Module 20: Text Chunking & Embedding Techniques

• Understanding document splitting
• Hierarchical & semantic chunking
• Embedding types & use cases
• Retrieval strategies

Module 21: Retrieval-Augmented Generation (RAG)

• Why RAG is essential for accuracy
• Building complete RAG pipelines
• Query compression & reranking
• Graph-based RAG
• Enterprise-ready RAG workflows
  
  Module 22: LangChain Developer Track
• Core building blocks (LLMs, Chains, Tools, Memory)
• Creating agents with LangChain
• Multi-agent systems (CrewAI, AutoGen)
• Implementing tool calling
• Building an intelligent assistant app

Module 23: Vector Databases

• How vector databases work
• ChromaDB
• FAISS
• Pinecone
• Weaviate
• Qdrant
• Storing & retrieving embeddings