Retrieval
Retrieval selects the chunks most likely to contain evidence for the user’s question.
Retrieval selects the chunks most likely to contain evidence for the user’s question.
Represent what the user needs.
Fetch several plausible chunks.
Send only the best evidence onward.
Understand the working model
Good retrieval balances recall and precision. If you retrieve too little, you may miss the answer. If you retrieve too much, irrelevant text can distract the model and increase cost.
Inspect retrieval separately from answer generation. If the correct chunk never reaches the model, improving the final prompt cannot fix the real problem.
Practice
Apply the pattern above to one real task you already do. Keep the first version small enough that you can inspect every input and output.
Do not judge a RAG system only by whether the final answer sounds good.
Evaluate whether retrieval found the right evidence before evaluating the generated answer.