Learn to use AI

# Retrieval and tools

Retrieval and tools is a unit of 7 lessons in Rabbithole's Learn to use AI course, at level 2. The same lessons are also in Become an AI engineer as “Retrieval and tools, plainly”.

## Lessons

1. BM25: when exact words matter · Level 2
2. Chunking: cutting long text down to size · Level 2
3. Hybrid search: words plus meaning · Level 2
4. Knowledge graphs for RAG: linking facts across documents · Level 2
5. RAG: giving an AI a lookup memory · Level 2
6. Reranking: a second look at search results · Level 2
7. ReAct: an AI that thinks, then acts, then checks · Level 2

## Sources

These lessons draw on 10 sources. The most used:

- [Claude Cookbooks](https://github.com/anthropics/claude-cookbooks)
- [Supabase Documentation](https://supabase.com/docs)
- [openai/openai-cookbook](https://github.com/openai/openai-cookbook)
- [Anthropic Engineering blog](https://www.anthropic.com/engineering)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://arxiv.org/abs/2005.11401)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://arxiv.org/abs/2210.03629)
- [Hugging Face Agents Course](https://github.com/huggingface/agents-course)
- [Vercel Documentation](https://vercel.com/docs)

[All units in Learn to use AI](https://rabbithole.pro/courses/learn-ai)

Source page: https://rabbithole.pro/courses/learn-ai/retrieval-and-tools