Knowledge stores
A knowledge store is a persistent, queryable store of your videos plus the understanding the platform derives from them. It contains three layers:
- Spatiotemporal context - entities, moments, facts, and summaries extracted from your videos
- Typed ontology - a schema that organizes those elements and their relationships
- Embeddings - vector representations that make the content semantically retrievable
Together these layers form the substrate for corpus-level reasoning: the platform reasons across the full collection, not just individual clips.
Ingestion configuration
The ingestion config controls what the platform extracts from your videos. Set it when you create a knowledge store.
For the available approaches and guidance on choosing one, see the Configure ingestion guide.
Knowledge store items
A knowledge store item is an asset added to a knowledge store for indexing. Items are processed asynchronously.
All items must reach ready status before the knowledge store can return meaningful query results. Each query targets a single knowledge store - you cannot query across stores.
Jupyter notebook
Download the notebook to run through creating knowledge stores and adding items interactively.
API reference
- POST /knowledge-stores - create a knowledge store
- GET /knowledge-stores/{id} - retrieve a knowledge store
- POST /knowledge-stores/{id}/items - add an item
- GET /knowledge-stores/{id}/items/{item_id} - check item status
