Skip to main content
GET
List Available Feature Extractors

Authorizations

Authorization
string
header
required

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

Response

Successful Response

name
string
required

Feature extractor name (e.g., 'multimodal_extractor')

version
string
required

Feature extractor version (e.g., 'v1')

description
string
required

Human-readable description of what this extractor does

supported_modalities
string[]

List of supported input modalities (text, image, video, audio)

output_features
Output Features · object[]

List of features produced by this extractor

input_schema
Input Schema · object | null

JSON Schema for extractor inputs — what fields the extractor reads from source objects

parameter_schema
Parameter Schema · object | null

JSON Schema for tunable parameters (defaults, ranges, descriptions for every knob)

output_schema
Output Schema · object | null

JSON Schema for output documents — what fields appear in extracted documents

costs
CostsInfo · object | null

Credit cost information (tier, per-unit rates)

type_mode
string | null

What input types this extractor can handle: 'type_specific' (only one type, e.g. video-only) or 'multimodal' (handles multiple types with conditional processing). 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', 'thumbnail': 'image'}). For multimodal extractors: null.

inference_type
string | null

Kind of real-time inference this extractor provides: 'embedding', 'rerank', 'classify', 'generate', or 'general'. Determines which retriever stages are compatible. Null if the extractor is batch-only.

supported_input_types
string[]

Accepted input types (e.g., ['video', 'image'])

max_inputs
Max Inputs · object

Maximum number of inputs per type (e.g., {'video': 1})

default_parameters
Default Parameters · object

Default parameter values — use as a starting point for tuning

required_vector_indexes
Required Vector Indexes · object[] | null

Vector indexes produced by this extractor (name, dimensions, distance metric, feature_uri)

position_fields
string[]

Fields that uniquely identify each output document within a source object

capabilities
string[]

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

example_usage
Example Usage · object

Minimal working configuration for namespace + collection + input_mappings + parameters