courses vs rag-from-scratch
Claude API learning and RAG fundamentals compared
courses teaches developers to use Claude through its API, with lessons on prompting, evaluation, and tool use. rag-from-scratch teaches the stages of retrieval-augmented generation through notebooks and an accompanying video playlist.

courses: Learn to Build with Anthropic's Claude API
Anthropic's courses is a set of educational notebooks and tutorials for learning to build with Claude, from API fundamentals and prompt engineering to evaluations and tool use. It suits developers and teams who want guided, practical exercises rather than a standalone software package.

rag-from-scratch: Learn Retrieval-Augmented Generation Step by Step
A Jupyter notebook series that teaches the building blocks of retrieval-augmented generation, from indexing and retrieval to generation. It is aimed at learners who want to understand RAG concepts through an educational progression rather than adopt a ready-made application.
| courses | rag-from-scratch | |
|---|---|---|
| Language | Jupyter Notebook | Jupyter Notebook |
| Stars | 23k | 9.4k |
| Forks | 2.5k | 2.2k |
| Last analyzed | Nov 2, 2026 | Oct 3, 2026 |
Key differences
- courses focuses on Claude API workflows, while rag-from-scratch covers RAG concepts and stages.
- courses progresses from API fundamentals to prompting, evaluation, and tool use; rag-from-scratch builds understanding around indexing, retrieval, and generation.
- courses is archived, while rag-from-scratch is not archived.
- courses lists its license as NOASSERTION; rag-from-scratch does not specify a license in the supplied project details.
- courses has 22.9k stars and 2.5k forks; rag-from-scratch has 9.4k stars and 2.2k forks.
Choose courses if you…
- want guided lessons on Claude API fundamentals and prompting.
- need to learn about prompt evaluation or tool use in Claude workflows.
- prefer a suggested learning sequence from API basics to tool use.
Choose rag-from-scratch if you…
- want to learn RAG through its indexing, retrieval, and generation stages.
- prefer notebooks accompanied by a video playlist.
- need introductory material before evaluating a RAG implementation for a knowledge-grounding problem.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.