Tenant integration tests (#2913)

* check for index swap

* initial bones

* kk

* k

* k:

* nit

* nit

* rebase + update

* nit

* minior update

* k

* minor integration test fixes

* nit

* ensure we build test docker image

* remove one space

* k

* ensure we wipe volumes

* remove log

* typo

* nit

* k

* k

Author: pablonyx

.github/workflows/pr-Integration-tests.yml

@@ -72,7 +72,7 @@ jobs:
           load: true
           cache-from: type=s3,prefix=cache/${{ github.repository }}/integration-tests/model-server/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }}
           cache-to: type=s3,prefix=cache/${{ github.repository }}/integration-tests/model-server/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }},mode=max
-
+      
       - name: Build integration test Docker image
         uses: ./.github/actions/custom-build-and-push
         with:
@@ -85,7 +85,58 @@ jobs:
           cache-from: type=s3,prefix=cache/${{ github.repository }}/integration-tests/integration/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }}
           cache-to: type=s3,prefix=cache/${{ github.repository }}/integration-tests/integration/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }},mode=max
 
-      - name: Start Docker containers
+      # Start containers for multi-tenant tests
+      - name: Start Docker containers for multi-tenant tests
+        run: |
+          cd deployment/docker_compose
+          ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true \
+          MULTI_TENANT=true \
+          AUTH_TYPE=basic \
+          REQUIRE_EMAIL_VERIFICATION=false \
+          DISABLE_TELEMETRY=true \
+          IMAGE_TAG=test \
+          docker compose -f docker-compose.dev.yml -p danswer-stack up -d
+        id: start_docker_multi_tenant
+
+      # In practice, `cloud` Auth type would require OAUTH credentials to be set.
+      - name: Run Multi-Tenant Integration Tests
+        run: |
+          echo "Running integration tests..."
+          docker run --rm --network danswer-stack_default \
+            --name test-runner \
+            -e POSTGRES_HOST=relational_db \
+            -e POSTGRES_USER=postgres \
+            -e POSTGRES_PASSWORD=password \
+            -e POSTGRES_DB=postgres \
+            -e VESPA_HOST=index \
+            -e REDIS_HOST=cache \
+            -e API_SERVER_HOST=api_server \
+            -e OPENAI_API_KEY=${OPENAI_API_KEY} \
+            -e SLACK_BOT_TOKEN=${SLACK_BOT_TOKEN} \
+            -e TEST_WEB_HOSTNAME=test-runner \
+            -e AUTH_TYPE=cloud \
+            -e MULTI_TENANT=true \
+            danswer/danswer-integration:test \
+            /app/tests/integration/multitenant_tests
+        continue-on-error: true
+        id: run_multitenant_tests
+
+      - name: Check multi-tenant test results
+        run: |
+          if [ ${{ steps.run_tests.outcome }} == 'failure' ]; then
+            echo "Integration tests failed. Exiting with error."
+            exit 1
+          else
+            echo "All integration tests passed successfully."
+          fi 
+
+      - name: Stop multi-tenant Docker containers
+        run: |
+          cd deployment/docker_compose
+          docker compose -f docker-compose.dev.yml -p danswer-stack down -v
+
+
+      - name: Start Docker containers 
         run: |
           cd deployment/docker_compose
           ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true \
@@ -130,7 +181,7 @@ jobs:
           done
           echo "Finished waiting for service."
 
-      - name: Run integration tests
+      - name: Run Standard Integration Tests
         run: |
           echo "Running integration tests..."
           docker run --rm --network danswer-stack_default \
@@ -145,7 +196,8 @@ jobs:
             -e OPENAI_API_KEY=${OPENAI_API_KEY} \
             -e SLACK_BOT_TOKEN=${SLACK_BOT_TOKEN} \
             -e TEST_WEB_HOSTNAME=test-runner \
-            danswer/danswer-integration:test
+            danswer/danswer-integration:test \
+            /app/tests/integration/tests
         continue-on-error: true
         id: run_tests
 
@@ -158,6 +210,11 @@ jobs:
             echo "All integration tests passed successfully."
           fi
 
+      - name: Stop Docker containers
+        run: |
+          cd deployment/docker_compose
+          docker compose -f docker-compose.dev.yml -p danswer-stack down -v
+
       - name: Save Docker logs
         if: success() || failure()
         run: |

backend/danswer/auth/users.py

@@ -58,6 +58,7 @@
 from danswer.auth.schemas import UserUpdate
 from danswer.configs.app_configs import AUTH_TYPE
 from danswer.configs.app_configs import DISABLE_AUTH
+from danswer.configs.app_configs import DISABLE_VERIFICATION
 from danswer.configs.app_configs import EMAIL_FROM
 from danswer.configs.app_configs import MULTI_TENANT
 from danswer.configs.app_configs import REQUIRE_EMAIL_VERIFICATION
@@ -133,7 +134,9 @@ def get_display_email(email: str | None, space_less: bool = False) -> str:
 def user_needs_to_be_verified() -> bool:
     # all other auth types besides basic should require users to be
     # verified
-    return AUTH_TYPE != AuthType.BASIC or REQUIRE_EMAIL_VERIFICATION
+    return not DISABLE_VERIFICATION and (
+        AUTH_TYPE != AuthType.BASIC or REQUIRE_EMAIL_VERIFICATION
+    )
 
 
 def verify_email_is_invited(email: str) -> None:

backend/danswer/background/celery/apps/indexing.py

@@ -8,18 +8,11 @@
 from celery.signals import worker_init
 from celery.signals import worker_ready
 from celery.signals import worker_shutdown
-from sqlalchemy.orm import Session
 
 import danswer.background.celery.apps.app_base as app_base
 from danswer.configs.constants import POSTGRES_CELERY_WORKER_INDEXING_APP_NAME
 from danswer.db.engine import SqlEngine
-from danswer.db.search_settings import get_current_search_settings
-from danswer.db.swap_index import check_index_swap
-from danswer.natural_language_processing.search_nlp_models import EmbeddingModel
-from danswer.natural_language_processing.search_nlp_models import warm_up_bi_encoder
 from danswer.utils.logger import setup_logger
-from shared_configs.configs import INDEXING_MODEL_SERVER_HOST
-from shared_configs.configs import MODEL_SERVER_PORT
 
 
 logger = setup_logger()
@@ -67,27 +60,6 @@ def on_worker_init(sender: Any, **kwargs: Any) -> None:
     SqlEngine.set_app_name(POSTGRES_CELERY_WORKER_INDEXING_APP_NAME)
     SqlEngine.init_engine(pool_size=8, max_overflow=0)
 
-    # TODO: why is this necessary for the indexer to do?
-    engine = SqlEngine.get_engine()
-    with Session(engine) as db_session:
-        check_index_swap(db_session=db_session)
-        search_settings = get_current_search_settings(db_session)
-
-        # So that the first time users aren't surprised by really slow speed of first
-        # batch of documents indexed
-        if search_settings.provider_type is None:
-            logger.notice("Running a first inference to warm up embedding model")
-            embedding_model = EmbeddingModel.from_db_model(
-                search_settings=search_settings,
-                server_host=INDEXING_MODEL_SERVER_HOST,
-                server_port=MODEL_SERVER_PORT,
-            )
-
-            warm_up_bi_encoder(
-                embedding_model=embedding_model,
-            )
-            logger.notice("First inference complete.")
-
     app_base.wait_for_redis(sender, **kwargs)
     app_base.on_secondary_worker_init(sender, **kwargs)