agent Orchestration with Hermes, and Arm Metis AI Security Framework

Comments 1
3 min read
RAG with EF Core and pgvector

RAG with EF Core and pgvector

Comments
5 min read
I Got Tired of Reading Strangers’ Codebases, So I Built an AI That Reads Them For Me

Syntax-aware indexing via tree-sitter

I Got Tired of Reading Strangers’ Codebases, So I Built an AI That Reads Them For Me

11
Comments 6
4 min read
Route Context: How I Built Right Context for Agents

Route Context: How I Built Right Context for Agents

Comments 2
9 min read
I built a RAG pipeline from scratch, and one wrong answer made me dive even deeper into AI Engineering

I built a RAG pipeline from scratch, and one wrong answer made me dive even deeper into AI Engineering

Comments 5
4 min read
FreshContext in agent workflows: judgment at the context handoff

FreshContext in agent workflows: judgment at the context handoff

2
Comments 5
4 min read
LongTrainer: The Production-Ready Python RAG Framework That Replaces 500 Lines of LangChain Boilerplate

LongTrainer: The Production-Ready Python RAG Framework That Replaces 500 Lines of LangChain Boilerplate

Comments
8 min read
Building NotesGPT: An Offline-Capable AI Study Assistant with RAG, Local LLMs, and WebGPU

Building NotesGPT: An Offline-Capable AI Study Assistant with RAG, Local LLMs, and WebGPU

Comments
4 min read
GraphRAG Explained: How Knowledge Graphs Are Transforming Modern RAG Systems

GraphRAG Explained: How Knowledge Graphs Are Transforming Modern RAG Systems

Comments
3 min read
72% -> 75% -> 92%: a reproducible RAG validation

72% -> 75% -> 92%: a reproducible RAG validation

Comments 3
12 min read
Day 11: Conversational RAG — How to Chat with Your Documents 💬

Day 11: Conversational RAG — How to Chat with Your Documents 💬

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