GenAI in Python

Get a comprehensive introduction to one of the most powerful techniques in modern AI development with this free sample chapter from Generative AI with Python: The Developer’s Guide to Pretrained LLMs, Vector Databases, Retrieval-Augmented Generation, and Agentic Systems. Chapter 6 breaks down retrieval-augmented generation (RAG) from first principles to practical implementation, giving you everything you need to build systems that go beyond what standard LLMs can do alone. You'll learn:

• How RAG works — the retrieval, augmentation, and generation pipeline explained clearly
• Building a working RAG system backed by a vector database, step by step in Python
• Advanced pre-retrieval techniques including data cleaning, metadata enhancement, and chunk size optimization
• Hybrid search combining dense vector search with keyword-based algorithms like BM25 and TF-IDF
• Query expansion, context enrichment, reciprocal rank fusion, and prompt compression
• Prompt caching — a cost-saving technique for handling large, repeated contexts
• Evaluating your RAG system using metrics like context precision, answer faithfulness, and answer relevance with RAGAS

Whether you're building internal knowledge tools, document Q&A systems, or anything that requires an LLM to work with your own data, this chapter gives you a solid, practical foundation.

• Ideal for developers and data scientists building LLM-powered applications
• Valuable for anyone who needs AI systems grounded in accurate, up-to-date information

Ready to go beyond out-of-the-box LLMs? Fill out the form below to get this free chapter delivered straight to your inbox.

Send Me the PDF

This download is taken from Chapter 6 of the book Generative AI with Python: The Developer’s Guide to Pretrained LLMs, Vector Databases, Retrieval-Augmented Generation, and Agentic Systems.