add migration dockerfile

backend/Dockerfile.migrations

@@ -0,0 +1,32 @@
+FROM python:3.11.7-slim-bookworm
+
+# Set environment variables and labels as needed
+ENV DANSWER_RUNNING_IN_DOCKER="true"
+
+# Install system dependencies
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends \
+        libpq-dev \
+        gcc && \
+    rm -rf /var/lib/apt/lists/*
+
+# Install Python dependencies
+COPY ./requirements/default.txt /tmp/requirements.txt
+COPY ./requirements/ee.txt /tmp/ee-requirements.txt
+RUN pip install --no-cache-dir -r /tmp/requirements.txt -r /tmp/ee-requirements.txt
+
+# Copy Alembic and application files
+WORKDIR /app
+COPY ./danswer /app/danswer
+COPY ./alembic /app/alembic
+COPY ./alembic_tenants /app/alembic_tenants
+COPY ./alembic.ini /app/alembic.ini
+COPY ./danswer/configs /app/danswer/configs
+COPY ./danswer/utils /app/danswer/utils
+COPY shared_configs /app/shared_configs
+
+# Set PYTHONPATH
+ENV PYTHONPATH=/app
+
+# The entrypoint for the migration job
+ENTRYPOINT ["alembic"]

backend/alembic/env.py

@@ -13,7 +13,7 @@ from danswer.configs.app_configs import MULTI_TENANT
 from danswer.db.engine import build_connection_string
 from danswer.db.models import Base
 from celery.backends.database.session import ResultModelBase  # type: ignore
-from danswer.background.celery.celery_app import get_all_tenant_ids
+from danswer.db.engine import get_all_tenant_ids
 
 # Alembic Config object
 config = context.config

backend/danswer/db/engine.py

@@ -38,6 +38,7 @@ from danswer.configs.app_configs import POSTGRES_USER
 from danswer.configs.app_configs import SECRET_JWT_KEY
 from danswer.configs.constants import POSTGRES_DEFAULT_SCHEMA
 from danswer.configs.constants import POSTGRES_UNKNOWN_APP_NAME
+from danswer.configs.constants import TENANT_ID_PREFIX
 from danswer.utils.logger import setup_logger
 from shared_configs.configs import current_tenant_id
 
@@ -188,6 +189,29 @@ class SqlEngine:
         return cls._app_name
 
 
+def get_all_tenant_ids() -> list[str] | list[None]:
+    if not MULTI_TENANT:
+        return [None]
+    with get_session_with_tenant(tenant_id="public") as session:
+        result = session.execute(
+            text(
+                """
+            SELECT schema_name
+            FROM information_schema.schemata
+            WHERE schema_name NOT IN ('pg_catalog', 'information_schema', 'public')"""
+            )
+        )
+        tenant_ids = [row[0] for row in result]
+
+    valid_tenants = [
+        tenant
+        for tenant in tenant_ids
+        if tenant is None or tenant.startswith(TENANT_ID_PREFIX)
+    ]
+
+    return valid_tenants
+
+
 def build_connection_string(
     *,
     db_api: str = ASYNC_DB_API,

deployment/kubernetes/env-configmap.yaml

@@ -2,7 +2,8 @@ apiVersion: v1
 kind: ConfigMap
 metadata:
   name: env-configmap
-data:
+data: 
+
   # Auth Setting, also check the secrets file
   AUTH_TYPE: "disabled"  # Change this for production uses unless Danswer is only accessible behind VPN
   ENCRYPTION_KEY_SECRET: ""  # This should not be specified directly in the yaml, this is just for reference