Query points | Qdrant | API Reference

1 from qdrant_client import QdrantClient, models 2 3 client = QdrantClient(url="http://localhost:6333") 4 5 # Query nearest by ID 6 nearest = client.query_points( 7 collection_name="{collection_name}", 8 query="43cf51e2-8777-4f52-bc74-c2cbde0c8b04", 9 ) 10 11 # Recommend on the average of these vectors 12 recommended = client.query_points( 13 collection_name="{collection_name}", 14 query=models.RecommendQuery(recommend=models.RecommendInput( 15 positive=["43cf51e2-8777-4f52-bc74-c2cbde0c8b04", [0.11, 0.35, 0.6, ...]], 16 negative=[[0.01, 0.45, 0.67, ...]] 17 )) 18 ) 19 20 # Fusion query 21 hybrid = client.query_points( 22 collection_name="{collection_name}", 23 prefetch=[ 24 models.Prefetch( 25 query=models.SparseVector(indices=[1, 42], values=[0.22, 0.8]), 26 using="sparse", 27 limit=20, 28 ), 29 models.Prefetch( 30 query=[0.01, 0.45, 0.67, ...], # <-- dense vector 31 using="dense", 32 limit=20, 33 ), 34 ], 35 query=models.FusionQuery(fusion=models.Fusion.RRF), 36 ) 37 38 # 2-stage query 39 refined = client.query_points( 40 collection_name="{collection_name}", 41 prefetch=models.Prefetch( 42 query=[0.01, 0.45, 0.67, ...], # <-- dense vector 43 limit=100, 44 ), 45 query=[ 46 [0.1, 0.2, ...], # <─┐ 47 [0.2, 0.1, ...], # < ├─ multi-vector 48 [0.8, 0.9, ...], # < ┘ 49 ], 50 using="colbert", 51 limit=10, 52 ) 53 54 # Random sampling (as of 1.11.0) 55 sampled = client.query_points( 56 collection_name="{collection_name}", 57 query=models.SampleQuery(sample=models.Sample.RANDOM) 58 ) 59 60 # Score boost depending on payload conditions (as of 1.14.0) 61 tag_boosted = client.query_points( 62 collection_name="{collection_name}", 63 prefetch=models.Prefetch( 64 query=[0.2, 0.8, ...], # <-- dense vector 65 limit=50 66 ), 67 query=models.FormulaQuery( 68 formula=models.SumExpression(sum=[ 69 "$score", 70 models.MultExpression(mult=[0.5, models.FieldCondition(key="tag", match=models.MatchAny(any=["h1", "h2", "h3", "h4"]))]), 71 models.MultExpression(mult=[0.25, models.FieldCondition(key="tag", match=models.MatchAny(any=["p", "li"]))]) 72 ] 73 )) 74 ) 75 76 # Score boost geographically closer points (as of 1.14.0) 77 geo_boosted = client.query_points( 78 collection_name="{collection_name}", 79 prefetch=models.Prefetch( 80 query=[0.2, 0.8, ...], # <-- dense vector 81 limit=50 82 ), 83 query=models.FormulaQuery( 84 formula=models.SumExpression(sum=[ 85 "$score", 86 models.GaussDecayExpression( 87 gauss_decay=models.DecayParamsExpression( 88 x=models.GeoDistance( 89 geo_distance=models.GeoDistanceParams( 90 origin=models.GeoPoint( 91 lat=52.504043, 92 lon=13.393236 93 ), # Berlin 94 to="geo.location" 95 ) 96 ), 97 scale=5000 # 5km 98 ) 99 ) 100 ]), 101 defaults={"geo.location": models.GeoPoint(lat=48.137154, lon=11.576124)} # Munich 102 ) 103 )

1 { 2 "usage": { 3 "cpu": 1, 4 "payload_io_read": 1, 5 "payload_io_write": 1, 6 "payload_index_io_read": 1, 7 "payload_index_io_write": 1, 8 "vector_io_read": 1, 9 "vector_io_write": 1 10 }, 11 "time": 0.002, 12 "status": "ok", 13 "result": { 14 "points": [ 15 { 16 "id": 42, 17 "version": 3, 18 "score": 0.75, 19 "payload": { 20 "city": "London", 21 "color": "green" 22 }, 23 "vector": [ 24 0.875, 25 0.140625, 26 0.897599995136261 27 ], 28 "shard_key": "region_1", 29 "order_value": 42 30 } 31 ] 32 } 33 }

Universally query points. This endpoint covers all capabilities of search, recommend, discover, filters. But also enables hybrid and multi-stage queries.

Path parameters

collection_namestringRequired

Name of the collection to query

Query parameters

consistencyinteger or enumOptional

Define read consistency guarantees for the operation

timeoutintegerOptional>=1

If set, overrides global timeout for this request. Unit is seconds.

Request

This endpoint expects an object.

shard_keystring or uint64 or list of strings or uint64s or anyOptional

prefetchobject or list of objects or anyOptional

Sub-requests to perform first. If present, the query will be performed on the results of the prefetch(es).

querylist of doubles or object or list of lists of doubles or uint64 or string or object or anyOptional

Query to perform. If missing without prefetches, returns points ordered by their IDs.

usingstringOptional

Define which vector name to use for querying. If missing, the default vector is used.

filterobject or anyOptional

Filter conditions - return only those points that satisfy the specified conditions.

paramsobject or anyOptional

Search params for when there is no prefetch

score_thresholddoubleOptional

Return points with scores better than this threshold.

limitintegerOptional>=1

Max number of points to return. Default is 10.

offsetintegerOptional>=0

Offset of the result. Skip this many points. Default is 0

with_vectorboolean or list of strings or anyOptional

Options for specifying which vectors to include into the response. Default is false.

with_payloadboolean or list of strings or object or anyOptional

Options for specifying which payload to include or not. Default is false.

lookup_fromobject or anyOptional

The location to use for IDs lookup, if not specified - use the current collection and the ‘using’ vector Note: the other collection vectors should have the same vector size as the ‘using’ vector in the current collection

Response

successful operation

usageobject or anyOptional

timedoubleOptional

Time spent to process this request

statusstringOptional

resultobjectOptional

Path parameters

Headers

Query parameters

Request

Response