QueryBuilder

Description — How to use QueryBuilder to build effective queries with Couchbase Lite on Swift
Related Content — Live Queries | Indexing

The examples used in this topic are based on the Travel Sample app and data introduced in the Couchbase Mobile Workshop tutorial

Introduction

Couchbase Lite for Swift provides two ways to build and run database queries; the QueryBuilder API described in this topic and the SQL++ for Mobile.

Database queries defined with the QueryBuilder API use query statements of the form shown in Example 1. The structure and semantics of the query format are based on that of Couchbase’s SQL++ query language.

Example 1. Query Format

SELECT ____ (1)
FROM 'database' (2)
WHERE ____, (3)
JOIN ____ (4)
GROUP BY ____ (5)
ORDER BY ____ (6)

Query Components

1	The SELECT statement specifies the document properties that will be returned in the result set
2	FROM specifies the database to query the documents from
3	WHERE statement specifies the query criteria. The `SELECT`ed properties of documents matching this criteria will be returned in the result set
4	JOIN statement specifies the criteria for joining multiple documents
5	GROUP BY statement specifies the criteria used to group returned items in the result set
6	ORDER BY statement specifies the criteria used to order the items in the result set

We recommend working through the query section of the Couchbase Mobile Workshop tutorial as a good way to build your skills in this area.

Indexing

See the Indexing topic to learn more about indexing.

Before we begin querying documents, let’s briefly mention the importance of having a query index. A query can only be fast if there’s a pre-existing database index it can search to narrow down the set of documents to examine — see: Example 2, which shows how to create an index, and also the Query Troubleshooting topic.

See the Indexing topic to learn more about indexing.

A query can only be fast if there’s a pre-existing database index it can search to narrow down the set of documents to examine — see: Example 2, which shows how to create an index and our Query Troubleshooting topic.

However, every index has to be updated whenever a document is updated. So too many indexes can hurt performance.

Good performance depends on designing and creating the right indexes to go along with your queries.

Example 2. Creating a New Index

This example creates a new index for the `type` and `name` properties in the Data Model.

let config = ValueIndexConfiguration(["type", "name"])
try database.createIndex(config, name: "TypeNameIndex")

Data Model

[
  { (1)
    "id": "hotel123",
    "type": "hotel",
    "name": "Hotel Ghia"
  },
  { (2)
    "id": "hotel456",
    "type": "hotel",
    "name": "Hotel Deluxe",
  }
]

SELECT statement

In this section: Return Selected Properties | Return All Properties
Related: Handling result sets

Use the SELECT statement to specify which properties you want to return from the queried documents. You can opt to retrieve entire documents, or just the specific properties you need.

Return All Properties

Use the SelectResult.all() method to return all the properties of selected documents — see: Example 3.

Example 3. Using SELECT to Retrieve All Properties

This query shows how to retrieve all properties from all documents in your database.

query = QueryBuilder
    .select(SelectResult.all())
    .from(DataSource.database(database))

The query.execute statement returns the results in a dictionary, where the key is the database name — see Example 4.

Example 4. ResultSet Format from SelectResult.all()

[
  {
    "travel-sample": { (1)
      "callsign": "MILE-AIR",
      "country": "United States",
      "iata": "Q5",
      "icao": "MLA",
      "id": 10,
      "name": "40-Mile Air",
      "type": "airline"
    }
  },
  {
    "travel-sample": { (2)
      "callsign": "ALASKAN-AIR",
      "country": "United States",
      "iata": "AA",
      "icao": "AAA",
      "id": 10,
      "name": "Alaskan Airways",
      "type": "airline"
    }
  }
]

1	Here we see the result for the first document matching the query criteria.
2	Here we see the result for the next document matching the query criteria.

See: Result Sets for more on processing query results.

Return Selected Properties

To access only specific properties, specify a comma separated list of SelectResult expressions, one for each property, in the select statement of your query — see: Example 5

Example 5. Using SELECT to Retrieve Specific Properties

In this query we retrieve and then print the _id, type and name properties of each document.

let query = QueryBuilder
    .select(
        SelectResult.expression(Meta.id),
        SelectResult.property("type"),
        SelectResult.property("name")
    )
    .from(DataSource.database(database))

do {
    for result in try query.execute() {
        print("document id :: \(result.string(forKey: "id")!)")
        print("document name :: \(result.string(forKey: "name")!)")
    }
} catch {
    print(error)
}

The query.execute statement returns one or more key-value pairs, one for each SelectResult expression, with the property-name as the key — see Example 6

Example 6. Select Result Format

[
  { (1)
    "id": "hotel123",
    "type": "hotel",
    "name": "Hotel Ghia"
  },
  { (2)
    "id": "hotel456",
    "type": "hotel",
    "name": "Hotel Deluxe",
  }
]

1	Here we see the result for the first document matching the query criteria.
2	Here we see the result for the next document matching the query criteria.

See: Result Sets for more on processing query results.

WHERE statement

In this section: Comparison Operators | Collection Operators | Like Operator | Regex Operator | Deleted Document

Like SQL, you can use the WHERE statement to choose which documents are returned by your query. The select statement takes in an Expression. You can chain any number of Expressions in order to implement sophisticated filtering capabilities.

Comparison Operators

The Expression Comparators can be used in the WHERE statement to specify on which property to match documents. In the example below, we use the equalTo operator to query documents where the type property equals "hotel".

[
  { (1)
    "id": "hotel123",
    "type": "hotel",
    "name": "Hotel Ghia"
  },
  { (2)
    "id": "hotel456",
    "type": "hotel",
    "name": "Hotel Deluxe",
  }
]

Example 7. Using Where

let query = QueryBuilder
    .select(SelectResult.all())
    .from(DataSource.database(database))
    .where(Expression.property("type").equalTo(Expression.string("hotel")))
    .limit(Expression.int(10))

do {
    for result in try query.execute() {
        if let dict = result.dictionary(forKey: "travel-sample") {
            print("document name :: \(dict.string(forKey: "name")!)")
        }
    }
} catch {
    print(error)
}

Collection Operators

Array Collection Operators are useful to check if a given value is present in an array.

CONTAINS Operator

The following example uses the ArrayFunction to find documents where the public_likes array property contains a value equal to "Armani Langworth".

{
    "_id": "hotel123",
    "name": "Apple Droid",
    "public_likes": ["Armani Langworth", "Elfrieda Gutkowski", "Maureen Ruecker"]
}

let query = QueryBuilder
    .select(
        SelectResult.expression(Meta.id),
        SelectResult.property("name"),
        SelectResult.property("public_likes")
    )
    .from(DataSource.database(database))
    .where(Expression.property("type").equalTo(Expression.string("hotel"))
            .and(ArrayFunction.contains(Expression.property("public_likes"),
                                        value: Expression.string("Armani Langworth")))
    )

do {
    for result in try query.execute() {
        print("public_likes :: \(result.array(forKey: "public_likes")!.toArray())")
    }
}

IN Operator

The IN operator is useful when you need to explicitly list out the values to test against. The following example looks for documents whose first, last or username property value equals "Armani".

let values = [
    Expression.property("first"),
    Expression.property("last"),
    Expression.property("username")
]

let query = QueryBuilder.select(SelectResult.all())
    .from(DataSource.database(database))
    .where(Expression.string("Armani").in(values))

Like Operator

In this section: String Matching | Wildcard Match | Wildcard Character Match

String Matching

The like(_:) operator can be used for string matching — see Example 8

The like operator performs case sensitive matches.
To perform case insensitive matching, use Function.lower or Function.upper to ensure all comparators have the same case, thereby removing the case issue.

This query returns landmark type documents where the name matches the string "Royal Engineers Museum", regardless of how it is capitalized (so, it selects "royal engineers museum", "ROYAL ENGINEERS MUSEUM" and so on).

Example 8. Like with case-insensitive matching

let query = QueryBuilder
    .select(
        SelectResult.expression(Meta.id),
        SelectResult.property("country"),
        SelectResult.property("name")
    )
    .from(DataSource.database(database))
    .where(Expression.property("type").equalTo(Expression.string("landmark"))
            .and(Function.lower(Expression.property("name"))
                    .like(Expression.string("royal engineers museum")))
    )
    .limit(Expression.int(10))

do {
    for result in try query.execute() {
        print("name property :: \(result.string(forKey: "name")!)")
    }
}

Note the use of Function.lower to transform name values to the same case as the literal comparator.

Wildcard Match

We can use % sign within a like expression to do a wildcard match against zero or more characters. Using wildcards allows you to have some fuzziness in your search string.

In Example 9 below, we are looking for documents of type "landmark" where the name property matches any string that begins with "eng" followed by zero or more characters, the letter "e", followed by zero or more characters. Once again, we are using Function.lower to make the search case insensitive.

So "landmark" documents with names such as "Engineers", "engine", "english egg" and "England Eagle". Notice that the matches may span word boundaries.

Example 9. Wildcard Matches

let query = QueryBuilder
    .select(
        SelectResult.expression(Meta.id),
        SelectResult.property("country"),
        SelectResult.property("name")
    )
    .from(DataSource.database(database))
    .where(Expression.property("type").equalTo(Expression.string("landmark"))
            .and(Function.lower(Expression.property("name"))
                    .like(Expression.string("eng%e%")))
    )
    .limit(Expression.int(10))

Wildcard Character Match

We can use an _ sign within a like expression to do a wildcard match against a single character.

In Example 10 below, we are looking for documents of type "landmark" where the name property matches any string that begins with "eng" followed by exactly 4 wildcard characters and ending in the letter "r". The query returns "landmark" type documents with names such as "Engineer", "engineer" and so on.

Example 10. Wildcard Character Matching

let query = QueryBuilder
    .select(
        SelectResult.expression(Meta.id),
        SelectResult.property("country"),
        SelectResult.property("name")
    )
    .from(DataSource.database(database))
    .where(Expression.property("type").equalTo(Expression.string("landmark"))
            .and(Expression.property("name").like(Expression.string("eng____r")))
    )
    .limit(Expression.int(10))

Regex Operator

Similar to the wildcards in like expressions, regex based pattern matching allow you to introduce an element of fuzziness in your search string — see the code shown in Example 11.

The regex operator is case sensitive, use upper or lower functions to mitigate this if required.

Example 11. Using Regular Expressions

This example returns documents with a `type` of "landmark" and a `name` property that matches any string that begins with "eng" and ends in the letter "e".

let query = QueryBuilder
    .select(
        SelectResult.expression(Meta.id),
        SelectResult.property("name")
    )
    .from(DataSource.database(database))
    .where(Expression.property("type").equalTo(Expression.string("landmark"))
            .and(Expression.property("name").regex(Expression.string("\\bEng.*e\\b"))) (1)
    )
    .limit(Expression.int(10))

1	The `\b` specifies that the match must occur on word boundaries.

For more on the regex spec used by Couchbase Lite see cplusplus regex reference page

Deleted Document

You can query documents that have been deleted (tombstones) ^[1] as shown in Example 12.

Example 12. Query to select Deleted Documents

This example shows how to query deleted documents in the database. It returns is an array of key-value pairs.

// Query documents that have been deleted
let query = QueryBuilder
    .select(SelectResult.expression(Meta.id))
    .from(DataSource.database(database))
    .where(Meta.isDeleted)

JOIN statement

The JOIN clause enables you to select data from multiple documents that have been linked by criteria specified in the JOIN statement. For example to combine airline details with route details, linked by the airline id — see Example 13.

Example 13. Using JOIN to Combine Document Details

This example JOINS the document of type route with documents of type airline using the document ID (id) on the _airline document and airlineid on the route document.

let query = QueryBuilder
    .select(
        SelectResult.expression(Expression.property("name").from("airline")),
        SelectResult.expression(Expression.property("callsign").from("airline")),
        SelectResult.expression(Expression.property("destinationairport").from("route")),
        SelectResult.expression(Expression.property("stops").from("route")),
        SelectResult.expression(Expression.property("airline").from("route"))
    )
    .from(
        DataSource.database(database!).as("airline")
    )
    .join(
        Join.join(DataSource.database(database!).as("route"))
            .on(
                Meta.id.from("airline")
                    .equalTo(Expression.property("airlineid").from("route"))
            )
    )
    .where(
        Expression.property("type").from("route").equalTo(Expression.string("route"))
            .and(Expression.property("type").from("airline")
                    .equalTo(Expression.string("airline")))
            .and(Expression.property("sourceairport").from("route")
                    .equalTo(Expression.string("RIX")))
    )

GROUP BY statement

You can perform further processing on the data in your result set before the final projection is generated.

The following example looks for the number of airports at an altitude of 300 ft or higher and groups the results by country and timezone.

Data Model for Example

{
    "_id": "airport123",
    "type": "airport",
    "country": "United States",
    "geo": { "alt": 456 },
    "tz": "America/Anchorage"
}

Example 14. Query using GroupBy

This example shows a query that selects all airports with an altitude above 300ft. The output (a count, $1) is grouped by country, within timezone.

let query = QueryBuilder
    .select(
        SelectResult.expression(Function.count(Expression.all())),
        SelectResult.property("country"),
        SelectResult.property("tz"))
    .from(DataSource.database(database))
    .where(
        Expression.property("type").equalTo(Expression.string("airport"))
            .and(Expression.property("geo.alt").greaterThanOrEqualTo(Expression.int(300)))
    ).groupBy(
        Expression.property("country"),
        Expression.property("tz")
    )

do {
    for result in try query.execute() {
        print("""
            There are \(result.int(forKey: "$1")) airports on
                        the \(result.string(forKey: "tz")!)timezone located
                        in \(result.string(forKey: "country")!) and above 300 ft
        """)
    }
}

The query shown in Example 14 generates the following output:

There are 138 airports on the Europe/Paris timezone located in France and above 300 ft
There are 29 airports on the Europe/London timezone located in United Kingdom and above 300 ft
There are 50 airports on the America/Anchorage timezone located in United States and above 300 ft
There are 279 airports on the America/Chicago timezone located in United States and above 300 ft
There are 123 airports on the America/Denver timezone located in United States and above 300 ft

ORDER BY statement

It is possible to sort the results of a query based on a given expression result — see Example 15

Example 15. Query using OrderBy

This example shows a query that returns documents of type equal to "hotel" sorted in ascending order by the value of the title property.

let query = QueryBuilder
    .select(
        SelectResult.expression(Meta.id),
        SelectResult.property("title"))
    .from(DataSource.database(database))
    .where(Expression.property("type").equalTo(Expression.string("hotel")))
    .orderBy(Ordering.property("title").ascending())
    .limit(Expression.int(10))

The query shown in Example 15 generates the following output:

Aberdyfi
Achiltibuie
Altrincham
Ambleside
Annan
Ardèche
Armagh
Avignon

Date/Time Functions

Couchbase Lite documents support a date type that internally stores dates in ISO 8601 with the GMT/UTC timezone.

Couchbase Lite’s Query Builder API ^[1] includes four functions for date comparisons.

Function.StringToMillis(Expression.Property("date_time")): The input to this will be a validly formatted ISO 8601 date_time string. The end result will be an expression (with a numeric content) that can be further input into the query builder.
Function.StringToUTC(Expression.Property("date_time")): The input to this will be a validly formatted ISO 8601 date_time string. The end result will be an expression (with string content) that can be further input into the query builder.
Function.MillisToString(Expression.Property("date_time")): The input for this is a numeric value representing milliseconds since the Unix epoch. The end result will be an expression (with string content representing the date and time as an ISO 8601 string in the device’s timezone) that can be further input into the query builder.
Function.MillisToUTC(Expression.Property("date_time")): The input for this is a numeric value representing milliseconds since the Unix epoch. The end result will be an expression (with string content representing the date and time as a UTC ISO 8601 string) that can be further input into the query builder.

Result Sets

In this section: Processing | Select All Properties | Select Specific Properties | Select Document Id Only | Select Count-only | Handling Pagination

Processing

This section shows how to handle the returned result sets for different types of SELECT statements.

The result set format and its handling varies slightly depending on the type of SelectResult statements used. The result set formats you may encounter include those generated by :

SelectResult.all — see: All Properties
SelectResult.expression(property("name")) — see: Specific Properties
SelectResult.expression(meta.id) — Metadata (such as the _id) — see: Document ID Only
SelectResult.expression(Function.count(Expression.all())).as("mycount") — see: Select Count-only

To process the results of a query, you first need to execute it using Query.execute.

The execution of a Couchbase Lite for Swift’s database query typically returns an array of results, a result set.

The result set of an aggregate, count-only, query is a key-value pair — see Select Count-only — which you can access using the count name as its key.
The result set of a query returning document properties is an array.
Each array row represents the data from a document that matched your search criteria (the WHERE statements) The composition of each row is determined by the combination of SelectResult expressions provided in the SELECT statement. To unpack these result sets you need to iterate this array.

Select All Properties

Query

The Select statement for this type of query, which returns all document properties for each document matching the query criteria, is fairly straightforward — see Example 16

Example 16. Query selecting All Properties

let database = try Database(name: "hotel")
let query = QueryBuilder.select(SelectResult.all()).from(DataSource.database(database))

Result Set Format

The result set returned by queries using SelectResult.all is an array of dictionary objects — one for each document matching the query criteria.

For each result object, the key is the database name and the 'value' is a dictionary representing each document property as a key-value pair — see: Example 17.

Example 17. Format of Result Set (All Properties)

[
  {
    "travel-sample": { (1)
      "callsign": "MILE-AIR",
      "country": "United States",
      "iata": "Q5",
      "icao": "MLA",
      "id": 10,
      "name": "40-Mile Air",
      "type": "airline"
    }
  },
  {
    "travel-sample": { (2)
      "callsign": "ALASKAN-AIR",
      "country": "United States",
      "iata": "AA",
      "icao": "AAA",
      "id": 10,
      "name": "Alaskan Airways",
      "type": "airline"
    }
  }
]

1	Here we see the result for the first document matching the query criteria.
2	Here we see the result for the next document matching the query criteria.

Result Set Access

In this case access the retrieved document properties by converting each row’s value, in turn, to a dictionary — as shown in Example 18.

Example 18. Using Document Properties (All)

let results = try query.execute()
for row in results {
    let docsProps = row.dictionary(at: 0)! (1)

    let docid = docsProps.string(forKey: "id")
    let name = docsProps.string(forKey: "name")
    let type = docsProps.string(forKey: "type")
    let city = docsProps.string(forKey: "city")

    print("\(docid): \(name), \(type), \(city)")
    let hotel = row.dictionary(at: 0)!  (2)
    guard let hotelId = hotel.string(forKey: "id") else {
        continue
    }

    hotels[hotelId] = hotel
}

1	Here we get the dictionary of document properties using the database name as the key. You can add this dictionary to an array of returned matches, for processing elsewhere in the app.
2	Alternatively you can access the document properties here, by using the property names as keys to the dictionary object.

Select Specific Properties

Query

Here we use SelectResult.expression(property("<property-name>"))) to specify the document properties we want our query to return — see: Example 19.

Example 19. Query selecting Specific Properties

let database = try! Database(name: "hotel")

let query = QueryBuilder
    .select(SelectResult.expression(Meta.id).as("metaId"),
            SelectResult.expression(Expression.property("id")),
            SelectResult.expression(Expression.property("name")),
            SelectResult.expression(Expression.property("city")),
            SelectResult.expression(Expression.property("type")))
    .from(DataSource.database(database))

Result Set Format

The result set returned when selecting only specific document properties is an array of dictionary objects — one for each document matching the query criteria.

Each result object comprises a key-value pair for each selected document property — see Example 20

Example 20. Format of Result Set (Specific Properties)

[
  { (1)
    "id": "hotel123",
    "type": "hotel",
    "name": "Hotel Ghia"
  },
  { (2)
    "id": "hotel456",
    "type": "hotel",
    "name": "Hotel Deluxe",
  }
]

1	Here we see the result for the first document matching the query criteria.
2	Here we see the result for the next document matching the query criteria.

Result Set Access

Access the retrieved properties by converting each row into a dictionary — as shown in Example 21.

Example 21. Using Returned Document Properties (Specific Properties)

for result in try! query.execute() {
    let docID = result.string(forKey: "metaId")!
    print("processing doc: \(docID)")

    let id = result.string(forKey: "id")!
    var hotel = Hotel(id: id)
    hotel.name = result.string(forKey: "name")
    hotel.city = result.string(forKey: "city")
    hotel.type = result.string(forKey: "type")
    hotels[id] = hotel
} // end for

Select Document Id Only

Query

You would typically use this type of query if retrieval of document properties directly would consume excessive amounts of memory and-or processing time — see: Example 22.

Example 22. Query selecting only Doc Id

let database = try Database(name: "hotel")
let query = QueryBuilder.select(SelectResult.expression(Meta.id).as("metaId"))
    .from(DataSource.database(database))

Result Set Format

The result set returned by queries using a SelectResult expression of the form SelectResult.expression(meta.id) is an array of dictionary objects — one for each document matching the query criteria. Each result object has id as the key and the ID value as its value — -see Example 23.

Example 23. Format of Result Set (Doc Id only)

[
  {
    "id": "hotel123"
  },
  {
    "id": "hotel456"
  },
]

Result Set Access

In this case, access the required document’s properties by unpacking the id and using it to get the document from the database — see: Example 24.

Example 24. Using Returned Document Properties (Document Id)

let results = try query.execute()
for result in results {

    print(result.toDictionary())

    let docId = result.string(forKey: "metaId")! (1)
    print("Document Id is -- \(docId)")

    // Now you can get the document using the ID
    let doc = database.document(withID: docId)!

    let hotelId = doc.string(forKey: "id")!

    let name = doc.string(forKey: "name")

    let city = doc.string(forKey: "city")

    let type = doc.string(forKey: "type")

    // ... process document properties as required
    print("Result properties are: \(hotelId), \(name), \(city), \(type)")


}

1	Extract the Id value from the dictionary and use it to get the document from the database

Select Count-only

Query

Example 25. Query selecting a Count-only

let database = try Database(name: "hotel")
let query = QueryBuilder
    .select(SelectResult.expression(Function.count(Expression.all())).as("mycount"))
    .from (DataSource.database(database)).groupBy(Expression.property("type"))

1	The alias name, `mycount`, is used to access the count value.

Result Set Format

The result set returned by a count such as Select.expression(Function.count(Expression.all))) is a key-value pair. The key is the count name, as defined using SelectResult.as — see: Example 26 for the format and Example 25 for the query.

Example 26. Format of Result Set (Count)

{
  "mycount": 6
}

1	Here we see the key-value pair returned by a count.

Result Set Access

Access the count using its alias name (mycount in this example) — see Example 27

Example 27. Using Returned Document Properties (Count)

for result in try query.execute() {
    let count = result.int(forKey: "mycount") (1)
    print("There are ", count, " rows")
}

1	Get the count using the `SelectResult.as` alias, which is used as its key.

Handling Pagination

One way to handle pagination in high-volume queries is to retrieve the results in batches. Use the limit and offset feature, to return a defined number of results starting from a given offset — see: Example 28.

Example 28. Query Pagination

let offset = 0;
let limit = 20;
//
let query = QueryBuilder
    .select(SelectResult.all())
    .from(DataSource.database(database))
    .limit(Expression.int(limit), offset: Expression.int(offset))

1	Return a maximum of `limit` results starting from result number `offset`

For more on using the QueryBuilder API, see our blog: Introducing the Query Interface in Couchbase Mobile

JSON Result Sets

Couchbase Lite for Swift provides a convenience API to convert query results to JSON strings.

Example 29. Using JSON Results

Use result.toJSON() to transform your result string into a JSON string, which can easily be serialized or used as required in your application. See <> for a working example.


// In this example the Hotel class is defined using Codable
//
// class Hotel : Codable {
//   var id : String = "undefined"
//   var type : String = "hotel"
//   var name : String = "undefined"
//   var city : String = "undefined"
//   var country : String = "undefined"
//   var description : String? = ""
//   var text : String? = ""
//   ... other class content
// }

let results = try query.execute()
for row in  results {

    // get the result into a JSON String
    let jsonString = row.toJSON()

    let thisJsonObj:Dictionary =
    try (JSONSerialization.jsonObject(
        with: jsonString.data(using: .utf8)!,
        options: .allowFragments)
         as? [String: Any])!

    // Use Json Object to populate Native object
    // Use Codable class to unpack JSON data to native object
    var this_hotel: Hotel = try JSONDecoder().decode(Hotel.self, from: jsonString.data(using: .utf8)!) (1)

    // ALTERNATIVELY unpack in steps
    this_hotel.id = thisJsonObj["id"] as! String
    this_hotel.name = thisJsonObj["name"] as! String
    this_hotel.type = thisJsonObj["type"] as! String
    this_hotel.city = thisJsonObj["city"] as! String
    hotels[this_hotel.id] = this_hotel

} // end for

JSON String Format

If your query selects ALL then the JSON format will be:

{
  database-name: {
    key1: "value1",
    keyx: "valuex"
  }
}

If your query selects a sub-set of available properties then the JSON format will be:

{
  key1: "value1",
  keyx: "valuex"
}

Predictive Query

Enterprise Edition only

Predictive Query is an Enterprise Edition feature.

Predictive Query enables Couchbase Lite queries to use machine learning, by providing query functions that can process document data (properties or blobs) via trained ML models.

Let’s consider an image classifier model that takes a picture as input and outputs a label and probability.

To run a predictive query with a model as the one shown above, you must implement the following steps.

Integrate the Model
Register the Model
Create an Index (Optional)
Run a Prediction Query
Deregister the Model

Integrate the Model

To integrate a model with Couchbase Lite, you must implement the PredictiveModel interface which has only one function called predict() — see: Example 30.

Example 30. Integrating a predictive model

// `myMLModel` is a fake implementation
// this would be the implementation of the ml model you have chosen
class myMLModel {
    static func predictImage(data: Data) -> [String : AnyObject] { return [:] }
}

class ImageClassifierModel: PredictiveModel {
    func predict(input: DictionaryObject) -> DictionaryObject? {
        guard let blob = input.blob(forKey: "photo") else {
            return nil
        }

        let imageData = blob.content!
        // `myMLModel` is a fake implementation
        // this would be the implementation of the ml model you have chosen
        let modelOutput = myMLModel.predictImage(data: imageData)

        let output = MutableDictionaryObject(data: modelOutput)
        return output (1)
    }
}

1	The `predict(input) -> output` method provides the input and expects the result of using the machine learning model. The input and output of the predictive model is a `DictionaryObject`. Therefore, the supported data type will be constrained by the data type that the `DictionaryObject` supports.

Register the Model

To register the model you must create a new instance and pass it to the Database.prediction.registerModel static method.

Example 31. Registering a predictive model

let model = ImageClassifierModel()
Database.prediction.registerModel(model, withName: "ImageClassifier")

Create an Index

Creating an index for a predictive query is highly recommended. By computing the predictions during writes and building a prediction index, you can significantly improve the speed of prediction queries (which would otherwise have to be computed during reads).

There are two types of indexes for predictive queries:

Value Index
Predictive Index

Value Index

The code below creates a value index from the "label" value of the prediction result. When documents are added or updated, the index will call the prediction function to update the label value in the index.

Example 32. Creating a value index

let input = Expression.dictionary(["photo": Expression.property("photo")])
let prediction = Function.prediction(model: "ImageClassifier", input: input)

let index = IndexBuilder.valueIndex(items: ValueIndexItem.expression(prediction.property("label")))
try database.createIndex(index, withName: "value-index-image-classifier")

Predictive Index

Predictive Index is a new index type used for predictive query. It differs from the value index in that it caches the predictive results and creates a value index from that cache when the predictive results values are specified.

Example 33. Creating a predictive index

Here we create a predictive index from the label value of the prediction result.

let input = Expression.dictionary(["photo": Expression.property("photo")])

let index = IndexBuilder.predictiveIndex(model: "ImageClassifier", input: input)
try database.createIndex(index, withName: "predictive-index-image-classifier")

Run a Prediction Query

The code below creates a query that calls the prediction function to return the "label" value for the first 10 results in the database.

Example 34. Creating a value index

let input = Expression.dictionary(["photo": Expression.property("photo")])
let prediction = Function.prediction(model: "ImageClassifier", input: input) (1)

let query = QueryBuilder
    .select(SelectResult.all())
    .from(DataSource.database(database))
    .where(
        prediction.property("label").equalTo(Expression.string("car"))
            .and(
                prediction.property("probablity")
                    .greaterThanOrEqualTo(Expression.double(0.8))
            )
    )

// Run the query.
do {
    let result = try query.execute()
    print("Number of rows :: \(result.allResults().count)")
} catch {
    fatalError("Error running the query")
}

The PredictiveModel.predict() method returns a constructed Prediction Function object which can be used further to specify a property value extracted from the output dictionary of the PredictiveModel.predict() function.

The null value returned by the prediction method will be interpreted as MISSING value in queries.

Deregister the Model

To deregister the model you must call the Database.prediction.unregisterModel static method.

Example 35. Deregister a value index

Database.prediction.unregisterModel(withName: "ImageClassifier")

Integrate a Model with CoreMLPredictiveModel

iOS Only

CoreMLPredictiveModel is a Core ML based implementation of the PredictiveModel protocol that facilitates the integration of Core ML models with Couchbase Lite.

The following example describes how to load a Core ML model using CoreMLPredictiveModel. All other steps (register, indexing, query, unregister) are the same as with a model that is integrated using your own PredictiveModel implementation.

// Load MLModel from `ImageClassifier.mlmodel`
let modelURL = Bundle.main.url(forResource: "ImageClassifier", withExtension: "mlmodel")!
let compiledModelURL = try MLModel.compileModel(at: modelURL)
let model = try MLModel(contentsOf: compiledModelURL)
let predictiveModel = CoreMLPredictiveModel(mlModel: model)

// Register model
Database.prediction.registerModel(predictiveModel, withName: "ImageClassifier")

How to . . .

Learn more . . .

Dive Deeper . . .

Mobile Forum | Blog | Tutorials

1. Starting in Couchbase Lite 2.5