Turn text into vectors, build a semantic search index, and ground an LLM's answers in your own documents.
Retrieval-augmented generation (RAG) is the most common way to make a language model answer questions about your own documents. This course builds it from the ground up: embeddings, similarity search, chunking and finally the retrieval-plus-generation loop.
The examples use the all-MiniLM-L6-v2 model from the hub. Install with pip install sentence-transformers numpy.
4 lessons · 1 hr 10 min
Meaning as a position in space, and cosine similarity.
Embed a set of passages and rank them against a question.
How to split long documents so retrieval finds the right piece.
Put retrieval and generation together, and evaluate the result.
Sign in and enrol to leave a review.
No reviews yet — be the first once you have worked through it.
2 min read
2 min read
2 min read
2 min read
How LLMs work, how to write prompts that get reliable results, and how to check what comes back.
How LLM agents call tools in a loop, how to design tools they use well, and how to keep agents safe and reliable.
Build test sets, grade outputs with code, people and model-based graders, and catch regressions before your users do.