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.
RAG Series (19): Incremental Updates — Keeping the Knowledge Base Fresh

RAG Series (19): Incremental Updates — Keeping the Knowledge Base Fresh

2
Comments
6 min read
Llama.cpp's New MTP on MacOS

Llama.cpp's New MTP on MacOS

1
Comments
4 min read
The Amnesia Epidemic: Why the Next Era of Enterprise AI Requires "Hindsight"

The Amnesia Epidemic: Why the Next Era of Enterprise AI Requires "Hindsight"

Comments
4 min read
Build an End-to-End Smart Semantic Search App Using LangChain

Build an End-to-End Smart Semantic Search App Using LangChain

Comments
4 min read
Building a Biomedical GraphRAG Inference System: Comparing LLM-Only, Basic RAG, and GraphRAG Pipelines

Building a Biomedical GraphRAG Inference System: Comparing LLM-Only, Basic RAG, and GraphRAG Pipelines

1
Comments
3 min read
Applying RAG Architectures to Travel Knowledge Bases: A Practitioner's View

Applying RAG Architectures to Travel Knowledge Bases: A Practitioner's View

Comments
7 min read
LLM Prompting, AI-Generated Code Discussions & Python Workflow Automation

LLM Prompting, AI-Generated Code Discussions & Python Workflow Automation

Comments
3 min read
Building KernelMind, A Code-Aware Github Companion

Building KernelMind, A Code-Aware Github Companion

1
Comments 2
6 min read
Managing LLM Token Limits in Long MDX Articles

Managing LLM Token Limits in Long MDX Articles

Comments
5 min read
RAG- Understanding of Embedding

RAG- Understanding of Embedding

Comments
3 min read
Reducing LLM Hallucinations in 2026: LoRA, F-DPO, and the Math That Actually Works

Reducing LLM Hallucinations in 2026: LoRA, F-DPO, and the Math That Actually Works

Comments 1
13 min read
# Meet Hippo 🦛: A Python Native Alternative to Ollama for Local LLM Management

# Meet Hippo 🦛: A Python Native Alternative to Ollama for Local LLM Management

1
Comments
6 min read
The cracked mirror: why AI hallucination is structural, not a bug

The cracked mirror: why AI hallucination is structural, not a bug

1
Comments
6 min read
Building RAG Pipelines That Actually Work: Lessons from Microsoft Copilot

Building RAG Pipelines That Actually Work: Lessons from Microsoft Copilot

Comments
9 min read
RAG Series (18): Conversational RAG — The Pronoun Problem in Multi-Turn Dialogue

RAG Series (18): Conversational RAG — The Pronoun Problem in Multi-Turn Dialogue

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