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.
What poisoning a RAG store taught us about agent memory
jacksonxly profile

What poisoning a RAG store taught us about agent memory

#ai #rag #security #machinelearning
1
Comments 2
7 min read
Open Source Project of the Day (#116): SAG — Multi-Hop RAG Retrieval via SQL JOINs Instead of PageRank
wonderlab profile

Open Source Project of the Day (#116): SAG — Multi-Hop RAG Retrieval via SQL JOINs Instead of PageRank

#ai #rag #knowledgebase #sql
Comments
7 min read
Before adopting DSPy, prove the LM program has a contract
doramagic profile

Before adopting DSPy, prove the LM program has a contract

#ai #llm #python #rag
Comments
3 min read
RAG From Scratch in Java
gpuneet profile

RAG From Scratch in Java

#java #ai #llm #rag
Comments
12 min read
Making RAG Accurate in Java
gpuneet profile

Making RAG Accurate in Java

#java #ai #llm #rag
Comments
8 min read
Making RAG Accurate in Python
gpuneet profile

Making RAG Accurate in Python

#python #ai #llm #rag
Comments
8 min read
"You Probably Don't Need a Headless Browser to Feed Your RAG Pipeline"
scrapemint profile

"You Probably Don't Need a Headless Browser to Feed Your RAG Pipeline"

#showdev #ai #rag #webdev
Comments
3 min read
Why Your RAG Pipeline is Failing: The Chunk Mismatch Problem and How to Fix It
imhyke profile

Why Your RAG Pipeline is Failing: The Chunk Mismatch Problem and How to Fix It

#ai #rag #machinelearning
Comments 2
3 min read
RAG From Scratch in Python
gpuneet profile

RAG From Scratch in Python

#python #ai #llm #rag
Comments
11 min read
My First RAG Project: Building InsightFetch with LangChain
kishore_ganapathy profile

My First RAG Project: Building InsightFetch with LangChain

#ai #rag #langchain #programming
Comments
1 min read
I built NexRAG: a framework-agnostic RAG pipeline SDK.
kevinrawal profile

I built NexRAG: a framework-agnostic RAG pipeline SDK.

#ai #opensource #rag #learning
2
Comments
2 min read
How Forcing 1024-Dim Embeddings Cut Our Pinecone Bill by ~33%
atultrp profile

How Forcing 1024-Dim Embeddings Cut Our Pinecone Bill by ~33%

#ai #rag #claude #software
5
Comments 1
3 min read
What Building Anamnesis Taught Me About Giving AI a Memory
naazim_hussain_7fbe686d11 profile

What Building Anamnesis Taught Me About Giving AI a Memory

#ai #architecture #llm #rag
Comments
5 min read
The Best Vector Database in 2026: Qdrant vs Pinecone vs Weaviate vs Milvus vs pgvector
darshit_01 profile

The Best Vector Database in 2026: Qdrant vs Pinecone vs Weaviate vs Milvus vs pgvector

#ai #database #llm #rag
1
Comments
7 min read
The Second Brain They Can’t Subpoena: Local RAG on a Pi 5

Discoverable embeddings and chunking hurdles
numbpill3d profile

The Second Brain They Can’t Subpoena: Local RAG on a Pi 5

#raspberrypi #privacy #programming #rag
4
Comments 3
9 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.