Become an AI engineer

Retrieval and tools

Retrieval and tools is a unit of 9 lessons in Rabbithole's Become an AI engineer course, at levels 3 to 4.

Lessons

1. BM25: search that matches the exact wordsLevel 3
2. Chunking: cutting text into pieces that retrieve wellLevel 3
3. Hybrid Search with MongoDB $rankFusionLevel 3
4. Knowledge Graphs for RAGLevel 3
5. Retrieval-Augmented GenerationLevel 3
6. Vector SearchLevel 3
7. Reranking: re-scoring the short listLevel 3
8. Contextual Retrieval: Giving Each Chunk Its ContextLevel 4
9. ReAct: thinking and acting in one loopLevel 4

Sources

These lessons draw on 18 sources. The most used:

• Claude Cookbooks
• Supabase Documentation
• openai/openai-cookbook
• Improving language models by retrieving from trillions of tokens
• Anthropic Engineering blog
• REALM: Retrieval-Augmented Language Model Pre-Training
• Hugging Face Agents Course
• ReAct: Synergizing Reasoning and Acting in Language Models

All units in Become an AI engineer