For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
CloudGitHub
  • API Reference
      • POSTSearch points
      • POSTSearch batch points
      • POSTSearch point groups
      • POSTRecommend points
      • POSTRecommend batch points
      • POSTRecommend point groups
      • POSTDiscover points
      • POSTDiscover batch points
      • POSTQuery points
      • POSTQuery points in batch
      • POSTQuery point groups
      • POSTDistance matrix pairs
      • POSTDistance matrix offsets
LogoLogo
CloudGitHub
API ReferenceSearch

Recommend point groups

Deprecated
POST
/collections/:collection_name/points/recommend/groups
POST
/collections/:collection_name/points/recommend/groups
$curl  -X POST \
>  'http://localhost:6333/collections/collection_name/points/recommend/groups' \
>  --header 'api-key: <api-key-value>' \
>  --header 'Content-Type: application/json' \
>  --data-raw '{
>  "positive": [
>    100,
>    231
>  ],
>  "negative": [
>    718
>  ],
>  "group_by": "document_id",
>  "limit": 3,
>  "group_size": 2
>}'
200Successful
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    "groups": [
15      {
16        "hits": [
17          {
18            "id": 42,
19            "version": 3,
20            "score": 0.75,
21            "payload": {},
22            "vector": {},
23            "shard_key": "region_1",
24            "order_value": 42
25          }
26        ],
27        "id": "string",
28        "lookup": {
29          "id": 42,
30          "payload": {},
31          "vector": {},
32          "shard_key": "region_1",
33          "order_value": 42
34        }
35      }
36    ]
37  }
38}
Retrieves points that are closer to stored positive examples and further from negative examples. Results are grouped by the specified payload field.
Was this page helpful?
Previous

Discover points

Next
Built with

Authentication

api-keystring
API Key authentication via header

Path parameters

collection_namestringRequired
Name of the collection to search in

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

Request points based on positive and negative examples, grouped by a payload field.
group_bystringRequired>=1 character
Payload field to group by, must be a string or number field. If the field contains more than 1 value, all values will be used for grouping. One point can be in multiple groups.
group_sizeuintRequired
Maximum amount of points to return per group
limituintRequired
Maximum amount of groups 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
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_thresholddouble or nullOptional
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

with_lookupstring or object or anyOptional
Look for points in another collection using the group ids

Response

successful operation
usageobject or any
timedouble
Time spent to process this request
statusstring
resultobject