Skip to main content

Getting Started

The following setup will show you how to enable semantic search on arbitrary video in the Eluvio Content Fabric.

Tagging content​

First we must generate searchable tags on our content. The easiest way to do this is to run AI models via the EVIE AI Runtime application: https://dev.contentfabric.io/apps/Video%20Intelligence%20Editor#tagging/

AI Runtime

Shot Detection​

Default behavior assumes shot detection has been run

By default clips will be composed based on shot boundaries, which requires the shot_detection model to have been run.

If there is no suitable segmentation track for your content, you can aggregate documents into fixed time buckets instead. This will require configuring your desired window size, see the configuration docs: fixed time buckets

Tagger API​

Alternatively, you may elect to use the tagger API directly. see the API docs: Start tagging

Tagstore API​

Tags don't need to be generated via AI, you may also add tags directly via the tagstore API. see the API docs: Post tags

Search index Setup​

The next step is to configure your search index. A search index defines a grouping of searchable content.

1. Create a index content object in the fabric​

A search index must be associated with a content object in the Content Fabric.

The easiest way to create a content object is through the Fabric Browser application.

2. Create a collection in the vectorstore​

Create a collection containing a list of qids for content objects you wish to index, as well the relevant tenant id. see the API docs: Create a collection

Note: in order for the clip search API to return playable clips: the contents must be VOD/Title-Mezzanine type.

POST /collections HTTP/1.1
Host: https://ai.contentfabric.io/vectorstore
Authorization: Bearer <token>
Content-Type: application/json

{
  "name": "my collection",
  "qids": [
    "<qid1>",
    "<qid2>"
  ],
  "tenant": "<tenant id>"
}

Getting the tenant id (via Fabric Browser)​

  1. Click on user icon in top right of fabric browser and select "Profile"
Profile menu
  1. Copy the tenant id located under the user icon
Tenant id location

3. Create a clip-search index in the vectorstore​

Create a new index with type set to "clip-search", collection_id set to the collection you created in the last step, and <qid> set to the content object qid you created in step 1. See the API docs: Create an index

POST /indexes/<qid> HTTP/1.1
Host: https://ai.contentfabric.io/vectorstore
Authorization: Bearer <token>
Content-Type: application/json

{
	"collection_id": "<collection_id>",
	"name": "test",
	"type": "clip-search",
}

4. (optional) Check indexing status​

After creating your index and pointing it to your content collection, all tags associated with your content will be indexed automatically. This is an asynchronous process and you may check the progress by calling the status API on the index content object.

GET /indexes/<qid> HTTP/1.1
Host: https://ai.contentfabric.io/elv-indexer/indexes/<qid>
Authorization: Bearer <token>
Content-Type: application/json

See the API docs: Search for clips

EVIE​

Click on index configuration

Index configuration

Select Add Existing Index and enter the content id for the index.

Add existing index

Search results