{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://raw.githubusercontent.com/api-evangelist/telnyx/main/json-schema/telnyx-public-text-clustering-request-schema.json",
  "title": "PublicTextClusteringRequest",
  "x-generated": "2026-10-08",
  "x-method": "derived",
  "x-generator": "derive-json-schema.py",
  "x-source": "openapi/telnyx-clusters-api-openapi.yml#/components/schemas/PublicTextClusteringRequest",
  "properties": {
    "bucket": {
      "description": "The embedded storage bucket to compute the clusters from. The bucket must already be [embedded](https://developers.telnyx.com/api-reference/embeddings/embed-documents).",
      "type": "string"
    },
    "files": {
      "description": "Array of files to filter which are included.",
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "min_cluster_size": {
      "default": 25,
      "description": "Smallest number of related text chunks to qualify as a cluster. Top-level clusters should be thought of as identifying broad themes in your data.",
      "type": "integer"
    },
    "min_subcluster_size": {
      "default": 5,
      "description": "Smallest number of related text chunks to qualify as a sub-cluster. Sub-clusters should be thought of as identifying more specific topics within a broader theme.",
      "type": "integer"
    },
    "prefix": {
      "description": "Prefix to filter whcih files in the buckets are included.",
      "type": "string"
    }
  },
  "required": [
    "bucket"
  ],
  "type": "object"
}