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.
Your Agent Memory Is Trapped. Here's the Key.

Your Agent Memory Is Trapped. Here's the Key.

1
Comments
6 min read
I built a RAG platform because I was tired of spending 15 minutes searching for team docs

I built a RAG platform because I was tired of spending 15 minutes searching for team docs

Comments
3 min read
From Flat Files to a Living Memory: Building Graph-Based Semantic Memory for PocketPaw

From Flat Files to a Living Memory: Building Graph-Based Semantic Memory for PocketPaw

1
Comments
6 min read
RAG vs. Agent Memory vs. LLM Wiki: A Practical Comparison

RAG vs. Agent Memory vs. LLM Wiki: A Practical Comparison

4
Comments 1
8 min read
Long Context vs RAG: When to Load the Whole Book

Long Context vs RAG: When to Load the Whole Book

Comments 1
6 min read
A Three-Layer Memory Architecture for LLMs (Redis + Postgres + Vector) MCP

A Three-Layer Memory Architecture for LLMs (Redis + Postgres + Vector) MCP

Comments
2 min read
Sentence Window Retrieval

Sentence Window Retrieval

1
Comments
4 min read
How I used DDD and hexagonal architecture to build klay+ — a flexible, provider-agnostic RAG infrastructure you can plug into any project.

How I used DDD and hexagonal architecture to build klay+ — a flexible, provider-agnostic RAG infrastructure you can plug into any project.

Comments
5 min read
I Built an Open Source AI Memory Layer. The Legacy File System Will Eventually Die.

I Built an Open Source AI Memory Layer. The Legacy File System Will Eventually Die.

Comments
3 min read
I Built a Knowledge Graph Into the Retrieval Pipeline and Then Dropped It in Production

I Built a Knowledge Graph Into the Retrieval Pipeline and Then Dropped It in Production

1
Comments 1
5 min read
The Prompt Tax Most LLM Teams Are Silently Paying

The Prompt Tax Most LLM Teams Are Silently Paying

2
Comments
4 min read
RAG and Vector Databases:

RAG and Vector Databases:

1
Comments
2 min read
I built a GraphRAG demo with FalkorDB’s new SDK, then benchmarked it against Neo4j

I built a GraphRAG demo with FalkorDB’s new SDK, then benchmarked it against Neo4j

4
Comments 2
16 min read
Index-RAG: Citation-first approach to RAG

Index-RAG: Citation-first approach to RAG

1
Comments
5 min read
# The 5 memory problems for agents

# The 5 memory problems for agents

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