Create Search Index

Indexes resulting video clips with object, event, text and scene metadata so they are searchable using Lumeo AI Search.

Overview

The "Create Search Index" node indexes resulting video clips with object, event, text and scene metadata so they are searchable using Lumeo AI Search. Add this node after any upstream AI Model, OCR, Caption Generator nodes, and add a Save Clip node downstream of this node that saves to Lumeo Cloud.

Inputs & Outputs

  • Inputs: 1, Media Format: Raw Video
  • Outputs: 1, Media Format: Raw Video
  • Output Metadata: Search Metadata

Properties

PropertyDescriptionTypeDefaultRequired
index_objectsIf enabled, index the objects and their attributes detected in the current framebooltrueNo
object_typesComma-separated list of object types to index. Empty list indexes all objects. Conditional on index_objectsmodel-labelnullNo
object_modeObject index mode. Options: labels, signature_once, signature_interval. Conditional on index_objectsenumlabelsYes
index_eventsIf enabled, index any events inserted by upstream Event nodes into the metadatabooltrueNo
index_textsIf enabled, index the resulting text descriptions from upstream nodes like Caption Generator and OCRbooltrueNo
index_vectorsIf enabled, index the scene extracted from the current imagebooltrueNo
vectors_modeScene index mode. Options: interval, trigger, interval_and_trigger. Conditional on index_vectorsenumintervalYes
trigger_typeIndex the scene automatically when key metadata changes, or using a custom trigger. Options: auto_trigger, custom_trigger. Conditional on index_vectorsenumauto_triggerYes
triggerCustom trigger condition, if Trigger type is set to Custom trigger. Conditional on index_vectorstrigger-conditionnullNo
intervalIndex the scene and/or objects at this interval.number1No
remove_other_metaRemove non-search metadata to reduce metadata size.boolfalseNo

Metadata

The metadata structure augmented by the Search is added to the top-level "search" field.

Example

{
  "search": {
    "events": [],
    "objects": [],
    "texts": [],
    "vectors": []
  }
}

Format

FieldDescription
eventsAugmented events metadata from upstream nodes.
objectsAugmented objects metadata from the current frame.
textsAugmented text metadata from upstream nodes like OCR and Caption Generator.
vectorsAugmented scene metadata.