Merge branch 'main' into feat/github-pages-connector

.github/workflows/nightly-scan-licenses.yml

@@ -0,0 +1,76 @@
+# Scan for problematic software licenses
+
+# trivy has their own rate limiting issues causing this action to flake
+# we worked around it by hardcoding to different db repos in env
+# can re-enable when they figure it out
+# https://github.com/aquasecurity/trivy/discussions/7538
+# https://github.com/aquasecurity/trivy-action/issues/389
+
+name: 'Nightly - Scan licenses'
+on:
+#   schedule:
+#     - cron: '0 14 * * *'  # Runs every day at 6 AM PST / 7 AM PDT / 2 PM UTC
+  workflow_dispatch:  # Allows manual triggering
+
+permissions:
+  actions: read
+  contents: read
+  security-events: write
+
+jobs:
+  scan-licenses:
+    # See https://runs-on.com/runners/linux/
+    runs-on: [runs-on,runner=2cpu-linux-x64,"run-id=${{ github.run_id }}"]
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+          cache: 'pip'
+          cache-dependency-path: |
+            backend/requirements/default.txt
+            backend/requirements/dev.txt
+            backend/requirements/model_server.txt
+      
+      - name: Get explicit and transitive dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install --retries 5 --timeout 30 -r backend/requirements/default.txt
+          pip install --retries 5 --timeout 30 -r backend/requirements/dev.txt
+          pip install --retries 5 --timeout 30 -r backend/requirements/model_server.txt
+          pip freeze > requirements-all.txt
+                    
+      - name: Check python
+        id: license_check_report
+        uses: pilosus/action-pip-license-checker@v2
+        with:
+          requirements: 'requirements-all.txt'
+          fail: 'Copyleft'
+          exclude: '(?i)^(pylint|aio[-_]*).*'
+
+      - name: Print report
+        if: ${{ always() }}
+        run: echo "${{ steps.license_check_report.outputs.report }}"
+
+      - name: Install npm dependencies
+        working-directory: ./web
+        run: npm ci
+
+      - name: Run Trivy vulnerability scanner in repo mode
+        uses: aquasecurity/trivy-action@0.28.0
+        with:
+          scan-type: fs
+          scanners: license
+          format: table
+#           format: sarif
+#           output: trivy-results.sarif
+          severity: HIGH,CRITICAL
+
+#       - name: Upload Trivy scan results to GitHub Security tab
+#         uses: github/codeql-action/upload-sarif@v3
+#         with:
+#           sarif_file: trivy-results.sarif

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

@@ -18,6 +18,9 @@ env:
   # Jira
   JIRA_USER_EMAIL: ${{ secrets.JIRA_USER_EMAIL }}
   JIRA_API_TOKEN: ${{ secrets.JIRA_API_TOKEN }}
+  # Google
+  GOOGLE_DRIVE_SERVICE_ACCOUNT_JSON_STR: ${{ secrets.GOOGLE_DRIVE_SERVICE_ACCOUNT_JSON_STR }}
+  GOOGLE_DRIVE_OAUTH_CREDENTIALS_JSON_STR: ${{ secrets.GOOGLE_DRIVE_OAUTH_CREDENTIALS_JSON_STR }}
 
 jobs:
   connectors-check:

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

@@ -15,7 +15,7 @@ env:
   OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
 
 jobs:
-  connectors-check:
+  model-check:
     # See https://runs-on.com/runners/linux/
     runs-on: [runs-on,runner=8cpu-linux-x64,"run-id=${{ github.run_id }}"]
 

README.md

@@ -1,4 +1,5 @@
 <!-- DANSWER_METADATA={"link": "https://github.com/danswer-ai/danswer/blob/main/README.md"} -->
+<a name="readme-top"></a>
 
 <h2 align="center">
 <a href="https://www.danswer.ai/"> <img width="50%" src="https://github.com/danswer-owners/danswer/blob/1fabd9372d66cd54238847197c33f091a724803b/DanswerWithName.png?raw=true)" /></a>
@@ -127,3 +128,19 @@ To try the Danswer Enterprise Edition:
 
 ## 💡 Contributing
 Looking to contribute? Please check out the [Contribution Guide](CONTRIBUTING.md) for more details.
+
+## ⭐Star History
+
+[![Star History Chart](https://api.star-history.com/svg?repos=danswer-ai/danswer&type=Date)](https://star-history.com/#danswer-ai/danswer&Date)
+
+## ✨Contributors
+
+<a href="https://github.com/aryn-ai/sycamore/graphs/contributors">
+  <img alt="contributors" src="https://contrib.rocks/image?repo=danswer-ai/danswer"/>
+</a>
+
+<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
+    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
+        ↑ Back to Top ↑
+    </a>
+</p>

backend/Dockerfile

@@ -12,7 +12,6 @@ ARG DANSWER_VERSION=0.8-dev
 ENV DANSWER_VERSION=${DANSWER_VERSION} \
     DANSWER_RUNNING_IN_DOCKER="true"
 
-ARG CA_CERT_CONTENT=""
 
 RUN echo "DANSWER_VERSION: ${DANSWER_VERSION}"
 # Install system dependencies
@@ -39,15 +38,6 @@ RUN apt-get update && \
     apt-get clean
 
 
-# Conditionally write the CA certificate and update certificates
-RUN if [ -n "$CA_CERT_CONTENT" ]; then \
-    echo "Adding custom CA certificate"; \
-    echo "$CA_CERT_CONTENT" > /usr/local/share/ca-certificates/my-ca.crt && \
-    chmod 644 /usr/local/share/ca-certificates/my-ca.crt && \
-    update-ca-certificates; \
-else \
-    echo "No custom CA certificate provided"; \
-fi
 
 # Install Python dependencies
 # Remove py which is pulled in by retry, py is not needed and is a CVE
@@ -87,7 +77,6 @@ RUN apt-get update && \
 RUN python -c "from tokenizers import Tokenizer; \
 Tokenizer.from_pretrained('nomic-ai/nomic-embed-text-v1')"
 
-
 # Pre-downloading NLTK for setups with limited egress
 RUN python -c "import nltk; \
 nltk.download('stopwords', quiet=True); \

backend/alembic/versions/5b29123cd710_nullable_search_settings_for_historic_.py

@@ -0,0 +1,70 @@
+"""nullable search settings for historic index attempts
+
+Revision ID: 5b29123cd710
+Revises: 949b4a92a401
+Create Date: 2024-10-30 19:37:59.630704
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "5b29123cd710"
+down_revision = "949b4a92a401"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # Drop the existing foreign key constraint
+    op.drop_constraint(
+        "fk_index_attempt_search_settings", "index_attempt", type_="foreignkey"
+    )
+
+    # Modify the column to be nullable
+    op.alter_column(
+        "index_attempt", "search_settings_id", existing_type=sa.INTEGER(), nullable=True
+    )
+
+    # Add back the foreign key with ON DELETE SET NULL
+    op.create_foreign_key(
+        "fk_index_attempt_search_settings",
+        "index_attempt",
+        "search_settings",
+        ["search_settings_id"],
+        ["id"],
+        ondelete="SET NULL",
+    )
+
+
+def downgrade() -> None:
+    # Warning: This will delete all index attempts that don't have search settings
+    op.execute(
+        """
+        DELETE FROM index_attempt
+        WHERE search_settings_id IS NULL
+    """
+    )
+
+    # Drop foreign key constraint
+    op.drop_constraint(
+        "fk_index_attempt_search_settings", "index_attempt", type_="foreignkey"
+    )
+
+    # Modify the column to be not nullable
+    op.alter_column(
+        "index_attempt",
+        "search_settings_id",
+        existing_type=sa.INTEGER(),
+        nullable=False,
+    )
+
+    # Add back the foreign key without ON DELETE SET NULL
+    op.create_foreign_key(
+        "fk_index_attempt_search_settings",
+        "index_attempt",
+        "search_settings",
+        ["search_settings_id"],
+        ["id"],
+    )

backend/danswer/auth/users.py

@@ -93,9 +93,9 @@
 from danswer.utils.telemetry import optional_telemetry
 from danswer.utils.telemetry import RecordType
 from danswer.utils.variable_functionality import fetch_versioned_implementation
-from shared_configs.configs import CURRENT_TENANT_ID_CONTEXTVAR
 from shared_configs.configs import MULTI_TENANT
 from shared_configs.configs import POSTGRES_DEFAULT_SCHEMA
+from shared_configs.contextvars import CURRENT_TENANT_ID_CONTEXTVAR
 
 
 logger = setup_logger()
@@ -510,19 +510,23 @@ async def get_user_manager(
 
 # This strategy is used to add tenant_id to the JWT token
 class TenantAwareJWTStrategy(JWTStrategy):
-    async def write_token(self, user: User) -> str:
+    async def _create_token_data(self, user: User, impersonate: bool = False) -> dict:
         tenant_id = get_tenant_id_for_email(user.email)
         data = {
             "sub": str(user.id),
             "aud": self.token_audience,
             "tenant_id": tenant_id,
         }
+        return data
+
+    async def write_token(self, user: User) -> str:
+        data = await self._create_token_data(user)
         return generate_jwt(
             data, self.encode_key, self.lifetime_seconds, algorithm=self.algorithm
         )
 
 
-def get_jwt_strategy() -> JWTStrategy:
+def get_jwt_strategy() -> TenantAwareJWTStrategy:
     return TenantAwareJWTStrategy(
         secret=USER_AUTH_SECRET,
         lifetime_seconds=SESSION_EXPIRE_TIME_SECONDS,

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

@@ -14,15 +14,16 @@
 
 from danswer.background.celery.apps.task_formatters import CeleryTaskColoredFormatter
 from danswer.background.celery.apps.task_formatters import CeleryTaskPlainFormatter
-from danswer.background.celery.celery_redis import RedisConnectorCredentialPair
-from danswer.background.celery.celery_redis import RedisConnectorDeletion
-from danswer.background.celery.celery_redis import RedisConnectorPruning
-from danswer.background.celery.celery_redis import RedisDocumentSet
-from danswer.background.celery.celery_redis import RedisUserGroup
 from danswer.background.celery.celery_utils import celery_is_worker_primary
 from danswer.configs.constants import DanswerRedisLocks
 from danswer.db.engine import get_all_tenant_ids
+from danswer.redis.redis_connector import RedisConnector
+from danswer.redis.redis_connector_credential_pair import RedisConnectorCredentialPair
+from danswer.redis.redis_connector_delete import RedisConnectorDelete
+from danswer.redis.redis_connector_prune import RedisConnectorPrune
+from danswer.redis.redis_document_set import RedisDocumentSet
 from danswer.redis.redis_pool import get_redis_client
+from danswer.redis.redis_usergroup import RedisUserGroup
 from danswer.utils.logger import ColoredFormatter
 from danswer.utils.logger import PlainFormatter
 from danswer.utils.logger import setup_logger
@@ -108,29 +109,27 @@ def on_task_postrun(
     if task_id.startswith(RedisDocumentSet.PREFIX):
         document_set_id = RedisDocumentSet.get_id_from_task_id(task_id)
         if document_set_id is not None:
-            rds = RedisDocumentSet(int(document_set_id))
+            rds = RedisDocumentSet(tenant_id, int(document_set_id))
             r.srem(rds.taskset_key, task_id)
         return
 
     if task_id.startswith(RedisUserGroup.PREFIX):
         usergroup_id = RedisUserGroup.get_id_from_task_id(task_id)
         if usergroup_id is not None:
-            rug = RedisUserGroup(int(usergroup_id))
+            rug = RedisUserGroup(tenant_id, int(usergroup_id))
             r.srem(rug.taskset_key, task_id)
         return
 
-    if task_id.startswith(RedisConnectorDeletion.PREFIX):
-        cc_pair_id = RedisConnectorDeletion.get_id_from_task_id(task_id)
+    if task_id.startswith(RedisConnectorDelete.PREFIX):
+        cc_pair_id = RedisConnector.get_id_from_task_id(task_id)
         if cc_pair_id is not None:
-            rcd = RedisConnectorDeletion(int(cc_pair_id))
-            r.srem(rcd.taskset_key, task_id)
+            RedisConnectorDelete.remove_from_taskset(int(cc_pair_id), task_id, r)
         return
 
-    if task_id.startswith(RedisConnectorPruning.SUBTASK_PREFIX):
-        cc_pair_id = RedisConnectorPruning.get_id_from_task_id(task_id)
+    if task_id.startswith(RedisConnectorPrune.SUBTASK_PREFIX):
+        cc_pair_id = RedisConnector.get_id_from_task_id(task_id)
         if cc_pair_id is not None:
-            rcp = RedisConnectorPruning(int(cc_pair_id))
-            r.srem(rcp.taskset_key, task_id)
+            RedisConnectorPrune.remove_from_taskset(int(cc_pair_id), task_id, r)
         return