Recommend points | Qdrant

Retrieves points that are closer to stored positive examples and further from negative examples.

Path parameters

collection_namestringRequired

Name of the collection to search in

Headers

api-keystringRequired

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.

limitintegerRequired>=1

Max number of result to return

shard_keystring or uint64 or list of strings or uint64s or anyOptional

Specify in which shards to look for the points, if not specified - look in all shards

positivelist of uint64s or strings or lists of doubles or objectsOptional

Look for vectors closest to those

negativelist of uint64s or strings or lists of doubles or objectsOptional

Try to avoid vectors like this

strategyenum or anyOptional

How to use positive and negative examples to find the results

filterobject or anyOptional

Look only for points which satisfies this conditions

paramsobject or anyOptional

Additional search params

offsetintegerOptional>=0

Offset of the first result to return. May be used to paginate results. Note: large offset values may cause performance issues.

with_payloadboolean or list of strings or object or anyOptional

Select which payload to return with the response. Default is false.

with_vectorboolean or list of strings or anyOptional

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

score_thresholddoubleOptional

Define a minimal score threshold for the result. If defined, less similar results will not be returned. Score of the returned result might be higher or smaller than the threshold depending on the Distance function used. E.g. for cosine similarity only higher scores will be returned.

usingstring or anyOptional

Define which vector to use for recommendation, if not specified - try to use default vector

lookup_fromobject or anyOptional

The location used to lookup vectors. If not specified - use current collection. Note: the other collection should have the same vector size as the current collection

Response

successful operation

usageobject or any or null

timedouble or null

Time spent to process this request

statusstring or null

resultlist of objects or null

Was this page helpful?

Recommend batch points

Built with

1	from qdrant_client import QdrantClient, models
2
3	client = QdrantClient(url="http://localhost:6333")
4
5	client.recommend(
6	collection_name="{collection_name}",
7	positive=[100, 231],
8	negative=[718, [0.2, 0.3, 0.4, 0.5]],
9	strategy=models.RecommendStrategy.AVERAGE_VECTOR,
10	query_filter=models.Filter(
11	must=[
12	models.FieldCondition(
13	key="city",
14	match=models.MatchValue(
15	value="London",
16	),
17	)
18	]
19	),
20	limit=3,
21	)

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	{
15	"id": 42,
16	"version": 3,
17	"score": 0.75,
18	"payload": {
19	"city": "London",
20	"color": "green"
21	},
22	"vector": [
23	0.875,
24	0.140625,
25	0.897599995136261
26	],
27	"shard_key": "region_1",
28	"order_value": 42
29	}
30	]
31	}