Skip to main content
GET
Get Feature Extractor by Name

Authorizations

Authorization
string
header
required

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

Path Parameters

feature_extractor_id
string
required

Response

Successful Response

Feature extractor response model for API responses.

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
default_parameters
Default Parameters · object
required
required_vector_indexes
VectorIndexDefinition · object[] | null
required
required_payload_indexes
PayloadIndexConfig · object[] | null
required
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.

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

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:
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