RetrievalDiversityScorer
Evaluates diversity of retrieved context chunks using cosine distance between embeddings. Higher scores indicate more diverse retrieved content, reducing redundancy in results.
Overview
Evaluates diversity of retrieved context chunks using cosine distance between embeddings. Higher scores indicate more diverse retrieved content, reducing redundancy in results.
Use Cases
- RAG-based question answering systems
How It Works
This scorer uses deterministic rule-based evaluation to validate outputs against specific criteria. It applies predefined rules and patterns to assess the response, providing consistent and reproducible results without requiring LLM inference.
Input Schema
| Parameter | Type | Required | Description |
|---|---|---|---|
| context.chunks | list[str] | Yes | At least 2 chunks for diversity comparison |
Output Schema
| Field | Type | Description |
|---|---|---|
| diversity | float | Diversity score (0-10, higher = more diverse) |
Score Interpretation
Default threshold: 6/10
Related Scorers
SemanticSimilarityScorer
Computes semantic similarity between query and retrieved context using sentence embeddings. Uses cos...
Basic RAGContextualPrecisionScorerPP
Computes precision for retrieved chunks using numerical relevance scoring. Precision = (Number of re...
Basic RAGContextualRecallScorerPP
Computes recall for retrieved chunks by estimating total relevant chunks available. Recall = (Number...
Basic RAGRetrievalF1Scorer
F1 score combining precision and recall for contextual evaluation. Computes harmonic mean of precisi...
Frequently Asked Questions
When should I use this scorer?
Use RetrievalDiversityScorer when you need to evaluate rag and rule-based aspects of your AI outputs. It's particularly useful for rag-based question answering systems.
Why doesn't this scorer need expected output?
This scorer evaluates quality aspects that don't require comparison against a reference answer. It uses the system prompt and context as the implicit ground truth.
Can I customize the threshold?
Yes, the default threshold of 6 can be customized when configuring the scorer.
Quick Info
Ready to try RetrievalDiversityScorer?
Start evaluating your AI agents with Noveum.ai's comprehensive scorer library.
Explore More Scorers
Discover 106 calibrated LLM-as-Judge scorers for comprehensive AI evaluation