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.
Detecting Embedding Drift: The Silent Killer of RAG Accuracy

Detecting Embedding Drift: The Silent Killer of RAG Accuracy

Comments
7 min read
RAG Decisions Without Retrieval Proof: The Compliance Gap No One Audits

RAG Decisions Without Retrieval Proof: The Compliance Gap No One Audits

5
Comments
5 min read
Agentic AI

Agentic AI

Comments
2 min read
From RAG to Knowledge Graphs Why the Agent Era Is Redefining AI Architecture

From RAG to Knowledge Graphs Why the Agent Era Is Redefining AI Architecture

4
Comments 5
15 min read
Document Tool: Grounding AI in Enterprise Knowledge

Document Tool: Grounding AI in Enterprise Knowledge

1
Comments 1
3 min read
Week 5: RAG Systems and AI Agents - Where Distributed Systems Meet LLMs

Week 5: RAG Systems and AI Agents - Where Distributed Systems Meet LLMs

Comments 2
6 min read
Bringing the LLM Wiki Idea to a Codebase

Bringing the LLM Wiki Idea to a Codebase

12
Comments 1
3 min read
FERPA Compliance in RAG Pipelines: Five Rules Your Enterprise System Probably Breaks

FERPA Compliance in RAG Pipelines: Five Rules Your Enterprise System Probably Breaks

Comments
6 min read
Building a Context-Aware AI Code Reviewer with Memory – Hackathon Project

Building a Context-Aware AI Code Reviewer with Memory – Hackathon Project

Comments
1 min read
LangChain vs LlamaIndex vs Haystack: Lo que aprendĂ­ construyendo RAG en producciĂłn

LangChain vs LlamaIndex vs Haystack: Lo que aprendĂ­ construyendo RAG en producciĂłn

1
Comments
7 min read
🍎 Your Health Data Stays Local: Building a Private RAG with Llama 3, MLX, and Apple Silicon

🍎 Your Health Data Stays Local: Building a Private RAG with Llama 3, MLX, and Apple Silicon

2
Comments
4 min read
Building RAG with pgvector: Why I Stopped Paying for Pinecone

Building RAG with pgvector: Why I Stopped Paying for Pinecone

1
Comments
6 min read
Work before work: Why Multi-Client AI Work Steals Your Best Build Hours (and How to Fix It)

Work before work: Why Multi-Client AI Work Steals Your Best Build Hours (and How to Fix It)

1
Comments
5 min read
Build an Simple AI Assistant Using PromptTemplate & LangChain

Build an Simple AI Assistant Using PromptTemplate & LangChain

Comments
4 min read
Como o RAG está sendo usado na indústria de software: o que dizem 26 estudos

Como o RAG está sendo usado na indústria de software: o que dizem 26 estudos

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