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.
Modern Search Techniques for Vector Databases (w/LangChain)

Modern Search Techniques for Vector Databases (w/LangChain)

1
Comments
4 min read
Our RAG system still failed on hierarchical metrics — Part 2

Our RAG system still failed on hierarchical metrics — Part 2

5
Comments
6 min read
đź§  Beyond Chatbots: Building 'Echo-Learn', an Agentic AI Tutor with Biological Memory

đź§  Beyond Chatbots: Building 'Echo-Learn', an Agentic AI Tutor with Biological Memory

1
Comments
4 min read
RAG Without the Internet - Lessons From Building an Internal-Only AI Assistant on Markdown and Confluence

RAG Without the Internet - Lessons From Building an Internal-Only AI Assistant on Markdown and Confluence

1
Comments
6 min read
Our RAG system failed to understand KPIs — Part 1: Metric retrieval design

Our RAG system failed to understand KPIs — Part 1: Metric retrieval design

4
Comments
5 min read
Building RAG Systems: From Zero to Hero

Building RAG Systems: From Zero to Hero

3
Comments
19 min read
Top LLM Tools Companies Are Using to Add AI to Their Products in 2025

Top LLM Tools Companies Are Using to Add AI to Their Products in 2025

1
Comments 1
6 min read
The Perfect Extraction: Unlocking Unstructured Data with Docling + LangExtract 🚀

The Perfect Extraction: Unlocking Unstructured Data with Docling + LangExtract 🚀

1
Comments
3 min read
RAG Chunking Strategies Deep Dive

RAG Chunking Strategies Deep Dive

1
Comments
7 min read
Why RAG and Agent Systems Are Unstable — A Minimal Deterministic Planner POC

Why RAG and Agent Systems Are Unstable — A Minimal Deterministic Planner POC

Comments 1
2 min read
Build a Multi-Tenant RAG with Fine-Grain Authorization using Motia and SpiceDB

Build a Multi-Tenant RAG with Fine-Grain Authorization using Motia and SpiceDB

1
Comments
20 min read
Build a Knowledge-Based Q&A Bot using Bedrock + S3 + DynamoDB/OpenSearch via AWS CDK

Build a Knowledge-Based Q&A Bot using Bedrock + S3 + DynamoDB/OpenSearch via AWS CDK

1
Comments
25 min read
Beyond Simple RAG: Building an Agentic Workflow with Next.js, Python, and Supabase

Beyond Simple RAG: Building an Agentic Workflow with Next.js, Python, and Supabase

Comments 1
2 min read
Building an AI Assistant That Actually Understands Company Policy

Building an AI Assistant That Actually Understands Company Policy

Comments
3 min read
Can tools automate ingestion and chunking steps reliably?

Can tools automate ingestion and chunking steps reliably?

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