mem0/docs/open-source/features/reranker-search.mdx

---
title: Reranker-Enhanced Search
description: 'Improve search relevance with reranking models in Mem0 1.0.0 Beta'
icon: "sort"
iconType: "solid"
---

<Info>
Reranker-enhanced search is available in **Mem0 1.0.0 Beta** and later versions. This feature significantly improves search relevance by using specialized reranking models to reorder search results.
</Info>

## Overview

Rerankers are specialized models that improve the quality of search results by reordering initially retrieved memories. They work as a second-stage ranking system that analyzes the semantic relationship between your query and retrieved memories to provide more relevant results.

## How Reranking Works

1. **Initial Vector Search**: Retrieves candidate memories using vector similarity
2. **Reranking**: Specialized model analyzes query-memory relationships
3. **Reordering**: Results are reordered based on semantic relevance
4. **Enhanced Results**: Final results with improved relevance scores

## Configuration

### Basic Setup

```python
from mem0 import Memory

config = {
    "reranker": {
        "provider": "cohere",
        "config": {
            "model": "rerank-english-v3.0",
            "api_key": "your-cohere-api-key"
        }
    }
}

m = Memory.from_config(config)
```

### Supported Providers

#### Cohere Reranker

```python
config = {
    "reranker": {
        "provider": "cohere",
        "config": {
            "model": "rerank-english-v3.0",
            "api_key": "your-cohere-api-key",
            "top_k": 10,  # Number of results to rerank
            "return_documents": True
        }
    }
}
```

#### Sentence Transformer Reranker

```python
config = {
    "reranker": {
        "provider": "sentence_transformer",
        "config": {
            "model": "cross-encoder/ms-marco-MiniLM-L-6-v2",
            "device": "cuda",  # Use GPU if available
            "max_length": 512
        }
    }
}
```

#### Hugging Face Reranker

```python
config = {
    "reranker": {
        "provider": "huggingface",
        "config": {
            "model": "BAAI/bge-reranker-base",
            "device": "cuda",
            "batch_size": 32
        }
    }
}
```

#### LLM-based Reranker

```python
config = {
    "reranker": {
        "provider": "llm_reranker",
        "config": {
            "llm": {
                "provider": "openai",
                "config": {
                    "model": "gpt-4",
                    "api_key": "your-openai-api-key"
                }
            },
            "top_k": 5
        }
    }
}
```

## Usage Examples

### Basic Reranked Search

```python
# Reranking is enabled by default when configured
results = m.search(
    "What are my food preferences?",
    user_id="alice"
)

# Results are automatically reranked for better relevance
for result in results["results"]:
    print(f"Memory: {result['memory']}")
    print(f"Score: {result['score']}")
```

### Controlling Reranking

```python
# Enable reranking explicitly
results_with_rerank = m.search(
    "What movies do I like?",
    user_id="alice",
    rerank=True
)

# Disable reranking for this search
results_without_rerank = m.search(
    "What movies do I like?",
    user_id="alice",
    rerank=False
)

# Compare the difference in results
print("With reranking:", len(results_with_rerank["results"]))
print("Without reranking:", len(results_without_rerank["results"]))
```

### Combining with Filters

```python
# Reranking works with metadata filtering
results = m.search(
    "important work tasks",
    user_id="alice",
    filters={
        "AND": [
            {"category": "work"},
            {"priority": {"gte": 7}}
        ]
    },
    rerank=True,
    limit=20
)
```

## Advanced Configuration

### Complete Configuration Example

```python
config = {
    "vector_store": {
        "provider": "qdrant",
        "config": {
            "host": "localhost",
            "port": 6333
        }
    },
    "llm": {
        "provider": "openai",
        "config": {
            "model": "gpt-4",
            "api_key": "your-openai-api-key"
        }
    },
    "embedder": {
        "provider": "openai",
        "config": {
            "model": "text-embedding-3-small",
            "api_key": "your-openai-api-key"
        }
    },
    "reranker": {
        "provider": "cohere",
        "config": {
            "model": "rerank-english-v3.0",
            "api_key": "your-cohere-api-key",
            "top_k": 15,
            "return_documents": True
        }
    }
}

m = Memory.from_config(config)
```

### Async Support

```python
from mem0 import AsyncMemory

# Reranking works with async operations
async_memory = AsyncMemory.from_config(config)

async def search_with_rerank():
    results = await async_memory.search(
        "What are my preferences?",
        user_id="alice",
        rerank=True
    )
    return results

# Use in async context
import asyncio
results = asyncio.run(search_with_rerank())
```

## Performance Considerations

### When to Use Reranking

✅ **Good Use Cases:**
- Complex semantic queries
- Domain-specific searches
- When precision is more important than speed
- Large memory collections
- Ambiguous or nuanced queries

❌ **Avoid When:**
- Simple keyword matching
- Real-time applications with strict latency requirements
- Small memory collections
- High-frequency searches where cost matters

### Performance Optimization

```python
# Optimize reranking performance
config = {
    "reranker": {
        "provider": "sentence_transformer",
        "config": {
            "model": "cross-encoder/ms-marco-MiniLM-L-6-v2",
            "device": "cuda",        # Use GPU
            "batch_size": 32,        # Process in batches
            "top_k": 10,            # Limit candidates
            "max_length": 256       # Reduce if appropriate
        }
    }
}
```

### Cost Management

```python
# For API-based rerankers like Cohere
config = {
    "reranker": {
        "provider": "cohere",
        "config": {
            "model": "rerank-english-v3.0",
            "api_key": "your-cohere-api-key",
            "top_k": 5,  # Reduce to control API costs
        }
    }
}

# Use reranking selectively
def smart_search(query, user_id, use_rerank=None):
    # Automatically decide when to use reranking
    if use_rerank is None:
        use_rerank = len(query.split()) > 3  # Complex queries only

    return m.search(query, user_id=user_id, rerank=use_rerank)
```

## Error Handling

```python
try:
    results = m.search(
        "test query",
        user_id="alice",
        rerank=True
    )
except Exception as e:
    print(f"Reranking failed: {e}")
    # Gracefully fall back to vector search
    results = m.search(
        "test query",
        user_id="alice",
        rerank=False
    )
```

## Reranker Comparison

| Provider | Latency | Quality | Cost | Local Deploy |
|----------|---------|---------|------|--------------|
| Cohere | Medium | High | API Cost | ❌ |
| Sentence Transformer | Low | Good | Free | ✅ |
| Hugging Face | Low-Medium | Variable | Free | ✅ |
| LLM Reranker | High | Very High | API Cost | Depends |

## Real-world Examples

### Customer Support

```python
# Improve support ticket relevance
config = {
    "reranker": {
        "provider": "cohere",
        "config": {
            "model": "rerank-english-v3.0",
            "api_key": "your-cohere-api-key"
        }
    }
}

m = Memory.from_config(config)

# Find relevant support cases
results = m.search(
    "customer having login issues with mobile app",
    agent_id="support_bot",
    filters={"category": "technical_support"},
    rerank=True
)
```

### Content Recommendation

```python
# Better content matching
results = m.search(
    "science fiction books with space exploration themes",
    user_id="reader123",
    filters={"content_type": "book_recommendation"},
    rerank=True,
    limit=10
)

for result in results["results"]:
    print(f"Recommendation: {result['memory']}")
    print(f"Relevance: {result['score']:.3f}")
```

### Personal Assistant

```python
# Enhanced personal queries
results = m.search(
    "What restaurants did I enjoy last month that had good vegetarian options?",
    user_id="foodie_user",
    filters={
        "AND": [
            {"category": "dining"},
            {"rating": {"gte": 4}},
            {"date": {"gte": "2024-01-01"}}
        ]
    },
    rerank=True
)
```

## Migration Guide

### From v0.x (No Reranking)

```python
# v0.x - basic vector search
results = m.search("query", user_id="alice")
```

### To v1.0.0 Beta (With Reranking)

```python
# Add reranker configuration
config = {
    "reranker": {
        "provider": "sentence_transformer",
        "config": {
            "model": "cross-encoder/ms-marco-MiniLM-L-6-v2"
        }
    }
}

m = Memory.from_config(config)

# Same search API, better results
results = m.search("query", user_id="alice")  # Automatically reranked
```

## Best Practices

1. **Start Simple**: Begin with Sentence Transformers for local deployment
2. **Monitor Performance**: Track both relevance improvements and latency
3. **Cost Awareness**: Use API-based rerankers judiciously
4. **Selective Usage**: Apply reranking where it provides the most value
5. **Fallback Strategy**: Always handle reranking failures gracefully
6. **Test Different Models**: Experiment to find the best fit for your domain

<Info>
Reranker-enhanced search significantly improves result relevance. Start with a local model and upgrade to API-based solutions as your needs grow.
</Info>