NEWVectors or files. Pick a path.Start →
    Content Processing

    Collections

    Turn raw objects into a searchable set of documents, derived from sources you never have to re-upload

    Why do anything?

    Uploaded media is not searchable. A two-hour video is one opaque file until something segments it, transcribes it, reads its on-screen text and embeds the result.

    Why now?

    Teams accumulate media faster than they can catalogue it, and every extractor change would otherwise mean re-uploading terabytes rather than re-running over what is already stored.

    Why this feature?

    A collection declares its sources and its extractors, then derives documents from them. Because the derivation is declared rather than hand-built, changing the configuration and re-running rebuilds the documents without touching the original objects.

    How It Works

    A collection is derived state. Sources hold what arrived; the collection holds what was computed from it, which is what queries actually run against.

    1

    Source resolution

    Resolve the declared sources, applying any per-source field map

    2

    Extraction

    Run the named extractors over objects in batches

    3

    Document write

    Write documents with signals, vectors and lineage

    4

    Index update

    Make the new documents queryable through the namespace indexes

    Why This Approach

    Keeping sources immutable and the collection derived means an extractor or model change is a re-run rather than a re-ingest, which is the difference between minutes and moving terabytes.

    Integration

    collection = client.collections.create(collection_name="catalogue", source={"type": "bucket", "bucket_ids": ["bkt_ads"]})