> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/MicrosoftDocs/azure-ai-docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Query Overview

> Learn about the types of queries supported in Azure AI Search including full-text, vector, and hybrid queries.

# Querying in Azure AI Search

Azure AI Search supports a broad range of query constructs for different scenarios, from free-form text search to vector similarity search.

## Query Types

<Tabs>
  <Tab title="Full-Text">
    **Full-Text Search**

    Traditional keyword-based search:

    * BM25 relevance ranking
    * Tokenization and analysis
    * Fast inverted index scans

    ```json theme={null}
    {
      "search": "luxury hotel",
      "searchFields": "title,description"
    }
    ```
  </Tab>

  <Tab title="Vector">
    **Vector Search**

    Semantic similarity using embeddings:

    * Cosine/euclidean similarity
    * Nearest neighbor algorithms
    * 1536-dimension vectors

    ```json theme={null}
    {
      "vectorQueries": [
        {
          "vector": [...],
          "fields": "contentVector",
          "k": 50
        }
      ]
    }
    ```
  </Tab>

  <Tab title="Hybrid">
    **Hybrid Search**

    Combined text and vector:

    * Best of both approaches
    * RRF result fusion
    * Optional semantic ranking

    ```json theme={null}
    {
      "search": "luxury hotel",
      "vectorQueries": [
        {
          "vector": [...],
          "fields": "contentVector",
          "k": 50
        }
      ]
    }
    ```
  </Tab>

  <Tab title="Agentic">
    **Agentic Retrieval**

    Multi-query pipeline:

    * LLM query planning
    * Parallel subqueries
    * Agent-optimized response

    ```json theme={null}
    POST /knowledgebases/my-kb/retrieve
    {
      "query": "complex question",
      "messageHistory": [...]
    }
    ```
  </Tab>
</Tabs>

## Query Components

### Search Parameters

* `search`: Full-text query string
* `searchFields`: Fields to search (optional)
* `searchMode`: any (OR) or all (AND)
* `queryType`: simple or full Lucene

### Filters

* `filter`: OData filter expression
* `facets`: Generate category counts
* `orderby`: Sort expression

### Result Control

* `select`: Fields to return
* `top`: Maximum results
* `skip`: Pagination offset
* `count`: Include total count

## Autocomplete and Suggestions

Type-ahead query experiences:

```json theme={null}
{
  "autocomplete": "hot",
  "suggesterName": "sg",
  "searchFields": "hotelName"
}
```

**Returns**: Completed terms like "hotel", "hotels"

## Geospatial Search

Location-based filtering:

```json theme={null}
{
  "filter": "geo.distance(location, geography'POINT(-122.12 47.67)') le 10"
}
```

**Functions**:

* `geo.distance`: Distance between points
* `geo.intersects`: Point within polygon

## Advanced Query Features

<CardGroup cols={2}>
  <Card title="Fuzzy Search" icon="spell-check">
    Handle typos with edit distance matching
  </Card>

  <Card title="Fielded Search" icon="crosshairs">
    Target specific fields with Lucene syntax
  </Card>

  <Card title="Proximity Search" icon="arrows-left-right">
    Find terms near each other in documents
  </Card>

  <Card title="Term Boosting" icon="arrow-trend-up">
    Increase relevance of specific terms
  </Card>
</CardGroup>

## Query Syntax

### Simple Syntax

Default, intuitive syntax:

```
luxury hotel AND (spa OR pool) -airport
"ocean view"
hotel*
```

### Full Lucene Syntax

Advanced operators and expressions:

```
title:luxury^2 description:beachfront
name:/[mh]otel/
"ocean view"~5
seatle~
```

Enable with `"queryType": "full"`

## Result Ranking

### BM25 Scoring

Default relevance algorithm:

* Term frequency (TF)
* Inverse document frequency (IDF)
* Field length normalization

### Vector Similarity

For vector queries:

* Cosine similarity (default)
* Euclidean distance
* Dot product

### RRF (Hybrid)

Reciprocal Rank Fusion for hybrid queries:

```
score = Σ 1/(k + rank)
```

## Query Example

Complete hybrid query with filters:

```json theme={null}
{
  "search": "luxury beachfront hotel",
  "searchFields": "hotelName,description",
  "filter": "rating ge 4.5 and priceRange eq 'high'",
  "orderby": "rating desc",
  "select": "hotelId,hotelName,description,rating",
  "vectorQueries": [
    {
      "kind": "vector",
      "vector": [-0.009, 0.018, ...],
      "fields": "descriptionVector",
      "k": 50
    }
  ],
  "queryType": "semantic",
  "semanticConfiguration": "my-semantic-config",
  "top": 10,
  "count": true
}
```

## Next Steps

<CardGroup cols={2}>
  <Card title="Full-Text Queries" icon="text" href="/search/queries/full-text">
    Master keyword search syntax
  </Card>

  <Card title="Vector Queries" icon="diagram-project" href="/search/queries/vector">
    Execute vector similarity searches
  </Card>

  <Card title="Query Examples" icon="code" href="https://learn.microsoft.com/azure/search/search-query-simple-examples">
    View more query patterns
  </Card>
</CardGroup>