Merge branch 'main' of https://github.com/ferdinandl007/onyx

.github/workflows/docker-build-push-cloud-web-container-on-tag.yml

@@ -65,6 +65,7 @@ jobs:
             NEXT_PUBLIC_POSTHOG_KEY=${{ secrets.POSTHOG_KEY }}
             NEXT_PUBLIC_POSTHOG_HOST=${{ secrets.POSTHOG_HOST }}
             NEXT_PUBLIC_SENTRY_DSN=${{ secrets.SENTRY_DSN }}
+            NEXT_PUBLIC_STRIPE_PUBLISHABLE_KEY=${{ secrets.STRIPE_PUBLISHABLE_KEY }}
             NEXT_PUBLIC_GTM_ENABLED=true
             NEXT_PUBLIC_FORGOT_PASSWORD_ENABLED=true
             NEXT_PUBLIC_INCLUDE_ERROR_POPUP_SUPPORT_LINK=true

.github/workflows/docker-build-push-model-server-container-on-tag.yml

@@ -12,7 +12,32 @@ env:
   BUILDKIT_PROGRESS: plain
 
 jobs:
+  # 1) Preliminary job to check if the changed files are relevant
+  check_model_server_changes:
+    runs-on: ubuntu-latest
+    outputs:
+      changed: ${{ steps.check.outputs.changed }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Check if relevant files changed
+        id: check
+        run: |
+          # Default to "false"
+          echo "changed=false" >> $GITHUB_OUTPUT
+
+          # Compare the previous commit (github.event.before) to the current one (github.sha)
+          # If any file in backend/model_server/** or backend/Dockerfile.model_server is changed,
+          # set changed=true
+          if git diff --name-only ${{ github.event.before }} ${{ github.sha }} \
+             | grep -E '^backend/model_server/|^backend/Dockerfile.model_server'; then
+            echo "changed=true" >> $GITHUB_OUTPUT
+          fi
+
   build-amd64:
+    needs: [check_model_server_changes]
+    if: needs.check_model_server_changes.outputs.changed == 'true'
     runs-on:
       [runs-on, runner=8cpu-linux-x64, "run-id=${{ github.run_id }}-amd64"]
     steps:
@@ -52,6 +77,8 @@ jobs:
           provenance: false
 
   build-arm64:
+    needs: [check_model_server_changes]
+    if: needs.check_model_server_changes.outputs.changed == 'true'
     runs-on:
       [runs-on, runner=8cpu-linux-x64, "run-id=${{ github.run_id }}-arm64"]
     steps:
@@ -91,7 +118,8 @@ jobs:
           provenance: false
 
   merge-and-scan:
-    needs: [build-amd64, build-arm64]
+    needs: [build-amd64, build-arm64, check_model_server_changes]
+    if: needs.check_model_server_changes.outputs.changed == 'true'
     runs-on: ubuntu-latest
     steps:
       - name: Login to Docker Hub

.github/workflows/pr-python-connector-tests.yml

@@ -44,6 +44,9 @@ env:
   SHAREPOINT_CLIENT_SECRET: ${{ secrets.SHAREPOINT_CLIENT_SECRET }}
   SHAREPOINT_CLIENT_DIRECTORY_ID: ${{ secrets.SHAREPOINT_CLIENT_DIRECTORY_ID }}
   SHAREPOINT_SITE: ${{ secrets.SHAREPOINT_SITE }}
+  # Gitbook
+  GITBOOK_SPACE_ID: ${{ secrets.GITBOOK_SPACE_ID }}
+  GITBOOK_API_KEY: ${{ secrets.GITBOOK_API_KEY }}
 
 jobs:
   connectors-check:

backend/Dockerfile

@@ -35,7 +35,9 @@ RUN apt-get update && \
         libuuid1=2.38.1-5+deb12u1 \
         libxmlsec1-dev \
         pkg-config \
-        gcc && \
+        gcc \
+        nano \
+        vim && \
     rm -rf /var/lib/apt/lists/* && \
     apt-get clean
 

backend/alembic/versions/2cdeff6d8c93_set_built_in_to_default.py

@@ -0,0 +1,32 @@
+"""set built in to default
+
+Revision ID: 2cdeff6d8c93
+Revises: f5437cc136c5
+Create Date: 2025-02-11 14:57:51.308775
+
+"""
+from alembic import op
+
+
+# revision identifiers, used by Alembic.
+revision = "2cdeff6d8c93"
+down_revision = "f5437cc136c5"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # Prior to this migration / point in the codebase history,
+    # built in personas were implicitly treated as default personas (with no option to change this)
+    # This migration makes that explicit
+    op.execute(
+        """
+        UPDATE persona
+        SET is_default_persona = TRUE
+        WHERE builtin_persona = TRUE
+    """
+    )
+
+
+def downgrade() -> None:
+    pass

backend/alembic/versions/f39c5794c10a_add_background_errors_table.py

@@ -0,0 +1,40 @@
+"""Add background errors table
+
+Revision ID: f39c5794c10a
+Revises: 2cdeff6d8c93
+Create Date: 2025-02-12 17:11:14.527876
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "f39c5794c10a"
+down_revision = "2cdeff6d8c93"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "background_error",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column("message", sa.String(), nullable=False),
+        sa.Column(
+            "time_created",
+            sa.DateTime(timezone=True),
+            server_default=sa.text("now()"),
+            nullable=False,
+        ),
+        sa.Column("cc_pair_id", sa.Integer(), nullable=True),
+        sa.PrimaryKeyConstraint("id"),
+        sa.ForeignKeyConstraint(
+            ["cc_pair_id"],
+            ["connector_credential_pair.id"],
+            ondelete="CASCADE",
+        ),
+    )
+
+
+def downgrade() -> None:
+    op.drop_table("background_error")

backend/ee/onyx/background/celery/tasks/beat_schedule.py

@@ -1,44 +1,46 @@
 from datetime import timedelta
 from typing import Any
 
+from onyx.background.celery.tasks.beat_schedule import (
+    beat_cloud_tasks as base_beat_system_tasks,
+)
 from onyx.background.celery.tasks.beat_schedule import BEAT_EXPIRES_DEFAULT
 from onyx.background.celery.tasks.beat_schedule import (
-    cloud_tasks_to_schedule as base_cloud_tasks_to_schedule,
+    beat_task_templates as base_beat_task_templates,
 )
+from onyx.background.celery.tasks.beat_schedule import generate_cloud_tasks
 from onyx.background.celery.tasks.beat_schedule import (
-    tasks_to_schedule as base_tasks_to_schedule,
+    get_tasks_to_schedule as base_get_tasks_to_schedule,
 )
-from onyx.configs.constants import ONYX_CLOUD_CELERY_TASK_PREFIX
 from onyx.configs.constants import OnyxCeleryPriority
 from onyx.configs.constants import OnyxCeleryTask
 from shared_configs.configs import MULTI_TENANT
 
-ee_cloud_tasks_to_schedule = [
-    {
-        "name": f"{ONYX_CLOUD_CELERY_TASK_PREFIX}_autogenerate-usage-report",
-        "task": OnyxCeleryTask.CLOUD_BEAT_TASK_GENERATOR,
-        "schedule": timedelta(days=30),
-        "options": {
-            "priority": OnyxCeleryPriority.HIGHEST,
-            "expires": BEAT_EXPIRES_DEFAULT,
-        },
-        "kwargs": {
-            "task_name": OnyxCeleryTask.AUTOGENERATE_USAGE_REPORT_TASK,
-        },
-    },
-    {
-        "name": f"{ONYX_CLOUD_CELERY_TASK_PREFIX}_check-ttl-management",
-        "task": OnyxCeleryTask.CLOUD_BEAT_TASK_GENERATOR,
-        "schedule": timedelta(hours=1),
-        "options": {
-            "priority": OnyxCeleryPriority.HIGHEST,
-            "expires": BEAT_EXPIRES_DEFAULT,
+ee_beat_system_tasks: list[dict] = []
+
+ee_beat_task_templates: list[dict] = []
+ee_beat_task_templates.extend(
+    [
+        {
+            "name": "autogenerate-usage-report",
+            "task": OnyxCeleryTask.AUTOGENERATE_USAGE_REPORT_TASK,
+            "schedule": timedelta(days=30),
+            "options": {
+                "priority": OnyxCeleryPriority.MEDIUM,
+                "expires": BEAT_EXPIRES_DEFAULT,
+            },
         },
-        "kwargs": {
-            "task_name": OnyxCeleryTask.CHECK_TTL_MANAGEMENT_TASK,
+        {
+            "name": "check-ttl-management",
+            "task": OnyxCeleryTask.CHECK_TTL_MANAGEMENT_TASK,
+            "schedule": timedelta(hours=1),
+            "options": {
+                "priority": OnyxCeleryPriority.MEDIUM,
+                "expires": BEAT_EXPIRES_DEFAULT,
+            },
         },
-    },
-]
+    ]
+)
 
 ee_tasks_to_schedule: list[dict] = []
 
@@ -65,9 +67,14 @@
     ]
 
 
-def get_cloud_tasks_to_schedule() -> list[dict[str, Any]]:
-    return ee_cloud_tasks_to_schedule + base_cloud_tasks_to_schedule
+def get_cloud_tasks_to_schedule(beat_multiplier: float) -> list[dict[str, Any]]:
+    beat_system_tasks = ee_beat_system_tasks + base_beat_system_tasks
+    beat_task_templates = ee_beat_task_templates + base_beat_task_templates
+    cloud_tasks = generate_cloud_tasks(
+        beat_system_tasks, beat_task_templates, beat_multiplier
+    )
+    return cloud_tasks
 
 
 def get_tasks_to_schedule() -> list[dict[str, Any]]:
-    return ee_tasks_to_schedule + base_tasks_to_schedule
+    return ee_tasks_to_schedule + base_get_tasks_to_schedule()

backend/ee/onyx/configs/app_configs.py

@@ -77,3 +77,5 @@
 HUBSPOT_TRACKING_URL = os.environ.get("HUBSPOT_TRACKING_URL")
 
 ANONYMOUS_USER_COOKIE_NAME = "onyx_anonymous_user"
+
+GATED_TENANTS_KEY = "gated_tenants"

backend/ee/onyx/external_permissions/confluence/group_sync.py

@@ -1,5 +1,6 @@
 from ee.onyx.db.external_perm import ExternalUserGroup
 from ee.onyx.external_permissions.confluence.constants import ALL_CONF_EMAILS_GROUP_NAME
+from onyx.background.error_logging import emit_background_error
 from onyx.connectors.confluence.onyx_confluence import build_confluence_client
 from onyx.connectors.confluence.onyx_confluence import OnyxConfluence
 from onyx.connectors.confluence.utils import get_user_email_from_username__server
@@ -10,16 +11,19 @@
 
 
 def _build_group_member_email_map(
-    confluence_client: OnyxConfluence,
+    confluence_client: OnyxConfluence, cc_pair_id: int
 ) -> dict[str, set[str]]:
     group_member_emails: dict[str, set[str]] = {}
     for user_result in confluence_client.paginated_cql_user_retrieval():
         logger.debug(f"Processing groups for user: {user_result}")
 
         user = user_result.get("user", {})
         if not user:
-            logger.warning(f"user result missing user field: {user_result}")
+            msg = f"user result missing user field: {user_result}"
+            emit_background_error(msg, cc_pair_id=cc_pair_id)
+            logger.error(msg)
             continue
+
         email = user.get("email")
         if not email:
             # This field is only present in Confluence Server
@@ -32,7 +36,12 @@ def _build_group_member_email_map(
                 )
         if not email:
             # If we still don't have an email, skip this user
-            logger.warning(f"user result missing email field: {user_result}")
+            msg = f"user result missing email field: {user_result}"
+            if user.get("type") == "app":
+                logger.warning(msg)
+            else:
+                emit_background_error(msg, cc_pair_id=cc_pair_id)
+                logger.error(msg)
             continue
 
         all_users_groups: set[str] = set()
@@ -42,11 +51,18 @@ def _build_group_member_email_map(
             group_member_emails.setdefault(group_id, set()).add(email)
             all_users_groups.add(group_id)
 
-        if not group_member_emails:
-            logger.warning(f"No groups found for user with email: {email}")
+        if not all_users_groups:
+            msg = f"No groups found for user with email: {email}"
+            emit_background_error(msg, cc_pair_id=cc_pair_id)
+            logger.error(msg)
         else:
             logger.debug(f"Found groups {all_users_groups} for user with email {email}")
 
+    if not group_member_emails:
+        msg = "No groups found for any users."
+        emit_background_error(msg, cc_pair_id=cc_pair_id)
+        logger.error(msg)
+
     return group_member_emails
 
 
@@ -61,6 +77,7 @@ def confluence_group_sync(
 
     group_member_email_map = _build_group_member_email_map(
         confluence_client=confluence_client,
+        cc_pair_id=cc_pair.id,
     )
     onyx_groups: list[ExternalUserGroup] = []
     all_found_emails = set()

backend/ee/onyx/server/query_and_chat/query_backend.py

@@ -83,6 +83,7 @@ def handle_search_request(
         user=user,
         llm=llm,
         fast_llm=fast_llm,
+        skip_query_analysis=False,
         db_session=db_session,
         bypass_acl=False,
     )