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.
Apex B. OpenClaw, Local Embeddings.

Apex B. OpenClaw, Local Embeddings.

Comments
2 min read
When building AI chat is actually hard (how and why we built our agents)

When building AI chat is actually hard (how and why we built our agents)

Comments 1
6 min read
I Built Student Memory Into Groq Prompts Via Hindsight

I Built Student Memory Into Groq Prompts Via Hindsight

2
Comments
10 min read
Re-ranking Isn't Just Sorting Your Search Results (Anthropic Academy Part 3)

Re-ranking Isn't Just Sorting Your Search Results (Anthropic Academy Part 3)

Comments
3 min read
Advanced RAG: Parsing Complex Medical PDFs with LayoutLMv3 and LlamaIndex

Advanced RAG: Parsing Complex Medical PDFs with LayoutLMv3 and LlamaIndex

1
Comments
3 min read
Stop over-engineering your n8n RAG pipeline before you've shipped anything

Stop over-engineering your n8n RAG pipeline before you've shipped anything

1
Comments
4 min read
What we learned from 100+ production RAG deployments (free 118-page handbook)

What we learned from 100+ production RAG deployments (free 118-page handbook)

Comments
1 min read
Simple RAG Application in .NET (Clean Architecture + Aspire)

Simple RAG Application in .NET (Clean Architecture + Aspire)

1
Comments 1
2 min read
Cracking the Databricks Generative AI Engineer Certification

Cracking the Databricks Generative AI Engineer Certification

3
Comments 2
4 min read
Run LLMs locally in Flutter apps

Run LLMs locally in Flutter apps

1
Comments
6 min read
Why Your AI Cites Real Sources That Never Said That (And the 3-Layer Fix)

Why Your AI Cites Real Sources That Never Said That (And the 3-Layer Fix)

Comments 1
6 min read
Loreguard.com - Built a NPC AI Engine that runs on player's machine (no pay-per-token)

Loreguard.com - Built a NPC AI Engine that runs on player's machine (no pay-per-token)

1
Comments
7 min read
Hybrid Knowledge Retrieval: Combining Neo4j Graph Queries, GraphRAG and Vector Search for Enterprise LLM Applications

Hybrid Knowledge Retrieval: Combining Neo4j Graph Queries, GraphRAG and Vector Search for Enterprise LLM Applications

5
Comments 1
12 min read
What MCP Actually Is (And Why It Exists)

What MCP Actually Is (And Why It Exists)

2
Comments 3
4 min read
Engineering GraphRAG for Production: API Design, Query Optimization, and Service Reliability

Engineering GraphRAG for Production: API Design, Query Optimization, and Service Reliability

5
Comments
6 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.