Fine-Tuning vs RAG
The strategic decision between customizing a model's weights (fine-tuning) or providing external knowledge at inference time (RAG). Each approach has different strengths and use cases.
Why It Matters
This is the most common architectural decision in enterprise AI. Choosing wrong means either unnecessary cost (fine-tuning) or poor quality (inadequate RAG).
Example
Fine-tuning for a medical chatbot that needs to 'speak doctor.' RAG for a support bot that needs access to frequently updated documentation.
Think of it like...
Like the choice between hiring a specialist (fine-tuning) or giving a generalist access to reference books (RAG) — depends on whether you need deep expertise or broad, current knowledge.
Related Terms
Fine-Tuning
The process of taking a pre-trained model and further training it on a smaller, domain-specific dataset to specialize its behavior for a particular task or domain. Fine-tuning adjusts the model's weights to improve performance on the target task.
Retrieval-Augmented Generation
A technique that enhances LLM outputs by first retrieving relevant information from external knowledge sources and then using that information as context for generation. RAG combines the power of search with the fluency of language models.
Knowledge Base
A structured or semi-structured collection of information used by AI systems to retrieve factual data. In the context of RAG, it typically refers to the document collection that the system can search.
Large Language Model
A type of AI model trained on massive amounts of text data that can understand and generate human-like text. LLMs use transformer architecture and typically have billions of parameters, enabling them to perform a wide range of language tasks.