MMR (Maximal Marginal Relevance)

MMR stage showing diversity-aware result selection

The MMR (Maximal Marginal Relevance) stage diversifies search results by iteratively selecting documents that are both relevant to the query and different from already-selected documents. This prevents redundant results and surfaces a broader range of relevant content.

Stage Category: SORT (Reorders with diversity)Transformation: N documents → top_k documents (diverse selection)

When to Use

Use Case	Description
Reduce redundancy	Avoid showing near-duplicate results
Exploration	Surface different aspects of a topic
Coverage	Ensure results span multiple subtopics
Recommendation diversity	Show varied options

When NOT to Use

Scenario	Recommended Alternative
Pure relevance ranking	`rerank`
Simple sorting	`sort_by_field`
Already diverse corpus	Skip MMR
Very small result sets	Not enough to diversify

Parameters

Parameter	Type	Default	Description
`lambda`	float	`0.7`	Balance: 0 = max diversity, 1 = max relevance
`top_k`	integer	`25`	Number of results to return
`diversity_feature_uri`	string	auto	Feature URI of the embedding used for diversity

Lambda Parameter

The lambda parameter controls the relevance-diversity trade-off:

Lambda	Behavior
`1.0`	Pure relevance (no diversification)
`0.7`	Slightly favor relevance
`0.5`	Balanced (default)
`0.3`	Favor diversity
`0.0`	Maximum diversity

Configuration Examples

{
  "stage_name": "mmr",
  "stage_type": "sort",
  "config": {
    "stage_id": "mmr",
    "parameters": {
      "lambda": 0.5,
      "top_k": 10
    }
  }
}

{
  "stage_name": "mmr",
  "stage_type": "sort",
  "config": {
    "stage_id": "mmr",
    "parameters": {
      "lambda": 0.3,
      "top_k": 15
    }
  }
}

{
  "stage_name": "mmr",
  "stage_type": "sort",
  "config": {
    "stage_id": "mmr",
    "parameters": {
      "lambda": 0.8,
      "top_k": 10
    }
  }
}

{
  "stage_name": "mmr",
  "stage_type": "sort",
  "config": {
    "stage_id": "mmr",
    "parameters": {
      "lambda": 0.5,
      "top_k": 20,
      "diversity_feature_uri": "mixpeek://text_extractor@v1/multilingual_e5_large_instruct_v1"
    }
  }
}

How MMR Works

The MMR algorithm iteratively selects documents using:

MMR = argmax[λ × Sim(doc, query) - (1-λ) × max(Sim(doc, selected_docs))]

First Selection: Choose the most relevant document
Subsequent Selections: Balance relevance against similarity to already-selected documents
Repeat: Until top_k documents are selected

Example Selection Process

Iteration	Selected	Reason
1	Doc A (0.95)	Highest relevance
2	Doc C (0.82)	High relevance, different from A
3	Doc E (0.78)	Good relevance, different from A & C
4	Doc B (0.90)	Skipped earlier due to similarity to A

Output Schema

{
  "document_id": "doc_123",
  "content": "Document content...",
  "score": 0.85,
  "mmr": {
    "relevance_score": 0.92,
    "diversity_penalty": 0.07,
    "mmr_score": 0.85,
    "selection_order": 3
  }
}

Performance

Metric	Value
Latency	10-50ms
Complexity	O(N × top_k)
Memory	O(N) embeddings
Cost	Free (no API calls)

Common Pipeline Patterns

Search + MMR

[
  {
    "stage_name": "semantic_search",
    "stage_type": "filter",
    "config": {
      "stage_id": "feature_search",
      "parameters": {
        "searches": [
          { "feature_uri": "mixpeek://text_extractor@v1/multilingual_e5_large_instruct_v1", "query": { "input_mode": "text", "value": "{{INPUT.query}}" }, "top_k": 100 }
        ],
        "final_top_k": 100
      }
    }
  },
  {
    "stage_name": "mmr",
    "stage_type": "sort",
    "config": {
      "stage_id": "mmr",
      "parameters": {
        "lambda": 0.5,
        "top_k": 10
      }
    }
  }
]

Search + Filter + MMR + Enrich

[
  {
    "stage_name": "hybrid_search",
    "stage_type": "filter",
    "config": {
      "stage_id": "feature_search",
      "parameters": {
        "searches": [
          { "feature_uri": "mixpeek://text_extractor@v1/multilingual_e5_large_instruct_v1", "query": { "input_mode": "text", "value": "{{INPUT.query}}" }, "top_k": 50 }
        ],
        "final_top_k": 50
      }
    }
  },
  {
    "stage_name": "structured_filter",
    "stage_type": "filter",
    "config": {
      "stage_id": "attribute_filter",
      "parameters": {
        "conditions": {
          "field": "metadata.category",
          "operator": "in",
          "value": ["tech", "science", "business"]
        }
      }
    }
  },
  {
    "stage_name": "mmr",
    "stage_type": "sort",
    "config": {
      "stage_id": "mmr",
      "parameters": {
        "lambda": 0.6,
        "top_k": 15
      }
    }
  },
  {
    "stage_name": "llm_enrichment",
    "stage_type": "enrich",
    "config": {
      "stage_id": "llm_enrich",
      "parameters": {
        "model": "gpt-4o-mini",
        "prompt": "Summarize in one sentence",
        "output_field": "summary"
      }
    }
  }
]

Diverse RAG Pipeline

[
  {
    "stage_name": "semantic_search",
    "stage_type": "filter",
    "config": {
      "stage_id": "feature_search",
      "parameters": {
        "searches": [
          { "feature_uri": "mixpeek://text_extractor@v1/multilingual_e5_large_instruct_v1", "query": { "input_mode": "text", "value": "{{INPUT.query}}" }, "top_k": 50 }
        ],
        "final_top_k": 50
      }
    }
  },
  {
    "stage_name": "mmr",
    "stage_type": "sort",
    "config": {
      "stage_id": "mmr",
      "parameters": {
        "lambda": 0.4,
        "top_k": 8
      }
    }
  },
  {
    "stage_name": "summarize",
    "stage_type": "reduce",
    "config": {
      "stage_id": "summarize",
      "parameters": {
        "provider": "openai",
        "model_name": "gpt-4o",
        "prompt": "Synthesize diverse perspectives on: {{INPUT.query}}\n\n{{DOCUMENTS}}"
      }
    }
  }
]

MMR vs Rerank

Aspect	MMR	Rerank
Goal	Diversity + relevance	Maximum relevance
Method	Embedding similarity	Cross-encoder scoring
Speed	Fast (10-50ms)	Slower (50-100ms)
Best for	Exploration, coverage	Precision, accuracy

Tuning Lambda

Use Case	Recommended Lambda
News aggregation	0.3-0.4 (high diversity)
Product search	0.5-0.6 (balanced)
Technical docs	0.7-0.8 (relevance focus)
Legal/compliance	0.8-0.9 (high precision)

Start with lambda=0.5 and adjust based on user feedback. If users complain about redundant results, lower lambda. If they miss relevant results, raise it.

Error Handling

Error	Behavior
Missing embeddings	Fall back to relevance sort
Empty input	Return empty
top_k > input size	Return all documents
Invalid lambda	Clamp to [0, 1]

Rerank - Pure relevance re-scoring
Sort Relevance - Simple score sorting
Sample - Random diversity

Get started

Connect your data

Extract features

Build retrievers

Enrich & organize

Integrate & operate

Resources

MMR (Maximal Marginal Relevance)

When to Use

When NOT to Use

Parameters

Lambda Parameter

Configuration Examples

How MMR Works

Example Selection Process

Output Schema

Performance

Common Pipeline Patterns

Search + MMR

Search + Filter + MMR + Enrich

Diverse RAG Pipeline

MMR vs Rerank

Tuning Lambda

Error Handling

​When to Use

​When NOT to Use

​Parameters

​Lambda Parameter

​Configuration Examples

​How MMR Works

​Example Selection Process

​Output Schema

​Performance

​Common Pipeline Patterns

​Search + MMR

​Search + Filter + MMR + Enrich

​Diverse RAG Pipeline

​MMR vs Rerank

​Tuning Lambda

​Error Handling

​Related

When to Use

When NOT to Use

Parameters

Lambda Parameter

Configuration Examples

How MMR Works

Example Selection Process

Output Schema

Performance

Common Pipeline Patterns

Search + MMR

Search + Filter + MMR + Enrich

Diverse RAG Pipeline

MMR vs Rerank

Tuning Lambda

Error Handling

Related