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
Property | Description | Type | Default | Required |
---|---|---|---|---|
index_objects | If enabled, index the objects and their attributes detected in the current frame | bool | true | No |
object_types | Comma-separated list of object types to index. Empty list indexes all objects. Conditional on index_objects | model-label | null | No |
object_mode | Object index mode. Options: labels , signature_once , signature_interval . Conditional on index_objects | enum | labels | Yes |
index_events | If enabled, index any events inserted by upstream Event nodes into the metadata | bool | true | No |
index_texts | If enabled, index the resulting text descriptions from upstream nodes like Caption Generator and OCR | bool | true | No |
index_vectors | If enabled, index the scene extracted from the current image | bool | true | No |
vectors_mode | Scene index mode. Options: interval , trigger , interval_and_trigger . Conditional on index_vectors | enum | interval | Yes |
trigger_type | Index the scene automatically when key metadata changes, or using a custom trigger. Options: auto_trigger , custom_trigger . Conditional on index_vectors | enum | auto_trigger | Yes |
trigger | Custom trigger condition, if Trigger type is set to Custom trigger. Conditional on index_vectors | trigger-condition | null | No |
interval | Index the scene and/or objects at this interval. | number | 1 | No |
remove_other_meta | Remove non-search metadata to reduce metadata size. | bool | false | No |
Metadata
The metadata structure augmented by the Search is added to the top-level "search"
field.
Example
{
"search": {
"events": [],
"objects": [],
"texts": [],
"vectors": []
}
}
Format
Field | Description |
---|---|
events | Augmented events metadata from upstream nodes. |
objects | Augmented objects metadata from the current frame. |
texts | Augmented text metadata from upstream nodes like OCR and Caption Generator. |
vectors | Augmented scene metadata. |
Updated about 2 months ago