-- Knowledge bases: collections of a company's documents that requests are
-- answered from (BACKLOG F). PostgreSQL only: there is no SQLite file of this
-- number, and on SQLite the feature is off.
--
-- The chunks themselves are not here. They need the pgvector extension, which
-- only a superuser can create and which a cluster may not have installed; a
-- migration that failed for want of it would stop the control plane from
-- starting at all. The store creates kb_chunks when it opens, if it can
-- (knowledge.go), and says why not when it cannot.

-- A collection has one owner in the tenancy tree and lives inside one
-- organization, which no grant can cross.
CREATE TABLE kb_collections (
  id          TEXT PRIMARY KEY,
  org_id      TEXT NOT NULL REFERENCES organizations(id),
  owner_scope TEXT NOT NULL,
  owner_id    TEXT NOT NULL,
  name        TEXT NOT NULL,
  -- Vectors from two models are not comparable, so a collection is embedded
  -- by one model and its dimension is fixed with it.
  embed_model TEXT NOT NULL,
  dims        INTEGER NOT NULL,
  created_at  BIGINT NOT NULL,
  created_by  TEXT NOT NULL DEFAULT '',
  UNIQUE (org_id, name)
);
CREATE INDEX kb_collections_by_owner ON kb_collections(owner_scope, owner_id);

-- Who else may read or write a collection. Like guard_attachments, keyed by
-- scope with everything below the scope included; unlike guard policies,
-- grants add up rather than narrow.
CREATE TABLE kb_grants (
  scope      TEXT NOT NULL,
  scope_id   TEXT NOT NULL,
  collection TEXT NOT NULL REFERENCES kb_collections(id) ON DELETE CASCADE,
  perm       TEXT NOT NULL,
  added_at   BIGINT NOT NULL,
  added_by   TEXT NOT NULL DEFAULT '',
  PRIMARY KEY (scope, scope_id, collection)
);
CREATE INDEX kb_grants_by_collection ON kb_grants(collection);

-- A document as added, by name within its collection. The digest is what
-- decides whether adding it again changes anything.
CREATE TABLE kb_documents (
  id         TEXT PRIMARY KEY,
  collection TEXT NOT NULL REFERENCES kb_collections(id) ON DELETE CASCADE,
  name       TEXT NOT NULL,
  digest     TEXT NOT NULL,
  bytes      BIGINT NOT NULL,
  chunks     INTEGER NOT NULL,
  added_at   BIGINT NOT NULL,
  added_by   TEXT NOT NULL DEFAULT '',
  UNIQUE (collection, name)
);