10 Introducing customized LLMs
This chapter covers
- Articulating how a lack of context impacts an LLM’s performance
- Outlining how Retrieval augmented generation works and its value
- Outlining how fine-tuning LLMs works and its value
- Comparing RAG and fine-tuning approaches
10.1 The challenge with LLMs and context
10.1.1 Tokens, context windows and limitations
10.1.2 Baking in context as a solution
10.2 Embedding context further into prompts and LLMs
10.2.1 Retrieval augmented generation
10.2.2 Fine-tuning Large Language Models
10.2.3 Comparing the two approaches
10.2.4 Combining RAG and fine-tuning
10.3 Summary