Core Concepts to Understand First

Vector Embeddings – How text is converted into numerical vectors that capture semantic meaning

Vector Databases – How these embeddings are stored and efficiently searched

Semantic Search – Finding relevant information based on meaning rather than keywords

Retrieval Strategies – Various approaches to find the most relevant information

Understanding Chunking in RAG Systems

Evaluation Metrics – How to measure RAG system performance

check this thread:
https://learnwithhasan.com/forum/discussion/rag-agents-implementation-in-python/

RAG today is simple as a prototype implementation like chat with docs or pdfs, there are thousands of tutorials and codes out there, the hard part is implementing in production, evaluating, monitoring, and scaling.