1:56:20 Let's build GPT: from scratch, in code, spelled out. Andrej Karpathy
6.8M views · 149.3K likes · 3 years ago
What Is RAG?
Retrieval-Augmented Generation
RAG is a technique that enhances LLM responses by retrieving relevant documents from your data before generating an answer. Instead of relying solely on the model's training data, RAG grounds answers in your specific content — reducing hallucinations and keeping responses current.
How RAG Works
The RAG pipeline: (1) User asks a question. (2) Your system converts the question to an embedding vector. (3) It searches a vector database for similar documents. (4) The retrieved documents are added to the LLM prompt as context. (5) The LLM generates an answer grounded in that context.
RAG is how you build AI that knows about YOUR data — company docs, product manuals, codebases — without expensive fine-tuning. Tools like LangChain, LlamaIndex, and Vercel AI SDK make building RAG pipelines straightforward.
Why Developers Use RAG
RAG powers custom knowledge chatbots, documentation search, customer support bots, and internal tools. It's the #1 pattern for building AI applications on proprietary data because it's cheaper and more flexible than fine-tuning.
Key Concepts
- Vector Search — Finding similar documents by comparing embedding vectors using cosine similarity or dot product
- Chunking — Splitting documents into smaller pieces (500-1000 tokens) for more precise retrieval
- Context Window — RAG is limited by the LLM's context window — you can only inject so many retrieved documents
- Hybrid Search — Combining vector (semantic) search with keyword (BM25) search for better retrieval accuracy
Learn RAG — Top Videos
1:56:20 
34:05 ChatGPT Tutorial - A Crash Course on Chat GPT for Beginners Adrian Twarog
6M views · 86.2K likes · 3 years ago
3:31:24 
18:22 RAG Educators
Leila Gharani
@leilagharani
AI Coding
Excel. Power Query. Copilot. ChatGPT. Power BI. PowerPoint. You use them every day to automate Excel and your work - s...
3M Subs
625 Videos
117.7K Avg Views
3.06% Engagement
OpenAI
@openai
AI Coding
OpenAI’s mission is to ensure that artificial general intelligence benefits all of humanity.
1.9M Subs
456 Videos
36.2K Avg Views
2.18% Engagement
Academind
@academind
AI Coding
There's always something to learn! We create courses and tutorials on tech-related topics since 2016! We teach develop...
929K Subs
752 Videos
17K Avg Views
2.39% Engagement
Anthropic
@anthropic-ai
AI Coding
We’re an AI safety and research company. Talk to our AI assistant Claude on claude.com. Download Claude on desktop, iOS,...
441K Subs
170 Videos
263.4K Avg Views
2.23% Engagement
Frequently Asked Questions
What is the difference between RAG and fine-tuning?
RAG retrieves relevant context at query time. Fine-tuning modifies the model's weights on your data. RAG is cheaper, faster to set up, and handles dynamic data. Fine-tuning is better for changing the model's style or behavior.
What tools do I need for RAG?
An embedding model (OpenAI, Cohere), a vector database (Pinecone, Weaviate, Cloudflare Vectorize), and an LLM API. Frameworks like LangChain or LlamaIndex tie them together.
Want a structured learning path?
Plan a RAG Lesson →