Skip to main content
Databases are physically isolated spaces for storing context. In most integrations you create a database once, wait for provisioning, then ingest and query inside it.

​
Endpoint references

​
Typical call sequence

For a new database from scratch:
  1. Create the database: POST /databases
  2. Wait for provisioning: GET /databases/status until infra.ready_for_ingestion is true
  3. Ingest content: POST /context/ingest
  4. Wait for indexing: GET /context/status until sources are searchable
  5. Retrieve context: POST /query
  6. Inspect usage: GET /databases/stats
  7. Delete: DELETE /databases
For routine operations on an existing database:
  • GET /databases: list databases in the org
  • GET /databases/collections: list active collections
  • GET /databases/stats: row counts for knowledge and memories

​
Key concepts

  • Database: A top-level isolated space. For example, you can dedicate one database to one enterprise customer.
  • Collection: Partitions within a database for per-user separation. The first collection is created implicitly at ingestion. Collections are useful when you need to scope data per user, team, or customer within a single database.
  • Database Metadata & Schema: Structured fields defined at database creation to enable query-time filtering. You can add fields later with Update Metadata Schema.