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.
Why RAG Fails for Ground-Truth Data | Nainik Mehta

Why RAG Fails for Ground-Truth Data | Nainik Mehta

Comments 1
3 min read
Docs-as-Evals: The New Job Technical Writers Didn’t Expect

Docs-as-Evals: The New Job Technical Writers Didn’t Expect

Comments 4
6 min read
Self-hosting AnythingLLM: the three settings that decide whether your workspaces survive a redeploy

Self-hosting AnythingLLM: the three settings that decide whether your workspaces survive a redeploy

Comments 1
3 min read
Wabe Labs Is Born, and Building With Blueprints

Wabe Labs Is Born, and Building With Blueprints

Comments 1
5 min read
Building a RAG-Powered Chatbot That Lets You Talk to Your Codebase

Building a RAG-Powered Chatbot That Lets You Talk to Your Codebase

Comments
2 min read
RAG Has a Routing Problem: Knowing Which Knowledge Source to Trust

RAG Has a Routing Problem: Knowing Which Knowledge Source to Trust

7
Comments
13 min read
How I Built a Bilingual RAG-Powered AI Calling & Chat Agent (With a Full Admin Ops Center)

How I Built a Bilingual RAG-Powered AI Calling & Chat Agent (With a Full Admin Ops Center)

1
Comments 1
3 min read
Nextpage – the missing next-page button for AI chat

Nextpage – the missing next-page button for AI chat

Comments
2 min read
RAG Retrieval Can Look Relevant and Still Be Wrong

RAG Retrieval Can Look Relevant and Still Be Wrong

Comments 1
2 min read
A five-minute test for any RAG assistant: two documents with conflicting dates

A five-minute test for any RAG assistant: two documents with conflicting dates

1
Comments 3
2 min read
Building Complete RAG AI Package- AI Curt

Building Complete RAG AI Package- AI Curt

1
Comments 1
3 min read
No citation, no claim: building a RAG backend that refuses to hallucinate"

No citation, no claim: building a RAG backend that refuses to hallucinate"

1
Comments 1
4 min read
Building an Internal AI Assistant on AWS: A Production-Ready RAG Architecture with Amazon Bedrock

Building an Internal AI Assistant on AWS: A Production-Ready RAG Architecture with Amazon Bedrock

1
Comments
15 min read
How I stopped an LLM from fabricating citations

How I stopped an LLM from fabricating citations

Comments
5 min read
Vector Databases: The Foundation of Modern AI Applications

Vector Databases: The Foundation of Modern AI Applications

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