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.
No ratings yet.
Sign in to leave a rating. Sign in
Use @handle to bring somebody in, and #tag to file it.
Nothing here yet. Ask a question, or say how you used it.
Sign in to join the discussion. Sign in
2 min read
2 min read
2 min read
2 min read
From a promising demo to something you can operate: scope, evaluation, interface and rollout.
Build test sets, grade outputs with code, people and model-based graders, and catch regressions before your users do.
How LLM agents call tools in a loop, how to design tools they use well, and how to keep agents safe and reliable.