hybrid-search-implementation

wshobson ｜ 資料與分析 ｜ 原文 ｜ MIT

結合向量相似度和關鍵字搜尋的混合搜尋模式與融合方法

---
name: hybrid-search-implementation
description: 結合向量與關鍵字搜尋以提升檢索效果。適用於實作 RAG 系統、建構搜尋引擎，或單靠任一種方法召回率都不夠的時候。
---

# 混合搜尋實作

結合向量相似度與關鍵字搜尋的模式。

## 什麼時候用這個 Skill

- 建構召回率更高的 RAG 系統
- 結合語意理解與精確比對
- 處理帶有特定詞彙（名稱、代碼）的查詢
- 改善針對特定領域詞彙的搜尋
- 純向量搜尋漏掉關鍵字命中的時候

## 核心概念

### 1. 混合搜尋架構

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

### 2. 融合方法

| 方法              | 說明                     | 最適合          |
| ----------------- | ------------------------ | --------------- |
| **RRF**           | Reciprocal Rank Fusion   | 通用            |
| **Linear**        | 分數的加權總和           | 可調整的平衡    |
| **Cross-encoder** | 用神經網路模型重新排序   | 品質最高        |
| **Cascade**       | 先過濾再重新排序         | 效率            |

## 範本與詳細實作範例

完整的範本庫和詳細實作範例放在 `references/details.md`，需要具體範本的時候去讀那份檔案。

## 最佳實務

### 該做的

- **憑經驗調整權重**：用你自己的資料測試
- **為了簡單用 RRF**：不用調整也運作得很好
- **加上 reranking**：品質大幅提升
- **兩種分數都記 log**：方便除錯
- **做 A/B 測試**：衡量對真實使用者的影響

### 不該做的

- **不要以為一種設定通吃**：不同的查詢需要不同的權重
- **不要跳過關鍵字搜尋**：它處理精確比對比較好
- **不要抓太多**：在召回率與延遲之間取得平衡
- **不要忽略邊界案例**：空結果、單字查詢

---
name: hybrid-search-implementation
description: Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall.
---

# 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