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.
Compound AI Systems: How I Connect Multiple Models in a Single Production Product

Compound AI Systems: How I Connect Multiple Models in a Single Production Product

Comments
2 min read
Why Your LLM Ignores Detailed Instructions (It's Not a Bug)

Why Your LLM Ignores Detailed Instructions (It's Not a Bug)

Comments
2 min read
Most GenAI chatbot tutorials stop at “call an LLM get an answer.”

Most GenAI chatbot tutorials stop at “call an LLM get an answer.”

Comments
1 min read
🚀 Beyond RAG: Simulating the Future with MiroFish

🚀 Beyond RAG: Simulating the Future with MiroFish

2
Comments
2 min read
Perfect Retrieval Recall on LongMemEval — Running Fully Local

Perfect Retrieval Recall on LongMemEval — Running Fully Local

Comments 1
4 min read
I Ran 500 More Agent Memory Experiments. The Real Problem Wasn’t Recall. It Was Binding.

Rigor beyond happy-path testing

I Ran 500 More Agent Memory Experiments. The Real Problem Wasn’t Recall. It Was Binding.

56
Comments 29
14 min read
Beyond Vector Search: Building a Clause Forest (FoC) Architecture for Financial RAG

Beyond Vector Search: Building a Clause Forest (FoC) Architecture for Financial RAG

Comments
7 min read
đź§  Streaming LLM APIs Can Quietly Give Free Tokens

đź§  Streaming LLM APIs Can Quietly Give Free Tokens

Comments
1 min read
How I caught a silent NaN bug in production RAG, by asking the system to debug itself

How I caught a silent NaN bug in production RAG, by asking the system to debug itself

Comments
6 min read
Measuring RAG vs. Fine-tuning ROI for Agent Knowledge

Measuring RAG vs. Fine-tuning ROI for Agent Knowledge

Comments
9 min read
Neo4j graph database for GraphRAG, install, Cypher, vectors, ops

Neo4j graph database for GraphRAG, install, Cypher, vectors, ops

Comments
6 min read
From 62% to 94% RAG Accuracy: The 5 Architecture Changes That Actually Moved the Needle

From 62% to 94% RAG Accuracy: The 5 Architecture Changes That Actually Moved the Needle

1
Comments
8 min read
Run LLMs locally in Flutter apps

Run LLMs locally in Flutter apps

Comments
6 min read
How Hindsight Turned Repeated Questions Into a Student Profile

How Hindsight Turned Repeated Questions Into a Student Profile

Comments 1
6 min read
Testing AI: How to Effectively Evaluate LLMs

Testing AI: How to Effectively Evaluate LLMs

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