Hybrid Search Implementation

Samira El-Masri

@samira-el-masri

·December 31, 2025

Build a hybrid search system combining dense embeddings and sparse retrieval with score fusion and reranking for improved retrieval accuracy.

34 copies0 forks

Share this prompt:

Implement a hybrid search system combining dense and sparse retrieval.

## Requirements
{{search_requirements}}

## Data Characteristics
{{data_characteristics}}

## Technology Stack
- Vector store: {{vector_store}}
- Full-text search: {{fts_engine}}

Create a complete implementation:

```python
class HybridSearcher:
    def __init__(self, dense_weight: float = 0.7):
        # Initialize both retrievers
        pass
    
    def search(self, query: str, top_k: int) -> List[Result]:
        # 1. Dense retrieval
        # 2. Sparse retrieval  
        # 3. Score fusion (RRF)
        # 4. Reranking
        pass
```

Include:
- Reciprocal Rank Fusion implementation
- Weight tuning methodology
- Evaluation metrics
- A/B test setup

Details

Category

Coding

Use Cases

Search improvementRetrieval optimizationHybrid search

Works Best With

claude-sonnet-4-20250514gpt-4o

Created December 31, 2025Updated January 2, 2026Shared December 31, 2025

Related Prompts

Context Relevance Scorer

by @crisdux

Build a context relevance scorer combining similarity, keyword, entity, and topic signals to filter retrieved documents before LLM generation.

Context Relevance Scorer

by @levi-smith

Build a context relevance scorer combining similarity, keyword, entity, and topic signals to filter retrieved documents before LLM generation.

Context Relevance Scorer

by @crisdux

Build a context relevance scorer combining similarity, keyword, entity, and topic signals to filter retrieved documents before LLM generation.

Context Relevance Scorer

by @livelybear1320

Build a context relevance scorer combining similarity, keyword, entity, and topic signals to filter retrieved documents before LLM generation.

Context Relevance Scorer

by @levi-smith

Build a context relevance scorer combining similarity, keyword, entity, and topic signals to filter retrieved documents before LLM generation.

Context Relevance Scorer

by @eagerlynx2759

Build a context relevance scorer combining similarity, keyword, entity, and topic signals to filter retrieved documents before LLM generation.

More from @samira-el-masri

Context Relevance Scorer

Zero-Shot Code Bug Detection

LLM Observability Stack Setup

Negative Sampling Strategy

Create your own prompt vault and start sharing