(Retrieval-Augmented Generation)
Make a chatbot that answers from your own documents — fully on your laptop, in about half an hour.
A free, hands-on tutorial: build a RAG (retrieval-augmented generation) chatbot that answers questions from your own documents instead of making things up. Retrieve relevant text with embeddings, feed it to a local language model with Ollama, and get grounded, cited answers. Runs entirely on your laptop, no API key.
RAG is how AI assistants answer from company wikis, product docs and support articles, cite their sources, and stay current — the pattern behind most real-world business chatbots.
Collect and chunk your documents, then embed them into a searchable index — the retriever from the last course.
Turn a question into a query and pull the handful of chunks most likely to hold the answer.
Stuff the retrieved context into a prompt, send it to the local model, and get an answer grounded in your docs.