Metadata Filtering
You can further restrict the vector similarity search by providing a filter based on a specific metadata criteria.
Queries with metadata filters only return vectors which have metadata matching with the filter.
Upstash Vector allows you to filter keys which have the following value types:
- string
- number
- boolean
- object
- array
Filtering is implemented as a combination of in and post-filtering. Every query is assigned a filtering budget,
determining the number of candidate vectors that can be compared against the filter during query execution. If this
budget is exceeded, the system fallbacks into post-filtering. Therefore, with highly selective filters, fewer
than topK vectors may be returned.
Filter Syntax
A filter has a syntax that resembles SQL, which consists of operators on object keys and boolean operators to combine them.
Assuming you have a metadata like below:
{ "city": "Istanbul", "country": "Turkey", "is_capital": false, "population": 15460000, "geography": { "continent": "Asia", "coordinates": { "latitude": 41.0082, "longitude": 28.9784 } }, "economy": { "currency": "TRY", "major_industries": [ "Tourism", "Textiles", "Finance" ] }}Then, you can query similar vectors with a filter like below:
from upstash_vector import Indexindex = Index( url="UPSTASH_VECTOR_REST_URL", token="UPSTASH_VECTOR_REST_TOKEN",)index.query( vector=[0.9215, 0.3897], filter="population >= 1000000 AND geography.continent = 'Asia'", top_k=5, include_metadata=True)import { Index } from "@upstash/vector"const index = new Index({ url: "UPSTASH_VECTOR_REST_URL", token: "UPSTASH_VECTOR_REST_TOKEN",})await index.query({ vector: [0.9215, 0.3897], filter: "population >= 1000000 AND geography.continent = 'Asia'", topK: 5, includeMetadata: true,});package mainimport ( "github.com/upstash/vector-go")func main() { index := vector.NewIndex("UPSTASH_VECTOR_REST_URL", "UPSTASH_VECTOR_REST_TOKEN") index.Query(vector.Query{ Vector: []float32{0.9215, 0.3897}, Filter: `population >= 1000000 AND geography.continent = 'Asia'`, TopK: 5, IncludeMetadata: true, })}use Upstash\Vector\Index;use Upstash\Vector\VectorQuery;$index = new Index( url: 'UPSTASH_VECTOR_REST_URL', token: 'UPSTASH_VECTOR_REST_TOKEN',);$index->query(new VectorQuery( vector: [0.9215, 0.3897], topK: 5, includeMetadata: true, filter: "population >= 1000000 AND geography.continent = 'Asia'",));curl $UPSTASH_VECTOR_REST_URL/query \ -H "Authorization: Bearer $UPSTASH_VECTOR_REST_TOKEN" \ -d '{ "vector":[0.9215,0.3897], "topK" : 5, "filter": "population >= 1000000 AND geography.continent = \"Asia\"", "includeMetadata": true}'Operators
Equals (=)
The equals operator filters keys whose values are equal to the given literal.
It is applicable to string, number, and boolean values.
country = 'Turkey' AND population = 15460000 AND is_capital = falseNot Equals (!=)
The not equals operator filters keys whose values are not equal to the given literal.
It is applicable to string, number, and boolean values.
country != 'Germany' AND population != 12500000 AND is_capital != trueLess Than (<)
The less than operator filters keys whose values are less than the given literal.
It is applicable to number values.
population < 20000000 OR geography.coordinates.longitude < 30.0Less Than or Equals (<=)
The less than or equals operator filters keys whose values are less than or equal to the given literal.
It is applicable to number values.
population <= 20000000 OR geography.coordinates.longitude <= 30.0Greater Than (>)
The greater than operator filters keys whose values are greater than the given literal.
It is applicable to number values.
population > 10000000 OR geography.coordinates.latitude > 39.5Greater Than or Equals (>=)
The greater than or equals operator filters keys whose values are greater than or equal to the given literal.
It is applicable to number values.
population >= 10000000 OR geography.coordinates.latitude >= 39.5Glob
The glob operator filters keys whose values match with the given UNIX glob pattern.
It is applicable to string values.
It is a case sensitive operator.
The glob operator supports the following wildcards:
*matches zero or more characters.?matches exactly one character.[]matches one character from the list[abc]matches eithera,b, orc.[a-z]matches one of the range of characters fromatoz.[^abc]matches any one character other thana,b, orc.[^a-z]matches any one character other thanatoz.
For example, the filter below would only match with city names whose second character is s or z,
and ends with anything other than m to z.
city GLOB '?[sz]*[^m-z]'Not Glob
The not glob operator filters keys whose values do not match with the given UNIX glob pattern.
It is applicable to string values.
It has the same properties with the glob operator.
For example, the filter below would only match with city names whose first character is anything other than A.
city NOT GLOB 'A*'In
The in operator filters keys whose values are equal to any of the given literals.
It is applicable to string, number, and boolean values.
country IN ('Germany', 'Turkey', 'France')Semantically, it is equivalent to equals operator applied to all of the given literals with OR boolean operator in between:
country = 'Germany' OR country = 'Turkey' OR country = 'France'Not In
The not in operator filters keys whose values are not equal to any of the given literals.
It is applicable to string, number, and boolean values.
economy.currency NOT IN ('USD', 'EUR')Semantically, it is equivalent to not equals operator applied to all of the given literals with AND boolean operator in between:
economy.currency != 'USD' AND economy.currency != 'EUR'Contains
The contains operator filters keys whose values contain the given literal.
It is applicable to array values.
economy.major_industries CONTAINS 'Tourism'Not Contains
The not contains operator filters keys whose values do not contain the given literal.
It is applicable to array values.
economy.major_industries NOT CONTAINS 'Steel Production'Has Field
The has field operator filters keys which have the given JSON field.
HAS FIELD geography.coordinatesHas Not Field
The has not field operator filters keys which do not have the given JSON field.
HAS NOT FIELD geography.coordinates.longitudeBoolean Operators
Operators above can be combined with AND and OR boolean operators to form
compound filters.
country = 'Turkey' AND population > 10000000Boolean operators can be grouped with parentheses to have higher precedence.
country = 'Turkey' AND (population > 10000000 OR is_capital = false)When no parentheses are provided in ambiguous filters, AND will have higher
precedence than OR. So, the filter
country = 'Turkey' AND population > 10000000 OR is_capital = falsewould be equivalent to
(country = 'Turkey' AND population > 10000000) OR is_capital = falseFiltering Nested Objects
It is possible to filter nested object keys by referencing them with the . accessor.
Nested objects can be at arbitrary depths, so more than one . accessor can be used
in the same identifier.
economy.currency != 'USD' AND geography.coordinates.latitude >= 35.0Filtering Array Elements
Apart from the CONTAINS and NOT CONTAINS operators, individual array elements can also
be filtered by referencing them with the [] accessor by their indexes.
Indexing is zero based.
economy.major_industries[0] = 'Tourism'Also, it is possible to index from the back using the # character with negative values.
# can be thought as the number of elements in the array, so [#-1] would reference the
last element.
economy.major_industries[#-1] = 'Finance'Miscellaneous
- Identifiers (the left side of the operators) should be of the form
[a-zA-Z_][a-zA-Z_0-9.[\]#-]*. In simpler terms, they should start with characters from the English alphabet or_, and can continue with same characters plus numbers and other accessors like.,[0], or[#-1]. - The string literals (strings in the right side of the operators) can be either single or double quoted.
- Boolean literals are represented as
1or0. - The operators, boolean operators, and boolean literals are case insensitive.