# Hybrid Search Implementation

> Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall.

Source: https://skillsagentes.com/skills/wshobson/agents/hybrid-search-implementation
Repository: https://github.com/wshobson/agents
Author: wshobson
License: MIT
Updated: hace 2 meses
Context cost: 44 tok installed, 508 tok once triggered, 4.5k tok with every bundled file
Bundle: 2 files, 18 KB
Permissions requested: none declared

## Install

```bash
npx -y skills add wshobson/agents --skill hybrid-search-implementation --agent claude-code
```

## What it does

- Combina búsqueda por similitud vectorial y búsqueda por palabras clave para mejorar el recall
- Explica arquitecturas de fusión (RRF, lineal, cross-encoder, cascada) para combinar resultados
- Remite a `references/details.md` para plantillas y ejemplos concretos
- Da buenas prácticas: ajustar pesos empíricamente, usar RRF, añadir reranking, hacer A/B testing

## Use it when

- Al construir sistemas RAG que necesitan mejor recall
- Al combinar comprensión semántica con coincidencia exacta
- Cuando las consultas incluyen términos específicos (nombres, códigos)
- Cuando la búsqueda vectorial pura no encuentra coincidencias de palabras clave

## What triggers it

- "Quiero implementar búsqueda híbrida vectorial y por palabras clave en mi RAG"
- "¿Cómo combino resultados de búsqueda semántica y keyword search con RRF?"
- "Ayúdame a mejorar el recall de mi motor de búsqueda con fusión de resultados"

## Files

- SKILL.md — 2 KB
- references/details.md — 16 KB

## SKILL.md

Reproduced verbatim from wshobson/agents under MIT. This section is the upstream document and is in English.

# Hybrid Search Implementation

Patterns for combining vector similarity and keyword-based search.

## When to Use This Skill

- Building RAG systems with improved recall
- Combining semantic understanding with exact matching
- Handling queries with specific terms (names, codes)
- Improving search for domain-specific vocabulary
- When pure vector search misses keyword matches

## Core Concepts

### 1. Hybrid Search Architecture

```
Query → ┬─► Vector Search ──► Candidates ─┐
        │                                  │
        └─► Keyword Search ─► Candidates ─┴─► Fusion ─► Results
```

### 2. Fusion Methods

| Method            | Description              | Best For        |
| ----------------- | ------------------------ | --------------- |
| **RRF**           | Reciprocal Rank Fusion   | General purpose |
| **Linear**        | Weighted sum of scores   | Tunable balance |
| **Cross-encoder** | Rerank with neural model | Highest quality |
| **Cascade**       | Filter then rerank       | Efficiency      |

## Templates and detailed worked examples

Full template library and detailed worked examples live in `references/details.md`. Read that file when you need the concrete templates.

## Best Practices

### Do's

- **Tune weights empirically** - Test on your data
- **Use RRF for simplicity** - Works well without tuning
- **Add reranking** - Significant quality improvement
- **Log both scores** - Helps with debugging
- **A/B test** - Measure real user impact

### Don'ts

- **Don't assume one size fits all** - Different queries need different weights
- **Don't skip keyword search** - Handles exact matches better
- **Don't over-fetch** - Balance recall vs latency
- **Don't ignore edge cases** - Empty results, single word queries

---

Skills Agentes — https://skillsagentes.com/skills/wshobson/agents/hybrid-search-implementation