fix

* Confluence fixes

* Small tweak

* Address greptile comments

.github/CODEOWNERS

@@ -0,0 +1 @@
+* @onyx-dot-app/onyx-core-team

.github/pull_request_template.md

@@ -1,29 +1,14 @@
 ## Description
+
 [Provide a brief description of the changes in this PR]
 
-
 ## How Has This Been Tested?
+
 [Describe the tests you ran to verify your changes]
 
-
-## Accepted Risk (provide if relevant)
-N/A
-
-
-## Related Issue(s) (provide if relevant)
-N/A
-
-
-## Mental Checklist:
-- All of the automated tests pass
-- All PR comments are addressed and marked resolved
-- If there are migrations, they have been rebased to latest main
-- If there are new dependencies, they are added to the requirements
-- If there are new environment variables, they are added to all of the deployment methods
-- If there are new APIs that don't require auth, they are added to PUBLIC_ENDPOINT_SPECS
-- Docker images build and basic functionalities work
-- Author has done a final read through of the PR right before merge
-
 ## Backporting (check the box to trigger backport action)
+
 Note: You have to check that the action passes, otherwise resolve the conflicts manually and tag the patches.
+
 - [ ] This PR should be backported (make sure to check that the backport attempt succeeds)
+- [ ] [Optional] Override Linear Check

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

@@ -6,7 +6,7 @@ on:
       - "*"
 
 env:
-  REGISTRY_IMAGE: ${{ contains(github.ref_name, 'cloud') && 'danswer/danswer-backend-cloud' || 'danswer/danswer-backend' }}
+  REGISTRY_IMAGE: ${{ contains(github.ref_name, 'cloud') && 'onyxdotapp/onyx-backend-cloud' || 'onyxdotapp/onyx-backend' }}
   LATEST_TAG: ${{ contains(github.ref_name, 'latest') }}
 
 jobs:
@@ -44,7 +44,7 @@ jobs:
             ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
             ${{ env.LATEST_TAG == 'true' && format('{0}:latest', env.REGISTRY_IMAGE) || '' }}
           build-args: |
-            DANSWER_VERSION=${{ github.ref_name }}
+            ONYX_VERSION=${{ github.ref_name }}
 
       # trivy has their own rate limiting issues causing this action to flake
       # we worked around it by hardcoding to different db repos in env
@@ -57,7 +57,7 @@ jobs:
           TRIVY_DB_REPOSITORY: "public.ecr.aws/aquasecurity/trivy-db:2"
           TRIVY_JAVA_DB_REPOSITORY: "public.ecr.aws/aquasecurity/trivy-java-db:1"
         with:
-          # To run locally: trivy image --severity HIGH,CRITICAL danswer/danswer-backend
+          # To run locally: trivy image --severity HIGH,CRITICAL onyxdotapp/onyx-backend
           image-ref: docker.io/${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
           severity: "CRITICAL,HIGH"
           trivyignores: ./backend/.trivyignore

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

@@ -60,12 +60,16 @@ jobs:
           platforms: ${{ matrix.platform }}
           push: true
           build-args: |
-            DANSWER_VERSION=${{ github.ref_name }}
+            ONYX_VERSION=${{ github.ref_name }}
             NEXT_PUBLIC_CLOUD_ENABLED=true
             NEXT_PUBLIC_POSTHOG_KEY=${{ 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
+            NODE_OPTIONS=--max-old-space-size=8192
           # needed due to weird interactions with the builds for different platforms
           no-cache: true
           labels: ${{ steps.meta.outputs.labels }}

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

@@ -6,20 +6,56 @@ on:
       - "*"
 
 env:
-  REGISTRY_IMAGE: ${{ contains(github.ref_name, 'cloud') && 'danswer/danswer-model-server-cloud' || 'danswer/danswer-model-server' }}
+  REGISTRY_IMAGE: ${{ contains(github.ref_name, 'cloud') && 'onyxdotapp/onyx-model-server-cloud' || 'onyxdotapp/onyx-model-server' }}
   LATEST_TAG: ${{ contains(github.ref_name, 'latest') }}
+  DOCKER_BUILDKIT: 1
+  BUILDKIT_PROGRESS: plain
 
 jobs:
-  build-and-push:
-    # See https://runs-on.com/runners/linux/
-    runs-on: [runs-on, runner=8cpu-linux-x64, "run-id=${{ github.run_id }}"]
-
+  # 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:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: System Info
+        run: |
+          df -h
+          free -h
+          docker system prune -af --volumes
+
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v3
+        with:
+          driver-opts: |
+            image=moby/buildkit:latest
+            network=host
 
       - name: Login to Docker Hub
         uses: docker/login-action@v3
@@ -27,29 +63,89 @@ jobs:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_TOKEN }}
 
-      - name: Model Server Image Docker Build and Push
+      - name: Build and Push AMD64
         uses: docker/build-push-action@v5
         with:
           context: ./backend
           file: ./backend/Dockerfile.model_server
-          platforms: linux/amd64,linux/arm64
+          platforms: linux/amd64
           push: true
-          tags: |
-            ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
-            ${{ env.LATEST_TAG == 'true' && format('{0}:latest', env.REGISTRY_IMAGE) || '' }}
+          tags: ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}-amd64
           build-args: |
             DANSWER_VERSION=${{ github.ref_name }}
+          outputs: type=registry
+          provenance: false
+
+  build-arm64:
+    needs: [check_model_server_changes]
+    if: needs.check_model_server_changes.outputs.changed == 'true'
+    runs-on:
+      [runs-on, runner=8cpu-linux-x64, "run-id=${{ github.run_id }}-arm64"]
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: System Info
+        run: |
+          df -h
+          free -h
+          docker system prune -af --volumes
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+        with:
+          driver-opts: |
+            image=moby/buildkit:latest
+            network=host
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_TOKEN }}
+
+      - name: Build and Push ARM64
+        uses: docker/build-push-action@v5
+        with:
+          context: ./backend
+          file: ./backend/Dockerfile.model_server
+          platforms: linux/arm64
+          push: true
+          tags: ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}-arm64
+          build-args: |
+            DANSWER_VERSION=${{ github.ref_name }}
+          outputs: type=registry
+          provenance: false
+
+  merge-and-scan:
+    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
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_TOKEN }}
+
+      - name: Create and Push Multi-arch Manifest
+        run: |
+          docker buildx create --use
+          docker buildx imagetools create -t ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }} \
+            ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}-amd64 \
+            ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}-arm64
+          if [[ "${{ env.LATEST_TAG }}" == "true" ]]; then
+            docker buildx imagetools create -t ${{ env.REGISTRY_IMAGE }}:latest \
+              ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}-amd64 \
+              ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}-arm64
+          fi
 
-      # 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: Run Trivy vulnerability scanner
         uses: aquasecurity/trivy-action@master
         env:
           TRIVY_DB_REPOSITORY: "public.ecr.aws/aquasecurity/trivy-db:2"
           TRIVY_JAVA_DB_REPOSITORY: "public.ecr.aws/aquasecurity/trivy-java-db:1"
         with:
-          image-ref: docker.io/danswer/danswer-model-server:${{ github.ref_name }}
+          image-ref: docker.io/${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
           severity: "CRITICAL,HIGH"
+          timeout: "10m"

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

@@ -59,7 +59,9 @@ jobs:
           platforms: ${{ matrix.platform }}
           push: true
           build-args: |
-            DANSWER_VERSION=${{ github.ref_name }}
+            ONYX_VERSION=${{ github.ref_name }}
+            NODE_OPTIONS=--max-old-space-size=8192
+
           # needed due to weird interactions with the builds for different platforms
           no-cache: true
           labels: ${{ steps.meta.outputs.labels }}

.github/workflows/hotfix-release-branches.yml

@@ -8,43 +8,42 @@ on:
   workflow_dispatch:
     inputs:
       hotfix_commit:
-        description: 'Hotfix commit hash'
+        description: "Hotfix commit hash"
         required: true
       hotfix_suffix:
-        description: 'Hotfix branch suffix (e.g. hotfix/v0.8-{suffix})'
+        description: "Hotfix branch suffix (e.g. hotfix/v0.8-{suffix})"
         required: true
       release_branch_pattern:
-        description: 'Release branch pattern (regex)'
+        description: "Release branch pattern (regex)"
         required: true
-        default: 'release/.*'
+        default: "release/.*"
       auto_merge:
-        description: 'Automatically merge the hotfix PRs'
+        description: "Automatically merge the hotfix PRs"
         required: true
         type: choice
-        default: 'true'
+        default: "true"
         options:
           - true
           - false
-          
+
 jobs:
   hotfix_release_branches:
     permissions: write-all
     # See https://runs-on.com/runners/linux/
     # use a lower powered instance since this just does i/o to docker hub
-    runs-on: [runs-on,runner=2cpu-linux-x64,"run-id=${{ github.run_id }}"]
+    runs-on: [runs-on, runner=2cpu-linux-x64, "run-id=${{ github.run_id }}"]
     steps:
-    
       # needs RKUO_DEPLOY_KEY for write access to merge PR's
       - name: Checkout Repository
         uses: actions/checkout@v4
         with:
           ssh-key: "${{ secrets.RKUO_DEPLOY_KEY }}"
           fetch-depth: 0
-          
+
       - name: Set up Git user
         run: |
           git config user.name "Richard Kuo [bot]"
-          git config user.email "rkuo[bot]@danswer.ai"
+          git config user.email "rkuo[bot]@onyx.app"
 
       - name: Fetch All Branches
         run: |
@@ -62,10 +61,10 @@ jobs:
             echo "No release branches found matching pattern '${{ github.event.inputs.release_branch_pattern }}'."
             exit 1
           fi
-          
+
           echo "Found release branches:"
           echo "$BRANCHES"
-          
+
           # Join the branches into a single line separated by commas
           BRANCHES_JOINED=$(echo "$BRANCHES" | tr '\n' ',' | sed 's/,$//')
 
@@ -169,4 +168,4 @@ jobs:
                 echo "Failed to merge pull request #$PR_NUMBER."
               fi
             fi
-          done
+          done

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

@@ -53,24 +53,90 @@ jobs:
           exclude: '(?i)^(pylint|aio[-_]*).*'
           
       - name: Print report
-        if: ${{ always() }}
+        if: always()
         run: echo "${{ 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
+        # be careful enabling the sarif and upload as it may spam the security tab
+        # with a huge amount of items. Work out the issues before enabling upload.       
+#       - name: Run Trivy vulnerability scanner in repo mode
+#         if: always()
+#         uses: aquasecurity/trivy-action@0.29.0
 #         with:
-#           sarif_file: trivy-results.sarif
+#           scan-type: fs
+#           scan-ref: .
+#           scanners: license
+#           format: table
+#           severity: HIGH,CRITICAL
+# #           format: sarif
+# #           output: trivy-results.sarif
+# 
+# #       - name: Upload Trivy scan results to GitHub Security tab
+# #         uses: github/codeql-action/upload-sarif@v3
+# #         with:
+# #           sarif_file: trivy-results.sarif
+
+  scan-trivy:
+    # See https://runs-on.com/runners/linux/
+    runs-on: [runs-on,runner=2cpu-linux-x64,"run-id=${{ github.run_id }}"]
+      
+    steps:
+    - name: Set up Docker Buildx
+      uses: docker/setup-buildx-action@v3
+
+    - name: Login to Docker Hub
+      uses: docker/login-action@v3
+      with:
+        username: ${{ secrets.DOCKER_USERNAME }}
+        password: ${{ secrets.DOCKER_TOKEN }}
+
+    # Backend
+    - name: Pull backend docker image
+      run: docker pull onyxdotapp/onyx-backend:latest
+
+    - name: Run Trivy vulnerability scanner on backend
+      uses: aquasecurity/trivy-action@0.29.0
+      env:
+        TRIVY_DB_REPOSITORY: 'public.ecr.aws/aquasecurity/trivy-db:2'
+        TRIVY_JAVA_DB_REPOSITORY: 'public.ecr.aws/aquasecurity/trivy-java-db:1'
+      with:
+        image-ref: onyxdotapp/onyx-backend:latest
+        scanners: license
+        severity: HIGH,CRITICAL
+        vuln-type: library
+        exit-code: 0  # Set to 1 if we want a failed scan to fail the workflow
+
+    # Web server
+    - name: Pull web server docker image
+      run: docker pull onyxdotapp/onyx-web-server:latest
+          
+    - name: Run Trivy vulnerability scanner on web server
+      uses: aquasecurity/trivy-action@0.29.0
+      env:
+        TRIVY_DB_REPOSITORY: 'public.ecr.aws/aquasecurity/trivy-db:2'
+        TRIVY_JAVA_DB_REPOSITORY: 'public.ecr.aws/aquasecurity/trivy-java-db:1'
+      with:
+        image-ref: onyxdotapp/onyx-web-server:latest
+        scanners: license
+        severity: HIGH,CRITICAL
+        vuln-type: library
+        exit-code: 0
+
+    # Model server
+    - name: Pull model server docker image
+      run: docker pull onyxdotapp/onyx-model-server:latest
+
+    - name: Run Trivy vulnerability scanner
+      uses: aquasecurity/trivy-action@0.29.0
+      env:
+        TRIVY_DB_REPOSITORY: 'public.ecr.aws/aquasecurity/trivy-db:2'
+        TRIVY_JAVA_DB_REPOSITORY: 'public.ecr.aws/aquasecurity/trivy-java-db:1'
+      with:
+        image-ref: onyxdotapp/onyx-model-server:latest
+        scanners: license
+        severity: HIGH,CRITICAL
+        vuln-type: library
+        exit-code: 0

.github/workflows/pr-backport-autotrigger.yml

@@ -4,7 +4,7 @@ name: Backport on Merge
 
 on:
   pull_request:
-    types: [closed]  # Later we check for merge so only PRs that go in can get backported
+    types: [closed] # Later we check for merge so only PRs that go in can get backported
 
 permissions:
   contents: write
@@ -26,9 +26,9 @@ jobs:
       - name: Set up Git user
         run: |
           git config user.name "Richard Kuo [bot]"
-          git config user.email "rkuo[bot]@danswer.ai"
+          git config user.email "rkuo[bot]@onyx.app"
           git fetch --prune
-      
+
       - name: Check for Backport Checkbox
         id: checkbox-check
         run: |
@@ -51,14 +51,14 @@ jobs:
           # Fetch latest tags for beta and stable
           LATEST_BETA_TAG=$(git tag -l "v[0-9]*.[0-9]*.[0-9]*-beta.[0-9]*" | grep -E "^v[0-9]+\.[0-9]+\.[0-9]+-beta\.[0-9]+$" | grep -v -- "-cloud" | sort -Vr | head -n 1)
           LATEST_STABLE_TAG=$(git tag -l "v[0-9]*.[0-9]*.[0-9]*" | grep -E "^v[0-9]+\.[0-9]+\.[0-9]+$" | sort -Vr | head -n 1)
-          
+
           # Handle case where no beta tags exist
           if [[ -z "$LATEST_BETA_TAG" ]]; then
             NEW_BETA_TAG="v1.0.0-beta.1"
           else
             NEW_BETA_TAG=$(echo $LATEST_BETA_TAG | awk -F '[.-]' '{print $1 "." $2 "." $3 "-beta." ($NF+1)}')
           fi
-          
+
           # Increment latest stable tag
           NEW_STABLE_TAG=$(echo $LATEST_STABLE_TAG | awk -F '.' '{print $1 "." $2 "." ($3+1)}')
           echo "latest_beta_tag=$LATEST_BETA_TAG" >> $GITHUB_OUTPUT
@@ -80,10 +80,10 @@ jobs:
         run: |
           set -e
           echo "Backporting to beta ${{ steps.list-branches.outputs.beta }} and stable ${{ steps.list-branches.outputs.stable }}"
-          
+
           # Echo the merge commit SHA
           echo "Merge commit SHA: ${{ github.event.pull_request.merge_commit_sha }}"
-          
+
           # Fetch all history for all branches and tags
           git fetch --prune
 
@@ -98,7 +98,7 @@ jobs:
             echo "Cherry-pick to beta failed due to conflicts."
             exit 1
           }
-          
+
           # Create new beta branch/tag
           git tag ${{ steps.list-branches.outputs.new_beta_tag }}
           # Push the changes and tag to the beta branch using PAT
@@ -110,13 +110,13 @@ jobs:
           echo "Last 5 commits on stable branch:"
           git log -n 5 --pretty=format:"%H"
           echo ""  # Newline for formatting
-          
+
           # Cherry-pick the merge commit from the merged PR
           git cherry-pick -m 1 ${{ github.event.pull_request.merge_commit_sha }} || {
             echo "Cherry-pick to stable failed due to conflicts."
             exit 1
           }
-          
+
           # Create new stable branch/tag
           git tag ${{ steps.list-branches.outputs.new_stable_tag }}
           # Push the changes and tag to the stable branch using PAT

.github/workflows/pr-helm-chart-testing.yml

@@ -21,10 +21,10 @@ jobs:
     - name: Set up Helm
       uses: azure/setup-helm@v4.2.0
       with:
-        version: v3.14.4
+        version: v3.17.0
       
     - name: Set up chart-testing
-      uses: helm/chart-testing-action@v2.6.1
+      uses: helm/chart-testing-action@v2.7.0
 
     # even though we specify chart-dirs in ct.yaml, it isn't used by ct for the list-changed command...
     - name: Run chart-testing (list-changed)
@@ -37,22 +37,6 @@ jobs:
           echo "changed=true" >> "$GITHUB_OUTPUT"
         fi
 
-#     rkuo: I don't think we need python?
-#     - 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
-#     - 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
-
     # lint all charts if any changes were detected
     - name: Run chart-testing (lint)
       if: steps.list-changed.outputs.changed == 'true'
@@ -62,7 +46,7 @@ jobs:
 
     - name: Create kind cluster
       if: steps.list-changed.outputs.changed == 'true'
-      uses: helm/kind-action@v1.10.0
+      uses: helm/kind-action@v1.12.0
 
     - name: Run chart-testing (install)
       if: steps.list-changed.outputs.changed == 'true'

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

@@ -20,8 +20,7 @@ env:
 jobs:
   integration-tests:
     # See https://runs-on.com/runners/linux/
-    runs-on:
-      [runs-on, runner=8cpu-linux-x64, ram=16, "run-id=${{ github.run_id }}"]
+    runs-on: [runs-on, runner=32cpu-linux-x64, "run-id=${{ github.run_id }}"]
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
@@ -95,23 +94,27 @@ jobs:
           cd deployment/docker_compose
           ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true \
           MULTI_TENANT=true \
-          AUTH_TYPE=basic \
+          AUTH_TYPE=cloud \
           REQUIRE_EMAIL_VERIFICATION=false \
           DISABLE_TELEMETRY=true \
           IMAGE_TAG=test \
-          docker compose -f docker-compose.dev.yml -p danswer-stack up -d
+          DEV_MODE=true \
+          docker compose -f docker-compose.multitenant-dev.yml -p onyx-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 "Waiting for 3 minutes to ensure API server is ready..."
+          sleep 180
           echo "Running integration tests..."
-          docker run --rm --network danswer-stack_default \
+          docker run --rm --network onyx-stack_default \
             --name test-runner \
             -e POSTGRES_HOST=relational_db \
             -e POSTGRES_USER=postgres \
             -e POSTGRES_PASSWORD=password \
             -e POSTGRES_DB=postgres \
+            -e POSTGRES_USE_NULL_POOL=true \
             -e VESPA_HOST=index \
             -e REDIS_HOST=cache \
             -e API_SERVER_HOST=api_server \
@@ -120,6 +123,10 @@ jobs:
             -e TEST_WEB_HOSTNAME=test-runner \
             -e AUTH_TYPE=cloud \
             -e MULTI_TENANT=true \
+            -e REQUIRE_EMAIL_VERIFICATION=false \
+            -e DISABLE_TELEMETRY=true \
+            -e IMAGE_TAG=test \
+            -e DEV_MODE=true \
             onyxdotapp/onyx-integration:test \
             /app/tests/integration/multitenant_tests
         continue-on-error: true
@@ -127,34 +134,38 @@ jobs:
 
       - name: Check multi-tenant test results
         run: |
-          if [ ${{ steps.run_tests.outcome }} == 'failure' ]; then
-            echo "Integration tests failed. Exiting with error."
+          if [ ${{ steps.run_multitenant_tests.outcome }} == 'failure' ]; then
+            echo "Multi-tenant integration tests failed. Exiting with error."
             exit 1
           else
-            echo "All integration tests passed successfully."
+            echo "All multi-tenant 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
+          docker compose -f docker-compose.multitenant-dev.yml -p onyx-stack down -v
 
+      # NOTE: Use pre-ping/null pool to reduce flakiness due to dropped connections
       - name: Start Docker containers
         run: |
           cd deployment/docker_compose
           ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true \
           AUTH_TYPE=basic \
+          POSTGRES_POOL_PRE_PING=true \
+          POSTGRES_USE_NULL_POOL=true \
           REQUIRE_EMAIL_VERIFICATION=false \
           DISABLE_TELEMETRY=true \
           IMAGE_TAG=test \
-          docker compose -f docker-compose.dev.yml -p danswer-stack up -d
+          INTEGRATION_TESTS_MODE=true \
+          docker compose -f docker-compose.dev.yml -p onyx-stack up -d
         id: start_docker
 
       - name: Wait for service to be ready
         run: |
           echo "Starting wait-for-service script..."
 
-          docker logs -f danswer-stack-api_server-1 &
+          docker logs -f onyx-stack-api_server-1 &
 
           start_time=$(date +%s)
           timeout=300  # 5 minutes in seconds
@@ -184,15 +195,24 @@ jobs:
           done
           echo "Finished waiting for service."
 
+      - name: Start Mock Services
+        run: |
+          cd backend/tests/integration/mock_services
+          docker compose -f docker-compose.mock-it-services.yml \
+            -p mock-it-services-stack up -d
+
+      # NOTE: Use pre-ping/null to reduce flakiness due to dropped connections
       - name: Run Standard Integration Tests
         run: |
           echo "Running integration tests..."
-          docker run --rm --network danswer-stack_default \
+          docker run --rm --network onyx-stack_default \
             --name test-runner \
             -e POSTGRES_HOST=relational_db \
             -e POSTGRES_USER=postgres \
             -e POSTGRES_PASSWORD=password \
             -e POSTGRES_DB=postgres \
+            -e POSTGRES_POOL_PRE_PING=true \
+            -e POSTGRES_USE_NULL_POOL=true \
             -e VESPA_HOST=index \
             -e REDIS_HOST=cache \
             -e API_SERVER_HOST=api_server \
@@ -202,6 +222,8 @@ jobs:
             -e CONFLUENCE_USER_NAME=${CONFLUENCE_USER_NAME} \
             -e CONFLUENCE_ACCESS_TOKEN=${CONFLUENCE_ACCESS_TOKEN} \
             -e TEST_WEB_HOSTNAME=test-runner \
+            -e MOCK_CONNECTOR_SERVER_HOST=mock_connector_server \
+            -e MOCK_CONNECTOR_SERVER_PORT=8001 \
             onyxdotapp/onyx-integration:test \
             /app/tests/integration/tests \
             /app/tests/integration/connector_job_tests
@@ -217,27 +239,30 @@ jobs:
             echo "All integration tests passed successfully."
           fi
 
-      # save before stopping the containers so the logs can be captured
-      - name: Save Docker logs
-        if: success() || failure()
+      # ------------------------------------------------------------
+      # Always gather logs BEFORE "down":
+      - name: Dump API server logs
+        if: always()
         run: |
           cd deployment/docker_compose
-          docker compose -f docker-compose.dev.yml -p danswer-stack logs > docker-compose.log
-          mv docker-compose.log ${{ github.workspace }}/docker-compose.log
+          docker compose -f docker-compose.dev.yml -p onyx-stack logs --no-color api_server > $GITHUB_WORKSPACE/api_server.log || true
 
-      - name: Stop Docker containers
+      - name: Dump all-container logs (optional)
+        if: always()
         run: |
           cd deployment/docker_compose
-          docker compose -f docker-compose.dev.yml -p danswer-stack down -v
+          docker compose -f docker-compose.dev.yml -p onyx-stack logs --no-color > $GITHUB_WORKSPACE/docker-compose.log || true
 
       - name: Upload logs
-        if: success() || failure()
+        if: always()
         uses: actions/upload-artifact@v4
         with:
-          name: docker-logs
+          name: docker-all-logs
           path: ${{ github.workspace }}/docker-compose.log
+      # ------------------------------------------------------------
 
       - name: Stop Docker containers
+        if: always()
         run: |
           cd deployment/docker_compose
-          docker compose -f docker-compose.dev.yml -p danswer-stack down -v
+          docker compose -f docker-compose.dev.yml -p onyx-stack down -v

.github/workflows/pr-linear-check.yml

@@ -0,0 +1,29 @@
+name: Ensure PR references Linear
+
+on:
+  pull_request:
+    types: [opened, edited, reopened, synchronize]
+
+jobs:
+  linear-check:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check PR body for Linear link or override
+        env:
+          PR_BODY: ${{ github.event.pull_request.body }}
+        run: |
+          # Looking for "https://linear.app" in the body
+          if echo "$PR_BODY" | grep -qE "https://linear\.app"; then
+            echo "Found a Linear link. Check passed."
+            exit 0
+          fi
+
+          # Looking for a checked override: "[x] Override Linear Check"
+          if echo "$PR_BODY" | grep -q "\[x\].*Override Linear Check"; then
+            echo "Override box is checked. Check passed."
+            exit 0
+          fi
+
+          # Otherwise, fail the run
+          echo "No Linear link or override found in the PR description."
+          exit 1

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

@@ -1,6 +1,6 @@
-name: Run Chromatic Tests
+name: Run Playwright Tests
 concurrency:
-  group: Run-Chromatic-Tests-${{ github.workflow }}-${{ github.head_ref || github.event.workflow_run.head_branch || github.run_id }}
+  group: Run-Playwright-Tests-${{ github.workflow }}-${{ github.head_ref || github.event.workflow_run.head_branch || github.run_id }}
   cancel-in-progress: true
 
 on: push
@@ -8,6 +8,8 @@ on: push
 env:
   OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
   SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
+  GEN_AI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+  MOCK_LLM_RESPONSE: true
 
 jobs:
   playwright-tests:
@@ -15,7 +17,12 @@ jobs:
 
     # See https://runs-on.com/runners/linux/
     runs-on:
-      [runs-on, runner=8cpu-linux-x64, ram=16, "run-id=${{ github.run_id }}"]
+      [
+        runs-on,
+        runner=32cpu-linux-x64,
+        disk=large,
+        "run-id=${{ github.run_id }}",
+      ]
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
@@ -111,6 +118,7 @@ jobs:
           cd deployment/docker_compose
           ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true \
           AUTH_TYPE=basic \
+          GEN_AI_API_KEY=${{ secrets.OPENAI_API_KEY }} \
           REQUIRE_EMAIL_VERIFICATION=false \
           DISABLE_TELEMETRY=true \
           IMAGE_TAG=test \
@@ -190,38 +198,47 @@ jobs:
           cd deployment/docker_compose
           docker compose -f docker-compose.dev.yml -p danswer-stack down -v
 
-  chromatic-tests:
-    name: Chromatic Tests
+# NOTE: Chromatic UI diff testing is currently disabled.
+# We are using Playwright for local and CI testing without visual regression checks.
+# Chromatic may be reintroduced in the future for UI diff testing if needed.
 
-    needs: playwright-tests
-    runs-on:
-      [runs-on, runner=8cpu-linux-x64, ram=16, "run-id=${{ github.run_id }}"]
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
+# chromatic-tests:
+#   name: Chromatic Tests
 
-      - name: Setup node
-        uses: actions/setup-node@v4
-        with:
-          node-version: 22
+#   needs: playwright-tests
+#   runs-on:
+#     [
+#       runs-on,
+#       runner=32cpu-linux-x64,
+#       disk=large,
+#       "run-id=${{ github.run_id }}",
+#     ]
+#   steps:
+#     - name: Checkout code
+#       uses: actions/checkout@v4
+#       with:
+#         fetch-depth: 0
 
-      - name: Install node dependencies
-        working-directory: ./web
-        run: npm ci
+#     - name: Setup node
+#       uses: actions/setup-node@v4
+#       with:
+#         node-version: 22
 
-      - name: Download Playwright test results
-        uses: actions/download-artifact@v4
-        with:
-          name: test-results
-          path: ./web/test-results
+#     - name: Install node dependencies
+#       working-directory: ./web
+#       run: npm ci
 
-      - name: Run Chromatic
-        uses: chromaui/action@latest
-        with:
-          playwright: true
-          projectToken: ${{ secrets.CHROMATIC_PROJECT_TOKEN }}
-          workingDir: ./web
-        env:
-          CHROMATIC_ARCHIVE_LOCATION: ./test-results
+#     - name: Download Playwright test results
+#       uses: actions/download-artifact@v4
+#       with:
+#         name: test-results
+#         path: ./web/test-results
+
+#     - name: Run Chromatic
+#       uses: chromaui/action@latest
+#       with:
+#         playwright: true
+#         projectToken: ${{ secrets.CHROMATIC_PROJECT_TOKEN }}
+#         workingDir: ./web
+#       env:
+#         CHROMATIC_ARCHIVE_LOCATION: ./test-results

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

@@ -26,6 +26,27 @@ env:
   GOOGLE_GMAIL_OAUTH_CREDENTIALS_JSON_STR: ${{ secrets.GOOGLE_GMAIL_OAUTH_CREDENTIALS_JSON_STR }}
   # Slab
   SLAB_BOT_TOKEN: ${{ secrets.SLAB_BOT_TOKEN }}
+  # Zendesk
+  ZENDESK_SUBDOMAIN: ${{ secrets.ZENDESK_SUBDOMAIN }}
+  ZENDESK_EMAIL: ${{ secrets.ZENDESK_EMAIL }}
+  ZENDESK_TOKEN: ${{ secrets.ZENDESK_TOKEN }}
+  # Salesforce
+  SF_USERNAME: ${{ secrets.SF_USERNAME }}
+  SF_PASSWORD: ${{ secrets.SF_PASSWORD }}
+  SF_SECURITY_TOKEN: ${{ secrets.SF_SECURITY_TOKEN }}
+  # Airtable
+  AIRTABLE_TEST_BASE_ID: ${{ secrets.AIRTABLE_TEST_BASE_ID }}
+  AIRTABLE_TEST_TABLE_ID: ${{ secrets.AIRTABLE_TEST_TABLE_ID }}
+  AIRTABLE_TEST_TABLE_NAME: ${{ secrets.AIRTABLE_TEST_TABLE_NAME }}
+  AIRTABLE_ACCESS_TOKEN: ${{ secrets.AIRTABLE_ACCESS_TOKEN }}
+  # Sharepoint
+  SHAREPOINT_CLIENT_ID: ${{ secrets.SHAREPOINT_CLIENT_ID }}
+  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:
@@ -53,7 +74,9 @@ jobs:
           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
-
+          playwright install chromium
+          playwright install-deps chromium
+          
       - name: Run Tests
         shell: script -q -e -c "bash --noprofile --norc -eo pipefail {0}"
         run: py.test -o junit_family=xunit2 -xv --ff backend/tests/daily/connectors

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

@@ -1,18 +1,29 @@
-name: Connector Tests
+name: Model Server Tests
 
 on:
   schedule:
     # This cron expression runs the job daily at 16:00 UTC (9am PT)
     - cron: "0 16 * * *"
-
+  workflow_dispatch:
+    inputs:
+      branch:
+        description: 'Branch to run the workflow on'
+        required: false
+        default: 'main'
+        
 env:
   # Bedrock
   AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
   AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
   AWS_REGION_NAME: ${{ secrets.AWS_REGION_NAME }}
 
-  # OpenAI
+  # API keys for testing
+  COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
+  LITELLM_API_KEY: ${{ secrets.LITELLM_API_KEY }}
+  LITELLM_API_URL: ${{ secrets.LITELLM_API_URL }}
   OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+  AZURE_API_KEY: ${{ secrets.AZURE_API_KEY }}
+  AZURE_API_URL: ${{ secrets.AZURE_API_URL }}
 
 jobs:
   model-check:
@@ -26,6 +37,23 @@ jobs:
       - name: Checkout code
         uses: actions/checkout@v4
 
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_TOKEN }}
+
+      # tag every docker image with "test" so that we can spin up the correct set
+      # of images during testing
+
+      # We don't need to build the Web Docker image since it's not yet used
+      # in the integration tests. We have a separate action to verify that it builds
+      # successfully.
+      - name: Pull Model Server Docker image
+        run: |
+          docker pull onyxdotapp/onyx-model-server:latest
+          docker tag onyxdotapp/onyx-model-server:latest onyxdotapp/onyx-model-server:test
+          
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
@@ -41,6 +69,49 @@ jobs:
           pip install --retries 5 --timeout 30 -r backend/requirements/default.txt
           pip install --retries 5 --timeout 30 -r backend/requirements/dev.txt
 
+      - name: Start Docker containers
+        run: |
+          cd deployment/docker_compose
+          ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true \
+          AUTH_TYPE=basic \
+          REQUIRE_EMAIL_VERIFICATION=false \
+          DISABLE_TELEMETRY=true \
+          IMAGE_TAG=test \
+          docker compose -f docker-compose.model-server-test.yml -p onyx-stack up -d indexing_model_server
+        id: start_docker
+
+      - name: Wait for service to be ready
+        run: |
+          echo "Starting wait-for-service script..."
+
+          start_time=$(date +%s)
+          timeout=300  # 5 minutes in seconds
+
+          while true; do
+            current_time=$(date +%s)
+            elapsed_time=$((current_time - start_time))
+            
+            if [ $elapsed_time -ge $timeout ]; then
+              echo "Timeout reached. Service did not become ready in 5 minutes."
+              exit 1
+            fi
+            
+            # Use curl with error handling to ignore specific exit code 56
+            response=$(curl -s -o /dev/null -w "%{http_code}" http://localhost:9000/api/health || echo "curl_error")
+            
+            if [ "$response" = "200" ]; then
+              echo "Service is ready!"
+              break
+            elif [ "$response" = "curl_error" ]; then
+              echo "Curl encountered an error, possibly exit code 56. Continuing to retry..."
+            else
+              echo "Service not ready yet (HTTP status $response). Retrying in 5 seconds..."
+            fi
+            
+            sleep 5
+          done
+          echo "Finished waiting for service."
+          
       - name: Run Tests
         shell: script -q -e -c "bash --noprofile --norc -eo pipefail {0}"
         run: |
@@ -56,3 +127,23 @@ jobs:
             -H 'Content-type: application/json' \
             --data '{"text":"Scheduled Model Tests failed! Check the run at: https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}"}' \
             $SLACK_WEBHOOK
+            
+      - name: Dump all-container logs (optional)
+        if: always()
+        run: |
+          cd deployment/docker_compose
+          docker compose -f docker-compose.model-server-test.yml -p onyx-stack logs --no-color > $GITHUB_WORKSPACE/docker-compose.log || true
+
+      - name: Upload logs
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: docker-all-logs
+          path: ${{ github.workspace }}/docker-compose.log
+          
+      - name: Stop Docker containers
+        if: always()
+        run: |
+          cd deployment/docker_compose
+          docker compose -f docker-compose.model-server-test.yml -p onyx-stack down -v
+          

.github/workflows/tag-nightly.yml

@@ -2,53 +2,52 @@ name: Nightly Tag Push
 
 on:
   schedule:
-    - cron: '0 10 * * *' # Runs every day at 2 AM PST / 3 AM PDT / 10 AM UTC
+    - cron: "0 10 * * *" # Runs every day at 2 AM PST / 3 AM PDT / 10 AM UTC
 
 permissions:
-  contents: write  # Allows pushing tags to the repository
+  contents: write # Allows pushing tags to the repository
 
 jobs:
   create-and-push-tag:
-    runs-on: [runs-on,runner=2cpu-linux-x64,"run-id=${{ github.run_id }}"]
+    runs-on: [runs-on, runner=2cpu-linux-x64, "run-id=${{ github.run_id }}"]
 
     steps:
-    # actions using GITHUB_TOKEN cannot trigger another workflow, but we do want this to trigger docker pushes
-    # see https://github.com/orgs/community/discussions/27028#discussioncomment-3254367 for the workaround we
-    # implement here which needs an actual user's deploy key
-    - name: Checkout code
-      uses: actions/checkout@v4
-      with:
-        ssh-key: "${{ secrets.RKUO_DEPLOY_KEY }}"
+      # actions using GITHUB_TOKEN cannot trigger another workflow, but we do want this to trigger docker pushes
+      # see https://github.com/orgs/community/discussions/27028#discussioncomment-3254367 for the workaround we
+      # implement here which needs an actual user's deploy key
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ssh-key: "${{ secrets.RKUO_DEPLOY_KEY }}"
 
-    - name: Set up Git user
-      run: |
-        git config user.name "Richard Kuo [bot]"
-        git config user.email "rkuo[bot]@danswer.ai"
+      - name: Set up Git user
+        run: |
+          git config user.name "Richard Kuo [bot]"
+          git config user.email "rkuo[bot]@onyx.app"
 
-    - name: Check for existing nightly tag
-      id: check_tag
-      run: |
-        if git tag --points-at HEAD --list "nightly-latest*" | grep -q .; then
-          echo "A tag starting with 'nightly-latest' already exists on HEAD."
-          echo "tag_exists=true" >> $GITHUB_OUTPUT
-        else
-          echo "No tag starting with 'nightly-latest' exists on HEAD."
-          echo "tag_exists=false" >> $GITHUB_OUTPUT
-        fi
-        
-    # don't tag again if HEAD already has a nightly-latest tag on it
-    - name: Create Nightly Tag
-      if: steps.check_tag.outputs.tag_exists == 'false'
-      env:
-        DATE: ${{ github.run_id }}
-      run: |
-        TAG_NAME="nightly-latest-$(date +'%Y%m%d')"
-        echo "Creating tag: $TAG_NAME"
-        git tag $TAG_NAME
+      - name: Check for existing nightly tag
+        id: check_tag
+        run: |
+          if git tag --points-at HEAD --list "nightly-latest*" | grep -q .; then
+            echo "A tag starting with 'nightly-latest' already exists on HEAD."
+            echo "tag_exists=true" >> $GITHUB_OUTPUT
+          else
+            echo "No tag starting with 'nightly-latest' exists on HEAD."
+            echo "tag_exists=false" >> $GITHUB_OUTPUT
+          fi
 
-    - name: Push Tag
-      if: steps.check_tag.outputs.tag_exists == 'false'
-      run: |
-        TAG_NAME="nightly-latest-$(date +'%Y%m%d')"
-        git push origin $TAG_NAME
-        
+      # don't tag again if HEAD already has a nightly-latest tag on it
+      - name: Create Nightly Tag
+        if: steps.check_tag.outputs.tag_exists == 'false'
+        env:
+          DATE: ${{ github.run_id }}
+        run: |
+          TAG_NAME="nightly-latest-$(date +'%Y%m%d')"
+          echo "Creating tag: $TAG_NAME"
+          git tag $TAG_NAME
+
+      - name: Push Tag
+        if: steps.check_tag.outputs.tag_exists == 'false'
+        run: |
+          TAG_NAME="nightly-latest-$(date +'%Y%m%d')"
+          git push origin $TAG_NAME

.gitignore

@@ -7,4 +7,6 @@
 .vscode/
 *.sw?
 /backend/tests/regression/answer_quality/search_test_config.yaml
-/web/test-results/
+/web/test-results/
+backend/onyx/agent_search/main/test_data.json
+backend/tests/regression/answer_quality/test_data.json

.vscode/env_template.txt

@@ -5,6 +5,8 @@
 # For local dev, often user Authentication is not needed
 AUTH_TYPE=disabled
 
+# Skip warm up for dev
+SKIP_WARM_UP=True
 
 # Always keep these on for Dev
 # Logs all model prompts to stdout
@@ -27,6 +29,7 @@ REQUIRE_EMAIL_VERIFICATION=False
 
 # Set these so if you wipe the DB, you don't end up having to go through the UI every time
 GEN_AI_API_KEY=<REPLACE THIS>
+OPENAI_API_KEY=<REPLACE THIS>
 # If answer quality isn't important for dev, use gpt-4o-mini since it's cheaper
 GEN_AI_MODEL_VERSION=gpt-4o
 FAST_GEN_AI_MODEL_VERSION=gpt-4o
@@ -49,3 +52,9 @@ BING_API_KEY=<REPLACE THIS>
 # Enable the full set of Danswer Enterprise Edition features
 # NOTE: DO NOT ENABLE THIS UNLESS YOU HAVE A PAID ENTERPRISE LICENSE (or if you are using this for local testing/development)
 ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=False
+
+# Agent Search configs  # TODO: Remove give proper namings
+AGENT_RETRIEVAL_STATS=False   # Note: This setting will incur substantial re-ranking effort
+AGENT_RERANKING_STATS=True
+AGENT_MAX_QUERY_RETRIEVAL_RESULTS=20
+AGENT_RERANKING_MAX_QUERY_RETRIEVAL_RESULTS=20

.vscode/launch.template.jsonc

@@ -17,7 +17,7 @@
 			 }
 		},
         {
-            "name": "Run All Danswer Services",
+            "name": "Run All Onyx Services",
             "configurations": [
                 "Web Server",
                 "Model Server",
@@ -28,6 +28,7 @@
 		  		"Celery heavy", 
 		  		"Celery indexing", 
 		  		"Celery beat",
+                "Celery monitoring",
             ],
 			"presentation": {
 				 "group": "1",
@@ -51,7 +52,8 @@
 		  		"Celery light", 
 		  		"Celery heavy", 
 		  		"Celery indexing", 
-		  		"Celery beat"
+		  		"Celery beat",
+                "Celery monitoring",
 		  	],
 			"presentation": {
 				 "group": "1",
@@ -122,7 +124,7 @@
                 "PYTHONUNBUFFERED": "1"
             },
             "args": [
-                "danswer.main:app",
+                "onyx.main:app",
                 "--reload",
                 "--port",
                 "8080"
@@ -139,7 +141,7 @@
             "consoleName": "Slack Bot",
             "type": "debugpy",
             "request": "launch",
-            "program": "danswer/danswerbot/slack/listener.py",
+            "program": "onyx/onyxbot/slack/listener.py",
             "cwd": "${workspaceFolder}/backend",
             "envFile": "${workspaceFolder}/.vscode/.env",
             "env": {
@@ -166,7 +168,7 @@
             },
             "args": [
                 "-A",
-                "danswer.background.celery.versioned_apps.primary",
+                "onyx.background.celery.versioned_apps.primary",
                 "worker",
                 "--pool=threads",
                 "--concurrency=4",
@@ -195,7 +197,7 @@
             },
             "args": [
                 "-A",
-                "danswer.background.celery.versioned_apps.light",
+                "onyx.background.celery.versioned_apps.light",
                 "worker",
                 "--pool=threads",
                 "--concurrency=64",
@@ -203,7 +205,7 @@
                 "--loglevel=INFO",
                 "--hostname=light@%n",
                 "-Q",
-                "vespa_metadata_sync,connector_deletion,doc_permissions_upsert",
+                "vespa_metadata_sync,connector_deletion,doc_permissions_upsert,checkpoint_cleanup",
             ],
             "presentation": {
 				 "group": "2",
@@ -224,7 +226,7 @@
             },
             "args": [
                 "-A",
-                "danswer.background.celery.versioned_apps.heavy",
+                "onyx.background.celery.versioned_apps.heavy",
                 "worker",
                 "--pool=threads",
                 "--concurrency=4",
@@ -254,7 +256,7 @@
             },
             "args": [
                 "-A",
-                "danswer.background.celery.versioned_apps.indexing",
+                "onyx.background.celery.versioned_apps.indexing",
                 "worker",
                 "--pool=threads",
                 "--concurrency=1",
@@ -269,6 +271,31 @@
 			 },
             "consoleTitle": "Celery indexing Console"
         },
+        {
+            "name": "Celery monitoring",
+            "type": "debugpy",
+            "request": "launch",
+            "module": "celery",
+            "cwd": "${workspaceFolder}/backend",
+            "envFile": "${workspaceFolder}/.vscode/.env",
+            "env": {},
+            "args": [
+                "-A",
+                "onyx.background.celery.versioned_apps.monitoring",
+                "worker",
+                "--pool=solo",
+                "--concurrency=1",
+                "--prefetch-multiplier=1",
+                "--loglevel=INFO",
+                "--hostname=monitoring@%n",
+                "-Q",
+                "monitoring",
+            ],
+            "presentation": {
+				 "group": "2",
+			 },
+            "consoleTitle": "Celery monitoring Console"
+        },
         {
             "name": "Celery beat",
             "type": "debugpy",
@@ -283,7 +310,7 @@
             },
             "args": [
                 "-A",
-                "danswer.background.celery.versioned_apps.beat",
+                "onyx.background.celery.versioned_apps.beat",
                 "beat",
                 "--loglevel=INFO",
             ],
@@ -308,7 +335,7 @@
             "args": [
                 "-v"
                 // Specify a sepcific module/test to run or provide nothing to run all tests
-                //"tests/unit/danswer/llm/answering/test_prune_and_merge.py"
+                //"tests/unit/onyx/llm/answering/test_prune_and_merge.py"
             ],
             "presentation": {
 				 "group": "2",
@@ -355,5 +382,20 @@
                 "PYTHONPATH": "."
             },
         },
+        {
+            "name": "Install Python Requirements",
+            "type": "node",
+            "request": "launch",
+            "runtimeExecutable": "bash",
+            "runtimeArgs": [
+                "-c",
+                "pip install -r backend/requirements/default.txt && pip install -r backend/requirements/dev.txt && pip install -r backend/requirements/ee.txt && pip install -r backend/requirements/model_server.txt"
+            ],
+            "cwd": "${workspaceFolder}",
+            "console": "integratedTerminal",
+            "presentation": {
+                 "group": "3"
+            }
+        },
     ]
 }

CONTRIBUTING.md

@@ -1,32 +1,38 @@
-<!-- DANSWER_METADATA={"link": "https://github.com/danswer-ai/danswer/blob/main/CONTRIBUTING.md"} -->
+<!-- DANSWER_METADATA={"link": "https://github.com/onyx-dot-app/onyx/blob/main/CONTRIBUTING.md"} -->
 
-# Contributing to Danswer
-Hey there! We are so excited that you're interested in Danswer.
+# Contributing to Onyx
+
+Hey there! We are so excited that you're interested in Onyx.
 
 As an open source project in a rapidly changing space, we welcome all contributions.
 
-
 ## 💃 Guidelines
+
 ### Contribution Opportunities
-The [GitHub Issues](https://github.com/danswer-ai/danswer/issues) page is a great place to start for contribution ideas.
+
+The [GitHub Issues](https://github.com/onyx-dot-app/onyx/issues) page is a great place to start for contribution ideas.
+
+To ensure that your contribution is aligned with the project's direction, please reach out to Hagen (or any other maintainer) on the Onyx team
+via [Slack](https://join.slack.com/t/onyx-dot-app/shared_invite/zt-2twesxdr6-5iQitKZQpgq~hYIZ~dv3KA) /
+[Discord](https://discord.gg/TDJ59cGV2X) or [email](mailto:founders@onyx.app).
 
 Issues that have been explicitly approved by the maintainers (aligned with the direction of the project)
 will be marked with the `approved by maintainers` label.
 Issues marked `good first issue` are an especially great place to start.
 
 **Connectors** to other tools are another great place to contribute. For details on how, refer to this
-[README.md](https://github.com/danswer-ai/danswer/blob/main/backend/danswer/connectors/README.md).
+[README.md](https://github.com/onyx-dot-app/onyx/blob/main/backend/onyx/connectors/README.md).
 
 If you have a new/different contribution in mind, we'd love to hear about it!
-Your input is vital to making sure that Danswer moves in the right direction.
+Your input is vital to making sure that Onyx moves in the right direction.
 Before starting on implementation, please raise a GitHub issue.
 
-And always feel free to message us (Chris Weaver / Yuhong Sun) on 
-[Slack](https://join.slack.com/t/danswer/shared_invite/zt-2lcmqw703-071hBuZBfNEOGUsLa5PXvQ) / 
-[Discord](https://discord.gg/TDJ59cGV2X) directly about anything at all. 
-
+Also, always feel free to message the founders (Chris Weaver / Yuhong Sun) on
+[Slack](https://join.slack.com/t/onyx-dot-app/shared_invite/zt-2twesxdr6-5iQitKZQpgq~hYIZ~dv3KA) /
+[Discord](https://discord.gg/TDJ59cGV2X) directly about anything at all.
 
 ### Contributing Code
+
 To contribute to this project, please follow the
 ["fork and pull request"](https://docs.github.com/en/get-started/quickstart/contributing-to-projects) workflow.
 When opening a pull request, mention related issues and feel free to tag relevant maintainers.
@@ -34,72 +40,78 @@ When opening a pull request, mention related issues and feel free to tag relevan
 Before creating a pull request please make sure that the new changes conform to the formatting and linting requirements.
 See the [Formatting and Linting](#formatting-and-linting) section for how to run these checks locally.
 
-
 ### Getting Help 🙋
+
 Our goal is to make contributing as easy as possible. If you run into any issues please don't hesitate to reach out.
 That way we can help future contributors and users can avoid the same issue.
 
 We also have support channels and generally interesting discussions on our
-[Slack](https://join.slack.com/t/danswer/shared_invite/zt-2afut44lv-Rw3kSWu6_OmdAXRpCv80DQ)
-and 
+[Slack](https://join.slack.com/t/onyx-dot-app/shared_invite/zt-2twesxdr6-5iQitKZQpgq~hYIZ~dv3KA)
+and
 [Discord](https://discord.gg/TDJ59cGV2X).
 
 We would love to see you there!
 
-
 ## Get Started 🚀
-Danswer being a fully functional app, relies on some external software, specifically:
+
+Onyx being a fully functional app, relies on some external software, specifically:
+
 - [Postgres](https://www.postgresql.org/) (Relational DB)
 - [Vespa](https://vespa.ai/) (Vector DB/Search Engine)
 - [Redis](https://redis.io/) (Cache)
 - [Nginx](https://nginx.org/) (Not needed for development flows generally)
 
-
 > **Note:**
-> This guide provides instructions to build and run Danswer locally from source with Docker containers providing the above external software. We believe this combination is easier for
-> development purposes. If you prefer to use pre-built container images, we provide instructions on running the full Danswer stack within Docker below.
-
+> This guide provides instructions to build and run Onyx locally from source with Docker containers providing the above external software. We believe this combination is easier for
+> development purposes. If you prefer to use pre-built container images, we provide instructions on running the full Onyx stack within Docker below.
 
 ### Local Set Up
+
 Be sure to use Python version 3.11. For instructions on installing Python 3.11 on macOS, refer to the [CONTRIBUTING_MACOS.md](./CONTRIBUTING_MACOS.md) readme.
 
 If using a lower version, modifications will have to be made to the code.
 If using a higher version, sometimes some libraries will not be available (i.e. we had problems with Tensorflow in the past with higher versions of python).
 
-
 #### Backend: Python requirements
+
 Currently, we use pip and recommend creating a virtual environment.
 
 For convenience here's a command for it:
+
 ```bash
 python -m venv .venv
 source .venv/bin/activate
 ```
 
 > **Note:**
-> This virtual environment MUST NOT be set up WITHIN the danswer directory if you plan on using mypy within certain IDEs.
-> For simplicity, we recommend setting up the virtual environment outside of the danswer directory.
+> This virtual environment MUST NOT be set up WITHIN the onyx directory if you plan on using mypy within certain IDEs.
+> For simplicity, we recommend setting up the virtual environment outside of the onyx directory.
 
 _For Windows, activate the virtual environment using Command Prompt:_
+
 ```bash
 .venv\Scripts\activate
 ```
+
 If using PowerShell, the command slightly differs:
+
 ```powershell
 .venv\Scripts\Activate.ps1
 ```
 
 Install the required python dependencies:
+
 ```bash
-pip install -r danswer/backend/requirements/default.txt
-pip install -r danswer/backend/requirements/dev.txt
-pip install -r danswer/backend/requirements/ee.txt
-pip install -r danswer/backend/requirements/model_server.txt
+pip install -r onyx/backend/requirements/default.txt
+pip install -r onyx/backend/requirements/dev.txt
+pip install -r onyx/backend/requirements/ee.txt
+pip install -r onyx/backend/requirements/model_server.txt
 ```
 
 Install Playwright for Python (headless browser required by the Web Connector)
 
 In the activated Python virtualenv, install Playwright for Python by running:
+
 ```bash
 playwright install
 ```
@@ -109,42 +121,90 @@ You may have to deactivate and reactivate your virtualenv for `playwright` to ap
 #### Frontend: Node dependencies
 
 Install [Node.js and npm](https://docs.npmjs.com/downloading-and-installing-node-js-and-npm) for the frontend.
-Once the above is done, navigate to `danswer/web` run:
+Once the above is done, navigate to `onyx/web` run:
+
 ```bash
 npm i
 ```
 
-#### Docker containers for external software
+## Formatting and Linting
+
+### Backend
+
+For the backend, you'll need to setup pre-commit hooks (black / reorder-python-imports).
+First, install pre-commit (if you don't have it already) following the instructions
+[here](https://pre-commit.com/#installation).
+
+With the virtual environment active, install the pre-commit library with:
+
+```bash
+pip install pre-commit
+```
+
+Then, from the `onyx/backend` directory, run:
+
+```bash
+pre-commit install
+```
+
+Additionally, we use `mypy` for static type checking.
+Onyx is fully type-annotated, and we want to keep it that way!
+To run the mypy checks manually, run `python -m mypy .` from the `onyx/backend` directory.
+
+### Web
+
+We use `prettier` for formatting. The desired version (2.8.8) will be installed via a `npm i` from the `onyx/web` directory.
+To run the formatter, use `npx prettier --write .` from the `onyx/web` directory.
+Please double check that prettier passes before creating a pull request.
+
+# Running the application for development
+
+## Developing using VSCode Debugger (recommended)
+
+We highly recommend using VSCode debugger for development.
+See [CONTRIBUTING_VSCODE.md](./CONTRIBUTING_VSCODE.md) for more details.
+
+Otherwise, you can follow the instructions below to run the application for development.
+
+## Manually running the application for development
+### Docker containers for external software
+
 You will need Docker installed to run these containers.
 
-First navigate to `danswer/deployment/docker_compose`, then start up Postgres/Vespa/Redis with:
+First navigate to `onyx/deployment/docker_compose`, then start up Postgres/Vespa/Redis with:
+
 ```bash
-docker compose -f docker-compose.dev.yml -p danswer-stack up -d index relational_db cache
+docker compose -f docker-compose.dev.yml -p onyx-stack up -d index relational_db cache
 ```
+
 (index refers to Vespa, relational_db refers to Postgres, and cache refers to Redis)
 
+### Running Onyx locally
+
+To start the frontend, navigate to `onyx/web` and run:
 
-#### Running Danswer locally
-To start the frontend, navigate to `danswer/web` and run:
 ```bash
 npm run dev
 ```
 
 Next, start the model server which runs the local NLP models.
-Navigate to `danswer/backend` and run:
+Navigate to `onyx/backend` and run:
+
 ```bash
 uvicorn model_server.main:app --reload --port 9000
 ```
 
 _For Windows (for compatibility with both PowerShell and Command Prompt):_
+
 ```bash
 powershell -Command "uvicorn model_server.main:app --reload --port 9000"
 ```
 
-The first time running Danswer, you will need to run the DB migrations for Postgres.
+The first time running Onyx, you will need to run the DB migrations for Postgres.
 After the first time, this is no longer required unless the DB models change.
 
-Navigate to `danswer/backend` and with the venv active, run:
+Navigate to `onyx/backend` and with the venv active, run:
+
 ```bash
 alembic upgrade head
 ```
@@ -152,21 +212,24 @@ alembic upgrade head
 Next, start the task queue which orchestrates the background jobs.
 Jobs that take more time are run async from the API server.
 
-Still in `danswer/backend`, run:
+Still in `onyx/backend`, run:
+
 ```bash
 python ./scripts/dev_run_background_jobs.py
 ```
 
-To run the backend API server, navigate back to `danswer/backend` and run:
+To run the backend API server, navigate back to `onyx/backend` and run:
+
 ```bash
-AUTH_TYPE=disabled uvicorn danswer.main:app --reload --port 8080
+AUTH_TYPE=disabled uvicorn onyx.main:app --reload --port 8080
 ```
 
 _For Windows (for compatibility with both PowerShell and Command Prompt):_
+
 ```bash
 powershell -Command "
     $env:AUTH_TYPE='disabled'
-    uvicorn danswer.main:app --reload --port 8080 
+    uvicorn onyx.main:app --reload --port 8080
 "
 ```
 
@@ -182,57 +245,32 @@ You should now have 4 servers running:
 - Model server
 - Background jobs
 
-Now, visit `http://localhost:3000` in your browser. You should see the Danswer onboarding wizard where you can connect your external LLM provider to Danswer.
+Now, visit `http://localhost:3000` in your browser. You should see the Onyx onboarding wizard where you can connect your external LLM provider to Onyx.
 
-You've successfully set up a local Danswer instance! 🏁
+You've successfully set up a local Onyx instance! 🏁
 
-#### Running the Danswer application in a container
+#### Running the Onyx application in a container
 
-You can run the full Danswer application stack from pre-built images including all external software dependencies.
+You can run the full Onyx application stack from pre-built images including all external software dependencies.
 
-Navigate to `danswer/deployment/docker_compose` and run:
+Navigate to `onyx/deployment/docker_compose` and run:
 
 ```bash
-docker compose -f docker-compose.dev.yml -p danswer-stack up -d
+docker compose -f docker-compose.dev.yml -p onyx-stack up -d
 ```
 
-After Docker pulls and starts these containers, navigate to `http://localhost:3000` to use Danswer.
+After Docker pulls and starts these containers, navigate to `http://localhost:3000` to use Onyx.
 
-If you want to make changes to Danswer and run those changes in Docker, you can also build a local version of the Danswer container images that incorporates your changes like so:
+If you want to make changes to Onyx and run those changes in Docker, you can also build a local version of the Onyx container images that incorporates your changes like so:
 
 ```bash
-docker compose -f docker-compose.dev.yml -p danswer-stack up -d --build
+docker compose -f docker-compose.dev.yml -p onyx-stack up -d --build
 ```
 
-### Formatting and Linting
-#### Backend
-For the backend, you'll need to setup pre-commit hooks (black / reorder-python-imports).
-First, install pre-commit (if you don't have it already) following the instructions
-[here](https://pre-commit.com/#installation).
-
-With the virtual environment active, install the pre-commit library with:
-```bash
-pip install pre-commit
-```
-
-Then, from the `danswer/backend` directory, run:
-```bash
-pre-commit install
-```
-
-Additionally, we use `mypy` for static type checking.
-Danswer is fully type-annotated, and we want to keep it that way! 
-To run the mypy checks manually, run `python -m mypy .` from the `danswer/backend` directory.
-
-
-#### Web
-We use `prettier` for formatting. The desired version (2.8.8) will be installed via a `npm i` from the `danswer/web` directory. 
-To run the formatter, use `npx prettier --write .` from the `danswer/web` directory.
-Please double check that prettier passes before creating a pull request.
-
 
 ### Release Process
-Danswer loosely follows the SemVer versioning standard.
+
+Onyx loosely follows the SemVer versioning standard.
 Major changes are released with a "minor" version bump. Currently we use patch release versions to indicate small feature changes.
 A set of Docker containers will be pushed automatically to DockerHub with every tag.
-You can see the containers [here](https://hub.docker.com/search?q=danswer%2F).
+You can see the containers [here](https://hub.docker.com/search?q=onyx%2F).

CONTRIBUTING_MACOS.md

@@ -1,15 +1,19 @@
 ## Some additional notes for Mac Users
-The base instructions to set up the development environment are located in [CONTRIBUTING.md](https://github.com/danswer-ai/danswer/blob/main/CONTRIBUTING.md).
+
+The base instructions to set up the development environment are located in [CONTRIBUTING.md](https://github.com/onyx-dot-app/onyx/blob/main/CONTRIBUTING.md).
 
 ### Setting up Python
+
 Ensure [Homebrew](https://brew.sh/) is already set up.
 
 Then install python 3.11.
+
 ```bash
 brew install python@3.11
 ```
 
 Add python 3.11 to your path: add the following line to ~/.zshrc
+
 ```
 export PATH="$(brew --prefix)/opt/python@3.11/libexec/bin:$PATH"
 ```
@@ -17,15 +21,16 @@ export PATH="$(brew --prefix)/opt/python@3.11/libexec/bin:$PATH"
 > **Note:**
 > You will need to open a new terminal for the path change above to take effect.
 
-
 ### Setting up Docker
-On macOS, you will need to install [Docker Desktop](https://www.docker.com/products/docker-desktop/) and 
+
+On macOS, you will need to install [Docker Desktop](https://www.docker.com/products/docker-desktop/) and
 ensure it is running before continuing with the docker commands.
 
-
 ### Formatting and Linting
+
 MacOS will likely require you to remove some quarantine attributes on some of the hooks for them to execute properly.
 After installing pre-commit, run the following command:
+
 ```bash
 sudo xattr -r -d com.apple.quarantine ~/.cache/pre-commit
-```
+```

CONTRIBUTING_VSCODE.md

@@ -0,0 +1,30 @@
+# VSCode Debugging Setup
+
+This guide explains how to set up and use VSCode's debugging capabilities with this project.
+
+## Initial Setup
+
+1. **Environment Setup**:
+   - Copy `.vscode/.env.template` to `.vscode/.env`
+   - Fill in the necessary environment variables in `.vscode/.env`
+2. **launch.json**:
+   - Copy `.vscode/launch.template.jsonc` to `.vscode/launch.json`
+
+## Using the Debugger
+
+Before starting, make sure the Docker Daemon is running.
+
+1. Open the Debug view in VSCode (Cmd+Shift+D on macOS)
+2. From the dropdown at the top, select "Clear and Restart External Volumes and Containers" and press the green play button
+3. From the dropdown at the top, select "Run All Onyx Services" and press the green play button
+4. CD into web, run "npm i" followed by npm run dev.
+5. Now, you can navigate to onyx in your browser (default is http://localhost:3000) and start using the app
+6. You can set breakpoints by clicking to the left of line numbers to help debug while the app is running
+7. Use the debug toolbar to step through code, inspect variables, etc.
+
+## Features
+
+- Hot reload is enabled for the web server and API servers
+- Python debugging is configured with debugpy
+- Environment variables are loaded from `.vscode/.env`
+- Console output is organized in the integrated terminal with labeled tabs

LICENSE

@@ -2,9 +2,9 @@ Copyright (c) 2023-present DanswerAI, Inc.
 
 Portions of this software are licensed as follows:
 
-* All content that resides under "ee" directories of this repository, if that directory exists, is licensed under the license defined in "backend/ee/LICENSE". Specifically all content under "backend/ee" and "web/src/app/ee" is licensed under the license defined in "backend/ee/LICENSE".
-* All third party components incorporated into the Danswer Software are licensed under the original license provided by the owner of the applicable component.
-* Content outside of the above mentioned directories or restrictions above is available under the "MIT Expat" license as defined below.
+- All content that resides under "ee" directories of this repository, if that directory exists, is licensed under the license defined in "backend/ee/LICENSE". Specifically all content under "backend/ee" and "web/src/app/ee" is licensed under the license defined in "backend/ee/LICENSE".
+- All third party components incorporated into the Onyx Software are licensed under the original license provided by the owner of the applicable component.
+- Content outside of the above mentioned directories or restrictions above is available under the "MIT Expat" license as defined below.
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

README.md

@@ -1,146 +1,116 @@
-<!-- DANSWER_METADATA={"link": "https://github.com/danswer-ai/danswer/blob/main/README.md"} -->
+<!-- DANSWER_METADATA={"link": "https://github.com/onyx-dot-app/onyx/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>
+<a href="https://www.onyx.app/"> <img width="50%" src="https://github.com/onyx-dot-app/onyx/blob/logo/OnyxLogoCropped.jpg?raw=true)" /></a>
 </h2>
 
 <p align="center">
-<p align="center">Open Source Gen-AI Chat + Unified Search.</p>
+<p align="center">Open Source Gen-AI + Enterprise Search.</p>
 
 <p align="center">
-<a href="https://docs.danswer.dev/" target="_blank">
+<a href="https://docs.onyx.app/" target="_blank">
     <img src="https://img.shields.io/badge/docs-view-blue" alt="Documentation">
 </a>
-<a href="https://join.slack.com/t/danswer/shared_invite/zt-2twesxdr6-5iQitKZQpgq~hYIZ~dv3KA" target="_blank">
+<a href="https://join.slack.com/t/onyx-dot-app/shared_invite/zt-2twesxdr6-5iQitKZQpgq~hYIZ~dv3KA" target="_blank">
     <img src="https://img.shields.io/badge/slack-join-blue.svg?logo=slack" alt="Slack">
 </a>
 <a href="https://discord.gg/TDJ59cGV2X" target="_blank">
     <img src="https://img.shields.io/badge/discord-join-blue.svg?logo=discord&logoColor=white" alt="Discord">
 </a>
-<a href="https://github.com/danswer-ai/danswer/blob/main/README.md" target="_blank">
+<a href="https://github.com/onyx-dot-app/onyx/blob/main/README.md" target="_blank">
     <img src="https://img.shields.io/static/v1?label=license&message=MIT&color=blue" alt="License">
 </a>
 </p>
 
-<strong>[Danswer](https://www.danswer.ai/)</strong> is the AI Assistant connected to your company's docs, apps, and people. 
-Danswer provides a Chat interface and plugs into any LLM of your choice. Danswer can be deployed anywhere and for any 
-scale - on a laptop, on-premise, or to cloud. Since you own the deployment, your user data and chats are fully in your 
-own control. Danswer is MIT licensed and designed to be modular and easily extensible. The system also comes fully ready 
-for production usage with user authentication, role management (admin/basic users), chat persistence, and a UI for 
-configuring Personas (AI Assistants) and their Prompts.
-
-Danswer also serves as a Unified Search across all common workplace tools such as Slack, Google Drive, Confluence, etc.
-By combining LLMs and team specific knowledge, Danswer becomes a subject matter expert for the team. Imagine ChatGPT if
-it had access to your team's unique knowledge! It enables questions such as "A customer wants feature X, is this already
-supported?" or "Where's the pull request for feature Y?"
-
-<h3>Usage</h3>
-
-Danswer Web App:
-
-https://github.com/danswer-ai/danswer/assets/32520769/563be14c-9304-47b5-bf0a-9049c2b6f410
+<strong>[Onyx](https://www.onyx.app/)</strong> (formerly Danswer) is the AI platform connected to your company's docs, apps, and people.
+Onyx provides a feature rich Chat interface and plugs into any LLM of your choice.
+Keep knowledge and access controls sync-ed across over 40 connectors like Google Drive, Slack, Confluence, Salesforce, etc.
+Create custom AI agents with unique prompts, knowledge, and actions that the agents can take.
+Onyx can be deployed securely anywhere and for any scale - on a laptop, on-premise, or to cloud.
 
 
-Or, plug Danswer into your existing Slack workflows (more integrations to come 😁):
+<h3>Feature Highlights</h3>
 
-https://github.com/danswer-ai/danswer/assets/25087905/3e19739b-d178-4371-9a38-011430bdec1b
+**Deep research over your team's knowledge:**
+
+https://private-user-images.githubusercontent.com/32520769/414509312-48392e83-95d0-4fb5-8650-a396e05e0a32.mp4?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.a9D8A0sgKE9AoaoE-mfFbJ6_OKYeqaf7TZ4Han2JfW8
 
 
-For more details on the Admin UI to manage connectors and users, check out our 
-<strong><a href="https://www.youtube.com/watch?v=geNzY1nbCnU">Full Video Demo</a></strong>!
+**Use Onyx as a secure AI Chat with any LLM:**
+
+![Onyx Chat Silent Demo](https://github.com/onyx-dot-app/onyx/releases/download/v0.21.1/OnyxChatSilentDemo.gif)
+
+
+**Easily set up connectors to your apps:**
+
+![Onyx Connector Silent Demo](https://github.com/onyx-dot-app/onyx/releases/download/v0.21.1/OnyxConnectorSilentDemo.gif)
+
+
+**Access Onyx where your team already works:**
+
+![Onyx Bot Demo](https://github.com/onyx-dot-app/onyx/releases/download/v0.21.1/OnyxBot.png)
+
 
 ## Deployment
+**To try it out for free and get started in seconds, check out [Onyx Cloud](https://cloud.onyx.app/signup)**.
 
-Danswer can easily be run locally (even on a laptop) or deployed on a virtual machine with a single
-`docker compose` command. Checkout our [docs](https://docs.danswer.dev/quickstart) to learn more.
+Onyx can also be run locally (even on a laptop) or deployed on a virtual machine with a single
+`docker compose` command. Checkout our [docs](https://docs.onyx.app/quickstart) to learn more.
 
-We also have built-in support for deployment on Kubernetes. Files for that can be found [here](https://github.com/danswer-ai/danswer/tree/main/deployment/kubernetes).
+We also have built-in support for high-availability/scalable deployment on Kubernetes.
+References [here](https://github.com/onyx-dot-app/onyx/tree/main/deployment).
 
 
-## 💃 Main Features 
-* Chat UI with the ability to select documents to chat with.
-* Create custom AI Assistants with different prompts and backing knowledge sets.
-* Connect Danswer with LLM of your choice (self-host for a fully airgapped solution).
-* Document Search + AI Answers for natural language queries.
-* Connectors to all common workplace tools like Google Drive, Confluence, Slack, etc.
-* Slack integration to get answers and search results directly in Slack.
+## 🔍 Other Notable Benefits of Onyx
+- Custom deep learning models for indexing and inference time, only through Onyx + learning from user feedback.
+- Flexible security features like SSO (OIDC/SAML/OAuth2), RBAC, encryption of credentials, etc.
+- Knowledge curation features like document-sets, query history, usage analytics, etc.
+- Scalable deployment options tested up to many tens of thousands users and hundreds of millions of documents.
 
 
 ## 🚧 Roadmap
-* Chat/Prompt sharing with specific teammates and user groups.
-* Multimodal model support, chat with images, video etc.
-* Choosing between LLMs and parameters during chat session.
-* Tool calling and agent configurations options.
-* Organizational understanding and ability to locate and suggest experts from your team.
-
-
-## Other Notable Benefits of Danswer
-* User Authentication with document level access management.
-* Best in class Hybrid Search across all sources (BM-25 + prefix aware embedding models).
-* Admin Dashboard to configure connectors, document-sets, access, etc.
-* Custom deep learning models + learn from user feedback.
-* Easy deployment and ability to host Danswer anywhere of your choosing.
+- New methods in information retrieval (StructRAG, LightGraphRAG, etc.)
+- Personalized Search
+- Organizational understanding and ability to locate and suggest experts from your team.
+- Code Search
+- SQL and Structured Query Language
 
 
 ## 🔌 Connectors
-Efficiently pulls the latest changes from:
-  * Slack
-  * GitHub
-  * Google Drive
-  * Confluence
-  * Jira
-  * Zendesk
-  * Gmail
-  * Notion
-  * Gong
-  * Slab
-  * Linear
-  * Productboard
-  * Guru
-  * Bookstack
-  * Document360
-  * Sharepoint
-  * Hubspot
-  * Local Files
-  * Websites
-  * And more ...
+Keep knowledge and access up to sync across 40+ connectors:
 
-## 📚 Editions
+- Google Drive
+- Confluence
+- Slack
+- Gmail
+- Salesforce
+- Microsoft Sharepoint
+- Github
+- Jira
+- Zendesk
+- Gong
+- Microsoft Teams
+- Dropbox
+- Local Files
+- Websites
+- And more ...
 
-There are two editions of Danswer:
+See the full list [here](https://docs.onyx.app/connectors).
 
-  * Danswer Community Edition (CE) is available freely under the MIT Expat license. This version has ALL the core features discussed above. This is the version of Danswer you will get if you follow the Deployment guide above.
-  * Danswer Enterprise Edition (EE) includes extra features that are primarily useful for larger organizations. Specifically, this includes:
-    * Single Sign-On (SSO), with support for both SAML and OIDC
-    * Role-based access control
-    * Document permission inheritance from connected sources
-    * Usage analytics and query history accessible to admins
-    * Whitelabeling
-    * API key authentication
-    * Encryption of secrets
-    * Any many more! Checkout [our website](https://www.danswer.ai/) for the latest.
 
-To try the Danswer Enterprise Edition: 
+## 📚 Licensing
+There are two editions of Onyx:
+
+- Onyx Community Edition (CE) is available freely under the MIT Expat license. Simply follow the Deployment guide above.
+- Onyx Enterprise Edition (EE) includes extra features that are primarily useful for larger organizations.
+For feature details, check out [our website](https://www.onyx.app/pricing).
+
+To try the Onyx Enterprise Edition:
+1. Checkout [Onyx Cloud](https://cloud.onyx.app/signup).
+2. For self-hosting the Enterprise Edition, contact us at [founders@onyx.app](mailto:founders@onyx.app) or book a call with us on our [Cal](https://cal.com/team/onyx/founders).
 
-  1. Checkout our [Cloud product](https://app.danswer.ai/signup).
-  2. For self-hosting, contact us at [founders@danswer.ai](mailto:founders@danswer.ai) or book a call with us on our [Cal](https://cal.com/team/danswer/founders).
 
 ## 💡 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/danswer-ai/danswer/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/.gitignore

@@ -9,3 +9,4 @@ api_keys.py
 vespa-app.zip
 dynamic_config_storage/
 celerybeat-schedule*
+onyx/connectors/salesforce/data/

backend/Dockerfile

@@ -1,19 +1,21 @@
 FROM python:3.11.7-slim-bookworm
 
-LABEL com.danswer.maintainer="founders@danswer.ai"
-LABEL com.danswer.description="This image is the web/frontend container of Danswer which \
-contains code for both the Community and Enterprise editions of Danswer. If you do not \
+LABEL com.danswer.maintainer="founders@onyx.app"
+LABEL com.danswer.description="This image is the web/frontend container of Onyx which \
+contains code for both the Community and Enterprise editions of Onyx. If you do not \
 have a contract or agreement with DanswerAI, you are not permitted to use the Enterprise \
 Edition features outside of personal development or testing purposes. Please reach out to \
-founders@danswer.ai for more information. Please visit https://github.com/danswer-ai/danswer"
+founders@onyx.app for more information. Please visit https://github.com/onyx-dot-app/onyx"
 
-# Default DANSWER_VERSION, typically overriden during builds by GitHub Actions.
-ARG DANSWER_VERSION=0.8-dev
-ENV DANSWER_VERSION=${DANSWER_VERSION} \
-    DANSWER_RUNNING_IN_DOCKER="true"
+# Default ONYX_VERSION, typically overriden during builds by GitHub Actions.
+ARG ONYX_VERSION=0.8-dev
+# DO_NOT_TRACK is used to disable telemetry for Unstructured
+ENV ONYX_VERSION=${ONYX_VERSION} \
+    DANSWER_RUNNING_IN_DOCKER="true" \
+    DO_NOT_TRACK="true"
 
 
-RUN echo "DANSWER_VERSION: ${DANSWER_VERSION}"
+RUN echo "ONYX_VERSION: ${ONYX_VERSION}"
 # Install system dependencies
 # cmake needed for psycopg (postgres)
 # libpq-dev needed for psycopg (postgres)
@@ -26,14 +28,16 @@ RUN apt-get update && \
         curl \
         zip \
         ca-certificates \
-        libgnutls30=3.7.9-2+deb12u3 \
-        libblkid1=2.38.1-5+deb12u1 \
-        libmount1=2.38.1-5+deb12u1 \
-        libsmartcols1=2.38.1-5+deb12u1 \
-        libuuid1=2.38.1-5+deb12u1 \
+        libgnutls30 \
+        libblkid1 \
+        libmount1 \
+        libsmartcols1 \
+        libuuid1 \
         libxmlsec1-dev \
         pkg-config \
-        gcc && \
+        gcc \
+        nano \
+        vim && \
     rm -rf /var/lib/apt/lists/* && \
     apt-get clean
 
@@ -56,7 +60,7 @@ RUN pip install --no-cache-dir --upgrade \
 # Cleanup for CVEs and size reduction
 # https://github.com/tornadoweb/tornado/issues/3107
 # xserver-common and xvfb included by playwright installation but not needed after
-# perl-base is part of the base Python Debian image but not needed for Danswer functionality
+# perl-base is part of the base Python Debian image but not needed for Onyx functionality
 # perl-base could only be removed with --allow-remove-essential
 RUN apt-get update && \
     apt-get remove -y --allow-remove-essential \
@@ -92,14 +96,15 @@ COPY ./ee /app/ee
 COPY supervisord.conf /etc/supervisor/conf.d/supervisord.conf
 
 # Set up application files
-COPY ./danswer /app/danswer
+COPY ./onyx /app/onyx
 COPY ./shared_configs /app/shared_configs
 COPY ./alembic /app/alembic
 COPY ./alembic_tenants /app/alembic_tenants
 COPY ./alembic.ini /app/alembic.ini
 COPY supervisord.conf /usr/etc/supervisord.conf
 
-# Escape hatch
+# Escape hatch scripts
+COPY ./scripts/debugging /app/scripts/debugging
 COPY ./scripts/force_delete_connector_by_id.py /app/scripts/force_delete_connector_by_id.py
 
 # Put logo in assets

backend/Dockerfile.model_server

@@ -1,18 +1,18 @@
 FROM python:3.11.7-slim-bookworm
 
-LABEL com.danswer.maintainer="founders@danswer.ai"
-LABEL com.danswer.description="This image is for the Danswer model server which runs all of the \
-AI models for Danswer. This container and all the code is MIT Licensed and free for all to use. \
-You can find it at https://hub.docker.com/r/danswer/danswer-model-server. For more details, \
-visit https://github.com/danswer-ai/danswer."
+LABEL com.danswer.maintainer="founders@onyx.app"
+LABEL com.danswer.description="This image is for the Onyx model server which runs all of the \
+AI models for Onyx. This container and all the code is MIT Licensed and free for all to use. \
+You can find it at https://hub.docker.com/r/onyx/onyx-model-server. For more details, \
+visit https://github.com/onyx-dot-app/onyx."
 
-# Default DANSWER_VERSION, typically overriden during builds by GitHub Actions.
-ARG DANSWER_VERSION=0.8-dev
-ENV DANSWER_VERSION=${DANSWER_VERSION} \
+# Default ONYX_VERSION, typically overriden during builds by GitHub Actions.
+ARG ONYX_VERSION=0.8-dev
+ENV ONYX_VERSION=${ONYX_VERSION} \
     DANSWER_RUNNING_IN_DOCKER="true"
 
 
-RUN echo "DANSWER_VERSION: ${DANSWER_VERSION}"
+RUN echo "ONYX_VERSION: ${ONYX_VERSION}"
 
 COPY ./requirements/model_server.txt /tmp/requirements.txt
 RUN pip install --no-cache-dir --upgrade \
@@ -20,11 +20,11 @@ RUN pip install --no-cache-dir --upgrade \
         --timeout 30 \
         -r /tmp/requirements.txt
 
-RUN apt-get remove -y --allow-remove-essential perl-base && \
+RUN apt-get remove -y --allow-remove-essential perl-base && \ 
     apt-get autoremove -y
 
 # Pre-downloading models for setups with limited egress
-# Download tokenizers, distilbert for the Danswer model
+# Download tokenizers, distilbert for the Onyx model
 # Download model weights
 # Run Nomic to pull in the custom architecture and have it cached locally
 RUN python -c "from transformers import AutoTokenizer; \
@@ -38,18 +38,18 @@ from sentence_transformers import SentenceTransformer; \
 SentenceTransformer(model_name_or_path='nomic-ai/nomic-embed-text-v1', trust_remote_code=True);"
 
 # In case the user has volumes mounted to /root/.cache/huggingface that they've downloaded while
-# running Danswer, don't overwrite it with the built in cache folder
+# running Onyx, don't overwrite it with the built in cache folder
 RUN mv /root/.cache/huggingface /root/.cache/temp_huggingface
 
 WORKDIR /app
 
 # Utils used by model server
-COPY ./danswer/utils/logger.py /app/danswer/utils/logger.py
+COPY ./onyx/utils/logger.py /app/onyx/utils/logger.py
 
 # Place to fetch version information
-COPY ./danswer/__init__.py /app/danswer/__init__.py
+COPY ./onyx/__init__.py /app/onyx/__init__.py
 
-# Shared between Danswer Backend and Model Server
+# Shared between Onyx Backend and Model Server
 COPY ./shared_configs /app/shared_configs
 
 # Model Server main code

backend/alembic/README.md

@@ -1,19 +1,22 @@
-<!-- DANSWER_METADATA={"link": "https://github.com/danswer-ai/danswer/blob/main/backend/alembic/README.md"} -->
+<!-- DANSWER_METADATA={"link": "https://github.com/onyx-dot-app/onyx/blob/main/backend/alembic/README.md"} -->
 
 # Alembic DB Migrations
-These files are for creating/updating the tables in the Relational DB (Postgres).
-Danswer migrations use a generic single-database configuration with an async dbapi.
 
-## To generate new migrations: 
-run from danswer/backend:
+These files are for creating/updating the tables in the Relational DB (Postgres).
+Onyx migrations use a generic single-database configuration with an async dbapi.
+
+## To generate new migrations:
+
+run from onyx/backend:
 `alembic revision --autogenerate -m <DESCRIPTION_OF_MIGRATION>`
 
 More info can be found here: https://alembic.sqlalchemy.org/en/latest/autogenerate.html
 
 ## Running migrations
+
 To run all un-applied migrations:
 `alembic upgrade head`
 
 To undo migrations:
-`alembic downgrade -X` 
+`alembic downgrade -X`
 where X is the number of migrations you want to undo from the current state

backend/alembic/env.py

@@ -1,39 +1,49 @@
+from typing import Any, Literal
+from onyx.db.engine import get_iam_auth_token
+from onyx.configs.app_configs import USE_IAM_AUTH
+from onyx.configs.app_configs import POSTGRES_HOST
+from onyx.configs.app_configs import POSTGRES_PORT
+from onyx.configs.app_configs import POSTGRES_USER
+from onyx.configs.app_configs import AWS_REGION_NAME
+from onyx.db.engine import build_connection_string
+from onyx.db.engine import get_all_tenant_ids
+from sqlalchemy import event
+from sqlalchemy import pool
+from sqlalchemy import text
 from sqlalchemy.engine.base import Connection
-from typing import Literal
+import os
+import ssl
 import asyncio
-from logging.config import fileConfig
 import logging
+from logging.config import fileConfig
 
 from alembic import context
-from sqlalchemy import pool
 from sqlalchemy.ext.asyncio import create_async_engine
-from sqlalchemy.sql import text
 from sqlalchemy.sql.schema import SchemaItem
-
-from shared_configs.configs import MULTI_TENANT
-from danswer.db.engine import build_connection_string
-from danswer.db.models import Base
+from onyx.configs.constants import SSL_CERT_FILE
+from shared_configs.configs import MULTI_TENANT, POSTGRES_DEFAULT_SCHEMA
+from onyx.db.models import Base
 from celery.backends.database.session import ResultModelBase  # type: ignore
-from danswer.db.engine import get_all_tenant_ids
-from shared_configs.configs import POSTGRES_DEFAULT_SCHEMA
 
 # Alembic Config object
 config = context.config
 
-# Interpret the config file for Python logging.
 if config.config_file_name is not None and config.attributes.get(
     "configure_logger", True
 ):
     fileConfig(config.config_file_name)
 
-# Add your model's MetaData object here for 'autogenerate' support
 target_metadata = [Base.metadata, ResultModelBase.metadata]
 
 EXCLUDE_TABLES = {"kombu_queue", "kombu_message"}
-
-# Set up logging
 logger = logging.getLogger(__name__)
 
+ssl_context: ssl.SSLContext | None = None
+if USE_IAM_AUTH:
+    if not os.path.exists(SSL_CERT_FILE):
+        raise FileNotFoundError(f"Expected {SSL_CERT_FILE} when USE_IAM_AUTH is true.")
+    ssl_context = ssl.create_default_context(cafile=SSL_CERT_FILE)
+
 
 def include_object(
     object: SchemaItem,
@@ -49,20 +59,12 @@ def include_object(
     reflected: bool,
     compare_to: SchemaItem | None,
 ) -> bool:
-    """
-    Determines whether a database object should be included in migrations.
-    Excludes specified tables from migrations.
-    """
     if type_ == "table" and name in EXCLUDE_TABLES:
         return False
     return True
 
 
 def get_schema_options() -> tuple[str, bool, bool]:
-    """
-    Parses command-line options passed via '-x' in Alembic commands.
-    Recognizes 'schema', 'create_schema', and 'upgrade_all_tenants' options.
-    """
     x_args_raw = context.get_x_argument()
     x_args = {}
     for arg in x_args_raw:
@@ -90,16 +92,12 @@ def get_schema_options() -> tuple[str, bool, bool]:
 def do_run_migrations(
     connection: Connection, schema_name: str, create_schema: bool
 ) -> None:
-    """
-    Executes migrations in the specified schema.
-    """
     logger.info(f"About to migrate schema: {schema_name}")
 
     if create_schema:
         connection.execute(text(f'CREATE SCHEMA IF NOT EXISTS "{schema_name}"'))
         connection.execute(text("COMMIT"))
 
-    # Set search_path to the target schema
     connection.execute(text(f'SET search_path TO "{schema_name}"'))
 
     context.configure(
@@ -117,11 +115,25 @@ def do_run_migrations(
         context.run_migrations()
 
 
+def provide_iam_token_for_alembic(
+    dialect: Any, conn_rec: Any, cargs: Any, cparams: Any
+) -> None:
+    if USE_IAM_AUTH:
+        # Database connection settings
+        region = AWS_REGION_NAME
+        host = POSTGRES_HOST
+        port = POSTGRES_PORT
+        user = POSTGRES_USER
+
+        # Get IAM authentication token
+        token = get_iam_auth_token(host, port, user, region)
+
+        # For Alembic / SQLAlchemy in this context, set SSL and password
+        cparams["password"] = token
+        cparams["ssl"] = ssl_context
+
+
 async def run_async_migrations() -> None:
-    """
-    Determines whether to run migrations for a single schema or all schemas,
-    and executes migrations accordingly.
-    """
     schema_name, create_schema, upgrade_all_tenants = get_schema_options()
 
     engine = create_async_engine(
@@ -129,10 +141,16 @@ async def run_async_migrations() -> None:
         poolclass=pool.NullPool,
     )
 
-    if upgrade_all_tenants:
-        # Run migrations for all tenant schemas sequentially
-        tenant_schemas = get_all_tenant_ids()
+    if USE_IAM_AUTH:
 
+        @event.listens_for(engine.sync_engine, "do_connect")
+        def event_provide_iam_token_for_alembic(
+            dialect: Any, conn_rec: Any, cargs: Any, cparams: Any
+        ) -> None:
+            provide_iam_token_for_alembic(dialect, conn_rec, cargs, cparams)
+
+    if upgrade_all_tenants:
+        tenant_schemas = get_all_tenant_ids()
         for schema in tenant_schemas:
             try:
                 logger.info(f"Migrating schema: {schema}")
@@ -162,15 +180,20 @@ async def run_async_migrations() -> None:
 
 
 def run_migrations_offline() -> None:
-    """
-    Run migrations in 'offline' mode.
-    """
     schema_name, _, upgrade_all_tenants = get_schema_options()
     url = build_connection_string()
 
     if upgrade_all_tenants:
-        # Run offline migrations for all tenant schemas
         engine = create_async_engine(url)
+
+        if USE_IAM_AUTH:
+
+            @event.listens_for(engine.sync_engine, "do_connect")
+            def event_provide_iam_token_for_alembic_offline(
+                dialect: Any, conn_rec: Any, cargs: Any, cparams: Any
+            ) -> None:
+                provide_iam_token_for_alembic(dialect, conn_rec, cargs, cparams)
+
         tenant_schemas = get_all_tenant_ids()
         engine.sync_engine.dispose()
 
@@ -207,9 +230,6 @@ def run_migrations_offline() -> None:
 
 
 def run_migrations_online() -> None:
-    """
-    Runs migrations in 'online' mode using an asynchronous engine.
-    """
     asyncio.run(run_async_migrations())
 
 

backend/alembic/versions/027381bce97c_add_shortcut_option_for_users.py

@@ -0,0 +1,29 @@
+"""add shortcut option for users
+
+Revision ID: 027381bce97c
+Revises: 6fc7886d665d
+Create Date: 2025-01-14 12:14:00.814390
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "027381bce97c"
+down_revision = "6fc7886d665d"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "user",
+        sa.Column(
+            "shortcut_enabled", sa.Boolean(), nullable=False, server_default="false"
+        ),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("user", "shortcut_enabled")

backend/alembic/versions/0a98909f2757_enable_encrypted_fields.py

@@ -11,7 +11,7 @@ from sqlalchemy.sql import table
 from sqlalchemy.dialects import postgresql
 import json
 
-from danswer.utils.encryption import encrypt_string_to_bytes
+from onyx.utils.encryption import encrypt_string_to_bytes
 
 # revision identifiers, used by Alembic.
 revision = "0a98909f2757"

backend/alembic/versions/0f7ff6d75b57_add_index_to_index_attempt_time_created.py

@@ -0,0 +1,36 @@
+"""add index to index_attempt.time_created
+
+Revision ID: 0f7ff6d75b57
+Revises: 369644546676
+Create Date: 2025-01-10 14:01:14.067144
+
+"""
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision = "0f7ff6d75b57"
+down_revision = "fec3db967bf7"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.create_index(
+        op.f("ix_index_attempt_status"),
+        "index_attempt",
+        ["status"],
+        unique=False,
+    )
+
+    op.create_index(
+        op.f("ix_index_attempt_time_created"),
+        "index_attempt",
+        ["time_created"],
+        unique=False,
+    )
+
+
+def downgrade() -> None:
+    op.drop_index(op.f("ix_index_attempt_time_created"), table_name="index_attempt")
+
+    op.drop_index(op.f("ix_index_attempt_status"), table_name="index_attempt")

backend/alembic/versions/15326fcec57e_introduce_onyx_apis.py

@@ -1,4 +1,4 @@
-"""Introduce Danswer APIs
+"""Introduce Onyx APIs
 
 Revision ID: 15326fcec57e
 Revises: 77d07dffae64
@@ -8,7 +8,7 @@ Create Date: 2023-11-11 20:51:24.228999
 from alembic import op
 import sqlalchemy as sa
 
-from danswer.configs.constants import DocumentSource
+from onyx.configs.constants import DocumentSource
 
 # revision identifiers, used by Alembic.
 revision = "15326fcec57e"

backend/alembic/versions/1a03d2c2856b_add_indexes_to_document__tag.py

@@ -0,0 +1,27 @@
+"""Add indexes to document__tag
+
+Revision ID: 1a03d2c2856b
+Revises: 9c00a2bccb83
+Create Date: 2025-02-18 10:45:13.957807
+
+"""
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision = "1a03d2c2856b"
+down_revision = "9c00a2bccb83"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.create_index(
+        op.f("ix_document__tag_tag_id"),
+        "document__tag",
+        ["tag_id"],
+        unique=False,
+    )
+
+
+def downgrade() -> None:
+    op.drop_index(op.f("ix_document__tag_tag_id"), table_name="document__tag")

backend/alembic/versions/1f60f60c3401_embedding_model_search_settings.py

@@ -10,7 +10,7 @@ from alembic import op
 import sqlalchemy as sa
 from sqlalchemy.dialects import postgresql
 
-from danswer.configs.chat_configs import NUM_POSTPROCESSED_RESULTS
+from onyx.configs.chat_configs import NUM_POSTPROCESSED_RESULTS
 
 # revision identifiers, used by Alembic.
 revision = "1f60f60c3401"

backend/alembic/versions/2955778aa44c_add_chunk_count_to_document.py

@@ -0,0 +1,24 @@
+"""add chunk count to document
+
+Revision ID: 2955778aa44c
+Revises: c0aab6edb6dd
+Create Date: 2025-01-04 11:39:43.268612
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "2955778aa44c"
+down_revision = "c0aab6edb6dd"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.add_column("document", sa.Column("chunk_count", sa.Integer(), nullable=True))
+
+
+def downgrade() -> None:
+    op.drop_column("document", "chunk_count")

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/2f80c6a2550f_add_chat_session_specific_temperature_.py

@@ -0,0 +1,36 @@
+"""add chat session specific temperature override
+
+Revision ID: 2f80c6a2550f
+Revises: 33ea50e88f24
+Create Date: 2025-01-31 10:30:27.289646
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "2f80c6a2550f"
+down_revision = "33ea50e88f24"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "chat_session", sa.Column("temperature_override", sa.Float(), nullable=True)
+    )
+    op.add_column(
+        "user",
+        sa.Column(
+            "temperature_override_enabled",
+            sa.Boolean(),
+            nullable=False,
+            server_default=sa.false(),
+        ),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("chat_session", "temperature_override")
+    op.drop_column("user", "temperature_override_enabled")

backend/alembic/versions/33ea50e88f24_foreign_key_input_prompts.py

@@ -0,0 +1,80 @@
+"""foreign key input prompts
+
+Revision ID: 33ea50e88f24
+Revises: a6df6b88ef81
+Create Date: 2025-01-29 10:54:22.141765
+
+"""
+from alembic import op
+
+
+# revision identifiers, used by Alembic.
+revision = "33ea50e88f24"
+down_revision = "a6df6b88ef81"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # Safely drop constraints if exists
+    op.execute(
+        """
+        ALTER TABLE inputprompt__user
+        DROP CONSTRAINT IF EXISTS inputprompt__user_input_prompt_id_fkey
+        """
+    )
+    op.execute(
+        """
+        ALTER TABLE inputprompt__user
+        DROP CONSTRAINT IF EXISTS inputprompt__user_user_id_fkey
+        """
+    )
+
+    # Recreate with ON DELETE CASCADE
+    op.create_foreign_key(
+        "inputprompt__user_input_prompt_id_fkey",
+        "inputprompt__user",
+        "inputprompt",
+        ["input_prompt_id"],
+        ["id"],
+        ondelete="CASCADE",
+    )
+
+    op.create_foreign_key(
+        "inputprompt__user_user_id_fkey",
+        "inputprompt__user",
+        "user",
+        ["user_id"],
+        ["id"],
+        ondelete="CASCADE",
+    )
+
+
+def downgrade() -> None:
+    # Drop the new FKs with ondelete
+    op.drop_constraint(
+        "inputprompt__user_input_prompt_id_fkey",
+        "inputprompt__user",
+        type_="foreignkey",
+    )
+    op.drop_constraint(
+        "inputprompt__user_user_id_fkey",
+        "inputprompt__user",
+        type_="foreignkey",
+    )
+
+    # Recreate them without cascading
+    op.create_foreign_key(
+        "inputprompt__user_input_prompt_id_fkey",
+        "inputprompt__user",
+        "inputprompt",
+        ["input_prompt_id"],
+        ["id"],
+    )
+    op.create_foreign_key(
+        "inputprompt__user_user_id_fkey",
+        "inputprompt__user",
+        "user",
+        ["user_id"],
+        ["id"],
+    )

backend/alembic/versions/35e518e0ddf4_properly_cascade.py

@@ -0,0 +1,121 @@
+"""properly_cascade
+
+Revision ID: 35e518e0ddf4
+Revises: 91a0a4d62b14
+Create Date: 2024-09-20 21:24:04.891018
+
+"""
+from alembic import op
+
+
+# revision identifiers, used by Alembic.
+revision = "35e518e0ddf4"
+down_revision = "91a0a4d62b14"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # Update chat_message foreign key constraint
+    op.drop_constraint(
+        "chat_message_chat_session_id_fkey", "chat_message", type_="foreignkey"
+    )
+    op.create_foreign_key(
+        "chat_message_chat_session_id_fkey",
+        "chat_message",
+        "chat_session",
+        ["chat_session_id"],
+        ["id"],
+        ondelete="CASCADE",
+    )
+
+    # Update chat_message__search_doc foreign key constraints
+    op.drop_constraint(
+        "chat_message__search_doc_chat_message_id_fkey",
+        "chat_message__search_doc",
+        type_="foreignkey",
+    )
+    op.drop_constraint(
+        "chat_message__search_doc_search_doc_id_fkey",
+        "chat_message__search_doc",
+        type_="foreignkey",
+    )
+
+    op.create_foreign_key(
+        "chat_message__search_doc_chat_message_id_fkey",
+        "chat_message__search_doc",
+        "chat_message",
+        ["chat_message_id"],
+        ["id"],
+        ondelete="CASCADE",
+    )
+    op.create_foreign_key(
+        "chat_message__search_doc_search_doc_id_fkey",
+        "chat_message__search_doc",
+        "search_doc",
+        ["search_doc_id"],
+        ["id"],
+        ondelete="CASCADE",
+    )
+
+    # Add CASCADE delete for tool_call foreign key
+    op.drop_constraint("tool_call_message_id_fkey", "tool_call", type_="foreignkey")
+    op.create_foreign_key(
+        "tool_call_message_id_fkey",
+        "tool_call",
+        "chat_message",
+        ["message_id"],
+        ["id"],
+        ondelete="CASCADE",
+    )
+
+
+def downgrade() -> None:
+    # Revert chat_message foreign key constraint
+    op.drop_constraint(
+        "chat_message_chat_session_id_fkey", "chat_message", type_="foreignkey"
+    )
+    op.create_foreign_key(
+        "chat_message_chat_session_id_fkey",
+        "chat_message",
+        "chat_session",
+        ["chat_session_id"],
+        ["id"],
+    )
+
+    # Revert chat_message__search_doc foreign key constraints
+    op.drop_constraint(
+        "chat_message__search_doc_chat_message_id_fkey",
+        "chat_message__search_doc",
+        type_="foreignkey",
+    )
+    op.drop_constraint(
+        "chat_message__search_doc_search_doc_id_fkey",
+        "chat_message__search_doc",
+        type_="foreignkey",
+    )
+
+    op.create_foreign_key(
+        "chat_message__search_doc_chat_message_id_fkey",
+        "chat_message__search_doc",
+        "chat_message",
+        ["chat_message_id"],
+        ["id"],
+    )
+    op.create_foreign_key(
+        "chat_message__search_doc_search_doc_id_fkey",
+        "chat_message__search_doc",
+        "search_doc",
+        ["search_doc_id"],
+        ["id"],
+    )
+
+    # Revert tool_call foreign key constraint
+    op.drop_constraint("tool_call_message_id_fkey", "tool_call", type_="foreignkey")
+    op.create_foreign_key(
+        "tool_call_message_id_fkey",
+        "tool_call",
+        "chat_message",
+        ["message_id"],
+        ["id"],
+    )

backend/alembic/versions/369644546676_add_composite_index_for_index_attempt_.py

@@ -0,0 +1,35 @@
+"""add composite index for index attempt time updated
+
+Revision ID: 369644546676
+Revises: 2955778aa44c
+Create Date: 2025-01-08 15:38:17.224380
+
+"""
+from alembic import op
+from sqlalchemy import text
+
+# revision identifiers, used by Alembic.
+revision = "369644546676"
+down_revision = "2955778aa44c"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.create_index(
+        "ix_index_attempt_ccpair_search_settings_time_updated",
+        "index_attempt",
+        [
+            "connector_credential_pair_id",
+            "search_settings_id",
+            text("time_updated DESC"),
+        ],
+        unique=False,
+    )
+
+
+def downgrade() -> None:
+    op.drop_index(
+        "ix_index_attempt_ccpair_search_settings_time_updated",
+        table_name="index_attempt",
+    )

backend/alembic/versions/3934b1bc7b62_update_github_connector_repo_name_to_.py

@@ -0,0 +1,125 @@
+"""Update GitHub connector repo_name to repositories
+
+Revision ID: 3934b1bc7b62
+Revises: b7c2b63c4a03
+Create Date: 2025-03-05 10:50:30.516962
+
+"""
+from alembic import op
+import sqlalchemy as sa
+import json
+import logging
+
+# revision identifiers, used by Alembic.
+revision = "3934b1bc7b62"
+down_revision = "b7c2b63c4a03"
+branch_labels = None
+depends_on = None
+
+logger = logging.getLogger("alembic.runtime.migration")
+
+
+def upgrade() -> None:
+    # Get all GitHub connectors
+    conn = op.get_bind()
+
+    # First get all GitHub connectors
+    github_connectors = conn.execute(
+        sa.text(
+            """
+            SELECT id, connector_specific_config
+            FROM connector
+            WHERE source = 'GITHUB'
+            """
+        )
+    ).fetchall()
+
+    # Update each connector's config
+    updated_count = 0
+    for connector_id, config in github_connectors:
+        try:
+            if not config:
+                logger.warning(f"Connector {connector_id} has no config, skipping")
+                continue
+
+            # Parse the config if it's a string
+            if isinstance(config, str):
+                config = json.loads(config)
+
+            if "repo_name" not in config:
+                continue
+
+            # Create new config with repositories instead of repo_name
+            new_config = dict(config)
+            repo_name_value = new_config.pop("repo_name")
+            new_config["repositories"] = repo_name_value
+
+            # Update the connector with the new config
+            conn.execute(
+                sa.text(
+                    """
+                    UPDATE connector
+                    SET connector_specific_config = :new_config
+                    WHERE id = :connector_id
+                    """
+                ),
+                {"connector_id": connector_id, "new_config": json.dumps(new_config)},
+            )
+            updated_count += 1
+        except Exception as e:
+            logger.error(f"Error updating connector {connector_id}: {str(e)}")
+
+
+def downgrade() -> None:
+    # Get all GitHub connectors
+    conn = op.get_bind()
+
+    logger.debug(
+        "Starting rollback of GitHub connectors from repositories to repo_name"
+    )
+
+    github_connectors = conn.execute(
+        sa.text(
+            """
+            SELECT id, connector_specific_config
+            FROM connector
+            WHERE source = 'GITHUB'
+            """
+        )
+    ).fetchall()
+
+    logger.debug(f"Found {len(github_connectors)} GitHub connectors to rollback")
+
+    # Revert each GitHub connector to use repo_name instead of repositories
+    reverted_count = 0
+    for connector_id, config in github_connectors:
+        try:
+            if not config:
+                continue
+
+            # Parse the config if it's a string
+            if isinstance(config, str):
+                config = json.loads(config)
+
+            if "repositories" not in config:
+                continue
+
+            # Create new config with repo_name instead of repositories
+            new_config = dict(config)
+            repositories_value = new_config.pop("repositories")
+            new_config["repo_name"] = repositories_value
+
+            # Update the connector with the new config
+            conn.execute(
+                sa.text(
+                    """
+                    UPDATE connector
+                    SET connector_specific_config = :new_config
+                    WHERE id = :connector_id
+                    """
+                ),
+                {"new_config": json.dumps(new_config), "connector_id": connector_id},
+            )
+            reverted_count += 1
+        except Exception as e:
+            logger.error(f"Error reverting connector {connector_id}: {str(e)}")

backend/alembic/versions/3bd4c84fe72f_improved_index.py

@@ -0,0 +1,84 @@
+"""improved index
+
+Revision ID: 3bd4c84fe72f
+Revises: 8f43500ee275
+Create Date: 2025-02-26 13:07:56.217791
+
+"""
+from alembic import op
+
+
+# revision identifiers, used by Alembic.
+revision = "3bd4c84fe72f"
+down_revision = "8f43500ee275"
+branch_labels = None
+depends_on = None
+
+
+# NOTE:
+# This migration addresses issues with the previous migration (8f43500ee275) which caused
+# an outage by creating an index without using CONCURRENTLY. This migration:
+#
+# 1. Creates more efficient full-text search capabilities using tsvector columns and GIN indexes
+# 2. Uses CONCURRENTLY for all index creation to prevent table locking
+# 3. Explicitly manages transactions with COMMIT statements to allow CONCURRENTLY to work
+# (see: https://www.postgresql.org/docs/9.4/sql-createindex.html#SQL-CREATEINDEX-CONCURRENTLY)
+# (see: https://github.com/sqlalchemy/alembic/issues/277)
+# 4. Adds indexes to both chat_message and chat_session tables for comprehensive search
+
+
+def upgrade() -> None:
+    # Create a GIN index for full-text search on chat_message.message
+    op.execute(
+        """
+        ALTER TABLE chat_message
+        ADD COLUMN message_tsv tsvector
+        GENERATED ALWAYS AS (to_tsvector('english', message)) STORED;
+        """
+    )
+
+    # Commit the current transaction before creating concurrent indexes
+    op.execute("COMMIT")
+
+    op.execute(
+        """
+        CREATE INDEX CONCURRENTLY IF NOT EXISTS idx_chat_message_tsv
+        ON chat_message
+        USING GIN (message_tsv)
+        """
+    )
+
+    # Also add a stored tsvector column for chat_session.description
+    op.execute(
+        """
+        ALTER TABLE chat_session
+        ADD COLUMN description_tsv tsvector
+        GENERATED ALWAYS AS (to_tsvector('english', coalesce(description, ''))) STORED;
+        """
+    )
+
+    # Commit again before creating the second concurrent index
+    op.execute("COMMIT")
+
+    op.execute(
+        """
+        CREATE INDEX CONCURRENTLY IF NOT EXISTS idx_chat_session_desc_tsv
+        ON chat_session
+        USING GIN (description_tsv)
+        """
+    )
+
+
+def downgrade() -> None:
+    # Drop the indexes first (use CONCURRENTLY for dropping too)
+    op.execute("COMMIT")
+    op.execute("DROP INDEX CONCURRENTLY IF EXISTS idx_chat_message_tsv;")
+
+    op.execute("COMMIT")
+    op.execute("DROP INDEX CONCURRENTLY IF EXISTS idx_chat_session_desc_tsv;")
+
+    # Then drop the columns
+    op.execute("ALTER TABLE chat_message DROP COLUMN IF EXISTS message_tsv;")
+    op.execute("ALTER TABLE chat_session DROP COLUMN IF EXISTS description_tsv;")
+
+    op.execute("DROP INDEX IF EXISTS idx_chat_message_message_lower;")

backend/alembic/versions/3c6531f32351_add_back_input_prompts.py

@@ -0,0 +1,59 @@
+"""add back input prompts
+
+Revision ID: 3c6531f32351
+Revises: aeda5f2df4f6
+Create Date: 2025-01-13 12:49:51.705235
+
+"""
+from alembic import op
+import sqlalchemy as sa
+import fastapi_users_db_sqlalchemy
+
+# revision identifiers, used by Alembic.
+revision = "3c6531f32351"
+down_revision = "aeda5f2df4f6"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "inputprompt",
+        sa.Column("id", sa.Integer(), autoincrement=True, nullable=False),
+        sa.Column("prompt", sa.String(), nullable=False),
+        sa.Column("content", sa.String(), nullable=False),
+        sa.Column("active", sa.Boolean(), nullable=False),
+        sa.Column("is_public", sa.Boolean(), nullable=False),
+        sa.Column(
+            "user_id",
+            fastapi_users_db_sqlalchemy.generics.GUID(),
+            nullable=True,
+        ),
+        sa.ForeignKeyConstraint(
+            ["user_id"],
+            ["user.id"],
+        ),
+        sa.PrimaryKeyConstraint("id"),
+    )
+    op.create_table(
+        "inputprompt__user",
+        sa.Column("input_prompt_id", sa.Integer(), nullable=False),
+        sa.Column(
+            "user_id", fastapi_users_db_sqlalchemy.generics.GUID(), nullable=False
+        ),
+        sa.Column("disabled", sa.Boolean(), nullable=False, default=False),
+        sa.ForeignKeyConstraint(
+            ["input_prompt_id"],
+            ["inputprompt.id"],
+        ),
+        sa.ForeignKeyConstraint(
+            ["user_id"],
+            ["user.id"],
+        ),
+        sa.PrimaryKeyConstraint("input_prompt_id", "user_id"),
+    )
+
+
+def downgrade() -> None:
+    op.drop_table("inputprompt__user")
+    op.drop_table("inputprompt")

backend/alembic/versions/46625e4745d4_remove_native_enum.py

@@ -17,7 +17,7 @@ depends_on: None = None
 
 def upgrade() -> None:
     # At this point, we directly changed some previous migrations,
-    # https://github.com/danswer-ai/danswer/pull/637
+    # https://github.com/onyx-dot-app/onyx/pull/637
     # Due to using Postgres native Enums, it caused some complications for first time users.
     # To remove those complications, all Enums are only handled application side moving forward.
     # This migration exists to ensure that existing users don't run into upgrade issues.

backend/alembic/versions/47e5bef3a1d7_add_persona_categories.py

@@ -40,6 +40,6 @@ def upgrade() -> None:
 
 
 def downgrade() -> None:
-    op.drop_constraint("fk_persona_category", "persona", type_="foreignkey")
+    op.drop_constraint("persona_category_id_fkey", "persona", type_="foreignkey")
     op.drop_column("persona", "category_id")
     op.drop_table("persona_category")

backend/alembic/versions/4d58345da04a_lowercase_user_emails.py

@@ -0,0 +1,37 @@
+"""lowercase_user_emails
+
+Revision ID: 4d58345da04a
+Revises: f1ca58b2f2ec
+Create Date: 2025-01-29 07:48:46.784041
+
+"""
+from alembic import op
+from sqlalchemy.sql import text
+
+
+# revision identifiers, used by Alembic.
+revision = "4d58345da04a"
+down_revision = "f1ca58b2f2ec"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # Get database connection
+    connection = op.get_bind()
+
+    # Update all user emails to lowercase
+    connection.execute(
+        text(
+            """
+            UPDATE "user"
+            SET email = LOWER(email)
+            WHERE email != LOWER(email)
+            """
+        )
+    )
+
+
+def downgrade() -> None:
+    # Cannot restore original case of emails
+    pass

backend/alembic/versions/4ee1287bd26a_add_multiple_slack_bot_support.py

@@ -5,13 +5,12 @@ Revises: 47e5bef3a1d7
 Create Date: 2024-11-06 13:15:53.302644
 
 """
-import logging
 from typing import cast
 from alembic import op
 import sqlalchemy as sa
 from sqlalchemy.orm import Session
-from danswer.key_value_store.factory import get_kv_store
-from danswer.db.models import SlackBot
+from onyx.key_value_store.factory import get_kv_store
+from onyx.db.models import SlackBot
 from sqlalchemy.dialects import postgresql
 
 # revision identifiers, used by Alembic.
@@ -20,13 +19,8 @@ down_revision = "47e5bef3a1d7"
 branch_labels: None = None
 depends_on: None = None
 
-# Configure logging
-logger = logging.getLogger("alembic.runtime.migration")
-logger.setLevel(logging.INFO)
-
 
 def upgrade() -> None:
-    logger.info(f"{revision}: create_table: slack_bot")
     # Create new slack_bot table
     op.create_table(
         "slack_bot",
@@ -63,7 +57,6 @@ def upgrade() -> None:
     )
 
     # Handle existing Slack bot tokens first
-    logger.info(f"{revision}: Checking for existing Slack bot.")
     bot_token = None
     app_token = None
     first_row_id = None
@@ -71,15 +64,12 @@ def upgrade() -> None:
     try:
         tokens = cast(dict, get_kv_store().load("slack_bot_tokens_config_key"))
     except Exception:
-        logger.warning("No existing Slack bot tokens found.")
         tokens = {}
 
     bot_token = tokens.get("bot_token")
     app_token = tokens.get("app_token")
 
     if bot_token and app_token:
-        logger.info(f"{revision}: Found bot and app tokens.")
-
         session = Session(bind=op.get_bind())
         new_slack_bot = SlackBot(
             name="Slack Bot (Migrated)",
@@ -170,10 +160,9 @@ def upgrade() -> None:
     # Clean up old tokens if they existed
     try:
         if bot_token and app_token:
-            logger.info(f"{revision}: Removing old bot and app tokens.")
             get_kv_store().delete("slack_bot_tokens_config_key")
     except Exception:
-        logger.warning("tried to delete tokens in dynamic config but failed")
+        pass
     # Rename the table
     op.rename_table(
         "slack_bot_config__standard_answer_category",
@@ -190,8 +179,6 @@ def upgrade() -> None:
     # Drop the table with CASCADE to handle dependent objects
     op.execute("DROP TABLE slack_bot_config CASCADE")
 
-    logger.info(f"{revision}: Migration complete.")
-
 
 def downgrade() -> None:
     # Recreate the old slack_bot_config table
@@ -273,7 +260,7 @@ def downgrade() -> None:
             }
             get_kv_store().store("slack_bot_tokens_config_key", tokens)
     except Exception:
-        logger.warning("Failed to save tokens back to KV store")
+        pass
 
     # Drop the new tables in reverse order
     op.drop_table("slack_channel_config")

backend/alembic/versions/54a74a0417fc_danswerbot_onyxbot.py

@@ -0,0 +1,23 @@
+"""danswerbot -> onyxbot
+
+Revision ID: 54a74a0417fc
+Revises: 94dc3d0236f8
+Create Date: 2024-12-11 18:05:05.490737
+
+"""
+from alembic import op
+
+
+# revision identifiers, used by Alembic.
+revision = "54a74a0417fc"
+down_revision = "94dc3d0236f8"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.alter_column("chat_session", "danswerbot_flow", new_column_name="onyxbot_flow")
+
+
+def downgrade() -> None:
+    op.alter_column("chat_session", "onyxbot_flow", new_column_name="danswerbot_flow")

backend/alembic/versions/570282d33c49_track_onyxbot_explicitly.py

@@ -1,4 +1,4 @@
-"""Track Danswerbot Explicitly
+"""Track Onyxbot Explicitly
 
 Revision ID: 570282d33c49
 Revises: 7547d982db8f

backend/alembic/versions/6fc7886d665d_make_categories_labels_and_many_to_many.py

@@ -0,0 +1,80 @@
+"""make categories labels and many to many
+
+Revision ID: 6fc7886d665d
+Revises: 3c6531f32351
+Create Date: 2025-01-13 18:12:18.029112
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "6fc7886d665d"
+down_revision = "3c6531f32351"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # Rename persona_category table to persona_label
+    op.rename_table("persona_category", "persona_label")
+
+    # Create the new association table
+    op.create_table(
+        "persona__persona_label",
+        sa.Column("persona_id", sa.Integer(), nullable=False),
+        sa.Column("persona_label_id", sa.Integer(), nullable=False),
+        sa.ForeignKeyConstraint(
+            ["persona_id"],
+            ["persona.id"],
+        ),
+        sa.ForeignKeyConstraint(
+            ["persona_label_id"],
+            ["persona_label.id"],
+            ondelete="CASCADE",
+        ),
+        sa.PrimaryKeyConstraint("persona_id", "persona_label_id"),
+    )
+
+    # Copy existing relationships to the new table
+    op.execute(
+        """
+        INSERT INTO persona__persona_label (persona_id, persona_label_id)
+        SELECT id, category_id FROM persona WHERE category_id IS NOT NULL
+    """
+    )
+
+    # Remove the old category_id column from persona table
+    op.drop_column("persona", "category_id")
+
+
+def downgrade() -> None:
+    # Rename persona_label table back to persona_category
+    op.rename_table("persona_label", "persona_category")
+
+    # Add back the category_id column to persona table
+    op.add_column("persona", sa.Column("category_id", sa.Integer(), nullable=True))
+    op.create_foreign_key(
+        "persona_category_id_fkey",
+        "persona",
+        "persona_category",
+        ["category_id"],
+        ["id"],
+    )
+
+    # Copy the first label relationship back to the persona table
+    op.execute(
+        """
+        UPDATE persona
+        SET category_id = (
+            SELECT persona_label_id
+            FROM persona__persona_label
+            WHERE persona__persona_label.persona_id = persona.id
+            LIMIT 1
+        )
+    """
+    )
+
+    # Drop the association table
+    op.drop_table("persona__persona_label")

backend/alembic/versions/703313b75876_add_tokenratelimit_tables.py

@@ -9,7 +9,7 @@ import json
 from typing import cast
 from alembic import op
 import sqlalchemy as sa
-from danswer.key_value_store.factory import get_kv_store
+from onyx.key_value_store.factory import get_kv_store
 
 # revision identifiers, used by Alembic.
 revision = "703313b75876"

backend/alembic/versions/776b3bbe9092_remove_remaining_enums.py

@@ -8,9 +8,9 @@ Create Date: 2024-03-22 21:34:27.629444
 from alembic import op
 import sqlalchemy as sa
 
-from danswer.db.models import IndexModelStatus
-from danswer.context.search.enums import RecencyBiasSetting
-from danswer.context.search.enums import SearchType
+from onyx.db.models import IndexModelStatus
+from onyx.context.search.enums import RecencyBiasSetting
+from onyx.context.search.enums import SearchType
 
 # revision identifiers, used by Alembic.
 revision = "776b3bbe9092"

backend/alembic/versions/77d07dffae64_forcibly_remove_more_enum_types_from_.py

@@ -18,7 +18,7 @@ depends_on: None = None
 
 def upgrade() -> None:
     # In a PR:
-    # https://github.com/danswer-ai/danswer/pull/397/files#diff-f05fb341f6373790b91852579631b64ca7645797a190837156a282b67e5b19c2
+    # https://github.com/onyx-dot-app/onyx/pull/397/files#diff-f05fb341f6373790b91852579631b64ca7645797a190837156a282b67e5b19c2
     # we directly changed some previous migrations. This caused some users to have native enums
     # while others wouldn't. This has caused some issues when adding new fields to these enums.
     # This migration manually changes the enum types to ensure that nobody uses native enums.

backend/alembic/versions/8f43500ee275_add_index.py

@@ -0,0 +1,32 @@
+"""add index
+
+Revision ID: 8f43500ee275
+Revises: da42808081e3
+Create Date: 2025-02-24 17:35:33.072714
+
+"""
+from alembic import op
+
+
+# revision identifiers, used by Alembic.
+revision = "8f43500ee275"
+down_revision = "da42808081e3"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # Create a basic index on the lowercase message column for direct text matching
+    # Limit to 1500 characters to stay well under the 2856 byte limit of btree version 4
+    # op.execute(
+    #     """
+    #     CREATE INDEX idx_chat_message_message_lower
+    #     ON chat_message (LOWER(substring(message, 1, 1500)))
+    #     """
+    # )
+    pass
+
+
+def downgrade() -> None:
+    # Drop the index
+    op.execute("DROP INDEX IF EXISTS idx_chat_message_message_lower;")

backend/alembic/versions/91a0a4d62b14_milestone.py

@@ -0,0 +1,45 @@
+"""Milestone
+
+Revision ID: 91a0a4d62b14
+Revises: dab04867cd88
+Create Date: 2024-12-13 19:03:30.947551
+
+"""
+from alembic import op
+import sqlalchemy as sa
+import fastapi_users_db_sqlalchemy
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision = "91a0a4d62b14"
+down_revision = "dab04867cd88"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "milestone",
+        sa.Column("id", sa.UUID(), nullable=False),
+        sa.Column("tenant_id", sa.String(), nullable=True),
+        sa.Column(
+            "user_id",
+            fastapi_users_db_sqlalchemy.generics.GUID(),
+            nullable=True,
+        ),
+        sa.Column("event_type", sa.String(), nullable=False),
+        sa.Column(
+            "time_created",
+            sa.DateTime(timezone=True),
+            server_default=sa.text("now()"),
+            nullable=False,
+        ),
+        sa.Column("event_tracker", postgresql.JSONB(), nullable=True),
+        sa.ForeignKeyConstraint(["user_id"], ["user.id"], ondelete="CASCADE"),
+        sa.PrimaryKeyConstraint("id"),
+        sa.UniqueConstraint("event_type", name="uq_milestone_event_type"),
+    )
+
+
+def downgrade() -> None:
+    op.drop_table("milestone")

backend/alembic/versions/91fd3b470d1a_remove_documentsource_from_tag.py

@@ -7,7 +7,7 @@ Create Date: 2024-03-21 12:05:23.956734
 """
 from alembic import op
 import sqlalchemy as sa
-from danswer.configs.constants import DocumentSource
+from onyx.configs.constants import DocumentSource
 
 # revision identifiers, used by Alembic.
 revision = "91fd3b470d1a"

backend/alembic/versions/949b4a92a401_remove_rt.py

@@ -10,7 +10,7 @@ from sqlalchemy.orm import Session
 from sqlalchemy import text
 
 # Import your models and constants
-from danswer.db.models import (
+from onyx.db.models import (
     Connector,
     ConnectorCredentialPair,
     Credential,

backend/alembic/versions/94dc3d0236f8_make_document_set_description_optional.py

@@ -0,0 +1,30 @@
+"""make document set description optional
+
+Revision ID: 94dc3d0236f8
+Revises: bf7a81109301
+Create Date: 2024-12-11 11:26:10.616722
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "94dc3d0236f8"
+down_revision = "bf7a81109301"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # Make document_set.description column nullable
+    op.alter_column(
+        "document_set", "description", existing_type=sa.String(), nullable=True
+    )
+
+
+def downgrade() -> None:
+    # Revert document_set.description column to non-nullable
+    op.alter_column(
+        "document_set", "description", existing_type=sa.String(), nullable=False
+    )

backend/alembic/versions/97dbb53fa8c8_add_syncrecord.py

@@ -0,0 +1,72 @@
+"""Add SyncRecord
+
+Revision ID: 97dbb53fa8c8
+Revises: 369644546676
+Create Date: 2025-01-11 19:39:50.426302
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "97dbb53fa8c8"
+down_revision = "be2ab2aa50ee"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "sync_record",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column("entity_id", sa.Integer(), nullable=False),
+        sa.Column(
+            "sync_type",
+            sa.Enum(
+                "DOCUMENT_SET",
+                "USER_GROUP",
+                "CONNECTOR_DELETION",
+                name="synctype",
+                native_enum=False,
+                length=40,
+            ),
+            nullable=False,
+        ),
+        sa.Column(
+            "sync_status",
+            sa.Enum(
+                "IN_PROGRESS",
+                "SUCCESS",
+                "FAILED",
+                "CANCELED",
+                name="syncstatus",
+                native_enum=False,
+                length=40,
+            ),
+            nullable=False,
+        ),
+        sa.Column("num_docs_synced", sa.Integer(), nullable=False),
+        sa.Column("sync_start_time", sa.DateTime(timezone=True), nullable=False),
+        sa.Column("sync_end_time", sa.DateTime(timezone=True), nullable=True),
+        sa.PrimaryKeyConstraint("id"),
+    )
+
+    # Add index for fetch_latest_sync_record query
+    op.create_index(
+        "ix_sync_record_entity_id_sync_type_sync_start_time",
+        "sync_record",
+        ["entity_id", "sync_type", "sync_start_time"],
+    )
+
+    # Add index for cleanup_sync_records query
+    op.create_index(
+        "ix_sync_record_entity_id_sync_type_sync_status",
+        "sync_record",
+        ["entity_id", "sync_type", "sync_status"],
+    )
+
+
+def downgrade() -> None:
+    op.drop_index("ix_sync_record_entity_id_sync_type_sync_status")
+    op.drop_index("ix_sync_record_entity_id_sync_type_sync_start_time")
+    op.drop_table("sync_record")

backend/alembic/versions/98a5008d8711_agent_tracking.py

@@ -0,0 +1,107 @@
+"""agent_tracking
+
+Revision ID: 98a5008d8711
+Revises: 2f80c6a2550f
+Create Date: 2025-01-29 17:00:00.000001
+
+"""
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+from sqlalchemy.dialects.postgresql import UUID
+
+# revision identifiers, used by Alembic.
+revision = "98a5008d8711"
+down_revision = "2f80c6a2550f"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "agent__search_metrics",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column("user_id", postgresql.UUID(as_uuid=True), nullable=True),
+        sa.Column("persona_id", sa.Integer(), nullable=True),
+        sa.Column("agent_type", sa.String(), nullable=False),
+        sa.Column("start_time", sa.DateTime(timezone=True), nullable=False),
+        sa.Column("base_duration_s", sa.Float(), nullable=False),
+        sa.Column("full_duration_s", sa.Float(), nullable=False),
+        sa.Column("base_metrics", postgresql.JSONB(), nullable=True),
+        sa.Column("refined_metrics", postgresql.JSONB(), nullable=True),
+        sa.Column("all_metrics", postgresql.JSONB(), nullable=True),
+        sa.ForeignKeyConstraint(
+            ["persona_id"],
+            ["persona.id"],
+        ),
+        sa.ForeignKeyConstraint(["user_id"], ["user.id"], ondelete="CASCADE"),
+        sa.PrimaryKeyConstraint("id"),
+    )
+
+    # Create sub_question table
+    op.create_table(
+        "agent__sub_question",
+        sa.Column("id", sa.Integer, primary_key=True),
+        sa.Column("primary_question_id", sa.Integer, sa.ForeignKey("chat_message.id")),
+        sa.Column(
+            "chat_session_id", UUID(as_uuid=True), sa.ForeignKey("chat_session.id")
+        ),
+        sa.Column("sub_question", sa.Text),
+        sa.Column(
+            "time_created", sa.DateTime(timezone=True), server_default=sa.func.now()
+        ),
+        sa.Column("sub_answer", sa.Text),
+        sa.Column("sub_question_doc_results", postgresql.JSONB(), nullable=True),
+        sa.Column("level", sa.Integer(), nullable=False),
+        sa.Column("level_question_num", sa.Integer(), nullable=False),
+    )
+
+    # Create sub_query table
+    op.create_table(
+        "agent__sub_query",
+        sa.Column("id", sa.Integer, primary_key=True),
+        sa.Column(
+            "parent_question_id", sa.Integer, sa.ForeignKey("agent__sub_question.id")
+        ),
+        sa.Column(
+            "chat_session_id", UUID(as_uuid=True), sa.ForeignKey("chat_session.id")
+        ),
+        sa.Column("sub_query", sa.Text),
+        sa.Column(
+            "time_created", sa.DateTime(timezone=True), server_default=sa.func.now()
+        ),
+    )
+
+    # Create sub_query__search_doc association table
+    op.create_table(
+        "agent__sub_query__search_doc",
+        sa.Column(
+            "sub_query_id",
+            sa.Integer,
+            sa.ForeignKey("agent__sub_query.id"),
+            primary_key=True,
+        ),
+        sa.Column(
+            "search_doc_id",
+            sa.Integer,
+            sa.ForeignKey("search_doc.id"),
+            primary_key=True,
+        ),
+    )
+
+    op.add_column(
+        "chat_message",
+        sa.Column(
+            "refined_answer_improvement",
+            sa.Boolean(),
+            nullable=True,
+        ),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("chat_message", "refined_answer_improvement")
+    op.drop_table("agent__sub_query__search_doc")
+    op.drop_table("agent__sub_query")
+    op.drop_table("agent__sub_question")
+    op.drop_table("agent__search_metrics")

backend/alembic/versions/9c00a2bccb83_chat_message_agentic.py

@@ -0,0 +1,43 @@
+"""chat_message_agentic
+
+Revision ID: 9c00a2bccb83
+Revises: b7a7eee5aa15
+Create Date: 2025-02-17 11:15:43.081150
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "9c00a2bccb83"
+down_revision = "b7a7eee5aa15"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # First add the column as nullable
+    op.add_column("chat_message", sa.Column("is_agentic", sa.Boolean(), nullable=True))
+
+    # Update existing rows based on presence of SubQuestions
+    op.execute(
+        """
+        UPDATE chat_message
+        SET is_agentic = EXISTS (
+            SELECT 1
+            FROM agent__sub_question
+            WHERE agent__sub_question.primary_question_id = chat_message.id
+        )
+        WHERE is_agentic IS NULL
+    """
+    )
+
+    # Make the column non-nullable with a default value of False
+    op.alter_column(
+        "chat_message", "is_agentic", nullable=False, server_default=sa.text("false")
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("chat_message", "is_agentic")

backend/alembic/versions/9f696734098f_combine_search_and_chat.py

@@ -0,0 +1,36 @@
+"""Combine Search and Chat
+
+Revision ID: 9f696734098f
+Revises: a8c2065484e6
+Create Date: 2024-11-27 15:32:19.694972
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "9f696734098f"
+down_revision = "a8c2065484e6"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.alter_column("chat_session", "description", nullable=True)
+    op.drop_column("chat_session", "one_shot")
+    op.drop_column("slack_channel_config", "response_type")
+
+
+def downgrade() -> None:
+    op.execute("UPDATE chat_session SET description = '' WHERE description IS NULL")
+    op.alter_column("chat_session", "description", nullable=False)
+    op.add_column(
+        "chat_session",
+        sa.Column("one_shot", sa.Boolean(), nullable=False, server_default=sa.false()),
+    )
+    op.add_column(
+        "slack_channel_config",
+        sa.Column(
+            "response_type", sa.String(), nullable=False, server_default="citations"
+        ),
+    )

backend/alembic/versions/a6df6b88ef81_remove_recent_assistants.py

@@ -0,0 +1,29 @@
+"""remove recent assistants
+
+Revision ID: a6df6b88ef81
+Revises: 4d58345da04a
+Create Date: 2025-01-29 10:25:52.790407
+
+"""
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision = "a6df6b88ef81"
+down_revision = "4d58345da04a"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.drop_column("user", "recent_assistants")
+
+
+def downgrade() -> None:
+    op.add_column(
+        "user",
+        sa.Column(
+            "recent_assistants", postgresql.JSONB(), server_default="[]", nullable=False
+        ),
+    )

backend/alembic/versions/acaab4ef4507_remove_inactive_ccpair_status_on_.py

@@ -0,0 +1,29 @@
+"""remove inactive ccpair status on downgrade
+
+Revision ID: acaab4ef4507
+Revises: b388730a2899
+Create Date: 2025-02-16 18:21:41.330212
+
+"""
+from alembic import op
+from onyx.db.models import ConnectorCredentialPair
+from onyx.db.enums import ConnectorCredentialPairStatus
+from sqlalchemy import update
+
+# revision identifiers, used by Alembic.
+revision = "acaab4ef4507"
+down_revision = "b388730a2899"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    pass
+
+
+def downgrade() -> None:
+    op.execute(
+        update(ConnectorCredentialPair)
+        .where(ConnectorCredentialPair.status == ConnectorCredentialPairStatus.INVALID)
+        .values(status=ConnectorCredentialPairStatus.ACTIVE)
+    )

backend/alembic/versions/aeda5f2df4f6_add_pinned_assistants.py

@@ -0,0 +1,27 @@
+"""add pinned assistants
+
+Revision ID: aeda5f2df4f6
+Revises: c5eae4a75a1b
+Create Date: 2025-01-09 16:04:10.770636
+
+"""
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision = "aeda5f2df4f6"
+down_revision = "c5eae4a75a1b"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "user", sa.Column("pinned_assistants", postgresql.JSONB(), nullable=True)
+    )
+    op.execute('UPDATE "user" SET pinned_assistants = chosen_assistants')
+
+
+def downgrade() -> None:
+    op.drop_column("user", "pinned_assistants")

backend/alembic/versions/b156fa702355_chat_reworked.py

@@ -10,7 +10,7 @@ from alembic import op
 import sqlalchemy as sa
 from sqlalchemy.dialects import postgresql
 from sqlalchemy.dialects.postgresql import ENUM
-from danswer.configs.constants import DocumentSource
+from onyx.configs.constants import DocumentSource
 
 # revision identifiers, used by Alembic.
 revision = "b156fa702355"

backend/alembic/versions/b388730a2899_nullable_preferences.py

@@ -0,0 +1,31 @@
+"""nullable preferences
+
+Revision ID: b388730a2899
+Revises: 1a03d2c2856b
+Create Date: 2025-02-17 18:49:22.643902
+
+"""
+from alembic import op
+
+
+# revision identifiers, used by Alembic.
+revision = "b388730a2899"
+down_revision = "1a03d2c2856b"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.alter_column("user", "temperature_override_enabled", nullable=True)
+    op.alter_column("user", "auto_scroll", nullable=True)
+
+
+def downgrade() -> None:
+    # Ensure no null values before making columns non-nullable
+    op.execute(
+        'UPDATE "user" SET temperature_override_enabled = false WHERE temperature_override_enabled IS NULL'
+    )
+    op.execute('UPDATE "user" SET auto_scroll = false WHERE auto_scroll IS NULL')
+
+    op.alter_column("user", "temperature_override_enabled", nullable=False)
+    op.alter_column("user", "auto_scroll", nullable=False)

backend/alembic/versions/b7a7eee5aa15_add_checkpointing_failure_handling.py

@@ -0,0 +1,124 @@
+"""Add checkpointing/failure handling
+
+Revision ID: b7a7eee5aa15
+Revises: f39c5794c10a
+Create Date: 2025-01-24 15:17:36.763172
+
+"""
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision = "b7a7eee5aa15"
+down_revision = "f39c5794c10a"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "index_attempt",
+        sa.Column("checkpoint_pointer", sa.String(), nullable=True),
+    )
+    op.add_column(
+        "index_attempt",
+        sa.Column("poll_range_start", sa.DateTime(timezone=True), nullable=True),
+    )
+    op.add_column(
+        "index_attempt",
+        sa.Column("poll_range_end", sa.DateTime(timezone=True), nullable=True),
+    )
+
+    op.create_index(
+        "ix_index_attempt_cc_pair_settings_poll",
+        "index_attempt",
+        [
+            "connector_credential_pair_id",
+            "search_settings_id",
+            "status",
+            sa.text("time_updated DESC"),
+        ],
+    )
+
+    # Drop the old IndexAttemptError table
+    op.drop_index("index_attempt_id", table_name="index_attempt_errors")
+    op.drop_table("index_attempt_errors")
+
+    # Create the new version of the table
+    op.create_table(
+        "index_attempt_errors",
+        sa.Column("id", sa.Integer(), primary_key=True),
+        sa.Column("index_attempt_id", sa.Integer(), nullable=False),
+        sa.Column("connector_credential_pair_id", sa.Integer(), nullable=False),
+        sa.Column("document_id", sa.String(), nullable=True),
+        sa.Column("document_link", sa.String(), nullable=True),
+        sa.Column("entity_id", sa.String(), nullable=True),
+        sa.Column("failed_time_range_start", sa.DateTime(timezone=True), nullable=True),
+        sa.Column("failed_time_range_end", sa.DateTime(timezone=True), nullable=True),
+        sa.Column("failure_message", sa.Text(), nullable=False),
+        sa.Column("is_resolved", sa.Boolean(), nullable=False, default=False),
+        sa.Column(
+            "time_created",
+            sa.DateTime(timezone=True),
+            server_default=sa.text("now()"),
+            nullable=False,
+        ),
+        sa.ForeignKeyConstraint(
+            ["index_attempt_id"],
+            ["index_attempt.id"],
+        ),
+        sa.ForeignKeyConstraint(
+            ["connector_credential_pair_id"],
+            ["connector_credential_pair.id"],
+        ),
+    )
+
+
+def downgrade() -> None:
+    op.execute("SET lock_timeout = '5s'")
+
+    # try a few times to drop the table, this has been observed to fail due to other locks
+    # blocking the drop
+    NUM_TRIES = 10
+    for i in range(NUM_TRIES):
+        try:
+            op.drop_table("index_attempt_errors")
+            break
+        except Exception as e:
+            if i == NUM_TRIES - 1:
+                raise e
+            print(f"Error dropping table: {e}. Retrying...")
+
+    op.execute("SET lock_timeout = DEFAULT")
+
+    # Recreate the old IndexAttemptError table
+    op.create_table(
+        "index_attempt_errors",
+        sa.Column("id", sa.Integer(), primary_key=True),
+        sa.Column("index_attempt_id", sa.Integer(), nullable=True),
+        sa.Column("batch", sa.Integer(), nullable=True),
+        sa.Column("doc_summaries", postgresql.JSONB(), nullable=False),
+        sa.Column("error_msg", sa.Text(), nullable=True),
+        sa.Column("traceback", sa.Text(), nullable=True),
+        sa.Column(
+            "time_created",
+            sa.DateTime(timezone=True),
+            server_default=sa.text("now()"),
+        ),
+        sa.ForeignKeyConstraint(
+            ["index_attempt_id"],
+            ["index_attempt.id"],
+        ),
+    )
+
+    op.create_index(
+        "index_attempt_id",
+        "index_attempt_errors",
+        ["time_created"],
+    )
+
+    op.drop_index("ix_index_attempt_cc_pair_settings_poll")
+    op.drop_column("index_attempt", "checkpoint_pointer")
+    op.drop_column("index_attempt", "poll_range_start")
+    op.drop_column("index_attempt", "poll_range_end")

backend/alembic/versions/b7c2b63c4a03_add_background_reindex_enabled_field.py

@@ -0,0 +1,55 @@
+"""add background_reindex_enabled field
+
+Revision ID: b7c2b63c4a03
+Revises: f11b408e39d3
+Create Date: 2024-03-26 12:34:56.789012
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+from onyx.db.enums import EmbeddingPrecision
+
+
+# revision identifiers, used by Alembic.
+revision = "b7c2b63c4a03"
+down_revision = "f11b408e39d3"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # Add background_reindex_enabled column with default value of True
+    op.add_column(
+        "search_settings",
+        sa.Column(
+            "background_reindex_enabled",
+            sa.Boolean(),
+            nullable=False,
+            server_default="true",
+        ),
+    )
+
+    # Add embedding_precision column with default value of FLOAT
+    op.add_column(
+        "search_settings",
+        sa.Column(
+            "embedding_precision",
+            sa.Enum(EmbeddingPrecision, native_enum=False),
+            nullable=False,
+            server_default=EmbeddingPrecision.FLOAT.name,
+        ),
+    )
+
+    # Add reduced_dimension column with default value of None
+    op.add_column(
+        "search_settings",
+        sa.Column("reduced_dimension", sa.Integer(), nullable=True),
+    )
+
+
+def downgrade() -> None:
+    # Remove the background_reindex_enabled column
+    op.drop_column("search_settings", "background_reindex_enabled")
+    op.drop_column("search_settings", "embedding_precision")
+    op.drop_column("search_settings", "reduced_dimension")

backend/alembic/versions/be2ab2aa50ee_fix_capitalization.py

@@ -0,0 +1,38 @@
+"""fix_capitalization
+
+Revision ID: be2ab2aa50ee
+Revises: 369644546676
+Create Date: 2025-01-10 13:13:26.228960
+
+"""
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision = "be2ab2aa50ee"
+down_revision = "369644546676"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.execute(
+        """
+        UPDATE document
+        SET
+            external_user_group_ids = ARRAY(
+                SELECT LOWER(unnest(external_user_group_ids))
+            ),
+            last_modified = NOW()
+        WHERE
+            external_user_group_ids IS NOT NULL
+            AND external_user_group_ids::text[] <> ARRAY(
+                SELECT LOWER(unnest(external_user_group_ids))
+            )::text[]
+    """
+    )
+
+
+def downgrade() -> None:
+    # No way to cleanly persist the bad state through an upgrade/downgrade
+    # cycle, so we just pass
+    pass

backend/alembic/versions/bf7a81109301_delete_input_prompts.py

@@ -0,0 +1,57 @@
+"""delete_input_prompts
+
+Revision ID: bf7a81109301
+Revises: f7a894b06d02
+Create Date: 2024-12-09 12:00:49.884228
+
+"""
+from alembic import op
+import sqlalchemy as sa
+import fastapi_users_db_sqlalchemy
+
+
+# revision identifiers, used by Alembic.
+revision = "bf7a81109301"
+down_revision = "f7a894b06d02"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.drop_table("inputprompt__user")
+    op.drop_table("inputprompt")
+
+
+def downgrade() -> None:
+    op.create_table(
+        "inputprompt",
+        sa.Column("id", sa.Integer(), autoincrement=True, nullable=False),
+        sa.Column("prompt", sa.String(), nullable=False),
+        sa.Column("content", sa.String(), nullable=False),
+        sa.Column("active", sa.Boolean(), nullable=False),
+        sa.Column("is_public", sa.Boolean(), nullable=False),
+        sa.Column(
+            "user_id",
+            fastapi_users_db_sqlalchemy.generics.GUID(),
+            nullable=True,
+        ),
+        sa.ForeignKeyConstraint(
+            ["user_id"],
+            ["user.id"],
+        ),
+        sa.PrimaryKeyConstraint("id"),
+    )
+    op.create_table(
+        "inputprompt__user",
+        sa.Column("input_prompt_id", sa.Integer(), nullable=False),
+        sa.Column("user_id", sa.Integer(), nullable=False),
+        sa.ForeignKeyConstraint(
+            ["input_prompt_id"],
+            ["inputprompt.id"],
+        ),
+        sa.ForeignKeyConstraint(
+            ["user_id"],
+            ["inputprompt.id"],
+        ),
+        sa.PrimaryKeyConstraint("input_prompt_id", "user_id"),
+    )

backend/alembic/versions/c0aab6edb6dd_delete_workspace.py

@@ -0,0 +1,87 @@
+"""delete workspace
+
+Revision ID: c0aab6edb6dd
+Revises: 35e518e0ddf4
+Create Date: 2024-12-17 14:37:07.660631
+
+"""
+
+from alembic import op
+
+
+# revision identifiers, used by Alembic.
+revision = "c0aab6edb6dd"
+down_revision = "35e518e0ddf4"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.execute(
+        """
+    UPDATE connector
+    SET connector_specific_config = connector_specific_config - 'workspace'
+    WHERE source = 'SLACK'
+    """
+    )
+
+
+def downgrade() -> None:
+    import json
+    from sqlalchemy import text
+    from slack_sdk import WebClient
+
+    conn = op.get_bind()
+
+    # Fetch all Slack credentials
+    creds_result = conn.execute(
+        text("SELECT id, credential_json FROM credential WHERE source = 'SLACK'")
+    )
+    all_slack_creds = creds_result.fetchall()
+    if not all_slack_creds:
+        return
+
+    for cred_row in all_slack_creds:
+        credential_id, credential_json = cred_row
+
+        credential_json = (
+            credential_json.tobytes().decode("utf-8")
+            if isinstance(credential_json, memoryview)
+            else credential_json.decode("utf-8")
+        )
+        credential_data = json.loads(credential_json)
+        slack_bot_token = credential_data.get("slack_bot_token")
+        if not slack_bot_token:
+            print(
+                f"No slack_bot_token found for credential {credential_id}. "
+                "Your Slack connector will not function until you upgrade and provide a valid token."
+            )
+            continue
+
+        client = WebClient(token=slack_bot_token)
+        try:
+            auth_response = client.auth_test()
+            workspace = auth_response["url"].split("//")[1].split(".")[0]
+
+            # Update only the connectors linked to this credential
+            # (and which are Slack connectors).
+            op.execute(
+                f"""
+                UPDATE connector AS c
+                SET connector_specific_config = jsonb_set(
+                    connector_specific_config,
+                    '{{workspace}}',
+                    to_jsonb('{workspace}'::text)
+                )
+                FROM connector_credential_pair AS ccp
+                WHERE ccp.connector_id = c.id
+                  AND c.source = 'SLACK'
+                  AND ccp.credential_id = {credential_id}
+            """
+            )
+        except Exception:
+            print(
+                f"We were unable to get the workspace url for your Slack Connector with id {credential_id}."
+            )
+            print("This connector will no longer work until you upgrade.")
+            continue

backend/alembic/versions/c5eae4a75a1b_add_chat_message__standard_answer_table.py

@@ -0,0 +1,36 @@
+"""Add chat_message__standard_answer table
+
+Revision ID: c5eae4a75a1b
+Revises: 0f7ff6d75b57
+Create Date: 2025-01-15 14:08:49.688998
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "c5eae4a75a1b"
+down_revision = "0f7ff6d75b57"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "chat_message__standard_answer",
+        sa.Column("chat_message_id", sa.Integer(), nullable=False),
+        sa.Column("standard_answer_id", sa.Integer(), nullable=False),
+        sa.ForeignKeyConstraint(
+            ["chat_message_id"],
+            ["chat_message.id"],
+        ),
+        sa.ForeignKeyConstraint(
+            ["standard_answer_id"],
+            ["standard_answer.id"],
+        ),
+        sa.PrimaryKeyConstraint("chat_message_id", "standard_answer_id"),
+    )
+
+
+def downgrade() -> None:
+    op.drop_table("chat_message__standard_answer")

backend/alembic/versions/c7bf5721733e_add_has_been_indexed_to_.py

@@ -0,0 +1,48 @@
+"""Add has_been_indexed to DocumentByConnectorCredentialPair
+
+Revision ID: c7bf5721733e
+Revises: fec3db967bf7
+Create Date: 2025-01-13 12:39:05.831693
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "c7bf5721733e"
+down_revision = "027381bce97c"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # assume all existing rows have been indexed, no better approach
+    op.add_column(
+        "document_by_connector_credential_pair",
+        sa.Column("has_been_indexed", sa.Boolean(), nullable=True),
+    )
+    op.execute(
+        "UPDATE document_by_connector_credential_pair SET has_been_indexed = TRUE"
+    )
+    op.alter_column(
+        "document_by_connector_credential_pair",
+        "has_been_indexed",
+        nullable=False,
+    )
+
+    # Add index to optimize get_document_counts_for_cc_pairs query pattern
+    op.create_index(
+        "idx_document_cc_pair_counts",
+        "document_by_connector_credential_pair",
+        ["connector_id", "credential_id", "has_been_indexed"],
+        unique=False,
+    )
+
+
+def downgrade() -> None:
+    # Remove the index first before removing the column
+    op.drop_index(
+        "idx_document_cc_pair_counts",
+        table_name="document_by_connector_credential_pair",
+    )
+    op.drop_column("document_by_connector_credential_pair", "has_been_indexed")

backend/alembic/versions/da42808081e3_migrate_jira_connectors_to_new_format.py

@@ -0,0 +1,120 @@
+"""migrate jira connectors to new format
+
+Revision ID: da42808081e3
+Revises: f13db29f3101
+Create Date: 2025-02-24 11:24:54.396040
+
+"""
+from alembic import op
+import sqlalchemy as sa
+import json
+
+from onyx.configs.constants import DocumentSource
+from onyx.connectors.onyx_jira.utils import extract_jira_project
+
+
+# revision identifiers, used by Alembic.
+revision = "da42808081e3"
+down_revision = "f13db29f3101"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # Get all Jira connectors
+    conn = op.get_bind()
+
+    # First get all Jira connectors
+    jira_connectors = conn.execute(
+        sa.text(
+            """
+            SELECT id, connector_specific_config
+            FROM connector
+            WHERE source = :source
+            """
+        ),
+        {"source": DocumentSource.JIRA.value.upper()},
+    ).fetchall()
+
+    # Update each connector's config
+    for connector_id, old_config in jira_connectors:
+        if not old_config:
+            continue
+
+        # Extract project key from URL if it exists
+        new_config: dict[str, str | None] = {}
+        if project_url := old_config.get("jira_project_url"):
+            # Parse the URL to get base and project
+            try:
+                jira_base, project_key = extract_jira_project(project_url)
+                new_config = {"jira_base_url": jira_base, "project_key": project_key}
+            except ValueError:
+                # If URL parsing fails, just use the URL as the base
+                new_config = {
+                    "jira_base_url": project_url.split("/projects/")[0],
+                    "project_key": None,
+                }
+        else:
+            # For connectors without a project URL, we need admin intervention
+            # Mark these for review
+            print(
+                f"WARNING: Jira connector {connector_id} has no project URL configured"
+            )
+            continue
+
+        # Update the connector config
+        conn.execute(
+            sa.text(
+                """
+                UPDATE connector
+                SET connector_specific_config = :new_config
+                WHERE id = :id
+                """
+            ),
+            {"id": connector_id, "new_config": json.dumps(new_config)},
+        )
+
+
+def downgrade() -> None:
+    # Get all Jira connectors
+    conn = op.get_bind()
+
+    # First get all Jira connectors
+    jira_connectors = conn.execute(
+        sa.text(
+            """
+            SELECT id, connector_specific_config
+            FROM connector
+            WHERE source = :source
+            """
+        ),
+        {"source": DocumentSource.JIRA.value.upper()},
+    ).fetchall()
+
+    # Update each connector's config back to the old format
+    for connector_id, new_config in jira_connectors:
+        if not new_config:
+            continue
+
+        old_config = {}
+        base_url = new_config.get("jira_base_url")
+        project_key = new_config.get("project_key")
+
+        if base_url and project_key:
+            old_config = {"jira_project_url": f"{base_url}/projects/{project_key}"}
+        elif base_url:
+            old_config = {"jira_project_url": base_url}
+        else:
+            continue
+
+        # Update the connector config
+        conn.execute(
+            sa.text(
+                """
+                UPDATE connector
+                SET connector_specific_config = :old_config
+                WHERE id = :id
+                """
+            ),
+            {"id": connector_id, "old_config": old_config},
+        )

backend/alembic/versions/dab04867cd88_add_composite_index_to_document_by_.py

@@ -0,0 +1,32 @@
+"""Add composite index to document_by_connector_credential_pair
+
+Revision ID: dab04867cd88
+Revises: 54a74a0417fc
+Create Date: 2024-12-13 22:43:20.119990
+
+"""
+from alembic import op
+
+
+# revision identifiers, used by Alembic.
+revision = "dab04867cd88"
+down_revision = "54a74a0417fc"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # Composite index on (connector_id, credential_id)
+    op.create_index(
+        "idx_document_cc_pair_connector_credential",
+        "document_by_connector_credential_pair",
+        ["connector_id", "credential_id"],
+        unique=False,
+    )
+
+
+def downgrade() -> None:
+    op.drop_index(
+        "idx_document_cc_pair_connector_credential",
+        table_name="document_by_connector_credential_pair",
+    )

backend/alembic/versions/dba7f71618f5_onyx_custom_tool_flow.py

@@ -1,4 +1,4 @@
-"""Danswer Custom Tool Flow
+"""Onyx Custom Tool Flow
 
 Revision ID: dba7f71618f5
 Revises: d5645c915d0e

backend/alembic/versions/dbaa756c2ccf_embedding_models.py

@@ -9,12 +9,12 @@ from alembic import op
 import sqlalchemy as sa
 from sqlalchemy import table, column, String, Integer, Boolean
 
-from danswer.db.search_settings import (
+from onyx.db.search_settings import (
     get_new_default_embedding_model,
     get_old_default_embedding_model,
     user_has_overridden_embedding_model,
 )
-from danswer.db.models import IndexModelStatus
+from onyx.db.models import IndexModelStatus
 
 # revision identifiers, used by Alembic.
 revision = "dbaa756c2ccf"

backend/alembic/versions/e50154680a5c_no_source_enum.py

@@ -8,7 +8,7 @@ Create Date: 2024-03-14 18:06:08.523106
 from alembic import op
 import sqlalchemy as sa
 
-from danswer.configs.constants import DocumentSource
+from onyx.configs.constants import DocumentSource
 
 # revision identifiers, used by Alembic.
 revision = "e50154680a5c"

backend/alembic/versions/eaa3b5593925_add_default_slack_channel_config.py

@@ -0,0 +1,80 @@
+"""add default slack channel config
+
+Revision ID: eaa3b5593925
+Revises: 98a5008d8711
+Create Date: 2025-02-03 18:07:56.552526
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "eaa3b5593925"
+down_revision = "98a5008d8711"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # Add is_default column
+    op.add_column(
+        "slack_channel_config",
+        sa.Column("is_default", sa.Boolean(), nullable=False, server_default="false"),
+    )
+
+    op.create_index(
+        "ix_slack_channel_config_slack_bot_id_default",
+        "slack_channel_config",
+        ["slack_bot_id", "is_default"],
+        unique=True,
+        postgresql_where=sa.text("is_default IS TRUE"),
+    )
+
+    # Create default channel configs for existing slack bots without one
+    conn = op.get_bind()
+    slack_bots = conn.execute(sa.text("SELECT id FROM slack_bot")).fetchall()
+
+    for slack_bot in slack_bots:
+        slack_bot_id = slack_bot[0]
+        existing_default = conn.execute(
+            sa.text(
+                "SELECT id FROM slack_channel_config WHERE slack_bot_id = :bot_id AND is_default = TRUE"
+            ),
+            {"bot_id": slack_bot_id},
+        ).fetchone()
+
+        if not existing_default:
+            conn.execute(
+                sa.text(
+                    """
+                    INSERT INTO slack_channel_config (
+                        slack_bot_id, persona_id, channel_config, enable_auto_filters, is_default
+                    ) VALUES (
+                        :bot_id, NULL,
+                        '{"channel_name": null, '
+                        '"respond_member_group_list": [], '
+                        '"answer_filters": [], '
+                        '"follow_up_tags": [], '
+                        '"respond_tag_only": true}',
+                        FALSE, TRUE
+                    )
+                """
+                ),
+                {"bot_id": slack_bot_id},
+            )
+
+
+def downgrade() -> None:
+    # Delete default slack channel configs
+    conn = op.get_bind()
+    conn.execute(sa.text("DELETE FROM slack_channel_config WHERE is_default = TRUE"))
+
+    # Remove index
+    op.drop_index(
+        "ix_slack_channel_config_slack_bot_id_default",
+        table_name="slack_channel_config",
+    )
+
+    # Remove is_default column
+    op.drop_column("slack_channel_config", "is_default")

backend/alembic/versions/f11b408e39d3_force_lowercase_all_users.py

@@ -0,0 +1,36 @@
+"""force lowercase all users
+
+Revision ID: f11b408e39d3
+Revises: 3bd4c84fe72f
+Create Date: 2025-02-26 17:04:55.683500
+
+"""
+
+
+# revision identifiers, used by Alembic.
+revision = "f11b408e39d3"
+down_revision = "3bd4c84fe72f"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # 1) Convert all existing user emails to lowercase
+    from alembic import op
+
+    op.execute(
+        """
+        UPDATE "user"
+        SET email = LOWER(email)
+        """
+    )
+
+    # 2) Add a check constraint to ensure emails are always lowercase
+    op.create_check_constraint("ensure_lowercase_email", "user", "email = LOWER(email)")
+
+
+def downgrade() -> None:
+    # Drop the check constraint
+    from alembic import op
+
+    op.drop_constraint("ensure_lowercase_email", "user", type_="check")

backend/alembic/versions/f13db29f3101_add_composite_index_for_last_modified_.py

@@ -0,0 +1,27 @@
+"""Add composite index for last_modified and last_synced to document
+
+Revision ID: f13db29f3101
+Revises: b388730a2899
+Create Date: 2025-02-18 22:48:11.511389
+
+"""
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision = "f13db29f3101"
+down_revision = "acaab4ef4507"
+branch_labels: str | None = None
+depends_on: str | None = None
+
+
+def upgrade() -> None:
+    op.create_index(
+        "ix_document_sync_status",
+        "document",
+        ["last_modified", "last_synced"],
+        unique=False,
+    )
+
+
+def downgrade() -> None:
+    op.drop_index("ix_document_sync_status", table_name="document")

backend/alembic/versions/f1ca58b2f2ec_add_passthrough_auth_to_tool.py

@@ -0,0 +1,33 @@
+"""add passthrough auth to tool
+
+Revision ID: f1ca58b2f2ec
+Revises: c7bf5721733e
+Create Date: 2024-03-19
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision: str = "f1ca58b2f2ec"
+down_revision: Union[str, None] = "c7bf5721733e"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    # Add passthrough_auth column to tool table with default value of False
+    op.add_column(
+        "tool",
+        sa.Column(
+            "passthrough_auth", sa.Boolean(), nullable=False, server_default=sa.false()
+        ),
+    )
+
+
+def downgrade() -> None:
+    # Remove passthrough_auth column from tool table
+    op.drop_column("tool", "passthrough_auth")

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/alembic/versions/f5437cc136c5_delete_non_search_assistants.py

@@ -0,0 +1,53 @@
+"""delete non-search assistants
+
+Revision ID: f5437cc136c5
+Revises: eaa3b5593925
+Create Date: 2025-02-04 16:17:15.677256
+
+"""
+from alembic import op
+
+
+# revision identifiers, used by Alembic.
+revision = "f5437cc136c5"
+down_revision = "eaa3b5593925"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    pass
+
+
+def downgrade() -> None:
+    # Fix: split the statements into multiple op.execute() calls
+    op.execute(
+        """
+        WITH personas_without_search AS (
+            SELECT p.id
+            FROM persona p
+            LEFT JOIN persona__tool pt ON p.id = pt.persona_id
+            LEFT JOIN tool t ON pt.tool_id = t.id
+            GROUP BY p.id
+            HAVING COUNT(CASE WHEN t.in_code_tool_id = 'run_search' THEN 1 END) = 0
+        )
+        UPDATE slack_channel_config
+        SET persona_id = NULL
+        WHERE is_default = TRUE AND persona_id IN (SELECT id FROM personas_without_search)
+        """
+    )
+
+    op.execute(
+        """
+        WITH personas_without_search AS (
+            SELECT p.id
+            FROM persona p
+            LEFT JOIN persona__tool pt ON p.id = pt.persona_id
+            LEFT JOIN tool t ON pt.tool_id = t.id
+            GROUP BY p.id
+            HAVING COUNT(CASE WHEN t.in_code_tool_id = 'run_search' THEN 1 END) = 0
+        )
+        DELETE FROM slack_channel_config
+        WHERE is_default = FALSE AND persona_id IN (SELECT id FROM personas_without_search)
+        """
+    )

backend/alembic/versions/f7a894b06d02_non_nullbale_slack_bot_id_in_channel_.py

@@ -0,0 +1,40 @@
+"""non-nullbale slack bot id in channel config
+
+Revision ID: f7a894b06d02
+Revises: 9f696734098f
+Create Date: 2024-12-06 12:55:42.845723
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "f7a894b06d02"
+down_revision = "9f696734098f"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # Delete all rows with null slack_bot_id
+    op.execute("DELETE FROM slack_channel_config WHERE slack_bot_id IS NULL")
+
+    # Make slack_bot_id non-nullable
+    op.alter_column(
+        "slack_channel_config",
+        "slack_bot_id",
+        existing_type=sa.Integer(),
+        nullable=False,
+    )
+
+
+def downgrade() -> None:
+    # Make slack_bot_id nullable again
+    op.alter_column(
+        "slack_channel_config",
+        "slack_bot_id",
+        existing_type=sa.Integer(),
+        nullable=True,
+    )

backend/alembic/versions/fec3db967bf7_add_time_updated_to_usergroup_and_.py

@@ -0,0 +1,41 @@
+"""Add time_updated to UserGroup and DocumentSet
+
+Revision ID: fec3db967bf7
+Revises: 97dbb53fa8c8
+Create Date: 2025-01-12 15:49:02.289100
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "fec3db967bf7"
+down_revision = "97dbb53fa8c8"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "document_set",
+        sa.Column(
+            "time_last_modified_by_user",
+            sa.DateTime(timezone=True),
+            nullable=False,
+            server_default=sa.func.now(),
+        ),
+    )
+    op.add_column(
+        "user_group",
+        sa.Column(
+            "time_last_modified_by_user",
+            sa.DateTime(timezone=True),
+            nullable=False,
+            server_default=sa.func.now(),
+        ),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("user_group", "time_last_modified_by_user")
+    op.drop_column("document_set", "time_last_modified_by_user")

backend/alembic_tenants/README.md

@@ -1,3 +1,3 @@
 These files are for public table migrations when operating with multi tenancy.
 
-If you are not a Danswer developer, you can ignore this directory entirely.
+If you are not a Onyx developer, you can ignore this directory entirely.

backend/alembic_tenants/env.py

@@ -8,8 +8,8 @@ from sqlalchemy.ext.asyncio import create_async_engine
 from sqlalchemy.schema import SchemaItem
 
 from alembic import context
-from danswer.db.engine import build_connection_string
-from danswer.db.models import PublicBase
+from onyx.db.engine import build_connection_string
+from onyx.db.models import PublicBase
 
 # this is the Alembic Config object, which provides
 # access to the values within the .ini file in use.

backend/alembic_tenants/versions/34e3630c7f32_lowercase_multi_tenant_user_auth.py

@@ -0,0 +1,42 @@
+"""lowercase multi-tenant user auth
+
+Revision ID: 34e3630c7f32
+Revises: a4f6ee863c47
+Create Date: 2025-02-26 15:03:01.211894
+
+"""
+from alembic import op
+
+
+# revision identifiers, used by Alembic.
+revision = "34e3630c7f32"
+down_revision = "a4f6ee863c47"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # 1) Convert all existing rows to lowercase
+    op.execute(
+        """
+        UPDATE user_tenant_mapping
+        SET email = LOWER(email)
+        """
+    )
+    # 2) Add a check constraint so that emails cannot be written in uppercase
+    op.create_check_constraint(
+        "ensure_lowercase_email",
+        "user_tenant_mapping",
+        "email = LOWER(email)",
+        schema="public",
+    )
+
+
+def downgrade() -> None:
+    # Drop the check constraint
+    op.drop_constraint(
+        "ensure_lowercase_email",
+        "user_tenant_mapping",
+        schema="public",
+        type_="check",
+    )

backend/alembic_tenants/versions/a4f6ee863c47_mapping_for_anonymous_user_path.py

@@ -0,0 +1,31 @@
+"""mapping for anonymous user path
+
+Revision ID: a4f6ee863c47
+Revises: 14a83a331951
+Create Date: 2025-01-04 14:16:58.697451
+
+"""
+import sqlalchemy as sa
+
+from alembic import op
+
+
+# revision identifiers, used by Alembic.
+revision = "a4f6ee863c47"
+down_revision = "14a83a331951"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "tenant_anonymous_user_path",
+        sa.Column("tenant_id", sa.String(), primary_key=True, nullable=False),
+        sa.Column("anonymous_user_path", sa.String(), nullable=False),
+        sa.PrimaryKeyConstraint("tenant_id"),
+        sa.UniqueConstraint("anonymous_user_path"),
+    )
+
+
+def downgrade() -> None:
+    op.drop_table("tenant_anonymous_user_path")

backend/danswer/__init__.py

@@ -1,3 +0,0 @@
-import os
-
-__version__ = os.environ.get("DANSWER_VERSION", "") or "Development"

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

@@ -1,172 +0,0 @@
-from datetime import timedelta
-from typing import Any
-
-from celery import Celery
-from celery import signals
-from celery.beat import PersistentScheduler  # type: ignore
-from celery.signals import beat_init
-
-import danswer.background.celery.apps.app_base as app_base
-from danswer.configs.constants import POSTGRES_CELERY_BEAT_APP_NAME
-from danswer.db.engine import get_all_tenant_ids
-from danswer.db.engine import SqlEngine
-from danswer.utils.logger import setup_logger
-from danswer.utils.variable_functionality import fetch_versioned_implementation
-from shared_configs.configs import IGNORED_SYNCING_TENANT_LIST
-from shared_configs.configs import MULTI_TENANT
-
-logger = setup_logger(__name__)
-
-celery_app = Celery(__name__)
-celery_app.config_from_object("danswer.background.celery.configs.beat")
-
-
-class DynamicTenantScheduler(PersistentScheduler):
-    def __init__(self, *args: Any, **kwargs: Any) -> None:
-        logger.info("Initializing DynamicTenantScheduler")
-        super().__init__(*args, **kwargs)
-        self._reload_interval = timedelta(minutes=2)
-        self._last_reload = self.app.now() - self._reload_interval
-        # Let the parent class handle store initialization
-        self.setup_schedule()
-        self._update_tenant_tasks()
-        logger.info(f"Set reload interval to {self._reload_interval}")
-
-    def setup_schedule(self) -> None:
-        logger.info("Setting up initial schedule")
-        super().setup_schedule()
-        logger.info("Initial schedule setup complete")
-
-    def tick(self) -> float:
-        retval = super().tick()
-        now = self.app.now()
-        if (
-            self._last_reload is None
-            or (now - self._last_reload) > self._reload_interval
-        ):
-            logger.info("Reload interval reached, initiating tenant task update")
-            self._update_tenant_tasks()
-            self._last_reload = now
-            logger.info("Tenant task update completed, reset reload timer")
-        return retval
-
-    def _update_tenant_tasks(self) -> None:
-        logger.info("Starting tenant task update process")
-        try:
-            logger.info("Fetching all tenant IDs")
-            tenant_ids = get_all_tenant_ids()
-            logger.info(f"Found {len(tenant_ids)} tenants")
-
-            logger.info("Fetching tasks to schedule")
-            tasks_to_schedule = fetch_versioned_implementation(
-                "danswer.background.celery.tasks.beat_schedule", "get_tasks_to_schedule"
-            )
-
-            new_beat_schedule: dict[str, dict[str, Any]] = {}
-
-            current_schedule = self.schedule.items()
-
-            existing_tenants = set()
-            for task_name, _ in current_schedule:
-                if "-" in task_name:
-                    existing_tenants.add(task_name.split("-")[-1])
-            logger.info(f"Found {len(existing_tenants)} existing tenants in schedule")
-
-            for tenant_id in tenant_ids:
-                if (
-                    IGNORED_SYNCING_TENANT_LIST
-                    and tenant_id in IGNORED_SYNCING_TENANT_LIST
-                ):
-                    logger.info(
-                        f"Skipping tenant {tenant_id} as it is in the ignored syncing list"
-                    )
-                    continue
-
-                if tenant_id not in existing_tenants:
-                    logger.info(f"Processing new tenant: {tenant_id}")
-
-                for task in tasks_to_schedule():
-                    task_name = f"{task['name']}-{tenant_id}"
-                    logger.debug(f"Creating task configuration for {task_name}")
-                    new_task = {
-                        "task": task["task"],
-                        "schedule": task["schedule"],
-                        "kwargs": {"tenant_id": tenant_id},
-                    }
-                    if options := task.get("options"):
-                        logger.debug(f"Adding options to task {task_name}: {options}")
-                        new_task["options"] = options
-                    new_beat_schedule[task_name] = new_task
-
-            if self._should_update_schedule(current_schedule, new_beat_schedule):
-                logger.info(
-                    "Schedule update required",
-                    extra={
-                        "new_tasks": len(new_beat_schedule),
-                        "current_tasks": len(current_schedule),
-                    },
-                )
-
-                # Create schedule entries
-                entries = {}
-                for name, entry in new_beat_schedule.items():
-                    entries[name] = self.Entry(
-                        name=name,
-                        app=self.app,
-                        task=entry["task"],
-                        schedule=entry["schedule"],
-                        options=entry.get("options", {}),
-                        kwargs=entry.get("kwargs", {}),
-                    )
-
-                # Update the schedule using the scheduler's methods
-                self.schedule.clear()
-                self.schedule.update(entries)
-
-                # Ensure changes are persisted
-                self.sync()
-
-                logger.info("Schedule update completed successfully")
-            else:
-                logger.info("Schedule is up to date, no changes needed")
-
-        except (AttributeError, KeyError):
-            logger.exception("Failed to process task configuration")
-        except Exception:
-            logger.exception("Unexpected error updating tenant tasks")
-
-    def _should_update_schedule(
-        self, current_schedule: dict, new_schedule: dict
-    ) -> bool:
-        """Compare schedules to determine if an update is needed."""
-        logger.debug("Comparing current and new schedules")
-        current_tasks = set(name for name, _ in current_schedule)
-        new_tasks = set(new_schedule.keys())
-        needs_update = current_tasks != new_tasks
-        logger.debug(f"Schedule update needed: {needs_update}")
-        return needs_update
-
-
-@beat_init.connect
-def on_beat_init(sender: Any, **kwargs: Any) -> None:
-    logger.info("beat_init signal received.")
-
-    # Celery beat shouldn't touch the db at all. But just setting a low minimum here.
-    SqlEngine.set_app_name(POSTGRES_CELERY_BEAT_APP_NAME)
-    SqlEngine.init_engine(pool_size=2, max_overflow=0)
-
-    # Startup checks are not needed in multi-tenant case
-    if MULTI_TENANT:
-        return
-
-    app_base.wait_for_redis(sender, **kwargs)
-
-
-@signals.setup_logging.connect
-def on_setup_logging(
-    loglevel: Any, logfile: Any, format: Any, colorize: Any, **kwargs: Any
-) -> None:
-    app_base.on_setup_logging(loglevel, logfile, format, colorize, **kwargs)
-
-
-celery_app.conf.beat_scheduler = DynamicTenantScheduler

backend/danswer/background/celery/celery_redis.py

@@ -1,25 +0,0 @@
-# These are helper objects for tracking the keys we need to write in redis
-from typing import cast
-
-from redis import Redis
-
-from danswer.background.celery.configs.base import CELERY_SEPARATOR
-from danswer.configs.constants import DanswerCeleryPriority
-
-
-def celery_get_queue_length(queue: str, r: Redis) -> int:
-    """This is a redis specific way to get the length of a celery queue.
-    It is priority aware and knows how to count across the multiple redis lists
-    used to implement task prioritization.
-    This operation is not atomic."""
-    total_length = 0
-    for i in range(len(DanswerCeleryPriority)):
-        queue_name = queue
-        if i > 0:
-            queue_name += CELERY_SEPARATOR
-            queue_name += str(i)
-
-        length = r.llen(queue_name)
-        total_length += cast(int, length)
-
-    return total_length

backend/danswer/background/celery/tasks/beat_schedule.py

@@ -1,61 +0,0 @@
-from datetime import timedelta
-from typing import Any
-
-from danswer.configs.constants import DanswerCeleryPriority
-from danswer.configs.constants import DanswerCeleryTask
-
-
-tasks_to_schedule = [
-    {
-        "name": "check-for-vespa-sync",
-        "task": DanswerCeleryTask.CHECK_FOR_VESPA_SYNC_TASK,
-        "schedule": timedelta(seconds=20),
-        "options": {"priority": DanswerCeleryPriority.HIGH},
-    },
-    {
-        "name": "check-for-connector-deletion",
-        "task": DanswerCeleryTask.CHECK_FOR_CONNECTOR_DELETION,
-        "schedule": timedelta(seconds=20),
-        "options": {"priority": DanswerCeleryPriority.HIGH},
-    },
-    {
-        "name": "check-for-indexing",
-        "task": DanswerCeleryTask.CHECK_FOR_INDEXING,
-        "schedule": timedelta(seconds=15),
-        "options": {"priority": DanswerCeleryPriority.HIGH},
-    },
-    {
-        "name": "check-for-prune",
-        "task": DanswerCeleryTask.CHECK_FOR_PRUNING,
-        "schedule": timedelta(seconds=15),
-        "options": {"priority": DanswerCeleryPriority.HIGH},
-    },
-    {
-        "name": "kombu-message-cleanup",
-        "task": DanswerCeleryTask.KOMBU_MESSAGE_CLEANUP_TASK,
-        "schedule": timedelta(seconds=3600),
-        "options": {"priority": DanswerCeleryPriority.LOWEST},
-    },
-    {
-        "name": "monitor-vespa-sync",
-        "task": DanswerCeleryTask.MONITOR_VESPA_SYNC,
-        "schedule": timedelta(seconds=5),
-        "options": {"priority": DanswerCeleryPriority.HIGH},
-    },
-    {
-        "name": "check-for-doc-permissions-sync",
-        "task": DanswerCeleryTask.CHECK_FOR_DOC_PERMISSIONS_SYNC,
-        "schedule": timedelta(seconds=30),
-        "options": {"priority": DanswerCeleryPriority.HIGH},
-    },
-    {
-        "name": "check-for-external-group-sync",
-        "task": DanswerCeleryTask.CHECK_FOR_EXTERNAL_GROUP_SYNC,
-        "schedule": timedelta(seconds=20),
-        "options": {"priority": DanswerCeleryPriority.HIGH},
-    },
-]
-
-
-def get_tasks_to_schedule() -> list[dict[str, Any]]:
-    return tasks_to_schedule

backend/danswer/background/celery/tasks/connector_deletion/tasks.py

@@ -1,186 +0,0 @@
-from datetime import datetime
-from datetime import timezone
-
-from celery import Celery
-from celery import shared_task
-from celery import Task
-from celery.exceptions import SoftTimeLimitExceeded
-from redis.lock import Lock as RedisLock
-from sqlalchemy.orm import Session
-
-from danswer.background.celery.apps.app_base import task_logger
-from danswer.configs.app_configs import JOB_TIMEOUT
-from danswer.configs.constants import CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT
-from danswer.configs.constants import DanswerCeleryTask
-from danswer.configs.constants import DanswerRedisLocks
-from danswer.db.connector_credential_pair import get_connector_credential_pair_from_id
-from danswer.db.connector_credential_pair import get_connector_credential_pairs
-from danswer.db.engine import get_session_with_tenant
-from danswer.db.enums import ConnectorCredentialPairStatus
-from danswer.db.search_settings import get_all_search_settings
-from danswer.redis.redis_connector import RedisConnector
-from danswer.redis.redis_connector_delete import RedisConnectorDeletePayload
-from danswer.redis.redis_pool import get_redis_client
-
-
-class TaskDependencyError(RuntimeError):
-    """Raised to the caller to indicate dependent tasks are running that would interfere
-    with connector deletion."""
-
-
-@shared_task(
-    name=DanswerCeleryTask.CHECK_FOR_CONNECTOR_DELETION,
-    soft_time_limit=JOB_TIMEOUT,
-    trail=False,
-    bind=True,
-)
-def check_for_connector_deletion_task(self: Task, *, tenant_id: str | None) -> None:
-    r = get_redis_client(tenant_id=tenant_id)
-
-    lock_beat: RedisLock = r.lock(
-        DanswerRedisLocks.CHECK_CONNECTOR_DELETION_BEAT_LOCK,
-        timeout=CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT,
-    )
-
-    try:
-        # these tasks should never overlap
-        if not lock_beat.acquire(blocking=False):
-            return
-
-        # collect cc_pair_ids
-        cc_pair_ids: list[int] = []
-        with get_session_with_tenant(tenant_id) as db_session:
-            cc_pairs = get_connector_credential_pairs(db_session)
-            for cc_pair in cc_pairs:
-                cc_pair_ids.append(cc_pair.id)
-
-        # try running cleanup on the cc_pair_ids
-        for cc_pair_id in cc_pair_ids:
-            with get_session_with_tenant(tenant_id) as db_session:
-                redis_connector = RedisConnector(tenant_id, cc_pair_id)
-                try:
-                    try_generate_document_cc_pair_cleanup_tasks(
-                        self.app, cc_pair_id, db_session, lock_beat, tenant_id
-                    )
-                except TaskDependencyError as e:
-                    # this means we wanted to start deleting but dependent tasks were running
-                    # Leave a stop signal to clear indexing and pruning tasks more quickly
-                    task_logger.info(str(e))
-                    redis_connector.stop.set_fence(True)
-                else:
-                    # clear the stop signal if it exists ... no longer needed
-                    redis_connector.stop.set_fence(False)
-
-    except SoftTimeLimitExceeded:
-        task_logger.info(
-            "Soft time limit exceeded, task is being terminated gracefully."
-        )
-    except Exception:
-        task_logger.exception(f"Unexpected exception: tenant={tenant_id}")
-    finally:
-        if lock_beat.owned():
-            lock_beat.release()
-
-
-def try_generate_document_cc_pair_cleanup_tasks(
-    app: Celery,
-    cc_pair_id: int,
-    db_session: Session,
-    lock_beat: RedisLock,
-    tenant_id: str | None,
-) -> int | None:
-    """Returns an int if syncing is needed. The int represents the number of sync tasks generated.
-    Note that syncing can still be required even if the number of sync tasks generated is zero.
-    Returns None if no syncing is required.
-
-    Will raise TaskDependencyError if dependent tasks such as indexing and pruning are
-    still running. In our case, the caller reacts by setting a stop signal in Redis to
-    exit those tasks as quickly as possible.
-    """
-
-    lock_beat.reacquire()
-
-    redis_connector = RedisConnector(tenant_id, cc_pair_id)
-
-    # don't generate sync tasks if tasks are still pending
-    if redis_connector.delete.fenced:
-        return None
-
-    # we need to load the state of the object inside the fence
-    # to avoid a race condition with db.commit/fence deletion
-    # at the end of this taskset
-    cc_pair = get_connector_credential_pair_from_id(cc_pair_id, db_session)
-    if not cc_pair:
-        return None
-
-    if cc_pair.status != ConnectorCredentialPairStatus.DELETING:
-        return None
-
-    # set a basic fence to start
-    fence_payload = RedisConnectorDeletePayload(
-        num_tasks=None,
-        submitted=datetime.now(timezone.utc),
-    )
-
-    redis_connector.delete.set_fence(fence_payload)
-
-    try:
-        # do not proceed if connector indexing or connector pruning are running
-        search_settings_list = get_all_search_settings(db_session)
-        for search_settings in search_settings_list:
-            redis_connector_index = redis_connector.new_index(search_settings.id)
-            if redis_connector_index.fenced:
-                raise TaskDependencyError(
-                    f"Connector deletion - Delayed (indexing in progress): "
-                    f"cc_pair={cc_pair_id} "
-                    f"search_settings={search_settings.id}"
-                )
-
-        if redis_connector.prune.fenced:
-            raise TaskDependencyError(
-                f"Connector deletion - Delayed (pruning in progress): "
-                f"cc_pair={cc_pair_id}"
-            )
-
-        if redis_connector.permissions.fenced:
-            raise TaskDependencyError(
-                f"Connector deletion - Delayed (permissions in progress): "
-                f"cc_pair={cc_pair_id}"
-            )
-
-        # add tasks to celery and build up the task set to monitor in redis
-        redis_connector.delete.taskset_clear()
-
-        # Add all documents that need to be updated into the queue
-        task_logger.info(
-            f"RedisConnectorDeletion.generate_tasks starting. cc_pair={cc_pair_id}"
-        )
-        tasks_generated = redis_connector.delete.generate_tasks(
-            app, db_session, lock_beat
-        )
-        if tasks_generated is None:
-            raise ValueError("RedisConnectorDeletion.generate_tasks returned None")
-    except TaskDependencyError:
-        redis_connector.delete.set_fence(None)
-        raise
-    except Exception:
-        task_logger.exception("Unexpected exception")
-        redis_connector.delete.set_fence(None)
-        return None
-    else:
-        # Currently we are allowing the sync to proceed with 0 tasks.
-        # It's possible for sets/groups to be generated initially with no entries
-        # and they still need to be marked as up to date.
-        # if tasks_generated == 0:
-        #     return 0
-
-        task_logger.info(
-            f"RedisConnectorDeletion.generate_tasks finished. "
-            f"cc_pair={cc_pair_id} tasks_generated={tasks_generated}"
-        )
-
-        # set this only after all tasks have been added
-        fence_payload.num_tasks = tasks_generated
-        redis_connector.delete.set_fence(fence_payload)
-
-    return tasks_generated

backend/danswer/background/celery/tasks/doc_permission_syncing/tasks.py

@@ -1,327 +0,0 @@
-from datetime import datetime
-from datetime import timedelta
-from datetime import timezone
-from uuid import uuid4
-
-from celery import Celery
-from celery import shared_task
-from celery import Task
-from celery.exceptions import SoftTimeLimitExceeded
-from redis import Redis
-from redis.lock import Lock as RedisLock
-
-from danswer.access.models import DocExternalAccess
-from danswer.background.celery.apps.app_base import task_logger
-from danswer.configs.app_configs import JOB_TIMEOUT
-from danswer.configs.constants import CELERY_PERMISSIONS_SYNC_LOCK_TIMEOUT
-from danswer.configs.constants import CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT
-from danswer.configs.constants import DANSWER_REDIS_FUNCTION_LOCK_PREFIX
-from danswer.configs.constants import DanswerCeleryPriority
-from danswer.configs.constants import DanswerCeleryQueues
-from danswer.configs.constants import DanswerCeleryTask
-from danswer.configs.constants import DanswerRedisLocks
-from danswer.configs.constants import DocumentSource
-from danswer.db.connector_credential_pair import get_connector_credential_pair_from_id
-from danswer.db.engine import get_session_with_tenant
-from danswer.db.enums import AccessType
-from danswer.db.enums import ConnectorCredentialPairStatus
-from danswer.db.models import ConnectorCredentialPair
-from danswer.db.users import batch_add_ext_perm_user_if_not_exists
-from danswer.redis.redis_connector import RedisConnector
-from danswer.redis.redis_connector_doc_perm_sync import (
-    RedisConnectorPermissionSyncPayload,
-)
-from danswer.redis.redis_pool import get_redis_client
-from danswer.utils.logger import doc_permission_sync_ctx
-from danswer.utils.logger import setup_logger
-from ee.danswer.db.connector_credential_pair import get_all_auto_sync_cc_pairs
-from ee.danswer.db.document import upsert_document_external_perms
-from ee.danswer.external_permissions.sync_params import DOC_PERMISSION_SYNC_PERIODS
-from ee.danswer.external_permissions.sync_params import DOC_PERMISSIONS_FUNC_MAP
-
-logger = setup_logger()
-
-
-DOCUMENT_PERMISSIONS_UPDATE_MAX_RETRIES = 3
-
-
-# 5 seconds more than RetryDocumentIndex STOP_AFTER+MAX_WAIT
-LIGHT_SOFT_TIME_LIMIT = 105
-LIGHT_TIME_LIMIT = LIGHT_SOFT_TIME_LIMIT + 15
-
-
-def _is_external_doc_permissions_sync_due(cc_pair: ConnectorCredentialPair) -> bool:
-    """Returns boolean indicating if external doc permissions sync is due."""
-
-    if cc_pair.access_type != AccessType.SYNC:
-        return False
-
-    # skip doc permissions sync if not active
-    if cc_pair.status != ConnectorCredentialPairStatus.ACTIVE:
-        return False
-
-    if cc_pair.status == ConnectorCredentialPairStatus.DELETING:
-        return False
-
-    # If the last sync is None, it has never been run so we run the sync
-    last_perm_sync = cc_pair.last_time_perm_sync
-    if last_perm_sync is None:
-        return True
-
-    source_sync_period = DOC_PERMISSION_SYNC_PERIODS.get(cc_pair.connector.source)
-
-    # If RESTRICTED_FETCH_PERIOD[source] is None, we always run the sync.
-    if not source_sync_period:
-        return True
-
-    # If the last sync is greater than the full fetch period, we run the sync
-    next_sync = last_perm_sync + timedelta(seconds=source_sync_period)
-    if datetime.now(timezone.utc) >= next_sync:
-        return True
-
-    return False
-
-
-@shared_task(
-    name=DanswerCeleryTask.CHECK_FOR_DOC_PERMISSIONS_SYNC,
-    soft_time_limit=JOB_TIMEOUT,
-    bind=True,
-)
-def check_for_doc_permissions_sync(self: Task, *, tenant_id: str | None) -> None:
-    r = get_redis_client(tenant_id=tenant_id)
-
-    lock_beat = r.lock(
-        DanswerRedisLocks.CHECK_CONNECTOR_DOC_PERMISSIONS_SYNC_BEAT_LOCK,
-        timeout=CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT,
-    )
-
-    try:
-        # these tasks should never overlap
-        if not lock_beat.acquire(blocking=False):
-            return
-
-        # get all cc pairs that need to be synced
-        cc_pair_ids_to_sync: list[int] = []
-        with get_session_with_tenant(tenant_id) as db_session:
-            cc_pairs = get_all_auto_sync_cc_pairs(db_session)
-
-            for cc_pair in cc_pairs:
-                if _is_external_doc_permissions_sync_due(cc_pair):
-                    cc_pair_ids_to_sync.append(cc_pair.id)
-
-        for cc_pair_id in cc_pair_ids_to_sync:
-            tasks_created = try_creating_permissions_sync_task(
-                self.app, cc_pair_id, r, tenant_id
-            )
-            if not tasks_created:
-                continue
-
-            task_logger.info(f"Doc permissions sync queued: cc_pair={cc_pair_id}")
-    except SoftTimeLimitExceeded:
-        task_logger.info(
-            "Soft time limit exceeded, task is being terminated gracefully."
-        )
-    except Exception:
-        task_logger.exception(f"Unexpected exception: tenant={tenant_id}")
-    finally:
-        if lock_beat.owned():
-            lock_beat.release()
-
-
-def try_creating_permissions_sync_task(
-    app: Celery,
-    cc_pair_id: int,
-    r: Redis,
-    tenant_id: str | None,
-) -> int | None:
-    """Returns an int if syncing is needed. The int represents the number of sync tasks generated.
-    Returns None if no syncing is required."""
-    redis_connector = RedisConnector(tenant_id, cc_pair_id)
-
-    LOCK_TIMEOUT = 30
-
-    lock: RedisLock = r.lock(
-        DANSWER_REDIS_FUNCTION_LOCK_PREFIX + "try_generate_permissions_sync_tasks",
-        timeout=LOCK_TIMEOUT,
-    )
-
-    acquired = lock.acquire(blocking_timeout=LOCK_TIMEOUT / 2)
-    if not acquired:
-        return None
-
-    try:
-        if redis_connector.permissions.fenced:
-            return None
-
-        if redis_connector.delete.fenced:
-            return None
-
-        if redis_connector.prune.fenced:
-            return None
-
-        redis_connector.permissions.generator_clear()
-        redis_connector.permissions.taskset_clear()
-
-        custom_task_id = f"{redis_connector.permissions.generator_task_key}_{uuid4()}"
-
-        result = app.send_task(
-            DanswerCeleryTask.CONNECTOR_PERMISSION_SYNC_GENERATOR_TASK,
-            kwargs=dict(
-                cc_pair_id=cc_pair_id,
-                tenant_id=tenant_id,
-            ),
-            queue=DanswerCeleryQueues.CONNECTOR_DOC_PERMISSIONS_SYNC,
-            task_id=custom_task_id,
-            priority=DanswerCeleryPriority.HIGH,
-        )
-
-        # set a basic fence to start
-        payload = RedisConnectorPermissionSyncPayload(
-            started=None, celery_task_id=result.id
-        )
-
-        redis_connector.permissions.set_fence(payload)
-    except Exception:
-        task_logger.exception(f"Unexpected exception: cc_pair={cc_pair_id}")
-        return None
-    finally:
-        if lock.owned():
-            lock.release()
-
-    return 1
-
-
-@shared_task(
-    name=DanswerCeleryTask.CONNECTOR_PERMISSION_SYNC_GENERATOR_TASK,
-    acks_late=False,
-    soft_time_limit=JOB_TIMEOUT,
-    track_started=True,
-    trail=False,
-    bind=True,
-)
-def connector_permission_sync_generator_task(
-    self: Task,
-    cc_pair_id: int,
-    tenant_id: str | None,
-) -> None:
-    """
-    Permission sync task that handles document permission syncing for a given connector credential pair
-    This task assumes that the task has already been properly fenced
-    """
-
-    doc_permission_sync_ctx_dict = doc_permission_sync_ctx.get()
-    doc_permission_sync_ctx_dict["cc_pair_id"] = cc_pair_id
-    doc_permission_sync_ctx_dict["request_id"] = self.request.id
-    doc_permission_sync_ctx.set(doc_permission_sync_ctx_dict)
-
-    redis_connector = RedisConnector(tenant_id, cc_pair_id)
-
-    r = get_redis_client(tenant_id=tenant_id)
-
-    lock = r.lock(
-        DanswerRedisLocks.CONNECTOR_DOC_PERMISSIONS_SYNC_LOCK_PREFIX
-        + f"_{redis_connector.id}",
-        timeout=CELERY_PERMISSIONS_SYNC_LOCK_TIMEOUT,
-    )
-
-    acquired = lock.acquire(blocking=False)
-    if not acquired:
-        task_logger.warning(
-            f"Permission sync task already running, exiting...: cc_pair={cc_pair_id}"
-        )
-        return None
-
-    try:
-        with get_session_with_tenant(tenant_id) as db_session:
-            cc_pair = get_connector_credential_pair_from_id(cc_pair_id, db_session)
-            if cc_pair is None:
-                raise ValueError(
-                    f"No connector credential pair found for id: {cc_pair_id}"
-                )
-
-            source_type = cc_pair.connector.source
-
-            doc_sync_func = DOC_PERMISSIONS_FUNC_MAP.get(source_type)
-            if doc_sync_func is None:
-                raise ValueError(
-                    f"No doc sync func found for {source_type} with cc_pair={cc_pair_id}"
-                )
-
-            logger.info(f"Syncing docs for {source_type} with cc_pair={cc_pair_id}")
-
-            payload = redis_connector.permissions.payload
-            if not payload:
-                raise ValueError(f"No fence payload found: cc_pair={cc_pair_id}")
-
-            payload.started = datetime.now(timezone.utc)
-            redis_connector.permissions.set_fence(payload)
-
-            document_external_accesses: list[DocExternalAccess] = doc_sync_func(cc_pair)
-
-            task_logger.info(
-                f"RedisConnector.permissions.generate_tasks starting. cc_pair={cc_pair_id}"
-            )
-            tasks_generated = redis_connector.permissions.generate_tasks(
-                self.app, lock, document_external_accesses, source_type
-            )
-            if tasks_generated is None:
-                return None
-
-            task_logger.info(
-                f"RedisConnector.permissions.generate_tasks finished. "
-                f"cc_pair={cc_pair_id} tasks_generated={tasks_generated}"
-            )
-
-            redis_connector.permissions.generator_complete = tasks_generated
-
-    except Exception as e:
-        task_logger.exception(f"Failed to run permission sync: cc_pair={cc_pair_id}")
-
-        redis_connector.permissions.generator_clear()
-        redis_connector.permissions.taskset_clear()
-        redis_connector.permissions.set_fence(None)
-        raise e
-    finally:
-        if lock.owned():
-            lock.release()
-
-
-@shared_task(
-    name=DanswerCeleryTask.UPDATE_EXTERNAL_DOCUMENT_PERMISSIONS_TASK,
-    soft_time_limit=LIGHT_SOFT_TIME_LIMIT,
-    time_limit=LIGHT_TIME_LIMIT,
-    max_retries=DOCUMENT_PERMISSIONS_UPDATE_MAX_RETRIES,
-    bind=True,
-)
-def update_external_document_permissions_task(
-    self: Task,
-    tenant_id: str | None,
-    serialized_doc_external_access: dict,
-    source_string: str,
-) -> bool:
-    document_external_access = DocExternalAccess.from_dict(
-        serialized_doc_external_access
-    )
-    doc_id = document_external_access.doc_id
-    external_access = document_external_access.external_access
-    try:
-        with get_session_with_tenant(tenant_id) as db_session:
-            # Then we build the update requests to update vespa
-            batch_add_ext_perm_user_if_not_exists(
-                db_session=db_session,
-                emails=list(external_access.external_user_emails),
-            )
-            upsert_document_external_perms(
-                db_session=db_session,
-                doc_id=doc_id,
-                external_access=external_access,
-                source_type=DocumentSource(source_string),
-            )
-
-            logger.debug(
-                f"Successfully synced postgres document permissions for {doc_id}"
-            )
-        return True
-    except Exception:
-        logger.exception("Error Syncing Document Permissions")
-        return False

backend/danswer/background/celery/tasks/external_group_syncing/tasks.py

@@ -1,278 +0,0 @@
-from datetime import datetime
-from datetime import timedelta
-from datetime import timezone
-from uuid import uuid4
-
-from celery import Celery
-from celery import shared_task
-from celery import Task
-from celery.exceptions import SoftTimeLimitExceeded
-from redis import Redis
-from redis.lock import Lock as RedisLock
-
-from danswer.background.celery.apps.app_base import task_logger
-from danswer.configs.app_configs import JOB_TIMEOUT
-from danswer.configs.constants import CELERY_EXTERNAL_GROUP_SYNC_LOCK_TIMEOUT
-from danswer.configs.constants import CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT
-from danswer.configs.constants import DANSWER_REDIS_FUNCTION_LOCK_PREFIX
-from danswer.configs.constants import DanswerCeleryPriority
-from danswer.configs.constants import DanswerCeleryQueues
-from danswer.configs.constants import DanswerCeleryTask
-from danswer.configs.constants import DanswerRedisLocks
-from danswer.db.connector import mark_cc_pair_as_external_group_synced
-from danswer.db.connector_credential_pair import get_connector_credential_pair_from_id
-from danswer.db.engine import get_session_with_tenant
-from danswer.db.enums import AccessType
-from danswer.db.enums import ConnectorCredentialPairStatus
-from danswer.db.models import ConnectorCredentialPair
-from danswer.redis.redis_connector import RedisConnector
-from danswer.redis.redis_connector_ext_group_sync import (
-    RedisConnectorExternalGroupSyncPayload,
-)
-from danswer.redis.redis_pool import get_redis_client
-from danswer.utils.logger import setup_logger
-from ee.danswer.db.connector_credential_pair import get_all_auto_sync_cc_pairs
-from ee.danswer.db.external_perm import ExternalUserGroup
-from ee.danswer.db.external_perm import replace_user__ext_group_for_cc_pair
-from ee.danswer.external_permissions.sync_params import EXTERNAL_GROUP_SYNC_PERIODS
-from ee.danswer.external_permissions.sync_params import GROUP_PERMISSIONS_FUNC_MAP
-
-logger = setup_logger()
-
-
-EXTERNAL_GROUPS_UPDATE_MAX_RETRIES = 3
-
-
-# 5 seconds more than RetryDocumentIndex STOP_AFTER+MAX_WAIT
-LIGHT_SOFT_TIME_LIMIT = 105
-LIGHT_TIME_LIMIT = LIGHT_SOFT_TIME_LIMIT + 15
-
-
-def _is_external_group_sync_due(cc_pair: ConnectorCredentialPair) -> bool:
-    """Returns boolean indicating if external group sync is due."""
-
-    if cc_pair.access_type != AccessType.SYNC:
-        return False
-
-    # skip external group sync if not active
-    if cc_pair.status != ConnectorCredentialPairStatus.ACTIVE:
-        return False
-
-    if cc_pair.status == ConnectorCredentialPairStatus.DELETING:
-        return False
-
-    # If there is not group sync function for the connector, we don't run the sync
-    # This is fine because all sources dont necessarily have a concept of groups
-    if not GROUP_PERMISSIONS_FUNC_MAP.get(cc_pair.connector.source):
-        return False
-
-    # If the last sync is None, it has never been run so we run the sync
-    last_ext_group_sync = cc_pair.last_time_external_group_sync
-    if last_ext_group_sync is None:
-        return True
-
-    source_sync_period = EXTERNAL_GROUP_SYNC_PERIODS.get(cc_pair.connector.source)
-
-    # If EXTERNAL_GROUP_SYNC_PERIODS is None, we always run the sync.
-    if not source_sync_period:
-        return True
-
-    # If the last sync is greater than the full fetch period, we run the sync
-    next_sync = last_ext_group_sync + timedelta(seconds=source_sync_period)
-    if datetime.now(timezone.utc) >= next_sync:
-        return True
-
-    return False
-
-
-@shared_task(
-    name=DanswerCeleryTask.CHECK_FOR_EXTERNAL_GROUP_SYNC,
-    soft_time_limit=JOB_TIMEOUT,
-    bind=True,
-)
-def check_for_external_group_sync(self: Task, *, tenant_id: str | None) -> None:
-    r = get_redis_client(tenant_id=tenant_id)
-
-    lock_beat = r.lock(
-        DanswerRedisLocks.CHECK_CONNECTOR_EXTERNAL_GROUP_SYNC_BEAT_LOCK,
-        timeout=CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT,
-    )
-
-    try:
-        # these tasks should never overlap
-        if not lock_beat.acquire(blocking=False):
-            return
-
-        cc_pair_ids_to_sync: list[int] = []
-        with get_session_with_tenant(tenant_id) as db_session:
-            cc_pairs = get_all_auto_sync_cc_pairs(db_session)
-
-            for cc_pair in cc_pairs:
-                if _is_external_group_sync_due(cc_pair):
-                    cc_pair_ids_to_sync.append(cc_pair.id)
-
-        for cc_pair_id in cc_pair_ids_to_sync:
-            tasks_created = try_creating_external_group_sync_task(
-                self.app, cc_pair_id, r, tenant_id
-            )
-            if not tasks_created:
-                continue
-
-            task_logger.info(f"External group sync queued: cc_pair={cc_pair_id}")
-    except SoftTimeLimitExceeded:
-        task_logger.info(
-            "Soft time limit exceeded, task is being terminated gracefully."
-        )
-    except Exception:
-        task_logger.exception(f"Unexpected exception: tenant={tenant_id}")
-    finally:
-        if lock_beat.owned():
-            lock_beat.release()
-
-
-def try_creating_external_group_sync_task(
-    app: Celery,
-    cc_pair_id: int,
-    r: Redis,
-    tenant_id: str | None,
-) -> int | None:
-    """Returns an int if syncing is needed. The int represents the number of sync tasks generated.
-    Returns None if no syncing is required."""
-    redis_connector = RedisConnector(tenant_id, cc_pair_id)
-
-    LOCK_TIMEOUT = 30
-
-    lock = r.lock(
-        DANSWER_REDIS_FUNCTION_LOCK_PREFIX + "try_generate_external_group_sync_tasks",
-        timeout=LOCK_TIMEOUT,
-    )
-
-    acquired = lock.acquire(blocking_timeout=LOCK_TIMEOUT / 2)
-    if not acquired:
-        return None
-
-    try:
-        # Dont kick off a new sync if the previous one is still running
-        if redis_connector.external_group_sync.fenced:
-            return None
-
-        redis_connector.external_group_sync.generator_clear()
-        redis_connector.external_group_sync.taskset_clear()
-
-        custom_task_id = f"{redis_connector.external_group_sync.taskset_key}_{uuid4()}"
-
-        result = app.send_task(
-            DanswerCeleryTask.CONNECTOR_EXTERNAL_GROUP_SYNC_GENERATOR_TASK,
-            kwargs=dict(
-                cc_pair_id=cc_pair_id,
-                tenant_id=tenant_id,
-            ),
-            queue=DanswerCeleryQueues.CONNECTOR_EXTERNAL_GROUP_SYNC,
-            task_id=custom_task_id,
-            priority=DanswerCeleryPriority.HIGH,
-        )
-
-        payload = RedisConnectorExternalGroupSyncPayload(
-            started=datetime.now(timezone.utc),
-            celery_task_id=result.id,
-        )
-
-        redis_connector.external_group_sync.set_fence(payload)
-
-    except Exception:
-        task_logger.exception(
-            f"Unexpected exception while trying to create external group sync task: cc_pair={cc_pair_id}"
-        )
-        return None
-    finally:
-        if lock.owned():
-            lock.release()
-
-    return 1
-
-
-@shared_task(
-    name=DanswerCeleryTask.CONNECTOR_EXTERNAL_GROUP_SYNC_GENERATOR_TASK,
-    acks_late=False,
-    soft_time_limit=JOB_TIMEOUT,
-    track_started=True,
-    trail=False,
-    bind=True,
-)
-def connector_external_group_sync_generator_task(
-    self: Task,
-    cc_pair_id: int,
-    tenant_id: str | None,
-) -> None:
-    """
-    Permission sync task that handles external group syncing for a given connector credential pair
-    This task assumes that the task has already been properly fenced
-    """
-
-    redis_connector = RedisConnector(tenant_id, cc_pair_id)
-
-    r = get_redis_client(tenant_id=tenant_id)
-
-    lock: RedisLock = r.lock(
-        DanswerRedisLocks.CONNECTOR_EXTERNAL_GROUP_SYNC_LOCK_PREFIX
-        + f"_{redis_connector.id}",
-        timeout=CELERY_EXTERNAL_GROUP_SYNC_LOCK_TIMEOUT,
-    )
-
-    try:
-        acquired = lock.acquire(blocking=False)
-        if not acquired:
-            task_logger.warning(
-                f"External group sync task already running, exiting...: cc_pair={cc_pair_id}"
-            )
-            return None
-
-        with get_session_with_tenant(tenant_id) as db_session:
-            cc_pair = get_connector_credential_pair_from_id(cc_pair_id, db_session)
-            if cc_pair is None:
-                raise ValueError(
-                    f"No connector credential pair found for id: {cc_pair_id}"
-                )
-
-            source_type = cc_pair.connector.source
-
-            ext_group_sync_func = GROUP_PERMISSIONS_FUNC_MAP.get(source_type)
-            if ext_group_sync_func is None:
-                raise ValueError(
-                    f"No external group sync func found for {source_type} for cc_pair: {cc_pair_id}"
-                )
-
-            logger.info(
-                f"Syncing external groups for {source_type} for cc_pair: {cc_pair_id}"
-            )
-
-            external_user_groups: list[ExternalUserGroup] = ext_group_sync_func(cc_pair)
-
-            logger.info(
-                f"Syncing {len(external_user_groups)} external user groups for {source_type}"
-            )
-
-            replace_user__ext_group_for_cc_pair(
-                db_session=db_session,
-                cc_pair_id=cc_pair.id,
-                group_defs=external_user_groups,
-                source=cc_pair.connector.source,
-            )
-            logger.info(
-                f"Synced {len(external_user_groups)} external user groups for {source_type}"
-            )
-
-            mark_cc_pair_as_external_group_synced(db_session, cc_pair.id)
-    except Exception as e:
-        task_logger.exception(
-            f"Failed to run external group sync: cc_pair={cc_pair_id}"
-        )
-
-        redis_connector.external_group_sync.generator_clear()
-        redis_connector.external_group_sync.taskset_clear()
-        raise e
-    finally:
-        # we always want to clear the fence after the task is done or failed so it doesn't get stuck
-        redis_connector.external_group_sync.set_fence(None)
-        if lock.owned():
-            lock.release()

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

@@ -1,886 +0,0 @@
-from datetime import datetime
-from datetime import timezone
-from http import HTTPStatus
-from time import sleep
-
-import redis
-import sentry_sdk
-from celery import Celery
-from celery import shared_task
-from celery import Task
-from celery.exceptions import SoftTimeLimitExceeded
-from redis import Redis
-from redis.exceptions import LockError
-from redis.lock import Lock as RedisLock
-from sqlalchemy.orm import Session
-
-from danswer.background.celery.apps.app_base import task_logger
-from danswer.background.indexing.job_client import SimpleJobClient
-from danswer.background.indexing.run_indexing import run_indexing_entrypoint
-from danswer.configs.app_configs import DISABLE_INDEX_UPDATE_ON_SWAP
-from danswer.configs.constants import CELERY_INDEXING_LOCK_TIMEOUT
-from danswer.configs.constants import CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT
-from danswer.configs.constants import DANSWER_REDIS_FUNCTION_LOCK_PREFIX
-from danswer.configs.constants import DanswerCeleryPriority
-from danswer.configs.constants import DanswerCeleryQueues
-from danswer.configs.constants import DanswerCeleryTask
-from danswer.configs.constants import DanswerRedisLocks
-from danswer.configs.constants import DocumentSource
-from danswer.db.connector import mark_ccpair_with_indexing_trigger
-from danswer.db.connector_credential_pair import fetch_connector_credential_pairs
-from danswer.db.connector_credential_pair import get_connector_credential_pair_from_id
-from danswer.db.engine import get_db_current_time
-from danswer.db.engine import get_session_with_tenant
-from danswer.db.enums import ConnectorCredentialPairStatus
-from danswer.db.enums import IndexingMode
-from danswer.db.enums import IndexingStatus
-from danswer.db.enums import IndexModelStatus
-from danswer.db.index_attempt import create_index_attempt
-from danswer.db.index_attempt import delete_index_attempt
-from danswer.db.index_attempt import get_all_index_attempts_by_status
-from danswer.db.index_attempt import get_index_attempt
-from danswer.db.index_attempt import get_last_attempt_for_cc_pair
-from danswer.db.index_attempt import mark_attempt_canceled
-from danswer.db.index_attempt import mark_attempt_failed
-from danswer.db.models import ConnectorCredentialPair
-from danswer.db.models import IndexAttempt
-from danswer.db.models import SearchSettings
-from danswer.db.search_settings import get_active_search_settings
-from danswer.db.search_settings import get_current_search_settings
-from danswer.db.swap_index import check_index_swap
-from danswer.indexing.indexing_heartbeat import IndexingHeartbeatInterface
-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.redis.redis_connector import RedisConnector
-from danswer.redis.redis_connector_index import RedisConnectorIndex
-from danswer.redis.redis_connector_index import RedisConnectorIndexPayload
-from danswer.redis.redis_pool import get_redis_client
-from danswer.utils.logger import setup_logger
-from danswer.utils.variable_functionality import global_version
-from shared_configs.configs import INDEXING_MODEL_SERVER_HOST
-from shared_configs.configs import INDEXING_MODEL_SERVER_PORT
-from shared_configs.configs import MULTI_TENANT
-from shared_configs.configs import SENTRY_DSN
-
-logger = setup_logger()
-
-
-class IndexingCallback(IndexingHeartbeatInterface):
-    def __init__(
-        self,
-        stop_key: str,
-        generator_progress_key: str,
-        redis_lock: RedisLock,
-        redis_client: Redis,
-    ):
-        super().__init__()
-        self.redis_lock: RedisLock = redis_lock
-        self.stop_key: str = stop_key
-        self.generator_progress_key: str = generator_progress_key
-        self.redis_client = redis_client
-        self.started: datetime = datetime.now(timezone.utc)
-        self.redis_lock.reacquire()
-
-        self.last_tag: str = "IndexingCallback.__init__"
-        self.last_lock_reacquire: datetime = datetime.now(timezone.utc)
-
-    def should_stop(self) -> bool:
-        if self.redis_client.exists(self.stop_key):
-            return True
-        return False
-
-    def progress(self, tag: str, amount: int) -> None:
-        try:
-            self.redis_lock.reacquire()
-            self.last_tag = tag
-            self.last_lock_reacquire = datetime.now(timezone.utc)
-        except LockError:
-            logger.exception(
-                f"IndexingCallback - lock.reacquire exceptioned. "
-                f"lock_timeout={self.redis_lock.timeout} "
-                f"start={self.started} "
-                f"last_tag={self.last_tag} "
-                f"last_reacquired={self.last_lock_reacquire} "
-                f"now={datetime.now(timezone.utc)}"
-            )
-            raise
-
-        self.redis_client.incrby(self.generator_progress_key, amount)
-
-
-def get_unfenced_index_attempt_ids(db_session: Session, r: redis.Redis) -> list[int]:
-    """Gets a list of unfenced index attempts. Should not be possible, so we'd typically
-    want to clean them up.
-
-    Unfenced = attempt not in terminal state and fence does not exist.
-    """
-    unfenced_attempts: list[int] = []
-
-    # inner/outer/inner double check pattern to avoid race conditions when checking for
-    # bad state
-    # inner = index_attempt in non terminal state
-    # outer = r.fence_key down
-
-    # check the db for index attempts in a non terminal state
-    attempts: list[IndexAttempt] = []
-    attempts.extend(
-        get_all_index_attempts_by_status(IndexingStatus.NOT_STARTED, db_session)
-    )
-    attempts.extend(
-        get_all_index_attempts_by_status(IndexingStatus.IN_PROGRESS, db_session)
-    )
-
-    for attempt in attempts:
-        fence_key = RedisConnectorIndex.fence_key_with_ids(
-            attempt.connector_credential_pair_id, attempt.search_settings_id
-        )
-
-        # if the fence is down / doesn't exist, possible error but not confirmed
-        if r.exists(fence_key):
-            continue
-
-        # Between the time the attempts are first looked up and the time we see the fence down,
-        # the attempt may have completed and taken down the fence normally.
-
-        # We need to double check that the index attempt is still in a non terminal state
-        # and matches the original state, which confirms we are really in a bad state.
-        attempt_2 = get_index_attempt(db_session, attempt.id)
-        if not attempt_2:
-            continue
-
-        if attempt.status != attempt_2.status:
-            continue
-
-        unfenced_attempts.append(attempt.id)
-
-    return unfenced_attempts
-
-
-@shared_task(
-    name=DanswerCeleryTask.CHECK_FOR_INDEXING,
-    soft_time_limit=300,
-    bind=True,
-)
-def check_for_indexing(self: Task, *, tenant_id: str | None) -> int | None:
-    tasks_created = 0
-    locked = False
-    r = get_redis_client(tenant_id=tenant_id)
-
-    lock_beat: RedisLock = r.lock(
-        DanswerRedisLocks.CHECK_INDEXING_BEAT_LOCK,
-        timeout=CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT,
-    )
-
-    try:
-        # these tasks should never overlap
-        if not lock_beat.acquire(blocking=False):
-            return None
-
-        locked = True
-
-        # check for search settings swap
-        with get_session_with_tenant(tenant_id=tenant_id) as db_session:
-            old_search_settings = check_index_swap(db_session=db_session)
-            current_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 current_search_settings.provider_type is None and not MULTI_TENANT:
-                if old_search_settings:
-                    embedding_model = EmbeddingModel.from_db_model(
-                        search_settings=current_search_settings,
-                        server_host=INDEXING_MODEL_SERVER_HOST,
-                        server_port=INDEXING_MODEL_SERVER_PORT,
-                    )
-
-                    # only warm up if search settings were changed
-                    warm_up_bi_encoder(
-                        embedding_model=embedding_model,
-                    )
-
-        # gather cc_pair_ids
-        cc_pair_ids: list[int] = []
-        with get_session_with_tenant(tenant_id) as db_session:
-            lock_beat.reacquire()
-            cc_pairs = fetch_connector_credential_pairs(db_session)
-            for cc_pair_entry in cc_pairs:
-                cc_pair_ids.append(cc_pair_entry.id)
-
-        # kick off index attempts
-        for cc_pair_id in cc_pair_ids:
-            lock_beat.reacquire()
-
-            redis_connector = RedisConnector(tenant_id, cc_pair_id)
-            with get_session_with_tenant(tenant_id) as db_session:
-                search_settings_list: list[SearchSettings] = get_active_search_settings(
-                    db_session
-                )
-                for search_settings_instance in search_settings_list:
-                    redis_connector_index = redis_connector.new_index(
-                        search_settings_instance.id
-                    )
-                    if redis_connector_index.fenced:
-                        continue
-
-                    cc_pair = get_connector_credential_pair_from_id(
-                        cc_pair_id, db_session
-                    )
-                    if not cc_pair:
-                        continue
-
-                    last_attempt = get_last_attempt_for_cc_pair(
-                        cc_pair.id, search_settings_instance.id, db_session
-                    )
-
-                    search_settings_primary = False
-                    if search_settings_instance.id == search_settings_list[0].id:
-                        search_settings_primary = True
-
-                    if not _should_index(
-                        cc_pair=cc_pair,
-                        last_index=last_attempt,
-                        search_settings_instance=search_settings_instance,
-                        search_settings_primary=search_settings_primary,
-                        secondary_index_building=len(search_settings_list) > 1,
-                        db_session=db_session,
-                    ):
-                        continue
-
-                    reindex = False
-                    if search_settings_instance.id == search_settings_list[0].id:
-                        # the indexing trigger is only checked and cleared with the primary search settings
-                        if cc_pair.indexing_trigger is not None:
-                            if cc_pair.indexing_trigger == IndexingMode.REINDEX:
-                                reindex = True
-
-                            task_logger.info(
-                                f"Connector indexing manual trigger detected: "
-                                f"cc_pair={cc_pair.id} "
-                                f"search_settings={search_settings_instance.id} "
-                                f"indexing_mode={cc_pair.indexing_trigger}"
-                            )
-
-                            mark_ccpair_with_indexing_trigger(
-                                cc_pair.id, None, db_session
-                            )
-
-                    # using a task queue and only allowing one task per cc_pair/search_setting
-                    # prevents us from starving out certain attempts
-                    attempt_id = try_creating_indexing_task(
-                        self.app,
-                        cc_pair,
-                        search_settings_instance,
-                        reindex,
-                        db_session,
-                        r,
-                        tenant_id,
-                    )
-                    if attempt_id:
-                        task_logger.info(
-                            f"Connector indexing queued: "
-                            f"index_attempt={attempt_id} "
-                            f"cc_pair={cc_pair.id} "
-                            f"search_settings={search_settings_instance.id}"
-                        )
-                        tasks_created += 1
-
-        # Fail any index attempts in the DB that don't have fences
-        # This shouldn't ever happen!
-        with get_session_with_tenant(tenant_id) as db_session:
-            unfenced_attempt_ids = get_unfenced_index_attempt_ids(db_session, r)
-            for attempt_id in unfenced_attempt_ids:
-                lock_beat.reacquire()
-
-                attempt = get_index_attempt(db_session, attempt_id)
-                if not attempt:
-                    continue
-
-                failure_reason = (
-                    f"Unfenced index attempt found in DB: "
-                    f"index_attempt={attempt.id} "
-                    f"cc_pair={attempt.connector_credential_pair_id} "
-                    f"search_settings={attempt.search_settings_id}"
-                )
-                task_logger.error(failure_reason)
-                mark_attempt_failed(
-                    attempt.id, db_session, failure_reason=failure_reason
-                )
-    except SoftTimeLimitExceeded:
-        task_logger.info(
-            "Soft time limit exceeded, task is being terminated gracefully."
-        )
-    except Exception:
-        task_logger.exception(f"Unexpected exception: tenant={tenant_id}")
-    finally:
-        if locked:
-            if lock_beat.owned():
-                lock_beat.release()
-            else:
-                task_logger.error(
-                    "check_for_indexing - Lock not owned on completion: "
-                    f"tenant={tenant_id}"
-                )
-
-    return tasks_created
-
-
-def _should_index(
-    cc_pair: ConnectorCredentialPair,
-    last_index: IndexAttempt | None,
-    search_settings_instance: SearchSettings,
-    search_settings_primary: bool,
-    secondary_index_building: bool,
-    db_session: Session,
-) -> bool:
-    """Checks various global settings and past indexing attempts to determine if
-    we should try to start indexing the cc pair / search setting combination.
-
-    Note that tactical checks such as preventing overlap with a currently running task
-    are not handled here.
-
-    Return True if we should try to index, False if not.
-    """
-    connector = cc_pair.connector
-
-    # uncomment for debugging
-    # task_logger.info(f"_should_index: "
-    #                  f"cc_pair={cc_pair.id} "
-    #                  f"connector={cc_pair.connector_id} "
-    #                  f"refresh_freq={connector.refresh_freq}")
-
-    # don't kick off indexing for `NOT_APPLICABLE` sources
-    if connector.source == DocumentSource.NOT_APPLICABLE:
-        return False
-
-    # User can still manually create single indexing attempts via the UI for the
-    # currently in use index
-    if DISABLE_INDEX_UPDATE_ON_SWAP:
-        if (
-            search_settings_instance.status == IndexModelStatus.PRESENT
-            and secondary_index_building
-        ):
-            return False
-
-    # When switching over models, always index at least once
-    if search_settings_instance.status == IndexModelStatus.FUTURE:
-        if last_index:
-            # No new index if the last index attempt succeeded
-            # Once is enough. The model will never be able to swap otherwise.
-            if last_index.status == IndexingStatus.SUCCESS:
-                return False
-
-            # No new index if the last index attempt is waiting to start
-            if last_index.status == IndexingStatus.NOT_STARTED:
-                return False
-
-            # No new index if the last index attempt is running
-            if last_index.status == IndexingStatus.IN_PROGRESS:
-                return False
-        else:
-            if (
-                connector.id == 0 or connector.source == DocumentSource.INGESTION_API
-            ):  # Ingestion API
-                return False
-        return True
-
-    # If the connector is paused or is the ingestion API, don't index
-    # NOTE: during an embedding model switch over, the following logic
-    # is bypassed by the above check for a future model
-    if (
-        not cc_pair.status.is_active()
-        or connector.id == 0
-        or connector.source == DocumentSource.INGESTION_API
-    ):
-        return False
-
-    if search_settings_primary:
-        if cc_pair.indexing_trigger is not None:
-            # if a manual indexing trigger is on the cc pair, honor it for primary search settings
-            return True
-
-    # if no attempt has ever occurred, we should index regardless of refresh_freq
-    if not last_index:
-        return True
-
-    if connector.refresh_freq is None:
-        return False
-
-    current_db_time = get_db_current_time(db_session)
-    time_since_index = current_db_time - last_index.time_updated
-    if time_since_index.total_seconds() < connector.refresh_freq:
-        return False
-
-    return True
-
-
-def try_creating_indexing_task(
-    celery_app: Celery,
-    cc_pair: ConnectorCredentialPair,
-    search_settings: SearchSettings,
-    reindex: bool,
-    db_session: Session,
-    r: Redis,
-    tenant_id: str | None,
-) -> int | None:
-    """Checks for any conditions that should block the indexing task from being
-    created, then creates the task.
-
-    Does not check for scheduling related conditions as this function
-    is used to trigger indexing immediately.
-    """
-
-    LOCK_TIMEOUT = 30
-    index_attempt_id: int | None = None
-
-    # we need to serialize any attempt to trigger indexing since it can be triggered
-    # either via celery beat or manually (API call)
-    lock: RedisLock = r.lock(
-        DANSWER_REDIS_FUNCTION_LOCK_PREFIX + "try_creating_indexing_task",
-        timeout=LOCK_TIMEOUT,
-    )
-
-    acquired = lock.acquire(blocking_timeout=LOCK_TIMEOUT / 2)
-    if not acquired:
-        return None
-
-    try:
-        redis_connector = RedisConnector(tenant_id, cc_pair.id)
-        redis_connector_index = redis_connector.new_index(search_settings.id)
-
-        # skip if already indexing
-        if redis_connector_index.fenced:
-            return None
-
-        # skip indexing if the cc_pair is deleting
-        if redis_connector.delete.fenced:
-            return None
-
-        db_session.refresh(cc_pair)
-        if cc_pair.status == ConnectorCredentialPairStatus.DELETING:
-            return None
-
-        # add a long running generator task to the queue
-        redis_connector_index.generator_clear()
-
-        # set a basic fence to start
-        payload = RedisConnectorIndexPayload(
-            index_attempt_id=None,
-            started=None,
-            submitted=datetime.now(timezone.utc),
-            celery_task_id=None,
-        )
-
-        redis_connector_index.set_fence(payload)
-
-        # create the index attempt for tracking purposes
-        # code elsewhere checks for index attempts without an associated redis key
-        # and cleans them up
-        # therefore we must create the attempt and the task after the fence goes up
-        index_attempt_id = create_index_attempt(
-            cc_pair.id,
-            search_settings.id,
-            from_beginning=reindex,
-            db_session=db_session,
-        )
-
-        custom_task_id = redis_connector_index.generate_generator_task_id()
-
-        # when the task is sent, we have yet to finish setting up the fence
-        # therefore, the task must contain code that blocks until the fence is ready
-        result = celery_app.send_task(
-            DanswerCeleryTask.CONNECTOR_INDEXING_PROXY_TASK,
-            kwargs=dict(
-                index_attempt_id=index_attempt_id,
-                cc_pair_id=cc_pair.id,
-                search_settings_id=search_settings.id,
-                tenant_id=tenant_id,
-            ),
-            queue=DanswerCeleryQueues.CONNECTOR_INDEXING,
-            task_id=custom_task_id,
-            priority=DanswerCeleryPriority.MEDIUM,
-        )
-        if not result:
-            raise RuntimeError("send_task for connector_indexing_proxy_task failed.")
-
-        # now fill out the fence with the rest of the data
-        payload.index_attempt_id = index_attempt_id
-        payload.celery_task_id = result.id
-        redis_connector_index.set_fence(payload)
-    except Exception:
-        task_logger.exception(
-            f"try_creating_indexing_task - Unexpected exception: "
-            f"tenant={tenant_id} "
-            f"cc_pair={cc_pair.id} "
-            f"search_settings={search_settings.id}"
-        )
-
-        if index_attempt_id is not None:
-            delete_index_attempt(db_session, index_attempt_id)
-        redis_connector_index.set_fence(None)
-        return None
-    finally:
-        if lock.owned():
-            lock.release()
-
-    return index_attempt_id
-
-
-@shared_task(
-    name=DanswerCeleryTask.CONNECTOR_INDEXING_PROXY_TASK,
-    bind=True,
-    acks_late=False,
-    track_started=True,
-)
-def connector_indexing_proxy_task(
-    self: Task,
-    index_attempt_id: int,
-    cc_pair_id: int,
-    search_settings_id: int,
-    tenant_id: str | None,
-) -> None:
-    """celery tasks are forked, but forking is unstable.  This proxies work to a spawned task."""
-    task_logger.info(
-        f"Indexing watchdog - starting: attempt={index_attempt_id} "
-        f"tenant={tenant_id} "
-        f"cc_pair={cc_pair_id} "
-        f"search_settings={search_settings_id}"
-    )
-
-    if not self.request.id:
-        task_logger.error("self.request.id is None!")
-
-    client = SimpleJobClient()
-
-    job = client.submit(
-        connector_indexing_task_wrapper,
-        index_attempt_id,
-        cc_pair_id,
-        search_settings_id,
-        tenant_id,
-        global_version.is_ee_version(),
-        pure=False,
-    )
-
-    if not job:
-        task_logger.info(
-            f"Indexing watchdog - spawn failed: attempt={index_attempt_id} "
-            f"tenant={tenant_id} "
-            f"cc_pair={cc_pair_id} "
-            f"search_settings={search_settings_id}"
-        )
-        return
-
-    task_logger.info(
-        f"Indexing watchdog - spawn succeeded: attempt={index_attempt_id} "
-        f"tenant={tenant_id} "
-        f"cc_pair={cc_pair_id} "
-        f"search_settings={search_settings_id}"
-    )
-
-    redis_connector = RedisConnector(tenant_id, cc_pair_id)
-    redis_connector_index = redis_connector.new_index(search_settings_id)
-
-    while True:
-        sleep(5)
-
-        if self.request.id and redis_connector_index.terminating(self.request.id):
-            task_logger.warning(
-                "Indexing watchdog - termination signal detected: "
-                f"attempt={index_attempt_id} "
-                f"tenant={tenant_id} "
-                f"cc_pair={cc_pair_id} "
-                f"search_settings={search_settings_id}"
-            )
-
-            try:
-                with get_session_with_tenant(tenant_id) as db_session:
-                    mark_attempt_canceled(
-                        index_attempt_id,
-                        db_session,
-                        "Connector termination signal detected",
-                    )
-            finally:
-                # if the DB exceptions, we'll just get an unfriendly failure message
-                # in the UI instead of the cancellation message
-                logger.exception(
-                    "Indexing watchdog - transient exception marking index attempt as canceled: "
-                    f"attempt={index_attempt_id} "
-                    f"tenant={tenant_id} "
-                    f"cc_pair={cc_pair_id} "
-                    f"search_settings={search_settings_id}"
-                )
-
-                job.cancel()
-
-            break
-
-        if not job.done():
-            # if the spawned task is still running, restart the check once again
-            # if the index attempt is not in a finished status
-            try:
-                with get_session_with_tenant(tenant_id) as db_session:
-                    index_attempt = get_index_attempt(
-                        db_session=db_session, index_attempt_id=index_attempt_id
-                    )
-
-                    if not index_attempt:
-                        continue
-
-                    if not index_attempt.is_finished():
-                        continue
-            except Exception:
-                # if the DB exceptioned, just restart the check.
-                # polling the index attempt status doesn't need to be strongly consistent
-                logger.exception(
-                    "Indexing watchdog - transient exception looking up index attempt: "
-                    f"attempt={index_attempt_id} "
-                    f"tenant={tenant_id} "
-                    f"cc_pair={cc_pair_id} "
-                    f"search_settings={search_settings_id}"
-                )
-                continue
-
-        if job.status == "error":
-            task_logger.error(
-                "Indexing watchdog - spawned task exceptioned: "
-                f"attempt={index_attempt_id} "
-                f"tenant={tenant_id} "
-                f"cc_pair={cc_pair_id} "
-                f"search_settings={search_settings_id} "
-                f"error={job.exception()}"
-            )
-
-        job.release()
-        break
-
-    task_logger.info(
-        f"Indexing watchdog - finished: attempt={index_attempt_id} "
-        f"tenant={tenant_id} "
-        f"cc_pair={cc_pair_id} "
-        f"search_settings={search_settings_id}"
-    )
-    return
-
-
-def connector_indexing_task_wrapper(
-    index_attempt_id: int,
-    cc_pair_id: int,
-    search_settings_id: int,
-    tenant_id: str | None,
-    is_ee: bool,
-) -> int | None:
-    """Just wraps connector_indexing_task so we can log any exceptions before
-    re-raising it."""
-    result: int | None = None
-
-    try:
-        result = connector_indexing_task(
-            index_attempt_id,
-            cc_pair_id,
-            search_settings_id,
-            tenant_id,
-            is_ee,
-        )
-    except:
-        logger.exception(
-            f"connector_indexing_task exceptioned: "
-            f"tenant={tenant_id} "
-            f"index_attempt={index_attempt_id} "
-            f"cc_pair={cc_pair_id} "
-            f"search_settings={search_settings_id}"
-        )
-        raise
-
-    return result
-
-
-def connector_indexing_task(
-    index_attempt_id: int,
-    cc_pair_id: int,
-    search_settings_id: int,
-    tenant_id: str | None,
-    is_ee: bool,
-) -> int | None:
-    """Indexing task. For a cc pair, this task pulls all document IDs from the source
-    and compares those IDs to locally stored documents and deletes all locally stored IDs missing
-    from the most recently pulled document ID list
-
-    acks_late must be set to False. Otherwise, celery's visibility timeout will
-    cause any task that runs longer than the timeout to be redispatched by the broker.
-    There appears to be no good workaround for this, so we need to handle redispatching
-    manually.
-
-    Returns None if the task did not run (possibly due to a conflict).
-    Otherwise, returns an int >= 0 representing the number of indexed docs.
-
-    NOTE: if an exception is raised out of this task, the primary worker will detect
-    that the task transitioned to a "READY" state but the generator_complete_key doesn't exist.
-    This will cause the primary worker to abort the indexing attempt and clean up.
-    """
-
-    # Since connector_indexing_proxy_task spawns a new process using this function as
-    # the entrypoint, we init Sentry here.
-    if SENTRY_DSN:
-        sentry_sdk.init(
-            dsn=SENTRY_DSN,
-            traces_sample_rate=0.1,
-        )
-        logger.info("Sentry initialized")
-    else:
-        logger.debug("Sentry DSN not provided, skipping Sentry initialization")
-
-    logger.info(
-        f"Indexing spawned task starting: "
-        f"attempt={index_attempt_id} "
-        f"tenant={tenant_id} "
-        f"cc_pair={cc_pair_id} "
-        f"search_settings={search_settings_id}"
-    )
-
-    attempt_found = False
-    n_final_progress: int | None = None
-
-    redis_connector = RedisConnector(tenant_id, cc_pair_id)
-    redis_connector_index = redis_connector.new_index(search_settings_id)
-
-    r = get_redis_client(tenant_id=tenant_id)
-
-    if redis_connector.delete.fenced:
-        raise RuntimeError(
-            f"Indexing will not start because connector deletion is in progress: "
-            f"attempt={index_attempt_id} "
-            f"cc_pair={cc_pair_id} "
-            f"fence={redis_connector.delete.fence_key}"
-        )
-
-    if redis_connector.stop.fenced:
-        raise RuntimeError(
-            f"Indexing will not start because a connector stop signal was detected: "
-            f"attempt={index_attempt_id} "
-            f"cc_pair={cc_pair_id} "
-            f"fence={redis_connector.stop.fence_key}"
-        )
-
-    while True:
-        if not redis_connector_index.fenced:  # The fence must exist
-            raise ValueError(
-                f"connector_indexing_task - fence not found: fence={redis_connector_index.fence_key}"
-            )
-
-        payload = redis_connector_index.payload  # The payload must exist
-        if not payload:
-            raise ValueError("connector_indexing_task: payload invalid or not found")
-
-        if payload.index_attempt_id is None or payload.celery_task_id is None:
-            logger.info(
-                f"connector_indexing_task - Waiting for fence: fence={redis_connector_index.fence_key}"
-            )
-            sleep(1)
-            continue
-
-        if payload.index_attempt_id != index_attempt_id:
-            raise ValueError(
-                f"connector_indexing_task - id mismatch. Task may be left over from previous run.: "
-                f"task_index_attempt={index_attempt_id} "
-                f"payload_index_attempt={payload.index_attempt_id}"
-            )
-
-        logger.info(
-            f"connector_indexing_task - Fence found, continuing...: fence={redis_connector_index.fence_key}"
-        )
-        break
-
-    # set thread_local=False since we don't control what thread the indexing/pruning
-    # might run our callback with
-    lock: RedisLock = r.lock(
-        redis_connector_index.generator_lock_key,
-        timeout=CELERY_INDEXING_LOCK_TIMEOUT,
-        thread_local=False,
-    )
-
-    acquired = lock.acquire(blocking=False)
-    if not acquired:
-        logger.warning(
-            f"Indexing task already running, exiting...: "
-            f"index_attempt={index_attempt_id} cc_pair={cc_pair_id} search_settings={search_settings_id}"
-        )
-        return None
-
-    payload.started = datetime.now(timezone.utc)
-    redis_connector_index.set_fence(payload)
-
-    try:
-        with get_session_with_tenant(tenant_id) as db_session:
-            attempt = get_index_attempt(db_session, index_attempt_id)
-            if not attempt:
-                raise ValueError(
-                    f"Index attempt not found: index_attempt={index_attempt_id}"
-                )
-            attempt_found = True
-
-            cc_pair = get_connector_credential_pair_from_id(
-                cc_pair_id=cc_pair_id,
-                db_session=db_session,
-            )
-
-            if not cc_pair:
-                raise ValueError(f"cc_pair not found: cc_pair={cc_pair_id}")
-
-            if not cc_pair.connector:
-                raise ValueError(
-                    f"Connector not found: cc_pair={cc_pair_id} connector={cc_pair.connector_id}"
-                )
-
-            if not cc_pair.credential:
-                raise ValueError(
-                    f"Credential not found: cc_pair={cc_pair_id} credential={cc_pair.credential_id}"
-                )
-
-        # define a callback class
-        callback = IndexingCallback(
-            redis_connector.stop.fence_key,
-            redis_connector_index.generator_progress_key,
-            lock,
-            r,
-        )
-
-        logger.info(
-            f"Indexing spawned task running entrypoint: attempt={index_attempt_id} "
-            f"tenant={tenant_id} "
-            f"cc_pair={cc_pair_id} "
-            f"search_settings={search_settings_id}"
-        )
-
-        run_indexing_entrypoint(
-            index_attempt_id,
-            tenant_id,
-            cc_pair_id,
-            is_ee,
-            callback=callback,
-        )
-
-        # get back the total number of indexed docs and return it
-        n_final_progress = redis_connector_index.get_progress()
-        redis_connector_index.set_generator_complete(HTTPStatus.OK.value)
-    except Exception as e:
-        logger.exception(
-            f"Indexing spawned task failed: attempt={index_attempt_id} "
-            f"tenant={tenant_id} "
-            f"cc_pair={cc_pair_id} "
-            f"search_settings={search_settings_id}"
-        )
-        if attempt_found:
-            with get_session_with_tenant(tenant_id) as db_session:
-                mark_attempt_failed(index_attempt_id, db_session, failure_reason=str(e))
-
-        raise e
-    finally:
-        if lock.owned():
-            lock.release()
-
-    logger.info(
-        f"Indexing spawned task finished: attempt={index_attempt_id} "
-        f"tenant={tenant_id} "
-        f"cc_pair={cc_pair_id} "
-        f"search_settings={search_settings_id}"
-    )
-    return n_final_progress