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

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

5
Comments 3
3 min read
Building Nexus: An Enterprise-Grade RAG & LLMOps Engine from Scratch

Building Nexus: An Enterprise-Grade RAG & LLMOps Engine from Scratch

Comments
4 min read
Your AI Forgets Everything. Here's How Cognee Fixes It.

Your AI Forgets Everything. Here's How Cognee Fixes It.

28
Comments 6
3 min read
I Designed a RAG Variant for Multi-Agent Simulations. Here's the Design and the Honest Tradeoffs.

I Designed a RAG Variant for Multi-Agent Simulations. Here's the Design and the Honest Tradeoffs.

2
Comments 3
9 min read
I built a 100% local Graph RAG engine for my Markdown notes

I built a 100% local Graph RAG engine for my Markdown notes

Comments
3 min read
Building Corroborate.ai: An Auditable Way to Decide What an AI Actually "Knows"

Building Corroborate.ai: An Auditable Way to Decide What an AI Actually "Knows"

3
Comments 2
9 min read
38/60 Days System Design Questions

38/60 Days System Design Questions

3
Comments 7
1 min read
You can't debug a RAG you didn't instrument

You can't debug a RAG you didn't instrument

3
Comments 28
3 min read
The Hidden Danger in Your n8n RAG Pipeline: What Happens When You Send Internal Docs to ChatGPT?

The Hidden Danger in Your n8n RAG Pipeline: What Happens When You Send Internal Docs to ChatGPT?

Comments 2
11 min read
LangGraph Production, RAG Memory Challenges, and AI Agent Patterns

LangGraph Production, RAG Memory Challenges, and AI Agent Patterns

Comments
3 min read
Stop Chunking Your Relationships: Why We Paired a Knowledge Graph with a Vector DB

Stop Chunking Your Relationships: Why We Paired a Knowledge Graph with a Vector DB

3
Comments 4
3 min read
OmniRetrieval: Source-Native Query Dispatch

OmniRetrieval: Source-Native Query Dispatch

Comments
6 min read
The .txt File as the Soul of a Personal AI — FileRAG Memory Architecture

The .txt File as the Soul of a Personal AI — FileRAG Memory Architecture

2
Comments
4 min read
I Scored 10,000 Job Listings a Day With GPT-4. Here's What Broke

I Scored 10,000 Job Listings a Day With GPT-4. Here's What Broke

Comments
4 min read
A RAG evaluator that admits what it can't judge

A RAG evaluator that admits what it can't judge

Comments 3
2 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.