schema

module wittgenstein_kg_client.schema

Bootstrap the knowledge_graphs/nodes/edges tables on a fresh Postgres instance.

Functions

• ensure_schema — Create the KG tables (and pgvector extension) if they don't exist yet.

wittgenstein_kg_client.schema.ensure_schema

ensure_schema(pg_dsn: str) → None

Create the KG tables (and pgvector extension) if they don't exist yet.

Idempotent — safe to call on every app startup. Only needed for standalone consumers; the platform's agent_platform database manages this schema via Alembic instead (see repository_structure_reference).

Also creates the HNSW index used by the RAG similarity search path (see schema.sql). Building that index for the first time against a table that already holds a large number of embedded rows can be slow/memory-heavy — see the comment above the index in schema.sql before calling this against a pre-populated database.