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.
I Built a Meeting Intelligence Platform Because I Was Drowning in Context-Switching

I Built a Meeting Intelligence Platform Because I Was Drowning in Context-Switching

Comments
3 min read
Cosine Similarity Failed Our RAG on Exact Terms — BM25 Fixed It

Cosine Similarity Failed Our RAG on Exact Terms — BM25 Fixed It

3
Comments
6 min read
My RAG Pipeline Was 84% Confident — And Completely Wrong.

My RAG Pipeline Was 84% Confident — And Completely Wrong.

1
Comments
6 min read
I Built an NL2SQL Agent for IPL Cricket While Learning How AI Agents Actually Work

I Built an NL2SQL Agent for IPL Cricket While Learning How AI Agents Actually Work

1
Comments
5 min read
Building an Automated AWS Security Advisor: RAG with AWS Bedrock and OpenSearch Serverless

Building an Automated AWS Security Advisor: RAG with AWS Bedrock and OpenSearch Serverless

Comments 1
7 min read
Building an Enterprise RAG System for Non-English Documents: A Turkish Case Study

Building an Enterprise RAG System for Non-English Documents: A Turkish Case Study

Comments
4 min read
The 10-Layer Security System Your RAG Pipeline Is Missing

The 10-Layer Security System Your RAG Pipeline Is Missing

12
Comments 1
7 min read
Le Wiki LLM : Une révolution dans la gestion de la connaissance

Le Wiki LLM : Une révolution dans la gestion de la connaissance

3
Comments
9 min read
Why Naive Similarity Search Will Destroy Your RAG Agent (And What To Do Instead)

Why Naive Similarity Search Will Destroy Your RAG Agent (And What To Do Instead)

Comments
4 min read
Building an Enterprise RAG System for Non-English Documents

Building an Enterprise RAG System for Non-English Documents

1
Comments
5 min read
Why RAG Is Failing at Complex Questions (And How Knowledge Graphs Fix It)

Why RAG Is Failing at Complex Questions (And How Knowledge Graphs Fix It)

Comments
6 min read
The Biggest Pitfall in GraphRAG: One Entity, Seven Identities

The Biggest Pitfall in GraphRAG: One Entity, Seven Identities

Comments 1
7 min read
A $0.25 model beat a $3 model -- with better context

A $0.25 model beat a $3 model -- with better context

Comments
7 min read
Migrating vector embeddings in production without downtime

Migrating vector embeddings in production without downtime

30
Comments 2
6 min read
Speaking the Corpus's Language: How Multilingual RAG Stays Coherent Across Turns

Speaking the Corpus's Language: How Multilingual RAG Stays Coherent Across Turns

Comments 1
8 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.