POST
/
v1
/
clusters
curl --request POST \
  --url https://api.mixpeek.com/v1/clusters \
  --header 'Content-Type: application/json' \
  --data '{
  "cluster_name": "<string>",
  "collection_id": "<string>",
  "cluster_type": "vector",
  "vector_config": {
    "feature_extractor_name": "<string>",
    "clustering_method": "hdbscan",
    "sample_size": 1000,
    "hdbscan_parameters": {
      "min_cluster_size": 3,
      "min_samples": 3,
      "umap_neighbors": 15
    }
  },
  "attribute_config": {
    "attributes": [
      "<string>"
    ],
    "hierarchical_grouping": false
  },
  "automatic_naming": {
    "enabled": true,
    "generative_model": "gpt-4",
    "method": "centroid",
    "num_nearest_points": 3
  }
}'
{
  "task_id": "<string>",
  "status": "PENDING",
  "inputs": [
    "<any>"
  ],
  "outputs": [
    "<any>"
  ]
}

Headers

​
Authorization
string | null

Bearer token authentication using your API key. Format: 'Bearer your_api_key'. To get an API key, create an account at mixpeek.com/start and generate a key in your account settings. Example: 'Bearer sk_1234567890abcdef'

​
X-Namespace
string | null

Optional namespace for data isolation. This can be a namespace name or namespace ID. Example: 'netflix_prod' or 'ns_1234567890'. To create a namespace, use the /namespaces endpoint.

Body

application/json
​
collection_id
string
required

ID of the collection to cluster

​
cluster_name
string | null

Name for the cluster (auto-generated if empty)

​
cluster_type
enum<string>
Available options:
vector,
attribute
​
vector_config
object | null
​
attribute_config
object | null
​
automatic_naming
object

Response

200
application/json
Successful Response
​
task_id
string
required
​
status
enum<string>
Available options:
DONE,
FAILED,
SKIPPED,
CANCELLED,
PROCESSING,
DOWNLOADING,
INITIALIZING,
UPLOADING,
QUEUED,
PENDING,
CONVERTING
​
inputs
any[] | null
​
outputs
any[] | null

Was this page helpful?

Suggest editsRaise issue