Create a hybrid query in Azure AI Search

2025-08-25

Hybrid search combines text (keyword) and vector queries in a single search request. Both queries execute in parallel. The results are merged and reordered by new search scores, using Reciprocal Rank Fusion (RRF) to return a unified result set.

In this article, learn how to:

Set up a basic hybrid request
Add parameters and filters
Improve relevance using semantic ranking or vector weights
Optimize query behaviors by controlling inputs (maxTextRecallSize)

Prerequisites

A search index containing searchable vector and nonvector fields. We recommend the Import and vectorize data wizard to create an index quickly. Otherwise, see Create an index and Add vector fields to a search index.
(Optional) If you want the semantic ranker, your search service must be Basic tier or higher, with semantic ranker enabled.
(Optional) If you want built-in text-to-vector conversion of a query string, create and assign a vectorizer to vector fields in the search index.

Choose an API or tool

Search Explorer in the Azure portal (supports both stable and preview API search syntax) has a JSON view that lets you paste in a hybrid request.
Stable REST APIs or a recent preview API version if you're using preview features like maxTextRecallSize and countAndFacetMode(preview).

For readability, we use REST examples to explain how the APIs work. You can use a REST client like Visual Studio Code with the REST extension to build hybrid queries. You can also use the Azure SDKs. For more information, see Quickstart: Vector search.

Set up a hybrid query

This section explains the basic structure of a hybrid query and how to set one up in either Search Explorer or for execution in a REST client.

Results are returned in plain text, including vectors in fields marked as retrievable. Because numeric vectors aren't useful in search results, choose other fields in the index as a proxy for the vector match. For example, if an index has "descriptionVector" and "descriptionText" fields, the query can match on "descriptionVector" but the search result can show "descriptionText". Use the select parameter to specify only human-readable fields in the results.

Azure portal
REST

Sign in to the Azure portal and find your search service.
Under Search management > Indexes, select an index that has vectors and non-vector content. Search Explorer is the first tab.
Under View, switch to JSON view so that you can paste in a vector query.
Replace the default query template with a hybrid query. A basic hybrid query has a text query specified in search, and a vector query specified under vectorQueries.vector. The text query and vector query can be equivalent or divergent, but it's common for them to share the same intent.

This example is from the vector quickstart that has vector and nonvector content, and several query examples. For brevity, the vector is truncated in this article.
```
{
    "search": "historic hotel walk to restaurants and shopping",
    "vectorQueries": [
        {
            "vector": [0.01944167, 0.0040178085, -0.007816401 ... <remaining values omitted> ], 
            "k": 7,
            "fields": "DescriptionVector",
            "kind": "vector",
            "exhaustive": true
        }
    ]
}
```
Select Search.

Tip

Search results are easier to read if you hide the vectors. In Query Options, turn on Hide vector values in search results.

Here's another version of the query. This one adds a count for the number of matches found, a select parameter for choosing specific fields, and a top parameter to return the top seven results.

 {
     "count": true,
     "search": "historic hotel walk to restaurants and shopping",
     "select": "HotelId, HotelName, Category, Tags, Description",
     "top": 7,
     "vectorQueries": [
         {
             "vector": [0.01944167, 0.0040178085, -0.007816401 ... <remaining values omitted> ], 
             "k": 7,
             "fields": "DescriptionVector",
             "kind": "vector",
             "exhaustive": true
         }
     ]
 }

The following example shows a hybrid query request using the REST API.

This example is from the vector quickstart that has vector and nonvector content, and several query examples. For brevity, the vector is truncated in this article.

POST https://{{search-service-name}}.search.azure.cn/indexes/{{index-name}}/docs/search?api-version=2024-07-01
Content-Type: application/json
api-key: {{admin-api-key}}
{
    "vectorQueries": [
        {
            "vector": [
                -0.009154141,
                0.018708462,
                . . . 
                -0.02178128,
                -0.00086512347
            ],
            "fields": "DescriptionVector",
            "kind": "vector",
            "exhaustive": true,
            "k": 10
        },
        {
            "vector": [
                -0.009154141,
                0.018708462,
                . . . 
                -0.02178128,
                -0.00086512347
            ],
            "fields": "DescriptionVector",
            "kind": "vector",
            "exhaustive": true,
            "k": 10
        }
    ],
    "search": "historic hotel walk to restaurants and shopping",
    "select": "HotelName, Description, Address/City",
    "top": 10
}

Key points:

The vector query string is specified through the vectorQueries.vector property. The query executes against the "DescriptionVector" field. Set kind to "vector" to indicate the query type. Optionally, set exhaustive to true to query the full contents of the vector field.
Keyword search is specified through search property. It executes in parallel with the vector query.
k determines how many nearest neighbor matches are returned from the vector query and provided to the RRF ranker.
top determines how many matches are returned in the response all-up. In this example, the response includes 10 results, assuming there are at least 10 matches in the merged results.

Examples of hybrid queries

This section has multiple query examples that illustrate hybrid query patterns.

Example: Hybrid search with filter

This example adds a filter, which is applied to the filterable nonvector fields of the search index.

POST https://{{search-service-name}}.search.azure.cn/indexes/{{index-name}}/docs/search?api-version=2024-07-01
Content-Type: application/json
api-key: {{admin-api-key}}
{
    "vectorQueries": [
        {
            "vector": [
                -0.009154141,
                0.018708462,
                . . . 
                -0.02178128,
                -0.00086512347
            ],
            "fields": "DescriptionVector",
            "kind": "vector",
            "k": 10
        }
    ],
    "search": "historic hotel walk to restaurants and shopping",
    "vectorFilterMode": "postFilter",
    "filter": "ParkingIncluded",
    "top": "10"
}

Key points:

Filters are applied to the content of filterable fields. In this example, the ParkingIncluded field is a boolean and it's marked as filterable in the index schema.
In hybrid queries, filters can be applied before query execution to reduce the query surface, or after query execution to trim results. "preFilter" is the default. To use postFilter, set the filter processing mode as shown in this example.
When you postfilter query results, the number of results might be less than top-n.

Configure a query response

When you're setting up the hybrid query, think about the response structure. The search engine ranks the matching documents and returns the most relevant results. The response is a flattened rowset. Parameters on the query determine which fields are in each row and how many rows are in the response.

Fields in a response

Search results are composed of retrievable fields from your search index. A result is either:

All retrievable fields (a REST API default).
Fields explicitly listed in a select parameter on the query.

The examples in this article used a select statement to specify text (nonvector) fields in the response.

Note

Vectors aren't reverse engineered into human readable text, so avoid returning them in the response. Instead, choose nonvector fields that are representative of the search document. For example, if the query targets a "DescriptionVector" field, return an equivalent text field if you have one ("Description") in the response.

Number of results

A query might match to any number of documents, as many as all of them if the search criteria are weak (for example "search=*" for a null query). Because it's seldom practical to return unbounded results, you should specify a maximum for the overall response:

"top": n results for keyword-only queries (no vector)
"k": n results for vector-only queries
"top": n results for hybrid queries (with or without semantic) that include a "search" parameter

Both k and top are optional. Unspecified, the default number of results in a response is 50. You can set top and skip to page through more results or change the default.

Note

If you're using hybrid search in 2024-05-01-preview API, you can control the number of results from the keyword query using maxTextRecallSize. Combine this with a setting for k to control the representation from each search subsystem (keyword and vector).

Semantic ranker results

Note

The semantic ranker can take up to 50 results.

If you're using semantic ranker in 2024-05-01-preview or later, it's a best practice to set k and maxTextRecallSize to sum to at least 50 total. You can then restrict the results returned to the user with the top parameter.

If you're using semantic ranker in previous APIs do the following:

For keyword-only search (no vectors) set top to 50
For hybrid search set k to 50, to ensure that the semantic ranker gets at least 50 results.

Ranking

Multiple sets are created for hybrid queries, with or without the optional semantic reranking. Ranking of results is computed by Reciprocal Rank Fusion (RRF).

In this section, compare the responses between single vector search and simple hybrid search for the top result. The different ranking algorithms, HNSW's similarity metric and RRF is this case, produce scores that have different magnitudes. This behavior is by design. RRF scores can appear quite low, even with a high similarity match. Lower scores are a characteristic of the RRF algorithm. In a hybrid query with RRF, more of the reciprocal of the ranked documents are included in the results, given the relatively smaller score of the RRF ranked documents, as opposed to pure vector search.

Single Vector Search: @search.score for results ordered by cosine similarity (default vector similarity distance function).

{
    "@search.score": 0.8399121,
    "HotelId": "49",
    "HotelName": "Swirling Currents Hotel",
    "Description": "Spacious rooms, glamorous suites and residences, rooftop pool, walking access to shopping, dining, entertainment and the city center.",
    "Category": "Luxury",
    "Address": {
    "City": "Arlington"
    }
}

Hybrid Search: @search.score for hybrid results ranked using Reciprocal Rank Fusion.

{
    "@search.score": 0.032786883413791656,
    "HotelId": "49",
    "HotelName": "Swirling Currents Hotel",
    "Description": "Spacious rooms, glamorous suites and residences, rooftop pool, walking access to shopping, dining, entertainment and the city center.",
    "Category": "Luxury",
    "Address": {
    "City": "Arlington"
    }
}

Next step

We recommend reviewing vector demo code for Python, C# or JavaScript.

Create a hybrid query in Azure AI Search

Prerequisites

Choose an API or tool

Set up a hybrid query

Additional resources