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.
Qdrant TypeScript in 2026: use query(), not stale search() examples

Qdrant TypeScript in 2026: use query(), not stale search() examples

Comments 1
3 min read
How to Tell When Your LLM's Knowledge Actually Stops

How to Tell When Your LLM's Knowledge Actually Stops

Comments
2 min read
When Your AI Confidently Replies to Emails It Shouldn't Touch

When Your AI Confidently Replies to Emails It Shouldn't Touch

1
Comments 2
7 min read
How MCP fetch servers keep getting SSRF wrong (and how I tried not to)

How MCP fetch servers keep getting SSRF wrong (and how I tried not to)

1
Comments
6 min read
BM25 Length Normalization: Why Long RAG Chunks Never Rank

BM25 Length Normalization: Why Long RAG Chunks Never Rank

Comments
7 min read
Closer look on DynamoDB vector search vs S3 Vectors

Closer look on DynamoDB vector search vs S3 Vectors

Comments
10 min read
ADR: Who Owns Scope in a Node.js Multi-Tenant Ask-Docs SaaS?

ADR: Who Owns Scope in a Node.js Multi-Tenant Ask-Docs SaaS?

Comments
7 min read
AI agent codebase semantic RAG: AST for 30% Fewer Hallucinations

AI agent codebase semantic RAG: AST for 30% Fewer Hallucinations

Comments
9 min read
Building a RAG System From Scratch — Four Components, One Working Pipeline

Building a RAG System From Scratch — Four Components, One Working Pipeline

Comments
5 min read
Building Meeting Audio RAG on Microsoft Foundry with Fast Transcription and Foundry IQ

Building Meeting Audio RAG on Microsoft Foundry with Fast Transcription and Foundry IQ

1
Comments
16 min read
RAG Database with VLM as Extractor

RAG Database with VLM as Extractor

Comments
3 min read
Signed, verifiable receipts for RAG answers: what they actually prove

Signed, verifiable receipts for RAG answers: what they actually prove

Comments
5 min read
Dify vs Custom Development: When Visual AI Workflows Actually Work (and When They Don't)

Dify vs Custom Development: When Visual AI Workflows Actually Work (and When They Don't)

Comments
6 min read
PDF RAG Summarization Runbook: Semantic Search, Embeddings, Rerank, Final Summary

PDF RAG Summarization Runbook: Semantic Search, Embeddings, Rerank, Final Summary

Comments
7 min read
MCP vs RAG: Two AI Buzzwords, Explained Without the Buzzwords

MCP vs RAG: Two AI Buzzwords, Explained Without the Buzzwords

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