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.
Retrieval Architecture for Support PDFs — Bounded Queries and Recovery

Retrieval Architecture for Support PDFs — Bounded Queries and Recovery

Comments
5 min read
Privacy-Focused PDF Retrieval with Node.js Chunk Boundaries and Citations

Privacy-Focused PDF Retrieval with Node.js Chunk Boundaries and Citations

Comments
5 min read
Which API returns LLM answers as markdown with inline citation positions?

Which API returns LLM answers as markdown with inline citation positions?

Comments
6 min read
Clinical RAG Retrieval Evaluation: 6 Evidence Gates That Matter Before Shipping

Clinical RAG Retrieval Evaluation: 6 Evidence Gates That Matter Before Shipping

Comments
6 min read
Architecting an Enterprise Clinical AI Platform: Solving Unstructured Medical Data, Hallucinations, and Terminology Mapping with AWS Services

Architecting an Enterprise Clinical AI Platform: Solving Unstructured Medical Data, Hallucinations, and Terminology Mapping with AWS Services

1
Comments
7 min read
Support RAG Cost Estimate — 3 Token Count Limits Before Batch Embeddings

Support RAG Cost Estimate — 3 Token Count Limits Before Batch Embeddings

Comments
8 min read
I tested my RAG retriever on terms it hadn't seen

I tested my RAG retriever on terms it hadn't seen

Comments 1
7 min read
RAG Without a Second Database

RAG Without a Second Database

Comments 1
7 min read
Vector Search Limits: Why Similar Records Cannot Answer Fintech Questions

Vector Search Limits: Why Similar Records Cannot Answer Fintech Questions

Comments
8 min read
Vector Search vs Web Search for Insurance Claims Intake: Audit Logs and Freshness

Vector Search vs Web Search for Insurance Claims Intake: Audit Logs and Freshness

Comments
7 min read
Citation Tracing for Retrieval Systems — Safer Healthcare Appointment Answers

Citation Tracing for Retrieval Systems — Safer Healthcare Appointment Answers

Comments
5 min read
Property Listing Discovery Schema: Bounded Retrieval Controls Index Cost

Property Listing Discovery Schema: Bounded Retrieval Controls Index Cost

Comments
6 min read
Postgres Metadata Filters: Multi-Tenant Vector Search Without Losing Relevant Answers

Postgres Metadata Filters: Multi-Tenant Vector Search Without Losing Relevant Answers

Comments
7 min read
How to Index Ecwid App Reviews in Python Without Mixing Rating Types

How to Index Ecwid App Reviews in Python Without Mixing Rating Types

Comments
6 min read
RAG vs Fine-Tuning vs Long Context: A Beginner Decision Guide

RAG vs Fine-Tuning vs Long Context: A Beginner Decision Guide

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