Retrieval Quality
A measure of how relevant and accurate the documents retrieved by a search or RAG system are relative to the user's query. Poor retrieval quality is the leading cause of RAG failures.
Why It Matters
Retrieval quality is the single biggest lever for improving RAG systems. Improving retrieval from 70% to 90% relevance often matters more than switching to a better LLM.
Example
Measuring that for 85% of test queries, the correct source document appears in the top 3 retrieved results — and identifying the 15% failure cases for improvement.
Think of it like...
Like the quality of ingredients in cooking — even the best chef cannot make a great meal with poor ingredients, and even the best LLM cannot generate good answers from irrelevant documents.
Related Terms
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.
Retrieval Evaluation
Methods for measuring how well a retrieval system finds relevant documents. Key metrics include recall at K, mean reciprocal rank, and normalized discounted cumulative gain.
Semantic Search
Search that understands the meaning and intent behind a query rather than just matching keywords. It uses embeddings to find results that are conceptually related even if they use different words.
Hybrid Search
A search approach that combines keyword-based (lexical) search with semantic (vector) search to get the benefits of both — exact matching for specific terms and meaning-based matching for conceptual queries.
Reranking
A second-stage ranking process that takes initial search results and reorders them using a more sophisticated model. Reranking improves precision by applying deeper analysis to a smaller candidate set.