Embeddings, chunking, retrieval, and the RAG pipeline. Eight questions, 80% pass.
| Lesson | Concept |
|---|---|
| 1 | Embeddings — text as vectors, cosine similarity |
| 2 | Embedding API shape — fixed dim, float-valued, check the contract |
| 3 | Chunking — sentence vs fixed-window with overlap |
| 4 | Storing embeddings — dict + JSON round-trip |
| 5 | Semantic search — top-k by cosine |
| 6 | RAG pipeline — retrieve → stuff → generate |
Week 2: making it good — citations, failure modes, evals at scale, model routing, caching, parallel calls.
Create a free account to get started. Paid plans unlock all tracks.
Embeddings, chunking, retrieval, and the RAG pipeline. Eight questions, 80% pass.
| Lesson | Concept |
|---|---|
| 1 | Embeddings — text as vectors, cosine similarity |
| 2 | Embedding API shape — fixed dim, float-valued, check the contract |
| 3 | Chunking — sentence vs fixed-window with overlap |
| 4 | Storing embeddings — dict + JSON round-trip |
| 5 | Semantic search — top-k by cosine |
| 6 | RAG pipeline — retrieve → stuff → generate |
Week 2: making it good — citations, failure modes, evals at scale, model routing, caching, parallel calls.