💬LLM & GenAI
📚
RAG Systems
Build Retrieval-Augmented Generation systems to ground LLMs with external knowledge
Prerequisites
🌱
Beginner
BeginnerRAG fundamentals
What to Learn
- •Why RAG? Limitations of parametric knowledge
- •Document chunking strategies
- •Embedding models for retrieval
- •Vector databases (Pinecone, Chroma, FAISS)
- •Basic RAG pipeline implementation
Resources
- 📚LangChain RAG tutorials
- 📚LlamaIndex documentation
- 📚Pinecone learning center
🌿
Intermediate
IntermediateProduction RAG systems
What to Learn
- •Hybrid search (semantic + keyword)
- •Reranking retrieved documents
- •Query transformation techniques
- •Evaluation metrics for RAG
- •Handling multi-modal content
Resources
- 📚RAGAS evaluation framework
- 📚Advanced RAG patterns blog posts
- 📚Cohere reranking documentation
🌳
Advanced
AdvancedAdvanced RAG research
What to Learn
- •Adaptive retrieval strategies
- •Self-RAG and corrective RAG
- •Graph RAG and knowledge graphs
- •Long-context vs RAG tradeoffs
- •Fine-tuning for retrieval
Resources
- 📚Self-RAG and CRAG papers
- 📚GraphRAG paper
- 📚RAPTOR and long-context RAG papers