Skip to main content
GET
Get extractor details

Authorizations

Authorization
string
header
required

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

Path Parameters

namespace_id
string
required
extractor_id
string
required

Response

Extractor details

Unified extractor response combining builtin and custom plugins.

This model provides a consistent view of all extractors available to a namespace, regardless of whether they are builtin or custom.

feature_extractor_name
string
required

Name of the feature extractor

version
string
required

Version of the feature extractor

feature_extractor_id
string
required

Unique identifier (name_version)

source
enum<string>
required

Origin of this extractor: 'builtin' (shipped with Mixpeek), 'custom' (user-uploaded plugin), or 'community' (marketplace)

Available options:
builtin,
custom,
community
description
string
required

Human-readable description

input_schema
Input Schema · object
required

JSON schema for input data

output_schema
Output Schema · object
required

JSON schema for output data

icon
string
default:box

Lucide-react icon name for frontend rendering

parameter_schema
Parameter Schema · object | null

JSON schema for parameters

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[]

Supported input types (video, image, text, etc.)

max_inputs
Max Inputs · object

Maximum number of inputs per type

default_parameters
Default Parameters · object

Default parameter values

costs
CostsInfo · object | null

Credit cost information (builtin extractors only)

required_vector_indexes
VectorIndexDefinition · object[] | null

Vector indexes this extractor produces

required_payload_indexes
PayloadIndexConfig · object[] | null

Payload indexes required by this extractor

position_fields
string[]

Fields that identify unique positions within output documents. Used for deterministic document ID generation.

feature_uri
string | null

Primary feature URI (e.g., mixpeek://text_extractor@v1/embedding)

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

plugin_id
string | null

Plugin ID (custom plugins only)

deployed
boolean | null

Whether the plugin is deployed (custom plugins only)

validation_status
enum<string> | null

Validation status (custom plugins only)

Available options:
passed,
failed,
pending
created_at
string<date-time> | null

Creation timestamp (custom plugins only)

updated_at
string<date-time> | null

Last update timestamp (custom plugins only)