Mongodb Search And Ai

# Hybrid Search

This guide covers hybrid search patterns in MongoDB Atlas: combining vector and lexical search using `$rankFusion` and `$scoreFusion`, and using lexical prefilters with the `vectorSearch` operator inside `$search`.

**Scope**: This guide covers hybrid pipelines. For pure vector search indexes and `$vectorSearch` query construction, see vector-search.md. For lexical index definitions and query patterns, see lexical-search-indexing.md and lexical-search-querying.md.

## Table of Contents

- [Overview](#overview)
- [Choosing the Right Approach](#choosing-the-right-approach)
- [Indexing for Hybrid Search](#indexing-for-hybrid-search)
- [$rankFusion](#rankfusion)
- [$scoreFusion](#scorefusion)
- [Lexical Prefilters (vectorSearch Operator)](#lexical-prefilters-vectorsearch-operator)
- [Best Practices and Limitations](#best-practices-and-limitations)

---

## Overview

Hybrid search combines multiple search methods on the same collection and merges the results into a single ranked or scored list.

**Three patterns covered in this guide:**

| Pattern | Stage / Operator | Use When |
|---|---|---|
| Rank-based fusion | `$rankFusion` | Document position matters; use RRF algorithm |
| Score-based fusion | `$scoreFusion` | Score magnitude matters; need custom math or normalization |
| Lexical prefilter | `$search` + `vectorSearch` operator | Need fuzzy/phrase/wildcard/compound pre-filtering before vector search |

**$rankFusion vs $scoreFusion:**
- `$rankFusion` ranks by position in each input pipeline using the Reciprocal Rank Fusion (RRF) algorithm. A document ranked #1 in multiple pipelines scores much higher than one ranked #1 in only one. Weights influence how much each pipeline's rank contributes.
- `$scoreFusion` ranks by the actual score values from each pipeline. Supports normalization (sigmoid, minMaxScaler) and custom combination expressions. Use when score magnitude, not just ordering, matters.

---

## Choosing the Right Approach

| Scenario | Recommended Approach |
|---|---|
| Combine lexical + vector, rank by position | `$rankFusion` |
| Combine lexical + vector, control score math or normalization | `$scoreFusion` |
| Multiple query vectors or embedding models on same collection | `$rankFusion` with multiple `$vectorSearch` pipelines |
| Pre-filter vector search with fuzzy, phrase, wildcard, or compound | `$search` + `vectorSearch` operator |
| Pre-filter vector search with simple equality or range | `filter` fields in `$vectorSearch` (see vector-search.md) |
| Cross-collection hybrid search | `$unionWith` + `$vectorSearch` (not `$rankFusion`/`$scoreFusion`) |

**Version requirements**: `$rankFusion` requires MongoDB 8.0+. `$scoreFusion` requires MongoDB 8.2+. Only proceed with this guide if the use case is lexical prefilters, or if the cluster meets the version requirement for the fusion stage of interest. Otherwise do not proceed.

---

## Indexing for Hybrid Search

### For $rankFusion and $scoreFusion

You need two separate indexes on the collection:

**1. A vectorSearch-type index** for the `$vectorSearch` input pipeline:
```javascript
db.collection.createSearchIndex(
  "<vector-index-name>",
  "vectorSearch",
  {
    "fields": [
      {
        "type": "vector",
        "path": "<embedding-field>",
        "numDimensions": <number>,
        "similarity": "dotProduct"
      }
    ]
  }
)
```

**2. A search-type index** for the `$search` input pipeline:
```javascript
db.collection.createSearchIndex(
  "<search-index-name>",
  {
    "mappings": { "dynamic": true }
  }
)
```

---

### For Lexical Prefilters (vectorSearch Operator)

The `vectorSearch` operator runs inside `$search`, so you need a **single search-type index** that includes a `vector` field type. This is different from a vectorSearch-type index — you cannot use the `$vectorSearch` stage to query fields indexed this way.

```javascript
db.collection.createSearchIndex(
  "<search-index-name>",
  {
    "mappings": {
      "dynamic": true,