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.
Securing a RAG Pipeline — The Threats I Designed Against and the Ones I Didn't
pgmpofu profile

Securing a RAG Pipeline — The Threats I Designed Against and the Ones I Didn't

#security #rag #python #ai
Comments
8 min read
Chunking Strategy: Why I Split on Paragraph Boundaries Instead of Token Count
pgmpofu profile

Chunking Strategy: Why I Split on Paragraph Boundaries Instead of Token Count

#ai #claude #python #rag
Comments
7 min read
How I Used Chroma as a Local Vector Store — And What You'd Swap It for in Production
pgmpofu profile

How I Used Chroma as a Local Vector Store — And What You'd Swap It for in Production

#ai #rag #python #vectordatabase
Comments
6 min read
Local Embeddings vs. API Embeddings — Why I Chose sentence-transformers
pgmpofu profile

Local Embeddings vs. API Embeddings — Why I Chose sentence-transformers

#python #ai #rag #architecture
Comments
6 min read
RAG vs fine-tuning: which one your problem actually needs
pranjulrathour profile

RAG vs fine-tuning: which one your problem actually needs

#rag #finetuning #architecture #decisionguide
Comments
3 min read
Multilingual RAG Architecture That Works in Production
vgoncharenko profile

Multilingual RAG Architecture That Works in Production

#ai #rag #machinelearning #architecture
Comments
7 min read
Query rewriting for RAG: expansion, decomposition and HyDE, explained simply
pranjulrathour profile

Query rewriting for RAG: expansion, decomposition and HyDE, explained simply

#rag #retrieval #queryrewriting #hyde
Comments
3 min read
Seven ways RAG fails in production, and the fix for each
pranjulrathour profile

Seven ways RAG fails in production, and the fix for each

#rag #production #debugging #guide
Comments
3 min read
Multi-provider LLM fallback: staying up when one API goes down
pranjulrathour profile

Multi-provider LLM fallback: staying up when one API goes down

#llmapps #reliability #architecture #rag
Comments
3 min read
FAISS vs Qdrant vs pgvector: choosing a vector store for a student or startup RAG project
pranjulrathour profile

FAISS vs Qdrant vs pgvector: choosing a vector store for a student or startup RAG project

#rag #vectordatabase #faiss #qdrant
Comments
3 min read
Citations in RAG answers: how to make every sentence traceable to a source
pranjulrathour profile

Citations in RAG answers: how to make every sentence traceable to a source

#rag #citations #trust #guide
Comments
3 min read
How to evaluate a RAG system: recall, faithfulness and the questions that matter
pranjulrathour profile

How to evaluate a RAG system: recall, faithfulness and the questions that matter

#rag #evaluation #metrics #guide
Comments
3 min read
A RAG project for your college: notes, syllabus and PYQs you can actually query
pranjulrathour profile

A RAG project for your college: notes, syllabus and PYQs you can actually query

#rag #studentproject #portfolio #college
Comments
3 min read
Choosing an embedding model for RAG (and when to switch)
pranjulrathour profile

Choosing an embedding model for RAG (and when to switch)

#rag #embeddings #retrieval #guide
Comments
3 min read
Chunking strategies for RAG: sizes, overlap and structure-aware splits
pranjulrathour profile

Chunking strategies for RAG: sizes, overlap and structure-aware splits

#rag #chunking #retrieval #guide
Comments
3 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.