Introduction to machine learning · Question 35 of 60
How does RAG work?
2 answers are correct. Medium
Show answer
Answer
- C Relevant documents are matched with the subject of the prompt and incorporated into an enhanced prompt
- D Task-specific data sources are transformed into a searchable format
Explanation
With RAG, task-specific data sources are transformed into a searchable format so that they can be compared with the subject of the prompt. Relevant documents are incorporated into an enhanced prompt that is passed to the LLM. The pretrained model is not changed.