The LLM Ops Playbooks
New course
fixed size chunking recursive chunking sliding window chunking semantic chunking sparse retrieval dense retrieval hybrid retrieval traditional alignment document domain alignment query domain alignment relevance scores perplexity and perplexity gain llm-based evaluation fact verification with a dedicated language model Chain of Thoughts (with examples) Tree of Thoughts Graph of Thoughts
Boost (RAG) information retrieval in 5 Days
From Chunking to RAG Performance
or login to view courses directly