What RAG Solves (Knowledge Cut-off, Hallucinations)
RAG retrieves relevant context at query time so the LLM cites real sources instead of making facts up.
Two Problems With Plain LLMs
Even the best LLMs have two structural problems:
- Knowledge cut-off — they only know what was in their training data. Ask GPT-4 about an event yesterday and it has no idea.
- Hallucination — when the model does not know, it confidently makes things up.
What RAG Is
Retrieval-Augmented Generation (RAG) means:
- Search a knowledge base for relevant chunks
- Stuff those chunks into the prompt
- Ask the LLM to answer using ONLY those chunks
The model becomes a "reader" over external knowledge instead of relying on its frozen weights.
All lessons in this course
- What RAG Solves (Knowledge Cut-off, Hallucinations)
- Chunking Strategies (Fixed, Sentence, Semantic)
- Indexing a Document Set
- Building a Naive RAG with FAISS or Chroma