🤖AI & Agentic
🔧Intermediate
RAG Systems
Retrieval-Augmented Generation - combining search with LLMs for grounded, accurate responses
StatusNot Started
What is RAG?
Retrieval-Augmented Generation connects LLMs to external knowledge bases, allowing them to:
- Access up-to-date information
- Cite sources
- Reduce hallucinations
- Work with private/proprietary data
Topics to Cover
- Vector embeddings and similarity search
- Chunking strategies for documents
- Vector databases (Pinecone, Weaviate, Chroma)
- Hybrid search (semantic + keyword)
- Reranking retrieved results
- Prompt construction with context
Resources
LangChain RAG Tutorial
Pinecone Vector Database Docs
Llamaindex Documentation