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.
Semantic Caching and Live Internet Search: Tools That Let AI Cache Answers to Save Money, and Pull Data From the Web When It Needs To

Semantic Caching and Live Internet Search: Tools That Let AI Cache Answers to Save Money, and Pull Data From the Web When It Needs To

Comments
10 min read
CRM Semantic Search for Ask-Your-Docs: Node.js Embeddings via APIs or a Gateway

CRM Semantic Search for Ask-Your-Docs: Node.js Embeddings via APIs or a Gateway

Comments
6 min read
Turn any web page into LLM-ready Markdown for RAG

Turn any web page into LLM-ready Markdown for RAG

Comments
3 min read
Your AI agent can't read a scanned PDF. This gives it the text, page by page

Your AI agent can't read a scanned PDF. This gives it the text, page by page

Comments
2 min read
Cohere Rerank v5 Pro and Fast for C# Developers

Cohere Rerank v5 Pro and Fast for C# Developers

Comments
10 min read
I wrote a 100-topic AI engineer roadmap that runs offline, with no API key

I wrote a 100-topic AI engineer roadmap that runs offline, with no API key

Comments
2 min read
Turn any website into clean Markdown for your RAG pipeline (no boilerplate, with token counts)

Turn any website into clean Markdown for your RAG pipeline (no boilerplate, with token counts)

Comments
3 min read
Node.js Knowledge Retrieval — 3 Access Rules for Internal Storefront Runbooks

Node.js Knowledge Retrieval — 3 Access Rules for Internal Storefront Runbooks

Comments 2
7 min read
RAG and Beyond: LLM Wiki and Recursive Language Model (RLM)

RAG and Beyond: LLM Wiki and Recursive Language Model (RLM)

Comments
12 min read
Self-hosted LLM on Hostinger KVM2: under 10s responses, 2 CPU cores, no GPU. Here's how!

Self-hosted LLM on Hostinger KVM2: under 10s responses, 2 CPU cores, no GPU. Here's how!

Comments
1 min read
Building a Production RAG API in Go with pgvector and Gemini

Building a Production RAG API in Go with pgvector and Gemini

Comments
6 min read
RAG Application Using Python & HTML

RAG Application Using Python & HTML

Comments
11 min read
If persistence is not permission, where would you have drawn the line: cards only, or the entire turn?

If persistence is not permission, where would you have drawn the line: cards only, or the entire turn?

1
Comments
11 min read
Ragas: how to actually measure your RAG pipeline (faithfulness, context precision/recall, relevancy)

Ragas: how to actually measure your RAG pipeline (faithfulness, context precision/recall, relevancy)

Comments
8 min read
Q&A over internal documents: make the system say "not in the docs"

Q&A over internal documents: make the system say "not in the docs"

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