Search Configuration

An index is configured by three things, all of which can be set when it is created and changed afterwards:

Setting	Purpose
features	What is searchable: which models run over the content, or which existing tag tracks are indexed.
aggregation	How tags are grouped into the documents that get searched.
search_config	The default behavior when searching the index.

Set on creation with Create an index:

POST /vector_search/indexes/<index_qid> HTTP/1.1
Host: ai-04.contentfabric.io
Authorization: Bearer <token>
Content-Type: application/json

{
  "qids": ["<qid1>", "<qid2>"],
  "features": ["scene_description", "celeb"],
  "aggregation": "shot",
  "search_config": {
    "rerank_level": "document",
    "clips_min_duration_seconds": 15,
    "clips_max_duration_seconds": 45
  }
}

Features

A feature is one searchable field. In the common case it is just the name of a tagger model: adding it starts that model on every content in the index and indexes the tags it produces. Alternatively you may pass a json object for advanced configuration.

"features": [
  "scene_description",
  {"name": "celeb", "params": {"model_params": {"thres": 0.7}}},
  {"name": "captions", "tracks": ["subtitles_en", "subtitles_es"]}
]

Field	Type	Description
name	string	The field name, which is a tagger model name unless tracks is given. See List available models.
params	object	Tagger overrides for this model, accepting whatever the tagger's per-job overrides section accepts. Mutually exclusive with tracks.
tracks	string[]	Existing tagstore tracks to index under name, instead of running a model. Nothing is tagged for you, so you are responsible for these tracks existing.

Multiple tracks under one name are grouped into a single search field.

Changing features

• Add: POST /indexes/{index_id}/features
• Remove: DELETE /indexes/{index_id}/features/{feature} — the index stops searching over it and the model stops running on contents added later. Tags already written are left alone.
• List: GET /indexes/{index_id}/features — every field the index searches over, with its sources and tagger overrides.

Changing contents

The set of contents is managed the same way, with POST /indexes/{index_id}/contents and DELETE /indexes/{index_id}/contents/{qid}. Contents added to an index are tagged with its features automatically.

Aggregation

Aggregation defines the video time-range segments over which we search. It defaults to "shot", which runs shot detection on the content and groups tags by shot boundary — for most content there is nothing to configure here.

When a segmentation model is used, the indexer creates aggregated documents for each of its segments: all configured tags overlapping that segment are grouped into a single textual document, along with the content's fabric-level field data.

What's the point?

Aggregating gives us rich contextual information for a scene that can be used to answer complex queries which might span across different fields. For example a query like: "Jennifer Lawrence talks with a mechanic in No Hard Feelings" could match 3 separate fields for cast/celebrity, visual scene description, and film title.

Fixed time buckets

Instead of a segmentation model, aggregation may be set to a fixed interval in whole seconds like "10s" or "15s". Tags are then grouped into contiguous, fixed-width windows of that duration. This is useful when shot boundaries are not a meaningful unit for your content.

"aggregation": "10s"

Search Defaults

search_config overrides the defaults for the clip search arguments, so callers don't have to specify them on every request. Update it with PATCH /indexes/{index_id}/search_config, which merges in only the options you supply.

PATCH /vector_search/indexes/<index_qid>/search_config HTTP/1.1
Host: ai-04.contentfabric.io
Authorization: Bearer <token>
Content-Type: application/json

{
  "rerank_level": "document",
  "rerank_user_query": true
}

Option	Type	Default	Description
clips_min_duration_seconds	number	—	Minimum clip duration in seconds.
clips_max_duration_seconds	number	—	Maximum clip duration in seconds.
rerank_level	string	"tag"	How much context to give the reranker: "chunk", "tag", or "document", in increasing order.
rerank_user_query	bool	false	Embed the user's original query for the semantic search instead of the decomposed semantic component.
disable_reranking	bool	false	Skip reranking entirely and leave results in order of vector similarity.
rewriter_prompt	string	—	Instructions for an LLM that rewrites the query before the rest of the pipeline runs. Empty skips the rewrite step.

note

For detailed explanations of these arguments, consult the clip search API docs.