Forem

# 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.
RAG debugging is harder than I expected

RAG debugging is harder than I expected

Comments
1 min read
Introduction to RAG (Retrieval-Augmented Generation)
Cover image for Introduction to RAG (Retrieval-Augmented Generation)

Introduction to RAG (Retrieval-Augmented Generation)

Comments
5 min read
The Compound Interest of AI Context: Why Your Knowledge Layer Will Be Your Most Valuable Business Asset

The Compound Interest of AI Context: Why Your Knowledge Layer Will Be Your Most Valuable Business Asset

Comments
4 min read
Vector Graph RAG: Multi-Hop RAG Without a Graph Database

Vector Graph RAG: Multi-Hop RAG Without a Graph Database

Comments 1
4 min read
I Tested 28 Query Pairs to See if Semantic Caches Actually Lie to Users. The Result Surprised Me
Cover image for I Tested 28 Query Pairs to See if Semantic Caches Actually Lie to Users. The Result Surprised Me

I Tested 28 Query Pairs to See if Semantic Caches Actually Lie to Users. The Result Surprised Me

7
Comments
11 min read
Notion + Twilio + WhatsApp = Give me what I want now

Notion + Twilio + WhatsApp = Give me what I want now

Comments
2 min read
From RAG to a “memory layer”: what building an AI assistant taught us
Cover image for From RAG to a “memory layer”: what building an AI assistant taught us

From RAG to a “memory layer”: what building an AI assistant taught us

Comments
3 min read
15 Engineering Decisions Behind RAG Hybrid Search
Cover image for 15 Engineering Decisions Behind RAG Hybrid Search

15 Engineering Decisions Behind RAG Hybrid Search

7
Comments
9 min read
I Built EvalGuard: A LLM Security & Evaluation Platform

I Built EvalGuard: A LLM Security & Evaluation Platform

Comments
6 min read
How We Cut Our AI API Bill by 78% (And Let Cursor See Our Entire Codebase)

How We Cut Our AI API Bill by 78% (And Let Cursor See Our Entire Codebase)

Comments
2 min read
AI Skills: Why the Future of Knowledge Alignment is in .md Files, Not Giant Datasets
Cover image for AI Skills: Why the Future of Knowledge Alignment is in .md Files, Not Giant Datasets

AI Skills: Why the Future of Knowledge Alignment is in .md Files, Not Giant Datasets

Comments
6 min read
RAG vs Fine-Tuning: When to Use Each AI Strategy
Cover image for RAG vs Fine-Tuning: When to Use Each AI Strategy

RAG vs Fine-Tuning: When to Use Each AI Strategy

Comments
6 min read
When Confident AI Becomes a Hidden Liability
Cover image for When Confident AI Becomes a Hidden Liability

When Confident AI Becomes a Hidden Liability

Comments
3 min read
Build Your Own AI Medical Brain: Transforming PDF Health Reports into a Graph-RAG Powerhouse with Neo4j and LangChain

Build Your Own AI Medical Brain: Transforming PDF Health Reports into a Graph-RAG Powerhouse with Neo4j and LangChain

1
Comments
4 min read
10 Years of Blood Reports into One Graph: Building a Personal Medical Knowledge Base with Unstructured.io, Neo4j, and LlamaIndex

10 Years of Blood Reports into One Graph: Building a Personal Medical Knowledge Base with Unstructured.io, Neo4j, and LlamaIndex

1
Comments
3 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.