List Feature Extractors

List all available feature extractors grouped by category

GET /v1/collections/features/extractors

List Feature Extractors

cURL

curl --request GET \
  --url https://api.mixpeek.com/v1/collections/features/extractors \
  --header 'Authorization: Bearer <token>'

200

[
  {
    "feature_extractor_name": "<string>",
    "version": "<string>",
    "feature_extractor_id": "<string>",
    "description": "<string>",
    "icon": "<string>",
    "input_schema": {},
    "output_schema": {},
    "parameter_schema": {},
    "supported_input_types": [
      "<string>"
    ],
    "max_inputs": {},
    "default_parameters": {},
    "required_vector_indexes": [
      {
        "description": "Vector index for text embeddings using E5-Large model.",
        "index": {
          "datatype": "float32",
          "description": "Dense vector embedding for text content",
          "dimensions": 1024,
          "distance": "cosine",
          "inference_name": "multilingual_e5_large_instruct_v1",
          "name": "text_extractor_v1_embedding",
          "supported_inputs": [
            "text",
            "string"
          ],
          "type": "dense"
        },
        "name": "embedding",
        "type": "single"
      }
    ],
    "required_payload_indexes": [
      {
        "description": "User-created text index for full-text search",
        "field_name": "metadata.description",
        "is_protected": false,
        "type": "text"
      }
    ],
    "category": "general",
    "source": "builtin",
    "type_mode": "<string>",
    "expected_input_types": {},
    "inference_type": "<string>",
    "costs": {
      "tier": 2,
      "tier_label": "<string>",
      "rates": [
        {
          "unit": "minute",
          "credits_per_unit": 123,
          "description": "<string>"
        }
      ]
    },
    "position_fields": [
      "start_time",
      "end_time"
    ],
    "capabilities": [
      "<string>"
    ],
    "example_usage": {},
    "realtime_available": true,
    "serve_apps": [
      {
        "name": "<string>",
        "status": "<string>"
      }
    ]
  }
]

Authorizations

Authorization · string · header · required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Response

200

application/json

Successful Response

feature_extractor_name · string · required

version · string · required

feature_extractor_id · string · required

description · string · required

icon · string · required

input_schema · Input Schema · object · required

output_schema · Output Schema · object · required

parameter_schema · Parameter Schema · object | null · required

supported_input_types · string[] · required

max_inputs · Max Inputs · object · required

Show child attributes

default_parameters · Default Parameters · object · required

required_vector_indexes · VectorIndexDefinition · object[] | null · required

Show child attributes

required_payload_indexes · PayloadIndexConfig · object[] | null · required

Show child attributes

category · string · default: general

Category of this extractor, used for UI grouping and filtering. Examples: 'text', 'image', 'multimodal', 'audio', 'video', 'document', 'face', 'corpus', 'utility', 'safety', 'classification', 'web', 'custom'.

source · enum<string> · default: builtin

The origin/source of this extractor: 'builtin' (shipped with Mixpeek), 'custom' (user-created), or 'community' (marketplace).

Available options: builtin, custom, community

type_mode · string | null

What input types this extractor can handle: 'type_specific' (only one type) or 'multimodal' (handles multiple types). Type-specific extractors cannot use automatic-typed bucket properties.

expected_input_types · Expected Input Types · object | null

For type-specific extractors: maps input keys to required types (e.g., {'video': 'video'}). For multimodal extractors: null.

Show child attributes

inference_type · string | null

Kind of real-time inference this extractor provides: 'embedding', 'rerank', 'classify', 'generate', or 'general'. Null if batch-only.

costs · CostsInfo · object | null

Credit cost information for this extractor

Show child attributes

position_fields · string[]

Output fields that uniquely identify each document within a source object. Enables idempotent reprocessing: rerunning a batch produces the same document IDs, so existing documents are updated instead of creating duplicates. Works with bucket unique_key to enable fully deterministic document IDs. Empty list means single-output extractor (one document per source). Read-only (set by extractor).

Examples:

["start_time", "end_time"]

["chunk_index"]

[]

capabilities · string[]

What this extractor can do: 'batch' (feature extraction during ingestion), 'realtime' (query-time inference for retriever stages)

example_usage · Example Usage · object | null

Minimal working configuration for namespace + collection + input_mappings + parameters

realtime_available · boolean | null

Whether every Ray Serve application this extractor needs for real-time inference is running on the deployment serving this request. True when all of them report RUNNING. False when one is absent or not running; see serve_apps for which. Null when the extractor needs none, or when the live list could not be read.

serve_apps · ServeAppStatus · object[]

The Ray Serve applications this extractor needs for real-time inference, each with its live status. Empty when it needs none.

Show child attributes