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.
Beyond Keywords: Mastering HyDE for Smarter Retrieval 🧠
rushanksavant profile

Beyond Keywords: Mastering HyDE for Smarter Retrieval 🧠

#ai #llm #rag #tutorial
Comments
4 min read
Query Rewriting Before Retrieval: The Cheap Recall Win Most Skip
gabrielanhaia profile

Query Rewriting Before Retrieval: The Cheap Recall Win Most Skip

#rag #ai #llm #howto
Comments
7 min read
Part 2: RAG Architecture: How Retrieval-Augmented Generation Actually Works
newavtar profile

Part 2: RAG Architecture: How Retrieval-Augmented Generation Actually Works

#ai #architecture #rag #tutorial
Comments
4 min read
The Gate: Architecting Deterministic Grounding for the Agentic Era
ai-alchemist profile

The Gate: Architecting Deterministic Grounding for the Agentic Era

#ai #architecture #rag #obsidian
5
Comments
6 min read
BM25 + Dense Fusion: When Keyword Search Saves Your RAG
gabrielanhaia profile

BM25 + Dense Fusion: When Keyword Search Saves Your RAG

#rag #ai #llm #search
Comments
7 min read
LLM Engineering: Architecting Agentic RAG and Conversational BI
soytuber profile
soy

LLM Engineering: Architecting Agentic RAG and Conversational BI

#ai #rag #automation
1
Comments
3 min read
Why Companies Will Stop Asking “Do You Know AI?” and Start Asking This Instead
minoltan profile

Why Companies Will Stop Asking “Do You Know AI?” and Start Asking This Instead

#mcp #rag #agents #ai
Comments
3 min read
Metadata Filtering Before Vector Search: The Recall Win Nobody Measures
gabrielanhaia profile

Metadata Filtering Before Vector Search: The Recall Win Nobody Measures

#rag #ai #llm #database
Comments
7 min read
Why Your RAG Chatbot Looks Great in Week 1 and Hallucinates by Month 2
akshay_kumar_bm profile

Why Your RAG Chatbot Looks Great in Week 1 and Hallucinates by Month 2

#ai #architecture #llm #rag
Comments 1
6 min read
# GraphRAG: The End-to-End Guide to Reducing Hallucination and Automating Complex Workflows
nikhil_ramank_152ca48266 profile

# GraphRAG: The End-to-End Guide to Reducing Hallucination and Automating Complex Workflows

#ai #rag #graphrag #llm
Comments
15 min read
Building a multi-tenant RAG pipeline with Postgres. Part 0: Overview
ja_su_1e698278f65839836aa profile

Building a multi-tenant RAG pipeline with Postgres. Part 0: Overview

#ai #rag #postgres #langchain
Comments
4 min read
I kept losing project context, so I built a local Mac workspace with MCP, CLI, and hybrid RAG
gl01 profile

I kept losing project context, so I built a local Mac workspace with MCP, CLI, and hybrid RAG

#mcp #rag #opensource #swift
Comments 1
3 min read
Most RAG failures don’t crash. They silently return bad answers. I built a repair layer for that.
bn3020 profile
BN

Most RAG failures don’t crash. They silently return bad answers. I built a repair layer for that.

#rag #llm #ai #deterministic
Comments
1 min read
Rerankers and the Latency Budget: When Cross-Encoders Are Worth It
gabrielanhaia profile

Rerankers and the Latency Budget: When Cross-Encoders Are Worth It

#rag #ai #llm #comparison
Comments
7 min read
Evaluating RAG: Separate Your Retrieval Metrics From Your Generation Metrics
gabrielanhaia profile

Evaluating RAG: Separate Your Retrieval Metrics From Your Generation Metrics

#rag #ai #llm #howto
Comments
7 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.