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.
The Unit of Return: a 4-Arm Retrieval Experiment on a Real Codebase

The Unit of Return: a 4-Arm Retrieval Experiment on a Real Codebase

3
Comments 2
12 min read
Retrieval, tools, or fine-tuning: how to decide for a voice agent

Retrieval, tools, or fine-tuning: how to decide for a voice agent

Comments
1 min read
Your Company Does Not Need Another AI Chatbot. It Needs a Knowledge Layer.

Your Company Does Not Need Another AI Chatbot. It Needs a Knowledge Layer.

Comments
12 min read
How to Flag Stale RAG Documents Before Generation

How to Flag Stale RAG Documents Before Generation

Comments
5 min read
I Built a Local RAG Pipeline with TypeScript, PostgreSQL and pgvector

I Built a Local RAG Pipeline with TypeScript, PostgreSQL and pgvector

Comments
4 min read
Healthcare RAG: Test the Claim-to-Source Contract

Healthcare RAG: Test the Claim-to-Source Contract

Comments
14 min read
3 Production GenAI Lessons From Building a RAG App on AWS

3 Production GenAI Lessons From Building a RAG App on AWS

Comments
2 min read
My RAG evaluation was lying to me, twice!!

My RAG evaluation was lying to me, twice!!

Comments
7 min read
Self-Hosted Deep Research Systems: 12 Tools Compared

Self-Hosted Deep Research Systems: 12 Tools Compared

Comments 1
18 min read
RAG Explained: A Beginner's Guide to Retrieval-Augmented Generation

RAG Explained: A Beginner's Guide to Retrieval-Augmented Generation

Comments
8 min read
Hexagonal Architecture for Provider-Agnostic RAG Pipelines

Hexagonal Architecture for Provider-Agnostic RAG Pipelines

Comments
6 min read
Your RAG Searches by Meaning. But What About Exact Words? Meet BM25

Your RAG Searches by Meaning. But What About Exact Words? Meet BM25

7
Comments 2
4 min read
PDF URLs to clean text and RAG chunks with one API call

PDF URLs to clean text and RAG chunks with one API call

Comments
3 min read
When an AI Agent Context Reaches 261k Tokens

When an AI Agent Context Reaches 261k Tokens

Comments 1
1 min read
Dragnet: an agentic fraud investigator on TigerGraph

Dragnet: an agentic fraud investigator on TigerGraph

Comments
10 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.