Qdrant Search API
Find points in a collection.
Qdrant Search API is one of 9 APIs that Qdrant publishes on the APIs.io network, described by a machine-readable OpenAPI specification.
Tagged areas include Search. The published artifact set on APIs.io includes an OpenAPI specification and API documentation.
This API exposes 13 operations across 13 paths, and defines 149 schemas. It is described by OpenAPI 3.0.1, at version master.
Requests are made against a single base URL, {protocol}://{hostname}:{port}.
13 operations
13 paths
149 schemas
13 POST
Metadata
The identity and technical contract details declared by the specification.
Authentication & Security 2
Qdrant Search API declares
2 security schemes
for authenticating requests.
An API key is passed in the header as api-key (api-key).
It accepts HTTP bearer tokens (bearerAuth).
By default, every request must be authenticated, though some operations may also be called without credentials.
api-key— Authorization key, either read-write or read-only
Paths & Operations 13
Across 13 paths, the API surfaces 13 operations — 13 POST. Each is listed below with its method, path, parameters, and response codes.
Search 13
Find points in a collection.
POST
/collections/{collection_name}/points/searchdeprecated
Search points
POST
/collections/{collection_name}/points/search/batchdeprecated
Search batch points
POST
/collections/{collection_name}/points/search/groupsdeprecated
Search point groups
POST
/collections/{collection_name}/points/recommenddeprecated
Recommend points
POST
/collections/{collection_name}/points/recommend/batchdeprecated
Recommend batch points
POST
/collections/{collection_name}/points/recommend/groupsdeprecated
Recommend point groups
POST
/collections/{collection_name}/points/discoverdeprecated
Discover points
POST
/collections/{collection_name}/points/discover/batchdeprecated
Discover batch points
POST
/collections/{collection_name}/points/query
Query points
POST
/collections/{collection_name}/points/query/batch
Query points in batch
POST
/collections/{collection_name}/points/query/groups
Query points, grouped by a given payload field
POST
/collections/{collection_name}/points/search/matrix/pairs
Search points matrix distance pairs
POST
/collections/{collection_name}/points/search/matrix/offsets
Search points matrix distance offsets
Schemas 149
The contract defines 149 schemas that model the data the API accepts and returns. The most detailed are RecommendGroupsRequest (15 properties), QueryGroupsRequest (14 properties), RecommendRequest (13 properties), QueryRequest (12 properties). Each schema is shown below with its type and property counts.
RecommendInput
object
3 properties
WithVector
Options for specifying which vector to include
SearchMatrixPair
object
Pair of points (a, b) with score
3 properties
3 required
SumExpression
object
1 property
1 required
SearchMatrixRequest
object
5 properties
IsNullCondition
object
Select points with null payload for a specified field
1 property
1 required
FieldCondition
object
All possible payload filtering conditions
9 properties
1 required
HasIdCondition
object
ID-based filtering condition
1 property
1 required
AbsExpression
object
1 property
1 required
GeoLineString
object
Ordered sequence of GeoPoints representing the line
1 property
1 required
OrderByQuery
object
1 property
1 required
IsEmptyCondition
object
Select points with empty payload for a specified field
1 property
1 required
Usage
object
Usage of the hardware resources, spent to process the request
2 properties
DiscoverInput
object
2 properties
2 required
Payload
object
FusionQuery
object
1 property
1 required
Prefetch
object
8 properties
Filter
object
4 properties
ExtendedPointId
Type, used for specifying point ID in user interface
VectorInput
InferenceUsage
object
1 property
1 required
VectorOutput
Vector Data stored in Point
ShardKey
RecommendStrategy
string
How to use positive and negative examples to find the results, default is averagevector: averagevector - Average positive and negative vectors and create a sin…
SparseVector
object
Sparse vector structure
2 properties
2 required
LookupLocation
object
Defines a location to use for looking up the vector. Specifies collection and vector field name.
3 properties
1 required
GeoDistanceParams
object
2 properties
2 required
DivExpression
object
1 property
1 required
HasVectorCondition
object
Filter points which have specific vector assigned
1 property
1 required
OrderByInterface
ContextExamplePair
object
2 properties
2 required
StartFrom
RecommendGroupsRequest
object
15 properties
3 required
VectorStructOutput
Vector data stored in Point
MatchAny
object
Exact match on any of the given values
1 property
1 required
WithPayloadInterface
Options for specifying which payload to include or not
MatchPhrase
object
Full-text phrase match of the string.
1 property
1 required
DiscoverRequestBatch
object
1 property
1 required
InferenceObject
object
WARN: Work-in-progress, unimplemented Custom object for embedding. Requires inference infrastructure, unimplemented.
3 properties
2 required
SearchMatrixOffsetsResponse
object
4 properties
4 required
DatetimeExpression
object
1 property
1 required
Expression
ReadConsistencyType
string
majority - send N/2+1 random request and return points, which present on all of them quorum - send requests to all nodes and return points which present on maj…
ExpExpression
object
1 property
1 required
SearchMatrixPairsResponse
object
1 property
1 required
ContextQuery
object
1 property
1 required
Range
object
Range filter request
4 properties
Condition
SearchRequestBatch
object
1 property
1 required
ReadConsistency
Read consistency parameter Defines how many replicas should be queried to get the result N - send N random request and return points, which present on all of t…
NamedVector
object
Dense vector data with name
2 properties
2 required
ContextInput
StopwordsSet
object
2 properties
NamedSparseVector
object
Sparse vector data with name
2 properties
2 required
QueryResponse
object
1 property
1 required
PayloadSelectorExclude
object
1 property
1 required
Image
object
WARN: Work-in-progress, unimplemented Image object for embedding. Requires inference infrastructure, unimplemented.
3 properties
2 required
MinShould
object
2 properties
2 required
MatchTextAny
object
Full-text match of at least one token of the string.
1 property
1 required
PayloadField
object
Payload field
1 property
1 required
GeoRadius
object
Geo filter request Matches coordinates inside the circle of radius and center with coordinates center
2 properties
2 required
ModelUsage
object
1 property
1 required
RelevanceFeedbackInput
object
3 properties
3 required
LnExpression
object
1 property
1 required
FormulaQuery
object
2 properties
1 required
NaiveFeedbackStrategy
object
1 property
1 required
StemmingAlgorithm
Different stemming algorithms with their configs.
RelevanceFeedbackQuery
object
1 property
1 required
SearchParams
object
Additional parameters of the search
5 properties
MatchValue
object
Exact match of the given value
1 property
1 required
Nested
object
Select points with payload for a specified nested field
2 properties
2 required
HardwareUsage
object
Usage of the hardware resources, spent to process the request
7 properties
7 required
TokenizerType
string
DatetimeRange
object
Range filter request
4 properties
LinDecayExpression
object
1 property
1 required
NegExpression
object
1 property
1 required
PayloadSelectorInclude
object
1 property
1 required
DecayParamsExpression
object
4 properties
1 required
Rrf
object
Parameters for Reciprocal Rank Fusion
2 properties
NamedVectorStruct
Vector data separator for named and unnamed modes Unnamed mode: { "vector": [1.0, 2.0, 3.0] } or named mode: { "vector": { "vector": [1.0, 2.0, 3.0], "name": "…
DiscoverQuery
object
1 property
1 required
Log10Expression
object
1 property
1 required
ScoredPoint
object
Search result
7 properties
3 required
GeoPolygon
object
Geo filter request Matches coordinates inside the polygon, defined by exterior and interiors
2 properties
1 required
ErrorResponse
object
3 properties
ShardKeySelector
RecommendQuery
object
1 property
1 required
QuantizationSearchParams
object
Additional parameters of the search
3 properties
Record
object
Point data
5 properties
1 required
ValuesCount
object
Values count filter request
4 properties
GeoDistance
object
1 property
1 required
OrderBy
object
3 properties
1 required
RecommendRequest
object
Recommendation request. Provides positive and negative examples of the vectors, which can be ids of points that are already stored in the collection, raw vecto…
13 properties
1 required
ValueVariants
UsingVector
PowParams
object
2 properties
2 required
QueryInterface
ShardKeyWithFallback
object
2 properties
2 required
Fusion
string
Fusion algorithm allows to combine results of multiple prefetches. Available fusion algorithms: rrf - Reciprocal Rank Fusion (with default parameters) dbsf - D…
WithLookupInterface
GeoPoint
object
Geo point payload schema
2 properties
2 required
QueryRequest
object
12 properties
Mmr
object
Maximal Marginal Relevance (MMR) algorithm for re-ranking the points.
2 properties
FeedbackStrategy
Bm25Config
object
Configuration of the local bm25 models.
11 properties
GeoBoundingBox
object
Geo filter request Matches coordinates inside the rectangle, described by coordinates of lop-left and bottom-right edges
2 properties
2 required
NaiveFeedbackStrategyParams
object
3 properties
3 required
FeedbackItem
object
2 properties
2 required
RangeInterface
QueryGroupsRequest
object
14 properties
1 required
DocumentOptions
Option variants for text documents. Ether general-purpose options or BM25-specific options. BM25-specific will only take effect if the qdrant/bm25 is specified…
SnowballParams
object
2 properties
2 required
PowExpression
object
1 property
1 required
PayloadSelector
Specifies how to treat payload selector
SearchGroupsRequest
object
11 properties
4 required
RecommendRequestBatch
object
1 property
1 required
Sample
string
OrderValue
GaussDecayExpression
object
1 property
1 required
Query
Snowball
string
AnyVariants
GroupId
Value of the groupby key, shared across all the hits in the group
RecommendExample
NearestQuery
object
2 properties
1 required
DatetimeKeyExpression
object
1 property
1 required
Document
object
WARN: Work-in-progress, unimplemented Text document for embedding. Requires inference infrastructure, unimplemented.
3 properties
2 required
GroupsResult
object
1 property
1 required
SnowballLanguage
string
Languages supported by snowball stemmer.
QueryRequestBatch
object
1 property
1 required
Direction
string
StopwordsInterface
MultExpression
object
1 property
1 required
ContextPair
object
2 properties
2 required
MatchText
object
Full-text match of the strings.
1 property
1 required
Match
Match filter request
SearchRequest
object
Search request. Holds all conditions and parameters for the search of most similar points by vector similarity given the filtering restrictions.
9 properties
2 required
ExpDecayExpression
object
1 property
1 required
SqrtExpression
object
1 property
1 required
DiscoverRequest
object
Use context and a target to find the most similar points, constrained by the context.
11 properties
1 required
NestedCondition
object
1 property
1 required
DivParams
object
3 properties
2 required
RrfQuery
object
1 property
1 required
MatchExcept
object
Should have at least one value not matching the any given values
1 property
1 required
Language
string
SampleQuery
object
1 property
1 required
PointGroup
object
3 properties
2 required
WithLookup
object
3 properties
1 required
AcornSearchParams
object
ACORN-related search parameters
2 properties
Specification
The full machine-readable OpenAPI contract behind this narrative.
Source
More from Qdrant 8
Other APIs Qdrant publishes across the network.
Qdrant Aliases API
Qdrant Beta API
Qdrant Collections API
Qdrant Distributed API
Qdrant Indexes API
Qdrant Points API
Qdrant Service API
Qdrant Snapshots API
#Search