Forem

# 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.
🧠 Build a Document Search with RAG | Hugging Face Transformers + Flan-T5 + NLP Tutorial
Cover image for 🧠 Build a Document Search with RAG | Hugging Face Transformers + Flan-T5 + NLP Tutorial

🧠 Build a Document Search with RAG | Hugging Face Transformers + Flan-T5 + NLP Tutorial

Comments
2 min read
RAG with MongoDB Vector Search PART 1
Cover image for RAG with MongoDB Vector Search PART 1

RAG with MongoDB Vector Search PART 1

6
Comments 1
5 min read
RAG is more than Vector Search

RAG is more than Vector Search

1
Comments
4 min read
🚀 How I Created an AI-Powered Secret Santa Using Cognee as the Memory Layer
Cover image for 🚀 How I Created an AI-Powered Secret Santa Using Cognee as the Memory Layer

🚀 How I Created an AI-Powered Secret Santa Using Cognee as the Memory Layer

10
Comments 4
5 min read
✌️5 AI Document Parsing Tools That Actually Work 🚀🔥
Cover image for ✌️5 AI Document Parsing Tools That Actually Work 🚀🔥

✌️5 AI Document Parsing Tools That Actually Work 🚀🔥

134
Comments 10
11 min read
Build Better RAG Pipelines: Scraping Technical Docs to Clean Markdown

Build Better RAG Pipelines: Scraping Technical Docs to Clean Markdown

Comments 1
2 min read
Why your AI assistant lies to you (and how to fix it)
Cover image for Why your AI assistant lies to you (and how to fix it)

Why your AI assistant lies to you (and how to fix it)

Comments
4 min read
Beyond Vanilla RAG: The 7 Modern RAG Architectures Every AI Engineer Must Know
Cover image for Beyond Vanilla RAG: The 7 Modern RAG Architectures Every AI Engineer Must Know

Beyond Vanilla RAG: The 7 Modern RAG Architectures Every AI Engineer Must Know

7
Comments
15 min read
Cut AI Costs Without Losing Capability: The Rise of Small LLMs
Cover image for Cut AI Costs Without Losing Capability: The Rise of Small LLMs

Cut AI Costs Without Losing Capability: The Rise of Small LLMs

Comments
5 min read
You may not need pg_vector, sqlite-vss, etc.
Cover image for You may not need pg_vector, sqlite-vss, etc.

You may not need pg_vector, sqlite-vss, etc.

Comments
2 min read
LLMs as Unreliable Narrators: Dealing with UUID Hallucination

LLMs as Unreliable Narrators: Dealing with UUID Hallucination

8
Comments
5 min read
How to Convert JSON to TOON: 4 Methods Compared
Cover image for How to Convert JSON to TOON: 4 Methods Compared

How to Convert JSON to TOON: 4 Methods Compared

1
Comments
4 min read
Build a RAG App With Django MongoDB Backend in 30 minutes
Cover image for Build a RAG App With Django MongoDB Backend in 30 minutes

Build a RAG App With Django MongoDB Backend in 30 minutes

1
Comments
12 min read
Title: LLMs for Your Business: Is it Better to Retrain the Brain or Give it an Open Book? (RAG vs. Fine-Tuning)
Cover image for Title: LLMs for Your Business: Is it Better to Retrain the Brain or Give it an Open Book? (RAG vs. Fine-Tuning)

Title: LLMs for Your Business: Is it Better to Retrain the Brain or Give it an Open Book? (RAG vs. Fine-Tuning)

Comments
4 min read
How to Design Two Practical Orchestration Loops for LLM Agents
Cover image for How to Design Two Practical Orchestration Loops for LLM Agents

How to Design Two Practical Orchestration Loops for LLM Agents

9
Comments
9 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.