nit

* Various fixes/improvements to document counting

* Add new column + index

* Avoid double scan

* comment fixes

* Fix revision history

* Fix IT

* Fix IT

* Fix migration

* Rebase

.github/pull_request_template.md

@@ -1,25 +1,15 @@
 ## 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]
 
+## Backporting (check the box to trigger backport action)
 
-## Accepted Risk
-[Any know risks or failure modes to point out to reviewers]
+Note: You have to check that the action passes, otherwise resolve the conflicts manually and tag the patches.
 
-
-## Related Issue(s)
-[If applicable, link to the issue(s) this PR addresses]
-
-
-## 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
+- [ ] This PR should be backported (make sure to check that the backport attempt succeeds)
+- [ ] I have included a link to a Linear ticket in my description.
+- [ ] [Optional] Override Linear Check

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

@@ -3,61 +3,61 @@ name: Build and Push Backend Image on Tag
 on:
   push:
     tags:
-      - '*'
+      - "*"
 
 env:
-  REGISTRY_IMAGE: danswer/danswer-backend
+  REGISTRY_IMAGE: ${{ contains(github.ref_name, 'cloud') && 'onyxdotapp/onyx-backend-cloud' || 'onyxdotapp/onyx-backend' }}
   LATEST_TAG: ${{ contains(github.ref_name, 'latest') }}
-  
+
 jobs:
   build-and-push:
-    # TODO: investigate a matrix build like the web container 
+    # TODO: investigate a matrix build like the web container
     # See https://runs-on.com/runners/linux/
-    runs-on: [runs-on,runner=8cpu-linux-x64,"run-id=${{ github.run_id }}"]
+    runs-on: [runs-on, runner=8cpu-linux-x64, "run-id=${{ github.run_id }}"]
 
     steps:
-    - name: Checkout code
-      uses: actions/checkout@v4
+      - name: Checkout code
+        uses: actions/checkout@v4
 
-    - name: Set up Docker Buildx
-      uses: docker/setup-buildx-action@v3
+      - 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 }}
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_TOKEN }}
 
-    - name: Install build-essential
-      run: |
-        sudo apt-get update
-        sudo apt-get install -y build-essential
-          
-    - name: Backend Image Docker Build and Push
-      uses: docker/build-push-action@v5
-      with:
-        context: ./backend
-        file: ./backend/Dockerfile
-        platforms: linux/amd64,linux/arm64
-        push: true
-        tags: |
-          ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
-          ${{ env.LATEST_TAG == 'true' && format('{0}:latest', env.REGISTRY_IMAGE) || '' }}
-        build-args: |
-          DANSWER_VERSION=${{ github.ref_name }}
+      - name: Install build-essential
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y build-essential
 
-    # 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:
-        # To run locally: trivy image --severity HIGH,CRITICAL danswer/danswer-backend
-        image-ref: docker.io/${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
-        severity: 'CRITICAL,HIGH'
-        trivyignores: ./backend/.trivyignore
+      - name: Backend Image Docker Build and Push
+        uses: docker/build-push-action@v5
+        with:
+          context: ./backend
+          file: ./backend/Dockerfile
+          platforms: linux/amd64,linux/arm64
+          push: true
+          tags: |
+            ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
+            ${{ env.LATEST_TAG == 'true' && format('{0}:latest', env.REGISTRY_IMAGE) || '' }}
+          build-args: |
+            ONYX_VERSION=${{ 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
+      # 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:
+          # 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

@@ -0,0 +1,138 @@
+name: Build and Push Cloud Web Image on Tag
+# Identical to the web container build, but with correct image tag and build args
+
+on:
+  push:
+    tags:
+      - "*"
+
+env:
+  REGISTRY_IMAGE: onyxdotapp/onyx-web-server-cloud
+  LATEST_TAG: ${{ contains(github.ref_name, 'latest') }}
+
+jobs:
+  build:
+    runs-on:
+      - runs-on
+      - runner=${{ matrix.platform == 'linux/amd64' && '8cpu-linux-x64' || '8cpu-linux-arm64' }}
+      - run-id=${{ github.run_id }}
+      - tag=platform-${{ matrix.platform }}
+    strategy:
+      fail-fast: false
+      matrix:
+        platform:
+          - linux/amd64
+          - linux/arm64
+
+    steps:
+      - name: Prepare
+        run: |
+          platform=${{ matrix.platform }}
+          echo "PLATFORM_PAIR=${platform//\//-}" >> $GITHUB_ENV
+
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Docker meta
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.REGISTRY_IMAGE }}
+          tags: |
+            type=raw,value=${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
+            type=raw,value=${{ env.LATEST_TAG == 'true' && format('{0}:latest', env.REGISTRY_IMAGE) || '' }}
+
+      - 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 }}
+
+      - name: Build and push by digest
+        id: build
+        uses: docker/build-push-action@v5
+        with:
+          context: ./web
+          file: ./web/Dockerfile
+          platforms: ${{ matrix.platform }}
+          push: true
+          build-args: |
+            ONYX_VERSION=${{ 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_GTM_ENABLED=true
+            NEXT_PUBLIC_FORGOT_PASSWORD_ENABLED=true
+          # needed due to weird interactions with the builds for different platforms
+          no-cache: true
+          labels: ${{ steps.meta.outputs.labels }}
+          outputs: type=image,name=${{ env.REGISTRY_IMAGE }},push-by-digest=true,name-canonical=true,push=true
+
+      - name: Export digest
+        run: |
+          mkdir -p /tmp/digests
+          digest="${{ steps.build.outputs.digest }}"
+          touch "/tmp/digests/${digest#sha256:}"
+
+      - name: Upload digest
+        uses: actions/upload-artifact@v4
+        with:
+          name: digests-${{ env.PLATFORM_PAIR }}
+          path: /tmp/digests/*
+          if-no-files-found: error
+          retention-days: 1
+
+  merge:
+    runs-on: ubuntu-latest
+    needs:
+      - build
+    steps:
+      - name: Download digests
+        uses: actions/download-artifact@v4
+        with:
+          path: /tmp/digests
+          pattern: digests-*
+          merge-multiple: true
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Docker meta
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.REGISTRY_IMAGE }}
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_TOKEN }}
+
+      - name: Create manifest list and push
+        working-directory: /tmp/digests
+        run: |
+          docker buildx imagetools create $(jq -cr '.tags | map("-t " + .) | join(" ")' <<< "$DOCKER_METADATA_OUTPUT_JSON") \
+            $(printf '${{ env.REGISTRY_IMAGE }}@sha256:%s ' *)
+
+      - name: Inspect image
+        run: |
+          docker buildx imagetools inspect ${{ env.REGISTRY_IMAGE }}:${{ steps.meta.outputs.version }}
+
+      # 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/${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
+          severity: "CRITICAL,HIGH"

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

@@ -3,53 +3,121 @@ name: Build and Push Model Server Image on Tag
 on:
   push:
     tags:
-      - '*'
+      - "*"
 
 env:
-  REGISTRY_IMAGE: 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 }}"]
-
+  build-amd64:
+    runs-on:
+      [runs-on, runner=8cpu-linux-x64, "run-id=${{ github.run_id }}-amd64"]
     steps:
-    - name: Checkout code
-      uses: actions/checkout@v4
+      - name: Checkout code
+        uses: actions/checkout@v4
 
-    - name: Set up Docker Buildx
-      uses: docker/setup-buildx-action@v3
+      - name: System Info
+        run: |
+          df -h
+          free -h
+          docker system prune -af --volumes
 
-    - name: Login to Docker Hub
-      uses: docker/login-action@v3
-      with:
-        username: ${{ secrets.DOCKER_USERNAME }}
-        password: ${{ secrets.DOCKER_TOKEN }}
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+        with:
+          driver-opts: |
+            image=moby/buildkit:latest
+            network=host
 
-    - name: Model Server Image Docker Build and Push
-      uses: docker/build-push-action@v5
-      with:
-        context: ./backend
-        file: ./backend/Dockerfile.model_server
-        platforms: linux/amd64,linux/arm64
-        push: true
-        tags: |
-          ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
-          ${{ env.LATEST_TAG == 'true' && format('{0}:latest', env.REGISTRY_IMAGE) || '' }}
-        build-args: |
-          DANSWER_VERSION=${{ github.ref_name }}
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_TOKEN }}
 
-    # 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 }}
-        severity: 'CRITICAL,HIGH'
+      - name: Build and Push AMD64
+        uses: docker/build-push-action@v5
+        with:
+          context: ./backend
+          file: ./backend/Dockerfile.model_server
+          platforms: linux/amd64
+          push: true
+          tags: ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}-amd64
+          build-args: |
+            DANSWER_VERSION=${{ github.ref_name }}
+          outputs: type=registry
+          provenance: false
+
+  build-arm64:
+    runs-on:
+      [runs-on, runner=8cpu-linux-x64, "run-id=${{ 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]
+    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
+
+      - 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/${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
+          severity: "CRITICAL,HIGH"
+          timeout: "10m"

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

@@ -3,12 +3,12 @@ name: Build and Push Web Image on Tag
 on:
   push:
     tags:
-      - '*'
+      - "*"
 
 env:
-  REGISTRY_IMAGE: danswer/danswer-web-server
+  REGISTRY_IMAGE: onyxdotapp/onyx-web-server
   LATEST_TAG: ${{ contains(github.ref_name, 'latest') }}
-  
+
 jobs:
   build:
     runs-on:
@@ -27,11 +27,11 @@ jobs:
       - name: Prepare
         run: |
           platform=${{ matrix.platform }}
-          echo "PLATFORM_PAIR=${platform//\//-}" >> $GITHUB_ENV          
-      
+          echo "PLATFORM_PAIR=${platform//\//-}" >> $GITHUB_ENV
+
       - name: Checkout
         uses: actions/checkout@v4
-      
+
       - name: Docker meta
         id: meta
         uses: docker/metadata-action@v5
@@ -40,16 +40,16 @@ jobs:
           tags: |
             type=raw,value=${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
             type=raw,value=${{ env.LATEST_TAG == 'true' && format('{0}:latest', env.REGISTRY_IMAGE) || '' }}
-      
+
       - 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 }}
-    
+
       - name: Build and push by digest
         id: build
         uses: docker/build-push-action@v5
@@ -59,18 +59,18 @@ jobs:
           platforms: ${{ matrix.platform }}
           push: true
           build-args: |
-            DANSWER_VERSION=${{ github.ref_name }}
-          # needed due to weird interactions with the builds for different platforms  
+            ONYX_VERSION=${{ github.ref_name }}
+          # needed due to weird interactions with the builds for different platforms
           no-cache: true
           labels: ${{ steps.meta.outputs.labels }}
           outputs: type=image,name=${{ env.REGISTRY_IMAGE }},push-by-digest=true,name-canonical=true,push=true
-      
+
       - name: Export digest
         run: |
           mkdir -p /tmp/digests
           digest="${{ steps.build.outputs.digest }}"
-          touch "/tmp/digests/${digest#sha256:}"          
-      
+          touch "/tmp/digests/${digest#sha256:}"
+
       - name: Upload digest
         uses: actions/upload-artifact@v4
         with:
@@ -90,42 +90,42 @@ jobs:
           path: /tmp/digests
           pattern: digests-*
           merge-multiple: true
-      
+
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v3
-      
+
       - name: Docker meta
         id: meta
         uses: docker/metadata-action@v5
         with:
           images: ${{ env.REGISTRY_IMAGE }}
-      
+
       - name: Login to Docker Hub
         uses: docker/login-action@v3
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_TOKEN }}
-      
+
       - name: Create manifest list and push
         working-directory: /tmp/digests
         run: |
           docker buildx imagetools create $(jq -cr '.tags | map("-t " + .) | join(" ")' <<< "$DOCKER_METADATA_OUTPUT_JSON") \
-            $(printf '${{ env.REGISTRY_IMAGE }}@sha256:%s ' *)          
-      
+            $(printf '${{ env.REGISTRY_IMAGE }}@sha256:%s ' *)
+
       - name: Inspect image
         run: |
           docker buildx imagetools inspect ${{ env.REGISTRY_IMAGE }}:${{ steps.meta.outputs.version }}
 
-    # 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
+      # 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'
+          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/${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
-          severity: 'CRITICAL,HIGH'
+          severity: "CRITICAL,HIGH"

.github/workflows/docker-tag-latest.yml

@@ -7,31 +7,31 @@ on:
   workflow_dispatch:
     inputs:
       version:
-        description: 'The version (ie v0.0.1) to tag as latest'
+        description: "The version (ie v0.0.1) to tag as latest"
         required: true
 
 jobs:
   tag:
     # 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:
-    - name: Set up Docker Buildx
-      uses: docker/setup-buildx-action@v1
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v1
 
-    - name: Login to Docker Hub
-      uses: docker/login-action@v1
-      with:
-        username: ${{ secrets.DOCKER_USERNAME }}
-        password: ${{ secrets.DOCKER_TOKEN }}
+      - name: Login to Docker Hub
+        uses: docker/login-action@v1
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_TOKEN }}
 
-    - name: Enable Docker CLI experimental features
-      run: echo "DOCKER_CLI_EXPERIMENTAL=enabled" >> $GITHUB_ENV
+      - name: Enable Docker CLI experimental features
+        run: echo "DOCKER_CLI_EXPERIMENTAL=enabled" >> $GITHUB_ENV
 
-    - name: Pull, Tag and Push Web Server Image
-      run: |
-        docker buildx imagetools create -t danswer/danswer-web-server:latest danswer/danswer-web-server:${{ github.event.inputs.version }}
+      - name: Pull, Tag and Push Web Server Image
+        run: |
+          docker buildx imagetools create -t onyxdotapp/onyx-web-server:latest onyxdotapp/onyx-web-server:${{ github.event.inputs.version }}
 
-    - name: Pull, Tag and Push API Server Image
-      run: |
-        docker buildx imagetools create -t danswer/danswer-backend:latest danswer/danswer-backend:${{ github.event.inputs.version }}
+      - name: Pull, Tag and Push API Server Image
+        run: |
+          docker buildx imagetools create -t onyxdotapp/onyx-backend:latest onyxdotapp/onyx-backend:${{ github.event.inputs.version }}

.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-close-stale-issues.yml

@@ -0,0 +1,23 @@
+name: 'Nightly - Close stale issues and PRs'
+on:
+  schedule:
+    - cron: '0 11 * * *' # Runs every day at 3 AM PST / 4 AM PDT / 11 AM UTC
+
+permissions:
+  # contents: write # only for delete-branch option
+  issues: write
+  pull-requests: write
+  
+jobs:
+  stale:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/stale@v9
+        with:
+          stale-issue-message: 'This issue is stale because it has been open 75 days with no activity. Remove stale label or comment or this will be closed in 15 days.'
+          stale-pr-message: 'This PR is stale because it has been open 75 days with no activity. Remove stale label or comment or this will be closed in 15 days.'
+          close-issue-message: 'This issue was closed because it has been stalled for 90 days with no activity.'
+          close-pr-message: 'This PR was closed because it has been stalled for 90 days with no activity.'
+          days-before-stale: 75
+#           days-before-close: 90  # uncomment after we test stale behavior
+          

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

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

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

@@ -0,0 +1,124 @@
+name: Backport on Merge
+
+# Note this workflow does not trigger the builds, be sure to manually tag the branches to trigger the builds
+
+on:
+  pull_request:
+    types: [closed] # Later we check for merge so only PRs that go in can get backported
+
+permissions:
+  contents: write
+  actions: write
+
+jobs:
+  backport:
+    if: github.event.pull_request.merged == true
+    runs-on: ubuntu-latest
+    env:
+      GITHUB_TOKEN: ${{ secrets.YUHONG_GH_ACTIONS }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ssh-key: "${{ 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]@onyx.app"
+          git fetch --prune
+
+      - name: Check for Backport Checkbox
+        id: checkbox-check
+        run: |
+          PR_BODY="${{ github.event.pull_request.body }}"
+          if [[ "$PR_BODY" == *"[x] This PR should be backported"* ]]; then
+            echo "backport=true" >> $GITHUB_OUTPUT
+          else
+            echo "backport=false" >> $GITHUB_OUTPUT
+          fi
+
+      - name: List and sort release branches
+        id: list-branches
+        run: |
+          git fetch --all --tags
+          BRANCHES=$(git for-each-ref --format='%(refname:short)' refs/remotes/origin/release/* | sed 's|origin/release/||' | sort -Vr)
+          BETA=$(echo "$BRANCHES" | head -n 1)
+          STABLE=$(echo "$BRANCHES" | head -n 2 | tail -n 1)
+          echo "beta=release/$BETA" >> $GITHUB_OUTPUT
+          echo "stable=release/$STABLE" >> $GITHUB_OUTPUT
+          # Fetch latest tags for beta and stable
+          LATEST_BETA_TAG=$(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" >> $GITHUB_OUTPUT
+          echo "latest_stable_tag=$LATEST_STABLE_TAG" >> $GITHUB_OUTPUT
+          echo "new_beta_tag=$NEW_BETA_TAG" >> $GITHUB_OUTPUT
+          echo "new_stable_tag=$NEW_STABLE_TAG" >> $GITHUB_OUTPUT
+
+      - name: Echo branch and tag information
+        run: |
+          echo "Beta branch: ${{ steps.list-branches.outputs.beta }}"
+          echo "Stable branch: ${{ steps.list-branches.outputs.stable }}"
+          echo "Latest beta tag: ${{ steps.list-branches.outputs.latest_beta_tag }}"
+          echo "Latest stable tag: ${{ steps.list-branches.outputs.latest_stable_tag }}"
+          echo "New beta tag: ${{ steps.list-branches.outputs.new_beta_tag }}"
+          echo "New stable tag: ${{ steps.list-branches.outputs.new_stable_tag }}"
+
+      - name: Trigger Backport
+        if: steps.checkbox-check.outputs.backport == 'true'
+        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
+
+          # Reset and prepare the beta branch
+          git checkout ${{ steps.list-branches.outputs.beta }}
+          echo "Last 5 commits on beta 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 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
+          git push origin ${{ steps.list-branches.outputs.beta }}
+          git push origin ${{ steps.list-branches.outputs.new_beta_tag }}
+
+          # Reset and prepare the stable branch
+          git checkout ${{ steps.list-branches.outputs.stable }}
+          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
+          git push origin ${{ steps.list-branches.outputs.stable }}
+          git push origin ${{ steps.list-branches.outputs.new_stable_tag }}

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

@@ -0,0 +1,238 @@
+name: Run Chromatic Tests
+concurrency:
+  group: Run-Chromatic-Tests-${{ github.workflow }}-${{ github.head_ref || github.event.workflow_run.head_branch || github.run_id }}
+  cancel-in-progress: true
+
+on: push
+
+env:
+  OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+  SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
+
+jobs:
+  playwright-tests:
+    name: Playwright Tests
+
+    # See https://runs-on.com/runners/linux/
+    runs-on:
+      [
+        runs-on,
+        runner=32cpu-linux-x64,
+        disk=large,
+        "run-id=${{ github.run_id }}",
+      ]
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: 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
+
+      - name: Setup node
+        uses: actions/setup-node@v4
+        with:
+          node-version: 22
+
+      - name: Install node dependencies
+        working-directory: ./web
+        run: npm ci
+
+      - name: Install playwright browsers
+        working-directory: ./web
+        run: npx playwright install --with-deps
+
+      - 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: ${{ secrets.DOCKER_TOKEN }}
+
+      # tag every docker image with "test" so that we can spin up the correct set
+      # of images during testing
+
+      # we use the runs-on cache for docker builds
+      # in conjunction with runs-on runners, it has better speed and unlimited caching
+      # https://runs-on.com/caching/s3-cache-for-github-actions/
+      # https://runs-on.com/caching/docker/
+      # https://github.com/moby/buildkit#s3-cache-experimental
+
+      # images are built and run locally for testing purposes. Not pushed.
+
+      - name: Build Web Docker image
+        uses: ./.github/actions/custom-build-and-push
+        with:
+          context: ./web
+          file: ./web/Dockerfile
+          platforms: linux/amd64
+          tags: onyxdotapp/onyx-web-server:test
+          push: false
+          load: true
+          cache-from: type=s3,prefix=cache/${{ github.repository }}/integration-tests/web-server/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }}
+          cache-to: type=s3,prefix=cache/${{ github.repository }}/integration-tests/web-server/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }},mode=max
+
+      - name: Build Backend Docker image
+        uses: ./.github/actions/custom-build-and-push
+        with:
+          context: ./backend
+          file: ./backend/Dockerfile
+          platforms: linux/amd64
+          tags: onyxdotapp/onyx-backend:test
+          push: false
+          load: true
+          cache-from: type=s3,prefix=cache/${{ github.repository }}/integration-tests/backend/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }}
+          cache-to: type=s3,prefix=cache/${{ github.repository }}/integration-tests/backend/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }},mode=max
+
+      - name: Build Model Server Docker image
+        uses: ./.github/actions/custom-build-and-push
+        with:
+          context: ./backend
+          file: ./backend/Dockerfile.model_server
+          platforms: linux/amd64
+          tags: onyxdotapp/onyx-model-server:test
+          push: false
+          load: true
+          cache-from: type=s3,prefix=cache/${{ github.repository }}/integration-tests/model-server/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }}
+          cache-to: type=s3,prefix=cache/${{ github.repository }}/integration-tests/model-server/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }},mode=max
+
+      - name: Start Docker containers
+        run: |
+          cd deployment/docker_compose
+          ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true \
+          AUTH_TYPE=basic \
+          GEN_AI_API_KEY=${{ secrets.OPENAI_API_KEY }} \
+          REQUIRE_EMAIL_VERIFICATION=false \
+          DISABLE_TELEMETRY=true \
+          IMAGE_TAG=test \
+          docker compose -f docker-compose.dev.yml -p danswer-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 &
+
+          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:8080/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 pytest playwright test init
+        working-directory: ./backend
+        env:
+          PYTEST_IGNORE_SKIP: true
+        run: pytest -s tests/integration/tests/playwright/test_playwright.py
+
+      - name: Run Playwright tests
+        working-directory: ./web
+        run: npx playwright test
+
+      - uses: actions/upload-artifact@v4
+        if: always()
+        with:
+          # Chromatic automatically defaults to the test-results directory.
+          # Replace with the path to your custom directory and adjust the CHROMATIC_ARCHIVE_LOCATION environment variable accordingly.
+          name: test-results
+          path: ./web/test-results
+          retention-days: 30
+
+      # save before stopping the containers so the logs can be captured
+      - name: Save Docker logs
+        if: success() || failure()
+        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
+
+      - name: Upload logs
+        if: success() || failure()
+        uses: actions/upload-artifact@v4
+        with:
+          name: docker-logs
+          path: ${{ github.workspace }}/docker-compose.log
+
+      - name: Stop Docker containers
+        run: |
+          cd deployment/docker_compose
+          docker compose -f docker-compose.dev.yml -p danswer-stack down -v
+
+  chromatic-tests:
+    name: Chromatic Tests
+
+    needs: playwright-tests
+    runs-on:
+      [
+        runs-on,
+        runner=32cpu-linux-x64,
+        disk=large,
+        "run-id=${{ github.run_id }}",
+      ]
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Setup node
+        uses: actions/setup-node@v4
+        with:
+          node-version: 22
+
+      - name: Install node dependencies
+        working-directory: ./web
+        run: npm ci
+
+      - 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-helm-chart-testing.yml

@@ -0,0 +1,72 @@
+name: Helm - Lint and Test Charts
+
+on:
+  merge_group:
+  pull_request:
+    branches: [ main ]
+  workflow_dispatch:  # Allows manual triggering
+  
+jobs:
+  helm-chart-check:
+    # See https://runs-on.com/runners/linux/
+    runs-on: [runs-on,runner=8cpu-linux-x64,hdd=256,"run-id=${{ github.run_id }}"]
+
+    # fetch-depth 0 is required for helm/chart-testing-action
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v4
+      with:
+        fetch-depth: 0
+        
+    - name: Set up Helm
+      uses: azure/setup-helm@v4.2.0
+      with:
+        version: v3.14.4
+      
+    - name: Set up chart-testing
+      uses: helm/chart-testing-action@v2.6.1
+
+    # 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)
+      id: list-changed
+      run: |
+        echo "default_branch: ${{ github.event.repository.default_branch }}"
+        changed=$(ct list-changed --remote origin --target-branch ${{ github.event.repository.default_branch }} --chart-dirs deployment/helm/charts)
+        echo "list-changed output: $changed"
+        if [[ -n "$changed" ]]; then
+          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'
+      run: ct lint --config ct.yaml --all
+      # the following would lint only changed charts, but linting isn't expensive
+      # run: ct lint --config ct.yaml --target-branch ${{ github.event.repository.default_branch }}
+
+    - name: Create kind cluster
+      if: steps.list-changed.outputs.changed == 'true'
+      uses: helm/kind-action@v1.10.0
+
+    - name: Run chart-testing (install)
+      if: steps.list-changed.outputs.changed == 'true'
+      run: ct install --all --helm-extra-set-args="--set=nginx.enabled=false" --debug --config ct.yaml
+      # the following would install only changed charts, but we only have one chart so 
+      # don't worry about that for now
+      # run: ct install --target-branch ${{ github.event.repository.default_branch }}

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

@@ -1,68 +0,0 @@
-# This workflow is intentionally disabled while we're still working on it
-# It's close to ready, but a race condition needs to be fixed with
-# API server and Vespa startup, and it needs to have a way to build/test against
-# local containers
-
-name: Helm - Lint and Test Charts
-
-on:
-  merge_group:
-  pull_request:
-    branches: [ main ]
-
-jobs:
-  lint-test:
-    # See https://runs-on.com/runners/linux/
-    runs-on: [runs-on,runner=8cpu-linux-x64,hdd=256,"run-id=${{ github.run_id }}"]
-
-    # fetch-depth 0 is required for helm/chart-testing-action
-    steps:
-    - name: Checkout code
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 0
-        
-    - name: Set up Helm
-      uses: azure/setup-helm@v4.2.0
-      with:
-        version: v3.14.4
-      
-    - name: Set up Python
-      uses: actions/setup-python@v4
-      with:
-        python-version: '3.11'
-        cache: 'pip'
-        cache-dependency-path: |
-          backend/requirements/default.txt
-          backend/requirements/dev.txt
-          backend/requirements/model_server.txt
-    - run: |
-        python -m pip install --upgrade pip
-        pip install --retries 5 --timeout 30 -r backend/requirements/default.txt
-        pip install --retries 5 --timeout 30 -r backend/requirements/dev.txt
-        pip install --retries 5 --timeout 30 -r backend/requirements/model_server.txt
-
-    - name: Set up chart-testing
-      uses: helm/chart-testing-action@v2.6.1
-
-    - name: Run chart-testing (list-changed)
-      id: list-changed
-      run: |
-        changed=$(ct list-changed --target-branch ${{ github.event.repository.default_branch }})
-        if [[ -n "$changed" ]]; then
-          echo "changed=true" >> "$GITHUB_OUTPUT"
-        fi
-
-    - name: Run chart-testing (lint)
-#       if: steps.list-changed.outputs.changed == 'true'
-      run: ct lint --all --config ct.yaml --target-branch ${{ github.event.repository.default_branch }}
-
-    - name: Create kind cluster
-#       if: steps.list-changed.outputs.changed == 'true'
-      uses: helm/kind-action@v1.10.0
-
-    - name: Run chart-testing (install)
-#       if: steps.list-changed.outputs.changed == 'true'
-      run: ct install --all --config ct.yaml
-#       run: ct install --target-branch ${{ github.event.repository.default_branch }}
-      

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

@@ -8,16 +8,19 @@ on:
   pull_request:
     branches:
       - main
-      - 'release/**'
+      - "release/**"
 
 env:
   OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
   SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
+  CONFLUENCE_TEST_SPACE_URL: ${{ secrets.CONFLUENCE_TEST_SPACE_URL }}
+  CONFLUENCE_USER_NAME: ${{ secrets.CONFLUENCE_USER_NAME }}
+  CONFLUENCE_ACCESS_TOKEN: ${{ secrets.CONFLUENCE_ACCESS_TOKEN }}
 
 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
@@ -33,21 +36,21 @@ jobs:
 
       # 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 
+      # in the integration tests. We have a separate action to verify that it builds
       # successfully.
       - name: Pull Web Docker image
         run: |
-          docker pull danswer/danswer-web-server:latest
-          docker tag danswer/danswer-web-server:latest danswer/danswer-web-server:test
+          docker pull onyxdotapp/onyx-web-server:latest
+          docker tag onyxdotapp/onyx-web-server:latest onyxdotapp/onyx-web-server:test
 
       # we use the runs-on cache for docker builds
       # in conjunction with runs-on runners, it has better speed and unlimited caching
       # https://runs-on.com/caching/s3-cache-for-github-actions/
       # https://runs-on.com/caching/docker/
       # https://github.com/moby/buildkit#s3-cache-experimental
-      
+
       # images are built and run locally for testing purposes. Not pushed.
       - name: Build Backend Docker image
         uses: ./.github/actions/custom-build-and-push
@@ -55,7 +58,7 @@ jobs:
           context: ./backend
           file: ./backend/Dockerfile
           platforms: linux/amd64
-          tags: danswer/danswer-backend:test
+          tags: onyxdotapp/onyx-backend:test
           push: false
           load: true
           cache-from: type=s3,prefix=cache/${{ github.repository }}/integration-tests/backend/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }}
@@ -67,7 +70,7 @@ jobs:
           context: ./backend
           file: ./backend/Dockerfile.model_server
           platforms: linux/amd64
-          tags: danswer/danswer-model-server:test
+          tags: onyxdotapp/onyx-model-server:test
           push: false
           load: true
           cache-from: type=s3,prefix=cache/${{ github.repository }}/integration-tests/model-server/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }}
@@ -79,12 +82,62 @@ jobs:
           context: ./backend
           file: ./backend/tests/integration/Dockerfile
           platforms: linux/amd64
-          tags: danswer/danswer-integration:test
+          tags: onyxdotapp/onyx-integration:test
           push: false
           load: true
           cache-from: type=s3,prefix=cache/${{ github.repository }}/integration-tests/integration/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }}
           cache-to: type=s3,prefix=cache/${{ github.repository }}/integration-tests/integration/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }},mode=max
 
+      # Start containers for multi-tenant tests
+      - name: Start Docker containers for multi-tenant tests
+        run: |
+          cd deployment/docker_compose
+          ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true \
+          MULTI_TENANT=true \
+          AUTH_TYPE=basic \
+          REQUIRE_EMAIL_VERIFICATION=false \
+          DISABLE_TELEMETRY=true \
+          IMAGE_TAG=test \
+          docker compose -f docker-compose.dev.yml -p danswer-stack up -d
+        id: start_docker_multi_tenant
+
+      # In practice, `cloud` Auth type would require OAUTH credentials to be set.
+      - name: Run Multi-Tenant Integration Tests
+        run: |
+          echo "Running integration tests..."
+          docker run --rm --network danswer-stack_default \
+            --name test-runner \
+            -e POSTGRES_HOST=relational_db \
+            -e POSTGRES_USER=postgres \
+            -e POSTGRES_PASSWORD=password \
+            -e POSTGRES_DB=postgres \
+            -e VESPA_HOST=index \
+            -e REDIS_HOST=cache \
+            -e API_SERVER_HOST=api_server \
+            -e OPENAI_API_KEY=${OPENAI_API_KEY} \
+            -e SLACK_BOT_TOKEN=${SLACK_BOT_TOKEN} \
+            -e TEST_WEB_HOSTNAME=test-runner \
+            -e AUTH_TYPE=cloud \
+            -e MULTI_TENANT=true \
+            onyxdotapp/onyx-integration:test \
+            /app/tests/integration/multitenant_tests
+        continue-on-error: true
+        id: run_multitenant_tests
+
+      - name: Check multi-tenant test results
+        run: |
+          if [ ${{ steps.run_tests.outcome }} == 'failure' ]; then
+            echo "Integration tests failed. Exiting with error."
+            exit 1
+          else
+            echo "All integration tests passed successfully."
+          fi
+
+      - name: Stop multi-tenant Docker containers
+        run: |
+          cd deployment/docker_compose
+          docker compose -f docker-compose.dev.yml -p danswer-stack down -v
+
       - name: Start Docker containers
         run: |
           cd deployment/docker_compose
@@ -99,12 +152,12 @@ jobs:
       - name: Wait for service to be ready
         run: |
           echo "Starting wait-for-service script..."
-          
+
           docker logs -f danswer-stack-api_server-1 &
 
           start_time=$(date +%s)
           timeout=300  # 5 minutes in seconds
-          
+
           while true; do
             current_time=$(date +%s)
             elapsed_time=$((current_time - start_time))
@@ -130,7 +183,7 @@ jobs:
           done
           echo "Finished waiting for service."
 
-      - name: Run integration tests
+      - name: Run Standard Integration Tests
         run: |
           echo "Running integration tests..."
           docker run --rm --network danswer-stack_default \
@@ -144,8 +197,13 @@ jobs:
             -e API_SERVER_HOST=api_server \
             -e OPENAI_API_KEY=${OPENAI_API_KEY} \
             -e SLACK_BOT_TOKEN=${SLACK_BOT_TOKEN} \
+            -e CONFLUENCE_TEST_SPACE_URL=${CONFLUENCE_TEST_SPACE_URL} \
+            -e CONFLUENCE_USER_NAME=${CONFLUENCE_USER_NAME} \
+            -e CONFLUENCE_ACCESS_TOKEN=${CONFLUENCE_ACCESS_TOKEN} \
             -e TEST_WEB_HOSTNAME=test-runner \
-            danswer/danswer-integration:test
+            onyxdotapp/onyx-integration:test \
+            /app/tests/integration/tests \
+            /app/tests/integration/connector_job_tests
         continue-on-error: true
         id: run_tests
 
@@ -158,13 +216,19 @@ 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()
         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
-      
+
+      - name: Stop Docker containers
+        run: |
+          cd deployment/docker_compose
+          docker compose -f docker-compose.dev.yml -p danswer-stack down -v
+
       - name: Upload logs
         if: success() || failure()
         uses: actions/upload-artifact@v4

.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
+        run: |
+          PR_BODY="${{ github.event.pull_request.body }}"
+
+          # Looking for "https://linear.app" in the body
+          if echo "$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-python-connector-tests.yml

@@ -18,7 +18,27 @@ env:
   # Jira
   JIRA_USER_EMAIL: ${{ secrets.JIRA_USER_EMAIL }}
   JIRA_API_TOKEN: ${{ secrets.JIRA_API_TOKEN }}
-
+  # Google
+  GOOGLE_DRIVE_SERVICE_ACCOUNT_JSON_STR: ${{ secrets.GOOGLE_DRIVE_SERVICE_ACCOUNT_JSON_STR }}
+  GOOGLE_DRIVE_OAUTH_CREDENTIALS_JSON_STR_TEST_USER_1: ${{ secrets.GOOGLE_DRIVE_OAUTH_CREDENTIALS_JSON_STR_TEST_USER_1 }}
+  GOOGLE_DRIVE_OAUTH_CREDENTIALS_JSON_STR: ${{ secrets.GOOGLE_DRIVE_OAUTH_CREDENTIALS_JSON_STR }}
+  GOOGLE_GMAIL_SERVICE_ACCOUNT_JSON_STR: ${{ secrets.GOOGLE_GMAIL_SERVICE_ACCOUNT_JSON_STR }}
+  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 }}
 jobs:
   connectors-check:
     # See https://runs-on.com/runners/linux/

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

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

.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

@@ -7,3 +7,4 @@
 .vscode/
 *.sw?
 /backend/tests/regression/answer_quality/search_test_config.yaml
+/web/test-results/

.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

.vscode/launch.template.jsonc

@@ -6,19 +6,71 @@
     // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
     "version": "0.2.0",
     "compounds": [
+		{
+			// Dummy entry used to label the group
+			"name": "--- Compound ---",
+		  	"configurations": [
+		  		"--- Individual ---"
+		  	],
+			"presentation": {
+				 "group": "1",
+			 }
+		},
         {
-            "name": "Run All Danswer Services",
+            "name": "Run All Onyx Services",
             "configurations": [
                 "Web Server",
                 "Model Server",
                 "API Server",
-                "Indexing",
-                "Background Jobs",
-                "Slack Bot"
-            ]
-        }
+                "Slack Bot",
+		  		"Celery primary", 
+		  		"Celery light", 
+		  		"Celery heavy", 
+		  		"Celery indexing", 
+		  		"Celery beat",
+                "Celery monitoring",
+            ],
+			"presentation": {
+				 "group": "1",
+			 }
+        },
+		{
+			"name": "Web / Model / API",
+		  	"configurations": [
+		  		"Web Server", 
+		  		"Model Server", 
+		  		"API Server",
+		  	],
+			"presentation": {
+				 "group": "1",
+			 }
+		},
+		{
+			"name": "Celery (all)",
+		  	"configurations": [
+		  		"Celery primary", 
+		  		"Celery light", 
+		  		"Celery heavy", 
+		  		"Celery indexing", 
+		  		"Celery beat",
+                "Celery monitoring",
+		  	],
+			"presentation": {
+				 "group": "1",
+			 }
+		}
     ],
     "configurations": [
+		{
+	    	// Dummy entry used to label the group
+			"name": "--- Individual ---",
+			"type": "node",
+			"request": "launch",
+			"presentation": {
+				"group": "2",
+				"order": 0
+			}
+		},
         {
             "name": "Web Server",
             "type": "node",
@@ -29,7 +81,11 @@
             "runtimeArgs": [
                 "run", "dev"
             ],
-            "console": "integratedTerminal"
+            "presentation": {
+				 "group": "2",
+			 },
+            "console": "integratedTerminal",
+            "consoleTitle": "Web Server Console"
         },
         {
             "name": "Model Server",
@@ -48,7 +104,11 @@
                 "--reload",
                 "--port",
                 "9000"
-            ]
+            ],
+            "presentation": {
+				 "group": "2",
+			},
+            "consoleTitle": "Model Server Console"
         },
         {
             "name": "API Server",
@@ -64,18 +124,128 @@
                 "PYTHONUNBUFFERED": "1"
             },
             "args": [
-                "danswer.main:app",
+                "onyx.main:app",
                 "--reload",
                 "--port",
                 "8080"
-            ]
+            ],
+            "presentation": {
+				 "group": "2",
+			 },
+            "consoleTitle": "API Server Console"
         },
+        // For the listener to access the Slack API,
+        // DANSWER_BOT_SLACK_APP_TOKEN & DANSWER_BOT_SLACK_BOT_TOKEN need to be set in .env file located in the root of the project
         {
-            "name": "Indexing",
-            "consoleName": "Indexing",
+            "name": "Slack Bot",
+            "consoleName": "Slack Bot",
             "type": "debugpy",
             "request": "launch",
-            "program": "danswer/background/update.py",
+            "program": "onyx/onyxbot/slack/listener.py",
+            "cwd": "${workspaceFolder}/backend",
+            "envFile": "${workspaceFolder}/.vscode/.env",
+            "env": {
+                "LOG_LEVEL": "DEBUG",
+                "PYTHONUNBUFFERED": "1",
+                "PYTHONPATH": "."
+            },
+            "presentation": {
+				 "group": "2",
+			},
+            "consoleTitle": "Slack Bot Console"
+        },
+        {
+            "name": "Celery primary",
+            "type": "debugpy",
+            "request": "launch",
+            "module": "celery",
+            "cwd": "${workspaceFolder}/backend",
+            "envFile": "${workspaceFolder}/.vscode/.env",
+            "env": {
+                "LOG_LEVEL": "INFO",
+                "PYTHONUNBUFFERED": "1",
+                "PYTHONPATH": "."
+            },
+            "args": [
+                "-A",
+                "onyx.background.celery.versioned_apps.primary",
+                "worker",
+                "--pool=threads",
+                "--concurrency=4",
+                "--prefetch-multiplier=1",
+                "--loglevel=INFO",
+                "--hostname=primary@%n",
+                "-Q",
+                "celery",
+            ],
+            "presentation": {
+				 "group": "2",
+			 },
+            "consoleTitle": "Celery primary Console"
+        },
+        {
+            "name": "Celery light",
+            "type": "debugpy",
+            "request": "launch",
+            "module": "celery",
+            "cwd": "${workspaceFolder}/backend",
+            "envFile": "${workspaceFolder}/.vscode/.env",
+            "env": {
+                "LOG_LEVEL": "INFO",
+                "PYTHONUNBUFFERED": "1",
+                "PYTHONPATH": "."
+            },
+            "args": [
+                "-A",
+                "onyx.background.celery.versioned_apps.light",
+                "worker",
+                "--pool=threads",
+                "--concurrency=64",
+                "--prefetch-multiplier=8",
+                "--loglevel=INFO",
+                "--hostname=light@%n",
+                "-Q",
+                "vespa_metadata_sync,connector_deletion,doc_permissions_upsert",
+            ],
+            "presentation": {
+				 "group": "2",
+			 },
+            "consoleTitle": "Celery light Console"
+        },
+        {
+            "name": "Celery heavy",
+            "type": "debugpy",
+            "request": "launch",
+            "module": "celery",
+            "cwd": "${workspaceFolder}/backend",
+            "envFile": "${workspaceFolder}/.vscode/.env",
+            "env": {
+                "LOG_LEVEL": "INFO",
+                "PYTHONUNBUFFERED": "1",
+                "PYTHONPATH": "."
+            },
+            "args": [
+                "-A",
+                "onyx.background.celery.versioned_apps.heavy",
+                "worker",
+                "--pool=threads",
+                "--concurrency=4",
+                "--prefetch-multiplier=1",
+                "--loglevel=INFO",
+                "--hostname=heavy@%n",
+                "-Q",
+                "connector_pruning,connector_doc_permissions_sync,connector_external_group_sync",
+            ],
+            "presentation": {
+				 "group": "2",
+			 },
+            "consoleTitle": "Celery heavy Console"
+        },
+        {
+            "name": "Celery indexing",
+            "type": "debugpy",
+            "request": "launch",
+            "module": "celery",
             "cwd": "${workspaceFolder}/backend",
             "envFile": "${workspaceFolder}/.vscode/.env",
             "env": {
@@ -83,42 +253,71 @@
                 "LOG_LEVEL": "DEBUG",
                 "PYTHONUNBUFFERED": "1",
                 "PYTHONPATH": "."
-            }
+            },
+            "args": [
+                "-A",
+                "onyx.background.celery.versioned_apps.indexing",
+                "worker",
+                "--pool=threads",
+                "--concurrency=1",
+                "--prefetch-multiplier=1",
+                "--loglevel=INFO",
+                "--hostname=indexing@%n",
+                "-Q",
+                "connector_indexing",
+            ],
+            "presentation": {
+				 "group": "2",
+			 },
+            "consoleTitle": "Celery indexing Console"
         },
-        // Celery and all async jobs, usually would include indexing as well but this is handled separately above for dev
         {
-            "name": "Background Jobs",
-            "consoleName": "Background Jobs",
+            "name": "Celery monitoring",
             "type": "debugpy",
             "request": "launch",
-            "program": "scripts/dev_run_background_jobs.py",
+            "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",
+            "request": "launch",
+            "module": "celery",
             "cwd": "${workspaceFolder}/backend",
             "envFile": "${workspaceFolder}/.vscode/.env",
             "env": {
-                "LOG_DANSWER_MODEL_INTERACTIONS": "True",
                 "LOG_LEVEL": "DEBUG",
                 "PYTHONUNBUFFERED": "1",
                 "PYTHONPATH": "."
             },
             "args": [
-                "--no-indexing"
-            ]
-        },
-        // For the listner to access the Slack API,
-        // DANSWER_BOT_SLACK_APP_TOKEN & DANSWER_BOT_SLACK_BOT_TOKEN need to be set in .env file located in the root of the project
-        {
-            "name": "Slack Bot",
-            "consoleName": "Slack Bot",
-            "type": "debugpy",
-            "request": "launch",
-            "program": "danswer/danswerbot/slack/listener.py",
-            "cwd": "${workspaceFolder}/backend",
-            "envFile": "${workspaceFolder}/.vscode/.env",
-            "env": {
-                "LOG_LEVEL": "DEBUG",
-                "PYTHONUNBUFFERED": "1",
-                "PYTHONPATH": "."
-            }
+                "-A",
+                "onyx.background.celery.versioned_apps.beat",
+                "beat",
+                "--loglevel=INFO",
+            ],
+            "presentation": {
+				 "group": "2",
+			 },
+            "consoleTitle": "Celery beat Console"
         },
         {
             "name": "Pytest",
@@ -136,9 +335,23 @@
             "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",
+			 },
+            "consoleTitle": "Pytest Console"
         },
+		{
+	    	// Dummy entry used to label the group
+			"name": "--- Tasks ---",
+			"type": "node",
+			"request": "launch",
+			"presentation": {
+				"group": "3",
+				"order": 0
+			}
+		},
         {
             "name": "Clear and Restart External Volumes and Containers",
             "type": "node",
@@ -147,7 +360,42 @@
             "runtimeArgs": ["${workspaceFolder}/backend/scripts/restart_containers.sh"],
             "cwd": "${workspaceFolder}",
             "console": "integratedTerminal",
-            "stopOnEntry": true
-        }
+            "stopOnEntry": true,
+            "presentation": {
+				 "group": "3",
+			 },
+        },
+        {
+	        // Celery jobs launched through a single background script (legacy)
+	        // Recommend using the "Celery (all)" compound launch instead.
+            "name": "Background Jobs",
+            "consoleName": "Background Jobs",
+            "type": "debugpy",
+            "request": "launch",
+            "program": "scripts/dev_run_background_jobs.py",
+            "cwd": "${workspaceFolder}/backend",
+            "envFile": "${workspaceFolder}/.vscode/.env",
+            "env": {
+                "LOG_DANSWER_MODEL_INTERACTIONS": "True",
+                "LOG_LEVEL": "DEBUG",
+                "PYTHONUNBUFFERED": "1",
+                "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

@@ -1,105 +1,117 @@
-<!-- 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.
 
 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.
-
+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

@@ -1,129 +1,135 @@
-<!-- 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-2lcmqw703-071hBuZBfNEOGUsLa5PXvQ" 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.
+<strong>[Onyx](https://www.onyx.app/)</strong> (formerly Danswer) is the AI Assistant connected to your company's docs, apps, and people.
+Onyx provides a Chat interface and plugs into any LLM of your choice. Onyx 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. Onyx is dual Licensed with most of it under MIT license 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 AI Assistants.
 
-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
+Onyx also serves as a Enterprise Search across all common workplace tools such as Slack, Google Drive, Confluence, etc.
+By combining LLMs and team specific knowledge, Onyx 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:
+Onyx Web App:
 
-https://github.com/danswer-ai/danswer/assets/32520769/563be14c-9304-47b5-bf0a-9049c2b6f410
+https://github.com/onyx-dot-app/onyx/assets/32520769/563be14c-9304-47b5-bf0a-9049c2b6f410
 
+Or, plug Onyx into your existing Slack workflows (more integrations to come 😁):
 
-Or, plug Danswer into your existing Slack workflows (more integrations to come 😁):
+https://github.com/onyx-dot-app/onyx/assets/25087905/3e19739b-d178-4371-9a38-011430bdec1b
 
-https://github.com/danswer-ai/danswer/assets/25087905/3e19739b-d178-4371-9a38-011430bdec1b
-
-
-For more details on the Admin UI to manage connectors and users, check out our 
+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>!
 
 ## Deployment
 
-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 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.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 deployment on Kubernetes. Files for that can be found [here](https://github.com/onyx-dot-app/onyx/tree/main/deployment/kubernetes).
 
+## 💃 Main Features
 
-## 💃 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.
-
+- Chat UI with the ability to select documents to chat with.
+- Create custom AI Assistants with different prompts and backing knowledge sets.
+- Connect Onyx 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.
 
 ## 🚧 Roadmap
-* Chat/Prompt sharing with specific teammates and user groups.
-* Multi-Model 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.
 
+- 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 Noteable 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.
+## Other Notable Benefits of Onyx
 
+- 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 Onyx anywhere of your choosing.
 
 ## 🔌 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 ...
+
+- Slack
+- GitHub
+- Google Drive
+- Confluence
+- Jira
+- Zendesk
+- Gmail
+- Notion
+- Gong
+- Slab
+- Linear
+- Productboard
+- Guru
+- Bookstack
+- Document360
+- Sharepoint
+- Hubspot
+- Local Files
+- Websites
+- And more ...
 
 ## 📚 Editions
 
-There are two editions of Danswer:
+There are two editions of Onyx:
 
-  * 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.
+- Onyx 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 Onyx you will get if you follow the Deployment guide above.
+- Onyx 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.onyx.app/) for the latest.
 
-To try the Danswer Enterprise Edition: 
+To try the Onyx Enterprise Edition:
 
-  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).
+1. Checkout our [Cloud product](https://cloud.onyx.app/signup).
+2. For self-hosting, contact us at [founders@onyx.app](mailto:founders@onyx.app) 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=onyx-dot-app/onyx&type=Date)](https://star-history.com/#onyx-dot-app/onyx&Date)

backend/.gitignore

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

backend/Dockerfile

@@ -1,18 +1,19 @@
 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=0.3-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}"
 # Install system dependencies
 # cmake needed for psycopg (postgres)
 # libpq-dev needed for psycopg (postgres)
@@ -36,6 +37,8 @@ RUN apt-get update && \
     rm -rf /var/lib/apt/lists/* && \
     apt-get clean
 
+
+
 # Install Python dependencies
 # Remove py which is pulled in by retry, py is not needed and is a CVE
 COPY ./requirements/default.txt /tmp/requirements.txt
@@ -53,7 +56,7 @@ 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 \
@@ -70,11 +73,11 @@ RUN apt-get update && \
     rm -rf /var/lib/apt/lists/* && \
     rm -f /usr/local/lib/python3.11/site-packages/tornado/test/test.key
 
+
 # Pre-downloading models for setups with limited egress
 RUN python -c "from tokenizers import Tokenizer; \
 Tokenizer.from_pretrained('nomic-ai/nomic-embed-text-v1')"
 
-
 # Pre-downloading NLTK for setups with limited egress
 RUN python -c "import nltk; \
 nltk.download('stopwords', quiet=True); \
@@ -89,7 +92,7 @@ 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

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=0.3-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

@@ -1,35 +1,70 @@
-from typing import Any
+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
+import os
+import ssl
 import asyncio
+import logging
 from logging.config import fileConfig
 
 from alembic import context
-from sqlalchemy import pool
-from sqlalchemy.engine import Connection
 from sqlalchemy.ext.asyncio import create_async_engine
-from sqlalchemy.sql import text
-
-from danswer.configs.app_configs import MULTI_TENANT
-from danswer.db.engine import build_connection_string
-from danswer.db.models import Base
+from sqlalchemy.sql.schema import SchemaItem
+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
 
 # 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
-# from myapp import mymodel
-# target_metadata = mymodel.Base.metadata
 target_metadata = [Base.metadata, ResultModelBase.metadata]
 
+EXCLUDE_TABLES = {"kombu_queue", "kombu_message"}
+logger = logging.getLogger(__name__)
 
-def get_schema_options() -> tuple[str, bool]:
+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,
+    name: str | None,
+    type_: Literal[
+        "schema",
+        "table",
+        "column",
+        "index",
+        "unique_constraint",
+        "foreign_key_constraint",
+    ],
+    reflected: bool,
+    compare_to: SchemaItem | None,
+) -> bool:
+    if type_ == "table" and name in EXCLUDE_TABLES:
+        return False
+    return True
+
+
+def get_schema_options() -> tuple[str, bool, bool]:
     x_args_raw = context.get_x_argument()
     x_args = {}
     for arg in x_args_raw:
@@ -37,63 +72,32 @@ def get_schema_options() -> tuple[str, bool]:
             if "=" in pair:
                 key, value = pair.split("=", 1)
                 x_args[key.strip()] = value.strip()
-    schema_name = x_args.get("schema", "public")
+    schema_name = x_args.get("schema", POSTGRES_DEFAULT_SCHEMA)
     create_schema = x_args.get("create_schema", "true").lower() == "true"
-    return schema_name, create_schema
+    upgrade_all_tenants = x_args.get("upgrade_all_tenants", "false").lower() == "true"
 
-
-EXCLUDE_TABLES = {"kombu_queue", "kombu_message"}
-
-
-def include_object(
-    object: Any, name: str, type_: str, reflected: bool, compare_to: Any
-) -> bool:
-    if type_ == "table" and name in EXCLUDE_TABLES:
-        return False
-    return True
-
-
-def run_migrations_offline() -> None:
-    """Run migrations in 'offline' mode.
-    This configures the context with just a URL
-    and not an Engine, though an Engine is acceptable
-    here as well.  By skipping the Engine creation
-    we don't even need a DBAPI to be available.
-    Calls to context.execute() here emit the given string to the
-    script output.
-    """
-    schema_name, _ = get_schema_options()
-    url = build_connection_string()
-
-    context.configure(
-        url=url,
-        target_metadata=target_metadata,  # type: ignore
-        literal_binds=True,
-        include_object=include_object,
-        version_table_schema=schema_name,
-        include_schemas=True,
-        script_location=config.get_main_option("script_location"),
-        dialect_opts={"paramstyle": "named"},
-    )
-
-    with context.begin_transaction():
-        context.run_migrations()
-
-
-def do_run_migrations(connection: Connection) -> None:
-    schema_name, create_schema = get_schema_options()
-
-    if MULTI_TENANT and schema_name == "public":
+    if (
+        MULTI_TENANT
+        and schema_name == POSTGRES_DEFAULT_SCHEMA
+        and not upgrade_all_tenants
+    ):
         raise ValueError(
             "Cannot run default migrations in public schema when multi-tenancy is enabled. "
             "Please specify a tenant-specific schema."
         )
 
+    return schema_name, create_schema, upgrade_all_tenants
+
+
+def do_run_migrations(
+    connection: Connection, schema_name: str, create_schema: bool
+) -> None:
+    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(
@@ -111,16 +115,118 @@ def do_run_migrations(connection: Connection) -> None:
         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:
-    connectable = create_async_engine(
+    schema_name, create_schema, upgrade_all_tenants = get_schema_options()
+
+    engine = create_async_engine(
         build_connection_string(),
         poolclass=pool.NullPool,
     )
 
-    async with connectable.connect() as connection:
-        await connection.run_sync(do_run_migrations)
+    if USE_IAM_AUTH:
 
-    await connectable.dispose()
+        @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}")
+                async with engine.connect() as connection:
+                    await connection.run_sync(
+                        do_run_migrations,
+                        schema_name=schema,
+                        create_schema=create_schema,
+                    )
+            except Exception as e:
+                logger.error(f"Error migrating schema {schema}: {e}")
+                raise
+    else:
+        try:
+            logger.info(f"Migrating schema: {schema_name}")
+            async with engine.connect() as connection:
+                await connection.run_sync(
+                    do_run_migrations,
+                    schema_name=schema_name,
+                    create_schema=create_schema,
+                )
+        except Exception as e:
+            logger.error(f"Error migrating schema {schema_name}: {e}")
+            raise
+
+    await engine.dispose()
+
+
+def run_migrations_offline() -> None:
+    schema_name, _, upgrade_all_tenants = get_schema_options()
+    url = build_connection_string()
+
+    if upgrade_all_tenants:
+        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()
+
+        for schema in tenant_schemas:
+            logger.info(f"Migrating schema: {schema}")
+            context.configure(
+                url=url,
+                target_metadata=target_metadata,  # type: ignore
+                literal_binds=True,
+                include_object=include_object,
+                version_table_schema=schema,
+                include_schemas=True,
+                script_location=config.get_main_option("script_location"),
+                dialect_opts={"paramstyle": "named"},
+            )
+
+            with context.begin_transaction():
+                context.run_migrations()
+    else:
+        logger.info(f"Migrating schema: {schema_name}")
+        context.configure(
+            url=url,
+            target_metadata=target_metadata,  # type: ignore
+            literal_binds=True,
+            include_object=include_object,
+            version_table_schema=schema_name,
+            include_schemas=True,
+            script_location=config.get_main_option("script_location"),
+            dialect_opts={"paramstyle": "named"},
+        )
+
+        with context.begin_transaction():
+            context.run_migrations()
 
 
 def run_migrations_online() -> None:

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/177de57c21c9_display_custom_llm_models.py

@@ -0,0 +1,59 @@
+"""display custom llm models
+
+Revision ID: 177de57c21c9
+Revises: 4ee1287bd26a
+Create Date: 2024-11-21 11:49:04.488677
+
+"""
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+from sqlalchemy import and_
+
+revision = "177de57c21c9"
+down_revision = "4ee1287bd26a"
+branch_labels = None
+depends_on = None
+depends_on = None
+
+
+def upgrade() -> None:
+    conn = op.get_bind()
+    llm_provider = sa.table(
+        "llm_provider",
+        sa.column("id", sa.Integer),
+        sa.column("provider", sa.String),
+        sa.column("model_names", postgresql.ARRAY(sa.String)),
+        sa.column("display_model_names", postgresql.ARRAY(sa.String)),
+    )
+
+    excluded_providers = ["openai", "bedrock", "anthropic", "azure"]
+
+    providers_to_update = sa.select(
+        llm_provider.c.id,
+        llm_provider.c.model_names,
+        llm_provider.c.display_model_names,
+    ).where(
+        and_(
+            ~llm_provider.c.provider.in_(excluded_providers),
+            llm_provider.c.model_names.isnot(None),
+        )
+    )
+
+    results = conn.execute(providers_to_update).fetchall()
+
+    for provider_id, model_names, display_model_names in results:
+        if display_model_names is None:
+            display_model_names = []
+
+        combined_model_names = list(set(display_model_names + model_names))
+        update_stmt = (
+            llm_provider.update()
+            .where(llm_provider.c.id == provider_id)
+            .values(display_model_names=combined_model_names)
+        )
+        conn.execute(update_stmt)
+
+
+def downgrade() -> None:
+    pass

backend/alembic/versions/1b10e1fda030_add_additional_data_to_notifications.py

@@ -0,0 +1,26 @@
+"""add additional data to notifications
+
+Revision ID: 1b10e1fda030
+Revises: 6756efa39ada
+Create Date: 2024-10-15 19:26:44.071259
+
+"""
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision = "1b10e1fda030"
+down_revision = "6756efa39ada"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "notification", sa.Column("additional_data", postgresql.JSONB(), nullable=True)
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("notification", "additional_data")

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/26b931506ecb_default_chosen_assistants_to_none.py

@@ -0,0 +1,68 @@
+"""default chosen assistants to none
+
+Revision ID: 26b931506ecb
+Revises: 2daa494a0851
+Create Date: 2024-11-12 13:23:29.858995
+
+"""
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision = "26b931506ecb"
+down_revision = "2daa494a0851"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "user", sa.Column("chosen_assistants_new", postgresql.JSONB(), nullable=True)
+    )
+
+    op.execute(
+        """
+    UPDATE "user"
+    SET chosen_assistants_new =
+        CASE
+            WHEN chosen_assistants = '[-2, -1, 0]' THEN NULL
+            ELSE chosen_assistants
+        END
+    """
+    )
+
+    op.drop_column("user", "chosen_assistants")
+
+    op.alter_column(
+        "user", "chosen_assistants_new", new_column_name="chosen_assistants"
+    )
+
+
+def downgrade() -> None:
+    op.add_column(
+        "user",
+        sa.Column(
+            "chosen_assistants_old",
+            postgresql.JSONB(),
+            nullable=False,
+            server_default="[-2, -1, 0]",
+        ),
+    )
+
+    op.execute(
+        """
+    UPDATE "user"
+    SET chosen_assistants_old =
+        CASE
+            WHEN chosen_assistants IS NULL THEN '[-2, -1, 0]'::jsonb
+            ELSE chosen_assistants
+        END
+    """
+    )
+
+    op.drop_column("user", "chosen_assistants")
+
+    op.alter_column(
+        "user", "chosen_assistants_old", new_column_name="chosen_assistants"
+    )

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/2daa494a0851_add_group_sync_time.py

@@ -0,0 +1,30 @@
+"""add-group-sync-time
+
+Revision ID: 2daa494a0851
+Revises: c0fd6e4da83a
+Create Date: 2024-11-11 10:57:22.991157
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "2daa494a0851"
+down_revision = "c0fd6e4da83a"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "connector_credential_pair",
+        sa.Column(
+            "last_time_external_group_sync",
+            sa.DateTime(timezone=True),
+            nullable=True,
+        ),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("connector_credential_pair", "last_time_external_group_sync")

backend/alembic/versions/33cb72ea4d80_single_tool_call_per_message.py

@@ -0,0 +1,50 @@
+"""single tool call per message
+
+Revision ID: 33cb72ea4d80
+Revises: 5b29123cd710
+Create Date: 2024-11-01 12:51:01.535003
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "33cb72ea4d80"
+down_revision = "5b29123cd710"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # Step 1: Delete extraneous ToolCall entries
+    # Keep only the ToolCall with the smallest 'id' for each 'message_id'
+    op.execute(
+        sa.text(
+            """
+            DELETE FROM tool_call
+            WHERE id NOT IN (
+                SELECT MIN(id)
+                FROM tool_call
+                WHERE message_id IS NOT NULL
+                GROUP BY message_id
+            );
+        """
+        )
+    )
+
+    # Step 2: Add a unique constraint on message_id
+    op.create_unique_constraint(
+        constraint_name="uq_tool_call_message_id",
+        table_name="tool_call",
+        columns=["message_id"],
+    )
+
+
+def downgrade() -> None:
+    # Step 1: Drop the unique constraint on message_id
+    op.drop_constraint(
+        constraint_name="uq_tool_call_message_id",
+        table_name="tool_call",
+        type_="unique",
+    )

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/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

@@ -0,0 +1,45 @@
+"""add persona categories
+
+Revision ID: 47e5bef3a1d7
+Revises: dfbe9e93d3c7
+Create Date: 2024-11-05 18:55:02.221064
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "47e5bef3a1d7"
+down_revision = "dfbe9e93d3c7"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # Create the persona_category table
+    op.create_table(
+        "persona_category",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column("name", sa.String(), nullable=False),
+        sa.Column("description", sa.String(), nullable=True),
+        sa.PrimaryKeyConstraint("id"),
+        sa.UniqueConstraint("name"),
+    )
+
+    # Add category_id to persona table
+    op.add_column("persona", sa.Column("category_id", sa.Integer(), nullable=True))
+    op.create_foreign_key(
+        "fk_persona_category",
+        "persona",
+        "persona_category",
+        ["category_id"],
+        ["id"],
+        ondelete="SET NULL",
+    )
+
+
+def downgrade() -> None:
+    op.drop_constraint("persona_category_id_fkey", "persona", type_="foreignkey")
+    op.drop_column("persona", "category_id")
+    op.drop_table("persona_category")

backend/alembic/versions/4ee1287bd26a_add_multiple_slack_bot_support.py

@@ -0,0 +1,280 @@
+"""add_multiple_slack_bot_support
+
+Revision ID: 4ee1287bd26a
+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 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.
+revision = "4ee1287bd26a"
+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",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column("name", sa.String(), nullable=False),
+        sa.Column("enabled", sa.Boolean(), nullable=False, server_default="true"),
+        sa.Column("bot_token", sa.LargeBinary(), nullable=False),
+        sa.Column("app_token", sa.LargeBinary(), nullable=False),
+        sa.PrimaryKeyConstraint("id"),
+        sa.UniqueConstraint("bot_token"),
+        sa.UniqueConstraint("app_token"),
+    )
+
+    # # Create new slack_channel_config table
+    op.create_table(
+        "slack_channel_config",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column("slack_bot_id", sa.Integer(), nullable=True),
+        sa.Column("persona_id", sa.Integer(), nullable=True),
+        sa.Column("channel_config", postgresql.JSONB(), nullable=False),
+        sa.Column("response_type", sa.String(), nullable=False),
+        sa.Column(
+            "enable_auto_filters", sa.Boolean(), nullable=False, server_default="false"
+        ),
+        sa.ForeignKeyConstraint(
+            ["slack_bot_id"],
+            ["slack_bot.id"],
+        ),
+        sa.ForeignKeyConstraint(
+            ["persona_id"],
+            ["persona.id"],
+        ),
+        sa.PrimaryKeyConstraint("id"),
+    )
+
+    # 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
+
+    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)",
+            enabled=True,
+            bot_token=bot_token,
+            app_token=app_token,
+        )
+        session.add(new_slack_bot)
+        session.commit()
+        first_row_id = new_slack_bot.id
+
+    # Create a default bot if none exists
+    # This is in case there are no slack tokens but there are channels configured
+    op.execute(
+        sa.text(
+            """
+            INSERT INTO slack_bot (name, enabled, bot_token, app_token)
+            SELECT 'Default Bot', true, '', ''
+            WHERE NOT EXISTS (SELECT 1 FROM slack_bot)
+            RETURNING id;
+            """
+        )
+    )
+
+    # Get the bot ID to use (either from existing migration or newly created)
+    bot_id_query = sa.text(
+        """
+        SELECT COALESCE(
+            :first_row_id,
+            (SELECT id FROM slack_bot ORDER BY id ASC LIMIT 1)
+        ) as bot_id;
+        """
+    )
+    result = op.get_bind().execute(bot_id_query, {"first_row_id": first_row_id})
+    bot_id = result.scalar()
+
+    # CTE (Common Table Expression) that transforms the old slack_bot_config table data
+    # This splits up the channel_names into their own rows
+    channel_names_cte = """
+        WITH channel_names AS (
+            SELECT
+                sbc.id as config_id,
+                sbc.persona_id,
+                sbc.response_type,
+                sbc.enable_auto_filters,
+                jsonb_array_elements_text(sbc.channel_config->'channel_names') as channel_name,
+                sbc.channel_config->>'respond_tag_only' as respond_tag_only,
+                sbc.channel_config->>'respond_to_bots' as respond_to_bots,
+                sbc.channel_config->'respond_member_group_list' as respond_member_group_list,
+                sbc.channel_config->'answer_filters' as answer_filters,
+                sbc.channel_config->'follow_up_tags' as follow_up_tags
+            FROM slack_bot_config sbc
+        )
+    """
+
+    # Insert the channel names into the new slack_channel_config table
+    insert_statement = """
+        INSERT INTO slack_channel_config (
+            slack_bot_id,
+            persona_id,
+            channel_config,
+            response_type,
+            enable_auto_filters
+        )
+        SELECT
+            :bot_id,
+            channel_name.persona_id,
+            jsonb_build_object(
+                'channel_name', channel_name.channel_name,
+                'respond_tag_only',
+                COALESCE((channel_name.respond_tag_only)::boolean, false),
+                'respond_to_bots',
+                COALESCE((channel_name.respond_to_bots)::boolean, false),
+                'respond_member_group_list',
+                COALESCE(channel_name.respond_member_group_list, '[]'::jsonb),
+                'answer_filters',
+                COALESCE(channel_name.answer_filters, '[]'::jsonb),
+                'follow_up_tags',
+                COALESCE(channel_name.follow_up_tags, '[]'::jsonb)
+            ),
+            channel_name.response_type,
+            channel_name.enable_auto_filters
+        FROM channel_names channel_name;
+    """
+
+    op.execute(sa.text(channel_names_cte + insert_statement).bindparams(bot_id=bot_id))
+
+    # 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")
+    # Rename the table
+    op.rename_table(
+        "slack_bot_config__standard_answer_category",
+        "slack_channel_config__standard_answer_category",
+    )
+
+    # Rename the column
+    op.alter_column(
+        "slack_channel_config__standard_answer_category",
+        "slack_bot_config_id",
+        new_column_name="slack_channel_config_id",
+    )
+
+    # 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
+    op.create_table(
+        "slack_bot_config",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column("persona_id", sa.Integer(), nullable=True),
+        sa.Column("channel_config", postgresql.JSONB(), nullable=False),
+        sa.Column("response_type", sa.String(), nullable=False),
+        sa.Column("enable_auto_filters", sa.Boolean(), nullable=False),
+        sa.ForeignKeyConstraint(
+            ["persona_id"],
+            ["persona.id"],
+        ),
+        sa.PrimaryKeyConstraint("id"),
+    )
+
+    # Migrate data back to the old format
+    # Group by persona_id to combine channel names back into arrays
+    op.execute(
+        sa.text(
+            """
+            INSERT INTO slack_bot_config (
+                persona_id,
+                channel_config,
+                response_type,
+                enable_auto_filters
+            )
+            SELECT DISTINCT ON (persona_id)
+                persona_id,
+                jsonb_build_object(
+                    'channel_names', (
+                        SELECT jsonb_agg(c.channel_config->>'channel_name')
+                        FROM slack_channel_config c
+                        WHERE c.persona_id = scc.persona_id
+                    ),
+                    'respond_tag_only', (channel_config->>'respond_tag_only')::boolean,
+                    'respond_to_bots', (channel_config->>'respond_to_bots')::boolean,
+                    'respond_member_group_list', channel_config->'respond_member_group_list',
+                    'answer_filters', channel_config->'answer_filters',
+                    'follow_up_tags', channel_config->'follow_up_tags'
+                ),
+                response_type,
+                enable_auto_filters
+            FROM slack_channel_config scc
+            WHERE persona_id IS NOT NULL;
+            """
+        )
+    )
+
+    # Rename the table back
+    op.rename_table(
+        "slack_channel_config__standard_answer_category",
+        "slack_bot_config__standard_answer_category",
+    )
+
+    # Rename the column back
+    op.alter_column(
+        "slack_bot_config__standard_answer_category",
+        "slack_channel_config_id",
+        new_column_name="slack_bot_config_id",
+    )
+
+    # Try to save the first bot's tokens back to KV store
+    try:
+        first_bot = (
+            op.get_bind()
+            .execute(
+                sa.text(
+                    "SELECT bot_token, app_token FROM slack_bot ORDER BY id LIMIT 1"
+                )
+            )
+            .first()
+        )
+        if first_bot and first_bot.bot_token and first_bot.app_token:
+            tokens = {
+                "bot_token": first_bot.bot_token,
+                "app_token": first_bot.app_token,
+            }
+            get_kv_store().store("slack_bot_tokens_config_key", tokens)
+    except Exception:
+        logger.warning("Failed to save tokens back to KV store")
+
+    # Drop the new tables in reverse order
+    op.drop_table("slack_channel_config")
+    op.drop_table("slack_bot")

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/5b29123cd710_nullable_search_settings_for_historic_.py

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

backend/alembic/versions/5d12a446f5c0_add_api_version_and_deployment_name_to_.py

@@ -0,0 +1,30 @@
+"""add api_version and deployment_name to search settings
+
+Revision ID: 5d12a446f5c0
+Revises: e4334d5b33ba
+Create Date: 2024-10-08 15:56:07.975636
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "5d12a446f5c0"
+down_revision = "e4334d5b33ba"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "embedding_provider", sa.Column("api_version", sa.String(), nullable=True)
+    )
+    op.add_column(
+        "embedding_provider", sa.Column("deployment_name", sa.String(), nullable=True)
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("embedding_provider", "deployment_name")
+    op.drop_column("embedding_provider", "api_version")

backend/alembic/versions/6756efa39ada_id_uuid_for_chat_session.py

@@ -0,0 +1,153 @@
+"""Migrate chat_session and chat_message tables to use UUID primary keys
+
+Revision ID: 6756efa39ada
+Revises: 5d12a446f5c0
+Create Date: 2024-10-15 17:47:44.108537
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+revision = "6756efa39ada"
+down_revision = "5d12a446f5c0"
+branch_labels = None
+depends_on = None
+
+"""
+This script:
+1. Adds UUID columns to chat_session and chat_message
+2. Populates new columns with UUIDs
+3. Updates foreign key relationships
+4. Removes old integer ID columns
+
+Note: Downgrade will assign new integer IDs, not restore original ones.
+"""
+
+
+def upgrade() -> None:
+    op.execute("CREATE EXTENSION IF NOT EXISTS pgcrypto;")
+
+    op.add_column(
+        "chat_session",
+        sa.Column(
+            "new_id",
+            sa.UUID(as_uuid=True),
+            server_default=sa.text("gen_random_uuid()"),
+            nullable=False,
+        ),
+    )
+
+    op.execute("UPDATE chat_session SET new_id = gen_random_uuid();")
+
+    op.add_column(
+        "chat_message",
+        sa.Column("new_chat_session_id", sa.UUID(as_uuid=True), nullable=True),
+    )
+
+    op.execute(
+        """
+        UPDATE chat_message
+        SET new_chat_session_id = cs.new_id
+        FROM chat_session cs
+        WHERE chat_message.chat_session_id = cs.id;
+        """
+    )
+
+    op.drop_constraint(
+        "chat_message_chat_session_id_fkey", "chat_message", type_="foreignkey"
+    )
+
+    op.drop_column("chat_message", "chat_session_id")
+    op.alter_column(
+        "chat_message", "new_chat_session_id", new_column_name="chat_session_id"
+    )
+
+    op.drop_constraint("chat_session_pkey", "chat_session", type_="primary")
+    op.drop_column("chat_session", "id")
+    op.alter_column("chat_session", "new_id", new_column_name="id")
+
+    op.create_primary_key("chat_session_pkey", "chat_session", ["id"])
+
+    op.create_foreign_key(
+        "chat_message_chat_session_id_fkey",
+        "chat_message",
+        "chat_session",
+        ["chat_session_id"],
+        ["id"],
+        ondelete="CASCADE",
+    )
+
+
+def downgrade() -> None:
+    op.drop_constraint(
+        "chat_message_chat_session_id_fkey", "chat_message", type_="foreignkey"
+    )
+
+    op.add_column(
+        "chat_session",
+        sa.Column("old_id", sa.Integer, autoincrement=True, nullable=True),
+    )
+
+    op.execute("CREATE SEQUENCE chat_session_old_id_seq OWNED BY chat_session.old_id;")
+    op.execute(
+        "ALTER TABLE chat_session ALTER COLUMN old_id SET DEFAULT nextval('chat_session_old_id_seq');"
+    )
+
+    op.execute(
+        "UPDATE chat_session SET old_id = nextval('chat_session_old_id_seq') WHERE old_id IS NULL;"
+    )
+
+    op.alter_column("chat_session", "old_id", nullable=False)
+
+    op.drop_constraint("chat_session_pkey", "chat_session", type_="primary")
+    op.create_primary_key("chat_session_pkey", "chat_session", ["old_id"])
+
+    op.add_column(
+        "chat_message",
+        sa.Column("old_chat_session_id", sa.Integer, nullable=True),
+    )
+
+    op.execute(
+        """
+        UPDATE chat_message
+        SET old_chat_session_id = cs.old_id
+        FROM chat_session cs
+        WHERE chat_message.chat_session_id = cs.id;
+        """
+    )
+
+    op.drop_column("chat_message", "chat_session_id")
+    op.alter_column(
+        "chat_message", "old_chat_session_id", new_column_name="chat_session_id"
+    )
+
+    op.create_foreign_key(
+        "chat_message_chat_session_id_fkey",
+        "chat_message",
+        "chat_session",
+        ["chat_session_id"],
+        ["old_id"],
+        ondelete="CASCADE",
+    )
+
+    op.drop_column("chat_session", "id")
+    op.alter_column("chat_session", "old_id", new_column_name="id")
+
+    op.alter_column(
+        "chat_session",
+        "id",
+        type_=sa.Integer(),
+        existing_type=sa.Integer(),
+        existing_nullable=False,
+        existing_server_default=False,
+    )
+
+    # Rename the sequence
+    op.execute("ALTER SEQUENCE chat_session_old_id_seq RENAME TO chat_session_id_seq;")
+
+    # Update the default value to use the renamed sequence
+    op.alter_column(
+        "chat_session",
+        "id",
+        server_default=sa.text("nextval('chat_session_id_seq'::regclass)"),
+    )

backend/alembic/versions/6d562f86c78b_remove_default_bot.py

@@ -0,0 +1,45 @@
+"""remove default bot
+
+Revision ID: 6d562f86c78b
+Revises: 177de57c21c9
+Create Date: 2024-11-22 11:51:29.331336
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "6d562f86c78b"
+down_revision = "177de57c21c9"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.execute(
+        sa.text(
+            """
+            DELETE FROM slack_bot
+            WHERE name = 'Default Bot'
+            AND bot_token = ''
+            AND app_token = ''
+            AND NOT EXISTS (
+                SELECT 1 FROM slack_channel_config
+                WHERE slack_channel_config.slack_bot_id = slack_bot.id
+            )
+            """
+        )
+    )
+
+
+def downgrade() -> None:
+    op.execute(
+        sa.text(
+            """
+            INSERT INTO slack_bot (name, enabled, bot_token, app_token)
+            SELECT 'Default Bot', true, '', ''
+            WHERE NOT EXISTS (SELECT 1 FROM slack_bot)
+            RETURNING id;
+            """
+        )
+    )

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.search.enums import RecencyBiasSetting
-from danswer.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/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/93560ba1b118_add_web_ui_option_to_slack_config.py

@@ -0,0 +1,35 @@
+"""add web ui option to slack config
+
+Revision ID: 93560ba1b118
+Revises: 6d562f86c78b
+Create Date: 2024-11-24 06:36:17.490612
+
+"""
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision = "93560ba1b118"
+down_revision = "6d562f86c78b"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # Add show_continue_in_web_ui with default False to all existing channel_configs
+    op.execute(
+        """
+        UPDATE slack_channel_config
+        SET channel_config = channel_config || '{"show_continue_in_web_ui": false}'::jsonb
+        WHERE NOT channel_config ? 'show_continue_in_web_ui'
+        """
+    )
+
+
+def downgrade() -> None:
+    # Remove show_continue_in_web_ui from all channel_configs
+    op.execute(
+        """
+        UPDATE slack_channel_config
+        SET channel_config = channel_config - 'show_continue_in_web_ui'
+        """
+    )

backend/alembic/versions/949b4a92a401_remove_rt.py

@@ -0,0 +1,72 @@
+"""remove rt
+
+Revision ID: 949b4a92a401
+Revises: 1b10e1fda030
+Create Date: 2024-10-26 13:06:06.937969
+
+"""
+from alembic import op
+from sqlalchemy.orm import Session
+from sqlalchemy import text
+
+# Import your models and constants
+from onyx.db.models import (
+    Connector,
+    ConnectorCredentialPair,
+    Credential,
+    IndexAttempt,
+)
+
+
+# revision identifiers, used by Alembic.
+revision = "949b4a92a401"
+down_revision = "1b10e1fda030"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # Deletes all RequestTracker connectors and associated data
+    bind = op.get_bind()
+    session = Session(bind=bind)
+
+    # Get connectors using raw SQL
+    result = bind.execute(
+        text("SELECT id FROM connector WHERE source = 'requesttracker'")
+    )
+    connector_ids = [row[0] for row in result]
+
+    if connector_ids:
+        cc_pairs_to_delete = (
+            session.query(ConnectorCredentialPair)
+            .filter(ConnectorCredentialPair.connector_id.in_(connector_ids))
+            .all()
+        )
+
+        cc_pair_ids = [cc_pair.id for cc_pair in cc_pairs_to_delete]
+
+        if cc_pair_ids:
+            session.query(IndexAttempt).filter(
+                IndexAttempt.connector_credential_pair_id.in_(cc_pair_ids)
+            ).delete(synchronize_session=False)
+
+            session.query(ConnectorCredentialPair).filter(
+                ConnectorCredentialPair.id.in_(cc_pair_ids)
+            ).delete(synchronize_session=False)
+
+        credential_ids = [cc_pair.credential_id for cc_pair in cc_pairs_to_delete]
+        if credential_ids:
+            session.query(Credential).filter(Credential.id.in_(credential_ids)).delete(
+                synchronize_session=False
+            )
+
+        session.query(Connector).filter(Connector.id.in_(connector_ids)).delete(
+            synchronize_session=False
+        )
+
+    session.commit()
+
+
+def downgrade() -> None:
+    # No-op downgrade as we cannot restore deleted data
+    pass

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/9cf5c00f72fe_add_creator_to_cc_pair.py

@@ -0,0 +1,30 @@
+"""add creator to cc pair
+
+Revision ID: 9cf5c00f72fe
+Revises: 26b931506ecb
+Create Date: 2024-11-12 15:16:42.682902
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "9cf5c00f72fe"
+down_revision = "26b931506ecb"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "connector_credential_pair",
+        sa.Column(
+            "creator_id",
+            sa.UUID(as_uuid=True),
+            nullable=True,
+        ),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("connector_credential_pair", "creator_id")

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/a8c2065484e6_add_auto_scroll_to_user_model.py

@@ -0,0 +1,27 @@
+"""add auto scroll to user model
+
+Revision ID: a8c2065484e6
+Revises: abe7378b8217
+Create Date: 2024-11-22 17:34:09.690295
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "a8c2065484e6"
+down_revision = "abe7378b8217"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "user",
+        sa.Column("auto_scroll", sa.Boolean(), nullable=True, server_default=None),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("user", "auto_scroll")

backend/alembic/versions/abe7378b8217_add_indexing_trigger_to_cc_pair.py

@@ -0,0 +1,30 @@
+"""add indexing trigger to cc_pair
+
+Revision ID: abe7378b8217
+Revises: 6d562f86c78b
+Create Date: 2024-11-26 19:09:53.481171
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "abe7378b8217"
+down_revision = "93560ba1b118"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "connector_credential_pair",
+        sa.Column(
+            "indexing_trigger",
+            sa.Enum("UPDATE", "REINDEX", name="indexingmode", native_enum=False),
+            nullable=True,
+        ),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("connector_credential_pair", "indexing_trigger")

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/b082fec533f0_make_last_attempt_status_nullable.py

@@ -31,6 +31,12 @@ def upgrade() -> None:
 
 
 def downgrade() -> None:
+    # First, update any null values to a default value
+    op.execute(
+        "UPDATE connector_credential_pair SET last_attempt_status = 'NOT_STARTED' WHERE last_attempt_status IS NULL"
+    )
+
+    # Then, make the column non-nullable
     op.alter_column(
         "connector_credential_pair",
         "last_attempt_status",

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"
@@ -288,6 +288,15 @@ def upgrade() -> None:
 
 
 def downgrade() -> None:
+    # NOTE: you will lose all chat history. This is to satisfy the non-nullable constraints
+    # below
+    op.execute("DELETE FROM chat_feedback")
+    op.execute("DELETE FROM chat_message__search_doc")
+    op.execute("DELETE FROM document_retrieval_feedback")
+    op.execute("DELETE FROM document_retrieval_feedback")
+    op.execute("DELETE FROM chat_message")
+    op.execute("DELETE FROM chat_session")
+
     op.drop_constraint(
         "chat_feedback__chat_message_fk", "chat_feedback", type_="foreignkey"
     )

backend/alembic/versions/b72ed7a5db0e_remove_description_from_starter_messages.py

@@ -0,0 +1,48 @@
+"""remove description from starter messages
+
+Revision ID: b72ed7a5db0e
+Revises: 33cb72ea4d80
+Create Date: 2024-11-03 15:55:28.944408
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "b72ed7a5db0e"
+down_revision = "33cb72ea4d80"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.execute(
+        sa.text(
+            """
+            UPDATE persona
+            SET starter_messages = (
+                SELECT jsonb_agg(elem - 'description')
+                FROM jsonb_array_elements(starter_messages) elem
+            )
+            WHERE starter_messages IS NOT NULL
+              AND jsonb_typeof(starter_messages) = 'array'
+            """
+        )
+    )
+
+
+def downgrade() -> None:
+    op.execute(
+        sa.text(
+            """
+            UPDATE persona
+            SET starter_messages = (
+                SELECT jsonb_agg(elem || '{"description": ""}')
+                FROM jsonb_array_elements(starter_messages) elem
+            )
+            WHERE starter_messages IS NOT NULL
+              AND jsonb_typeof(starter_messages) = 'array'
+            """
+        )
+    )

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/c0fd6e4da83a_add_recent_assistants.py

@@ -0,0 +1,29 @@
+"""add recent assistants
+
+Revision ID: c0fd6e4da83a
+Revises: b72ed7a5db0e
+Create Date: 2024-11-03 17:28:54.916618
+
+"""
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision = "c0fd6e4da83a"
+down_revision = "b72ed7a5db0e"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "user",
+        sa.Column(
+            "recent_assistants", postgresql.JSONB(), server_default="[]", nullable=False
+        ),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("user", "recent_assistants")

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/c99d76fcd298_add_nullable_to_persona_id_in_chat_.py

@@ -23,6 +23,56 @@ def upgrade() -> None:
 
 
 def downgrade() -> None:
+    # Delete chat messages and feedback first since they reference chat sessions
+    # Get chat messages from sessions with null persona_id
+    chat_messages_query = """
+        SELECT id
+        FROM chat_message
+        WHERE chat_session_id IN (
+            SELECT id
+            FROM chat_session
+            WHERE persona_id IS NULL
+        )
+    """
+
+    # Delete dependent records first
+    op.execute(
+        f"""
+        DELETE FROM document_retrieval_feedback
+        WHERE chat_message_id IN (
+            {chat_messages_query}
+        )
+    """
+    )
+    op.execute(
+        f"""
+        DELETE FROM chat_message__search_doc
+        WHERE chat_message_id IN (
+            {chat_messages_query}
+        )
+    """
+    )
+
+    # Delete chat messages
+    op.execute(
+        """
+        DELETE FROM chat_message
+        WHERE chat_session_id IN (
+            SELECT id
+            FROM chat_session
+            WHERE persona_id IS NULL
+        )
+    """
+    )
+
+    # Now we can safely delete the chat sessions
+    op.execute(
+        """
+        DELETE FROM chat_session
+        WHERE persona_id IS NULL
+    """
+    )
+
     op.alter_column(
         "chat_session",
         "persona_id",

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/dfbe9e93d3c7_extended_role_for_non_web.py

@@ -0,0 +1,42 @@
+"""extended_role_for_non_web
+
+Revision ID: dfbe9e93d3c7
+Revises: 9cf5c00f72fe
+Create Date: 2024-11-16 07:54:18.727906
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "dfbe9e93d3c7"
+down_revision = "9cf5c00f72fe"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.execute(
+        """
+        UPDATE "user"
+        SET role = 'EXT_PERM_USER'
+        WHERE has_web_login = false
+    """
+    )
+    op.drop_column("user", "has_web_login")
+
+
+def downgrade() -> None:
+    op.add_column(
+        "user",
+        sa.Column("has_web_login", sa.Boolean(), nullable=False, server_default="true"),
+    )
+
+    op.execute(
+        """
+        UPDATE "user"
+        SET has_web_login = false,
+            role = 'BASIC'
+        WHERE role IN ('SLACK_USER', 'EXT_PERM_USER')
+    """
+    )

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/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

@@ -1,5 +1,6 @@
 import asyncio
 from logging.config import fileConfig
+from typing import Literal
 
 from sqlalchemy import pool
 from sqlalchemy.engine import Connection
@@ -7,8 +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.
@@ -37,8 +38,15 @@ EXCLUDE_TABLES = {"kombu_queue", "kombu_message"}
 
 def include_object(
     object: SchemaItem,
-    name: str,
-    type_: str,
+    name: str | None,
+    type_: Literal[
+        "schema",
+        "table",
+        "column",
+        "index",
+        "unique_constraint",
+        "foreign_key_constraint",
+    ],
     reflected: bool,
     compare_to: SchemaItem | None,
 ) -> bool:

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 "0.3-dev"

backend/danswer/auth/noauth_user.py

@@ -1,38 +0,0 @@
-from collections.abc import Mapping
-from typing import Any
-from typing import cast
-
-from danswer.auth.schemas import UserRole
-from danswer.configs.constants import KV_NO_AUTH_USER_PREFERENCES_KEY
-from danswer.key_value_store.store import KeyValueStore
-from danswer.key_value_store.store import KvKeyNotFoundError
-from danswer.server.manage.models import UserInfo
-from danswer.server.manage.models import UserPreferences
-
-
-def set_no_auth_user_preferences(
-    store: KeyValueStore, preferences: UserPreferences
-) -> None:
-    store.store(KV_NO_AUTH_USER_PREFERENCES_KEY, preferences.model_dump())
-
-
-def load_no_auth_user_preferences(store: KeyValueStore) -> UserPreferences:
-    try:
-        preferences_data = cast(
-            Mapping[str, Any], store.load(KV_NO_AUTH_USER_PREFERENCES_KEY)
-        )
-        return UserPreferences(**preferences_data)
-    except KvKeyNotFoundError:
-        return UserPreferences(chosen_assistants=None, default_model=None)
-
-
-def fetch_no_auth_user(store: KeyValueStore) -> UserInfo:
-    return UserInfo(
-        id="__no_auth_user__",
-        email="anonymous@danswer.ai",
-        is_active=True,
-        is_superuser=False,
-        is_verified=True,
-        role=UserRole.ADMIN,
-        preferences=load_no_auth_user_preferences(store),
-    )

backend/danswer/auth/users.py

@@ -1,656 +0,0 @@
-import smtplib
-import uuid
-from collections.abc import AsyncGenerator
-from datetime import datetime
-from datetime import timezone
-from email.mime.multipart import MIMEMultipart
-from email.mime.text import MIMEText
-from typing import Optional
-from typing import Tuple
-
-import jwt
-from email_validator import EmailNotValidError
-from email_validator import EmailUndeliverableError
-from email_validator import validate_email
-from fastapi import APIRouter
-from fastapi import Depends
-from fastapi import HTTPException
-from fastapi import Request
-from fastapi import Response
-from fastapi import status
-from fastapi.security import OAuth2PasswordRequestForm
-from fastapi_users import BaseUserManager
-from fastapi_users import exceptions
-from fastapi_users import FastAPIUsers
-from fastapi_users import models
-from fastapi_users import schemas
-from fastapi_users import UUIDIDMixin
-from fastapi_users.authentication import AuthenticationBackend
-from fastapi_users.authentication import CookieTransport
-from fastapi_users.authentication import JWTStrategy
-from fastapi_users.authentication import Strategy
-from fastapi_users.authentication.strategy.db import AccessTokenDatabase
-from fastapi_users.authentication.strategy.db import DatabaseStrategy
-from fastapi_users.openapi import OpenAPIResponseType
-from fastapi_users_db_sqlalchemy import SQLAlchemyUserDatabase
-from sqlalchemy import select
-from sqlalchemy.orm import attributes
-from sqlalchemy.orm import Session
-
-from danswer.auth.invited_users import get_invited_users
-from danswer.auth.schemas import UserCreate
-from danswer.auth.schemas import UserRole
-from danswer.auth.schemas import UserUpdate
-from danswer.configs.app_configs import AUTH_TYPE
-from danswer.configs.app_configs import DISABLE_AUTH
-from danswer.configs.app_configs import EMAIL_FROM
-from danswer.configs.app_configs import MULTI_TENANT
-from danswer.configs.app_configs import REQUIRE_EMAIL_VERIFICATION
-from danswer.configs.app_configs import SECRET_JWT_KEY
-from danswer.configs.app_configs import SESSION_EXPIRE_TIME_SECONDS
-from danswer.configs.app_configs import SMTP_PASS
-from danswer.configs.app_configs import SMTP_PORT
-from danswer.configs.app_configs import SMTP_SERVER
-from danswer.configs.app_configs import SMTP_USER
-from danswer.configs.app_configs import TRACK_EXTERNAL_IDP_EXPIRY
-from danswer.configs.app_configs import USER_AUTH_SECRET
-from danswer.configs.app_configs import VALID_EMAIL_DOMAINS
-from danswer.configs.app_configs import WEB_DOMAIN
-from danswer.configs.constants import AuthType
-from danswer.configs.constants import DANSWER_API_KEY_DUMMY_EMAIL_DOMAIN
-from danswer.configs.constants import DANSWER_API_KEY_PREFIX
-from danswer.configs.constants import UNNAMED_KEY_PLACEHOLDER
-from danswer.db.auth import get_access_token_db
-from danswer.db.auth import get_default_admin_user_emails
-from danswer.db.auth import get_user_count
-from danswer.db.auth import get_user_db
-from danswer.db.auth import SQLAlchemyUserAdminDB
-from danswer.db.engine import get_async_session_with_tenant
-from danswer.db.engine import get_session
-from danswer.db.engine import get_session_with_tenant
-from danswer.db.engine import get_sqlalchemy_engine
-from danswer.db.models import AccessToken
-from danswer.db.models import OAuthAccount
-from danswer.db.models import User
-from danswer.db.models import UserTenantMapping
-from danswer.db.users import get_user_by_email
-from danswer.utils.logger import setup_logger
-from danswer.utils.telemetry import optional_telemetry
-from danswer.utils.telemetry import RecordType
-from danswer.utils.variable_functionality import fetch_versioned_implementation
-from shared_configs.configs import current_tenant_id
-
-logger = setup_logger()
-
-
-def is_user_admin(user: User | None) -> bool:
-    if AUTH_TYPE == AuthType.DISABLED:
-        return True
-    if user and user.role == UserRole.ADMIN:
-        return True
-    return False
-
-
-def verify_auth_setting() -> None:
-    if AUTH_TYPE not in [AuthType.DISABLED, AuthType.BASIC, AuthType.GOOGLE_OAUTH]:
-        raise ValueError(
-            "User must choose a valid user authentication method: "
-            "disabled, basic, or google_oauth"
-        )
-    logger.notice(f"Using Auth Type: {AUTH_TYPE.value}")
-
-
-def get_display_email(email: str | None, space_less: bool = False) -> str:
-    if email and email.endswith(DANSWER_API_KEY_DUMMY_EMAIL_DOMAIN):
-        name = email.split("@")[0]
-        if name == DANSWER_API_KEY_PREFIX + UNNAMED_KEY_PLACEHOLDER:
-            return "Unnamed API Key"
-
-        if space_less:
-            return name
-
-        return name.replace("API_KEY__", "API Key: ")
-
-    return email or ""
-
-
-def user_needs_to_be_verified() -> bool:
-    # all other auth types besides basic should require users to be
-    # verified
-    return AUTH_TYPE != AuthType.BASIC or REQUIRE_EMAIL_VERIFICATION
-
-
-def verify_email_is_invited(email: str) -> None:
-    whitelist = get_invited_users()
-    if not whitelist:
-        return
-
-    if not email:
-        raise PermissionError("Email must be specified")
-
-    try:
-        email_info = validate_email(email)
-    except EmailUndeliverableError:
-        raise PermissionError("Email is not valid")
-
-    for email_whitelist in whitelist:
-        try:
-            # normalized emails are now being inserted into the db
-            # we can remove this normalization on read after some time has passed
-            email_info_whitelist = validate_email(email_whitelist)
-        except EmailNotValidError:
-            continue
-
-        # oddly, normalization does not include lowercasing the user part of the
-        # email address ... which we want to allow
-        if email_info.normalized.lower() == email_info_whitelist.normalized.lower():
-            return
-
-    raise PermissionError("User not on allowed user whitelist")
-
-
-def verify_email_in_whitelist(email: str, tenant_id: str | None = None) -> None:
-    with get_session_with_tenant(tenant_id) as db_session:
-        if not get_user_by_email(email, db_session):
-            verify_email_is_invited(email)
-
-
-def verify_email_domain(email: str) -> None:
-    if VALID_EMAIL_DOMAINS:
-        if email.count("@") != 1:
-            raise HTTPException(
-                status_code=status.HTTP_400_BAD_REQUEST,
-                detail="Email is not valid",
-            )
-        domain = email.split("@")[-1]
-        if domain not in VALID_EMAIL_DOMAINS:
-            raise HTTPException(
-                status_code=status.HTTP_400_BAD_REQUEST,
-                detail="Email domain is not valid",
-            )
-
-
-def get_tenant_id_for_email(email: str) -> str:
-    if not MULTI_TENANT:
-        return "public"
-    # Implement logic to get tenant_id from the mapping table
-    with Session(get_sqlalchemy_engine()) as db_session:
-        result = db_session.execute(
-            select(UserTenantMapping.tenant_id).where(UserTenantMapping.email == email)
-        )
-        tenant_id = result.scalar_one_or_none()
-    if tenant_id is None:
-        raise exceptions.UserNotExists()
-    return tenant_id
-
-
-def send_user_verification_email(
-    user_email: str,
-    token: str,
-    mail_from: str = EMAIL_FROM,
-) -> None:
-    msg = MIMEMultipart()
-    msg["Subject"] = "Danswer Email Verification"
-    msg["To"] = user_email
-    if mail_from:
-        msg["From"] = mail_from
-
-    link = f"{WEB_DOMAIN}/auth/verify-email?token={token}"
-
-    body = MIMEText(f"Click the following link to verify your email address: {link}")
-    msg.attach(body)
-
-    with smtplib.SMTP(SMTP_SERVER, SMTP_PORT) as s:
-        s.starttls()
-        # If credentials fails with gmail, check (You need an app password, not just the basic email password)
-        # https://support.google.com/accounts/answer/185833?sjid=8512343437447396151-NA
-        s.login(SMTP_USER, SMTP_PASS)
-        s.send_message(msg)
-
-
-class UserManager(UUIDIDMixin, BaseUserManager[User, uuid.UUID]):
-    reset_password_token_secret = USER_AUTH_SECRET
-    verification_token_secret = USER_AUTH_SECRET
-
-    async def create(
-        self,
-        user_create: schemas.UC | UserCreate,
-        safe: bool = False,
-        request: Optional[Request] = None,
-    ) -> User:
-        verify_email_is_invited(user_create.email)
-        verify_email_domain(user_create.email)
-        if hasattr(user_create, "role"):
-            user_count = await get_user_count()
-            if user_count == 0 or user_create.email in get_default_admin_user_emails():
-                user_create.role = UserRole.ADMIN
-            else:
-                user_create.role = UserRole.BASIC
-        user = None
-        try:
-            user = await super().create(user_create, safe=safe, request=request)  # type: ignore
-        except exceptions.UserAlreadyExists:
-            user = await self.get_by_email(user_create.email)
-            # Handle case where user has used product outside of web and is now creating an account through web
-            if (
-                not user.has_web_login
-                and hasattr(user_create, "has_web_login")
-                and user_create.has_web_login
-            ):
-                user_update = UserUpdate(
-                    password=user_create.password,
-                    has_web_login=True,
-                    role=user_create.role,
-                    is_verified=user_create.is_verified,
-                )
-                user = await self.update(user_update, user)
-            else:
-                raise exceptions.UserAlreadyExists()
-        return user
-
-    async def on_after_login(
-        self,
-        user: User,
-        request: Request | None = None,
-        response: Response | None = None,
-    ) -> None:
-        if response is None or not MULTI_TENANT:
-            return
-
-        tenant_id = get_tenant_id_for_email(user.email)
-
-        tenant_token = jwt.encode(
-            {"tenant_id": tenant_id}, SECRET_JWT_KEY, algorithm="HS256"
-        )
-
-        response.set_cookie(
-            key="tenant_details",
-            value=tenant_token,
-            httponly=True,
-            secure=WEB_DOMAIN.startswith("https"),
-            samesite="lax",
-        )
-
-    async def oauth_callback(
-        self: "BaseUserManager[models.UOAP, models.ID]",
-        oauth_name: str,
-        access_token: str,
-        account_id: str,
-        account_email: str,
-        expires_at: Optional[int] = None,
-        refresh_token: Optional[str] = None,
-        request: Optional[Request] = None,
-        *,
-        associate_by_email: bool = False,
-        is_verified_by_default: bool = False,
-    ) -> models.UOAP:
-        # Get tenant_id from mapping table
-        try:
-            tenant_id = (
-                get_tenant_id_for_email(account_email) if MULTI_TENANT else "public"
-            )
-        except exceptions.UserNotExists:
-            raise HTTPException(status_code=401, detail="User not found")
-
-        if not tenant_id:
-            raise HTTPException(status_code=401, detail="User not found")
-
-        token = None
-        async with get_async_session_with_tenant(tenant_id) as db_session:
-            token = current_tenant_id.set(tenant_id)
-            # Print a list of tables in the current database session
-            verify_email_in_whitelist(account_email, tenant_id)
-            verify_email_domain(account_email)
-            if MULTI_TENANT:
-                tenant_user_db = SQLAlchemyUserAdminDB(db_session, User, OAuthAccount)
-                self.user_db = tenant_user_db
-                self.database = tenant_user_db
-
-            oauth_account_dict = {
-                "oauth_name": oauth_name,
-                "access_token": access_token,
-                "account_id": account_id,
-                "account_email": account_email,
-                "expires_at": expires_at,
-                "refresh_token": refresh_token,
-            }
-
-            try:
-                # Attempt to get user by OAuth account
-                user = await self.get_by_oauth_account(oauth_name, account_id)
-
-            except exceptions.UserNotExists:
-                try:
-                    # Attempt to get user by email
-                    user = await self.get_by_email(account_email)
-                    if not associate_by_email:
-                        raise exceptions.UserAlreadyExists()
-
-                    user = await self.user_db.add_oauth_account(
-                        user, oauth_account_dict
-                    )
-
-                    # If user not found by OAuth account or email, create a new user
-                except exceptions.UserNotExists:
-                    password = self.password_helper.generate()
-                    user_dict = {
-                        "email": account_email,
-                        "hashed_password": self.password_helper.hash(password),
-                        "is_verified": is_verified_by_default,
-                    }
-
-                    user = await self.user_db.create(user_dict)
-                    user = await self.user_db.add_oauth_account(
-                        user, oauth_account_dict
-                    )
-                    await self.on_after_register(user, request)
-
-            else:
-                for existing_oauth_account in user.oauth_accounts:
-                    if (
-                        existing_oauth_account.account_id == account_id
-                        and existing_oauth_account.oauth_name == oauth_name
-                    ):
-                        user = await self.user_db.update_oauth_account(
-                            user, existing_oauth_account, oauth_account_dict
-                        )
-
-            # NOTE: Most IdPs have very short expiry times, and we don't want to force the user to
-            # re-authenticate that frequently, so by default this is disabled
-
-            if expires_at and TRACK_EXTERNAL_IDP_EXPIRY:
-                oidc_expiry = datetime.fromtimestamp(expires_at, tz=timezone.utc)
-                await self.user_db.update(
-                    user, update_dict={"oidc_expiry": oidc_expiry}
-                )
-
-            # Handle case where user has used product outside of web and is now creating an account through web
-            if not user.has_web_login:  # type: ignore
-                await self.user_db.update(
-                    user,
-                    {
-                        "is_verified": is_verified_by_default,
-                        "has_web_login": True,
-                    },
-                )
-                user.is_verified = is_verified_by_default
-                user.has_web_login = True  # type: ignore
-
-            # this is needed if an organization goes from `TRACK_EXTERNAL_IDP_EXPIRY=true` to `false`
-            # otherwise, the oidc expiry will always be old, and the user will never be able to login
-            if (
-                user.oidc_expiry is not None  # type: ignore
-                and not TRACK_EXTERNAL_IDP_EXPIRY
-            ):
-                await self.user_db.update(user, {"oidc_expiry": None})
-                user.oidc_expiry = None  # type: ignore
-
-            if token:
-                current_tenant_id.reset(token)
-
-            return user
-
-    async def on_after_register(
-        self, user: User, request: Optional[Request] = None
-    ) -> None:
-        logger.notice(f"User {user.id} has registered.")
-        optional_telemetry(
-            record_type=RecordType.SIGN_UP,
-            data={"action": "create"},
-            user_id=str(user.id),
-        )
-
-    async def on_after_forgot_password(
-        self, user: User, token: str, request: Optional[Request] = None
-    ) -> None:
-        logger.notice(f"User {user.id} has forgot their password. Reset token: {token}")
-
-    async def on_after_request_verify(
-        self, user: User, token: str, request: Optional[Request] = None
-    ) -> None:
-        verify_email_domain(user.email)
-
-        logger.notice(
-            f"Verification requested for user {user.id}. Verification token: {token}"
-        )
-
-        send_user_verification_email(user.email, token)
-
-    async def authenticate(
-        self, credentials: OAuth2PasswordRequestForm
-    ) -> Optional[User]:
-        email = credentials.username
-
-        # Get tenant_id from mapping table
-
-        tenant_id = get_tenant_id_for_email(email)
-        if not tenant_id:
-            # User not found in mapping
-            self.password_helper.hash(credentials.password)
-            return None
-
-        # Create a tenant-specific session
-        async with get_async_session_with_tenant(tenant_id) as tenant_session:
-            tenant_user_db: SQLAlchemyUserDatabase = SQLAlchemyUserDatabase(
-                tenant_session, User
-            )
-            self.user_db = tenant_user_db
-
-            # Proceed with authentication
-            try:
-                user = await self.get_by_email(email)
-
-            except exceptions.UserNotExists:
-                self.password_helper.hash(credentials.password)
-                return None
-
-            has_web_login = attributes.get_attribute(user, "has_web_login")
-
-            if not has_web_login:
-                raise HTTPException(
-                    status_code=status.HTTP_403_FORBIDDEN,
-                    detail="NO_WEB_LOGIN_AND_HAS_NO_PASSWORD",
-                )
-
-            verified, updated_password_hash = self.password_helper.verify_and_update(
-                credentials.password, user.hashed_password
-            )
-            if not verified:
-                return None
-
-            if updated_password_hash is not None:
-                await self.user_db.update(
-                    user, {"hashed_password": updated_password_hash}
-                )
-
-            return user
-
-
-async def get_user_manager(
-    user_db: SQLAlchemyUserDatabase = Depends(get_user_db),
-) -> AsyncGenerator[UserManager, None]:
-    yield UserManager(user_db)
-
-
-cookie_transport = CookieTransport(
-    cookie_max_age=SESSION_EXPIRE_TIME_SECONDS,
-    cookie_secure=WEB_DOMAIN.startswith("https"),
-)
-
-
-def get_jwt_strategy() -> JWTStrategy:
-    return JWTStrategy(
-        secret=USER_AUTH_SECRET,
-        lifetime_seconds=SESSION_EXPIRE_TIME_SECONDS,
-    )
-
-
-def get_database_strategy(
-    access_token_db: AccessTokenDatabase[AccessToken] = Depends(get_access_token_db),
-) -> DatabaseStrategy:
-    return DatabaseStrategy(
-        access_token_db, lifetime_seconds=SESSION_EXPIRE_TIME_SECONDS  # type: ignore
-    )
-
-
-auth_backend = AuthenticationBackend(
-    name="jwt" if MULTI_TENANT else "database",
-    transport=cookie_transport,
-    get_strategy=get_jwt_strategy if MULTI_TENANT else get_database_strategy,  # type: ignore
-)  # type: ignore
-
-
-class FastAPIUserWithLogoutRouter(FastAPIUsers[models.UP, models.ID]):
-    def get_logout_router(
-        self,
-        backend: AuthenticationBackend,
-        requires_verification: bool = REQUIRE_EMAIL_VERIFICATION,
-    ) -> APIRouter:
-        """
-        Provide a router for logout only for OAuth/OIDC Flows.
-        This way the login router does not need to be included
-        """
-        router = APIRouter()
-
-        get_current_user_token = self.authenticator.current_user_token(
-            active=True, verified=requires_verification
-        )
-
-        logout_responses: OpenAPIResponseType = {
-            **{
-                status.HTTP_401_UNAUTHORIZED: {
-                    "description": "Missing token or inactive user."
-                }
-            },
-            **backend.transport.get_openapi_logout_responses_success(),
-        }
-
-        @router.post(
-            "/logout", name=f"auth:{backend.name}.logout", responses=logout_responses
-        )
-        async def logout(
-            user_token: Tuple[models.UP, str] = Depends(get_current_user_token),
-            strategy: Strategy[models.UP, models.ID] = Depends(backend.get_strategy),
-        ) -> Response:
-            user, token = user_token
-            return await backend.logout(strategy, user, token)
-
-        return router
-
-
-fastapi_users = FastAPIUserWithLogoutRouter[User, uuid.UUID](
-    get_user_manager, [auth_backend]
-)
-
-
-# NOTE: verified=REQUIRE_EMAIL_VERIFICATION is not used here since we
-# take care of that in `double_check_user` ourself. This is needed, since
-# we want the /me endpoint to still return a user even if they are not
-# yet verified, so that the frontend knows they exist
-optional_fastapi_current_user = fastapi_users.current_user(active=True, optional=True)
-
-
-async def optional_user_(
-    request: Request,
-    user: User | None,
-    db_session: Session,
-) -> User | None:
-    """NOTE: `request` and `db_session` are not used here, but are included
-    for the EE version of this function."""
-    return user
-
-
-async def optional_user(
-    request: Request,
-    db_session: Session = Depends(get_session),
-    user: User | None = Depends(optional_fastapi_current_user),
-) -> User | None:
-    versioned_fetch_user = fetch_versioned_implementation(
-        "danswer.auth.users", "optional_user_"
-    )
-    return await versioned_fetch_user(request, user, db_session)
-
-
-async def double_check_user(
-    user: User | None,
-    optional: bool = DISABLE_AUTH,
-    include_expired: bool = False,
-) -> User | None:
-    if optional:
-        return None
-
-    if user is None:
-        raise HTTPException(
-            status_code=status.HTTP_403_FORBIDDEN,
-            detail="Access denied. User is not authenticated.",
-        )
-
-    if user_needs_to_be_verified() and not user.is_verified:
-        raise HTTPException(
-            status_code=status.HTTP_403_FORBIDDEN,
-            detail="Access denied. User is not verified.",
-        )
-
-    if (
-        user.oidc_expiry
-        and user.oidc_expiry < datetime.now(timezone.utc)
-        and not include_expired
-    ):
-        raise HTTPException(
-            status_code=status.HTTP_403_FORBIDDEN,
-            detail="Access denied. User's OIDC token has expired.",
-        )
-
-    return user
-
-
-async def current_user_with_expired_token(
-    user: User | None = Depends(optional_user),
-) -> User | None:
-    return await double_check_user(user, include_expired=True)
-
-
-async def current_user(
-    user: User | None = Depends(optional_user),
-) -> User | None:
-    return await double_check_user(user)
-
-
-async def current_curator_or_admin_user(
-    user: User | None = Depends(current_user),
-) -> User | None:
-    if DISABLE_AUTH:
-        return None
-
-    if not user or not hasattr(user, "role"):
-        raise HTTPException(
-            status_code=status.HTTP_403_FORBIDDEN,
-            detail="Access denied. User is not authenticated or lacks role information.",
-        )
-
-    allowed_roles = {UserRole.GLOBAL_CURATOR, UserRole.CURATOR, UserRole.ADMIN}
-    if user.role not in allowed_roles:
-        raise HTTPException(
-            status_code=status.HTTP_403_FORBIDDEN,
-            detail="Access denied. User is not a curator or admin.",
-        )
-
-    return user
-
-
-async def current_admin_user(user: User | None = Depends(current_user)) -> User | None:
-    if DISABLE_AUTH:
-        return None
-
-    if not user or not hasattr(user, "role") or user.role != UserRole.ADMIN:
-        raise HTTPException(
-            status_code=status.HTTP_403_FORBIDDEN,
-            detail="Access denied. User must be an admin to perform this action.",
-        )
-
-    return user
-
-
-def get_default_admin_user_emails_() -> list[str]:
-    # No default seeding available for Danswer MIT
-    return []

backend/danswer/background/celery/celery_app.py

@@ -1,494 +0,0 @@
-import logging
-import time
-from datetime import timedelta
-from typing import Any
-
-import redis
-from celery import bootsteps  # type: ignore
-from celery import Celery
-from celery import current_task
-from celery import signals
-from celery import Task
-from celery.exceptions import WorkerShutdown
-from celery.signals import beat_init
-from celery.signals import worker_init
-from celery.signals import worker_ready
-from celery.signals import worker_shutdown
-from celery.states import READY_STATES
-from celery.utils.log import get_task_logger
-
-from danswer.background.celery.celery_redis import RedisConnectorCredentialPair
-from danswer.background.celery.celery_redis import RedisConnectorDeletion
-from danswer.background.celery.celery_redis import RedisConnectorPruning
-from danswer.background.celery.celery_redis import RedisDocumentSet
-from danswer.background.celery.celery_redis import RedisUserGroup
-from danswer.background.celery.celery_utils import celery_is_worker_primary
-from danswer.background.update import get_all_tenant_ids
-from danswer.configs.constants import CELERY_PRIMARY_WORKER_LOCK_TIMEOUT
-from danswer.configs.constants import DanswerCeleryPriority
-from danswer.configs.constants import DanswerRedisLocks
-from danswer.configs.constants import POSTGRES_CELERY_BEAT_APP_NAME
-from danswer.configs.constants import POSTGRES_CELERY_WORKER_HEAVY_APP_NAME
-from danswer.configs.constants import POSTGRES_CELERY_WORKER_LIGHT_APP_NAME
-from danswer.configs.constants import POSTGRES_CELERY_WORKER_PRIMARY_APP_NAME
-from danswer.db.engine import SqlEngine
-from danswer.redis.redis_pool import get_redis_client
-from danswer.utils.logger import ColoredFormatter
-from danswer.utils.logger import PlainFormatter
-from danswer.utils.logger import setup_logger
-
-logger = setup_logger()
-
-# use this within celery tasks to get celery task specific logging
-task_logger = get_task_logger(__name__)
-
-celery_app = Celery(__name__)
-celery_app.config_from_object(
-    "danswer.background.celery.celeryconfig"
-)  # Load configuration from 'celeryconfig.py'
-
-
-@signals.task_postrun.connect
-def celery_task_postrun(
-    sender: Any | None = None,
-    task_id: str | None = None,
-    task: Task | None = None,
-    args: tuple | None = None,
-    kwargs: dict | None = None,
-    retval: Any | None = None,
-    state: str | None = None,
-    **kwds: Any,
-) -> None:
-    """We handle this signal in order to remove completed tasks
-    from their respective tasksets. This allows us to track the progress of document set
-    and user group syncs.
-
-    This function runs after any task completes (both success and failure)
-    Note that this signal does not fire on a task that failed to complete and is going
-    to be retried.
-    """
-    if not task:
-        return
-
-    task_logger.debug(f"Task {task.name} (ID: {task_id}) completed with state: {state}")
-
-    if state not in READY_STATES:
-        return
-
-    if not task_id:
-        return
-
-    r = get_redis_client()
-
-    if task_id.startswith(RedisConnectorCredentialPair.PREFIX):
-        r.srem(RedisConnectorCredentialPair.get_taskset_key(), task_id)
-        return
-
-    if task_id.startswith(RedisDocumentSet.PREFIX):
-        document_set_id = RedisDocumentSet.get_id_from_task_id(task_id)
-        if document_set_id is not None:
-            rds = RedisDocumentSet(document_set_id)
-            r.srem(rds.taskset_key, task_id)
-        return
-
-    if task_id.startswith(RedisUserGroup.PREFIX):
-        usergroup_id = RedisUserGroup.get_id_from_task_id(task_id)
-        if usergroup_id is not None:
-            rug = RedisUserGroup(usergroup_id)
-            r.srem(rug.taskset_key, task_id)
-        return
-
-    if task_id.startswith(RedisConnectorDeletion.PREFIX):
-        cc_pair_id = RedisConnectorDeletion.get_id_from_task_id(task_id)
-        if cc_pair_id is not None:
-            rcd = RedisConnectorDeletion(cc_pair_id)
-            r.srem(rcd.taskset_key, task_id)
-        return
-
-    if task_id.startswith(RedisConnectorPruning.SUBTASK_PREFIX):
-        cc_pair_id = RedisConnectorPruning.get_id_from_task_id(task_id)
-        if cc_pair_id is not None:
-            rcp = RedisConnectorPruning(cc_pair_id)
-            r.srem(rcp.taskset_key, task_id)
-        return
-
-
-@beat_init.connect
-def on_beat_init(sender: Any, **kwargs: Any) -> None:
-    SqlEngine.set_app_name(POSTGRES_CELERY_BEAT_APP_NAME)
-    SqlEngine.init_engine(pool_size=2, max_overflow=0)
-
-
-@worker_init.connect
-def on_worker_init(sender: Any, **kwargs: Any) -> None:
-    # decide some initial startup settings based on the celery worker's hostname
-    # (set at the command line)
-    hostname = sender.hostname
-    if hostname.startswith("light"):
-        SqlEngine.set_app_name(POSTGRES_CELERY_WORKER_LIGHT_APP_NAME)
-        SqlEngine.init_engine(pool_size=sender.concurrency, max_overflow=8)
-    elif hostname.startswith("heavy"):
-        SqlEngine.set_app_name(POSTGRES_CELERY_WORKER_HEAVY_APP_NAME)
-        SqlEngine.init_engine(pool_size=8, max_overflow=0)
-    else:
-        SqlEngine.set_app_name(POSTGRES_CELERY_WORKER_PRIMARY_APP_NAME)
-        SqlEngine.init_engine(pool_size=8, max_overflow=0)
-
-    r = get_redis_client()
-
-    WAIT_INTERVAL = 5
-    WAIT_LIMIT = 60
-
-    time_start = time.monotonic()
-    logger.info("Redis: Readiness check starting.")
-    while True:
-        try:
-            if r.ping():
-                break
-        except Exception:
-            pass
-
-        time_elapsed = time.monotonic() - time_start
-        logger.info(
-            f"Redis: Ping failed. elapsed={time_elapsed:.1f} timeout={WAIT_LIMIT:.1f}"
-        )
-        if time_elapsed > WAIT_LIMIT:
-            msg = (
-                f"Redis: Readiness check did not succeed within the timeout "
-                f"({WAIT_LIMIT} seconds). Exiting..."
-            )
-            logger.error(msg)
-            raise WorkerShutdown(msg)
-
-        time.sleep(WAIT_INTERVAL)
-
-    logger.info("Redis: Readiness check succeeded. Continuing...")
-
-    if not celery_is_worker_primary(sender):
-        logger.info("Running as a secondary celery worker.")
-        logger.info("Waiting for primary worker to be ready...")
-        time_start = time.monotonic()
-        while True:
-            if r.exists(DanswerRedisLocks.PRIMARY_WORKER):
-                break
-
-            time.monotonic()
-            time_elapsed = time.monotonic() - time_start
-            logger.info(
-                f"Primary worker is not ready yet. elapsed={time_elapsed:.1f} timeout={WAIT_LIMIT:.1f}"
-            )
-            if time_elapsed > WAIT_LIMIT:
-                msg = (
-                    f"Primary worker was not ready within the timeout. "
-                    f"({WAIT_LIMIT} seconds). Exiting..."
-                )
-                logger.error(msg)
-                raise WorkerShutdown(msg)
-
-            time.sleep(WAIT_INTERVAL)
-
-        logger.info("Wait for primary worker completed successfully. Continuing...")
-        return
-
-    logger.info("Running as the primary celery worker.")
-
-    # This is singleton work that should be done on startup exactly once
-    # by the primary worker
-    r = get_redis_client()
-
-    # For the moment, we're assuming that we are the only primary worker
-    # that should be running.
-    # TODO: maybe check for or clean up another zombie primary worker if we detect it
-    r.delete(DanswerRedisLocks.PRIMARY_WORKER)
-
-    # this process wide lock is taken to help other workers start up in order.
-    # it is planned to use this lock to enforce singleton behavior on the primary
-    # worker, since the primary worker does redis cleanup on startup, but this isn't
-    # implemented yet.
-    lock = r.lock(
-        DanswerRedisLocks.PRIMARY_WORKER,
-        timeout=CELERY_PRIMARY_WORKER_LOCK_TIMEOUT,
-    )
-
-    logger.info("Primary worker lock: Acquire starting.")
-    acquired = lock.acquire(blocking_timeout=CELERY_PRIMARY_WORKER_LOCK_TIMEOUT / 2)
-    if acquired:
-        logger.info("Primary worker lock: Acquire succeeded.")
-    else:
-        logger.error("Primary worker lock: Acquire failed!")
-        raise WorkerShutdown("Primary worker lock could not be acquired!")
-
-    sender.primary_worker_lock = lock
-
-    r.delete(DanswerRedisLocks.CHECK_VESPA_SYNC_BEAT_LOCK)
-    r.delete(DanswerRedisLocks.MONITOR_VESPA_SYNC_BEAT_LOCK)
-
-    r.delete(RedisConnectorCredentialPair.get_taskset_key())
-    r.delete(RedisConnectorCredentialPair.get_fence_key())
-
-    for key in r.scan_iter(RedisDocumentSet.TASKSET_PREFIX + "*"):
-        r.delete(key)
-
-    for key in r.scan_iter(RedisDocumentSet.FENCE_PREFIX + "*"):
-        r.delete(key)
-
-    for key in r.scan_iter(RedisUserGroup.TASKSET_PREFIX + "*"):
-        r.delete(key)
-
-    for key in r.scan_iter(RedisUserGroup.FENCE_PREFIX + "*"):
-        r.delete(key)
-
-    for key in r.scan_iter(RedisConnectorDeletion.TASKSET_PREFIX + "*"):
-        r.delete(key)
-
-    for key in r.scan_iter(RedisConnectorDeletion.FENCE_PREFIX + "*"):
-        r.delete(key)
-
-    for key in r.scan_iter(RedisConnectorPruning.TASKSET_PREFIX + "*"):
-        r.delete(key)
-
-    for key in r.scan_iter(RedisConnectorPruning.GENERATOR_COMPLETE_PREFIX + "*"):
-        r.delete(key)
-
-    for key in r.scan_iter(RedisConnectorPruning.GENERATOR_PROGRESS_PREFIX + "*"):
-        r.delete(key)
-
-    for key in r.scan_iter(RedisConnectorPruning.FENCE_PREFIX + "*"):
-        r.delete(key)
-
-
-@worker_ready.connect
-def on_worker_ready(sender: Any, **kwargs: Any) -> None:
-    task_logger.info("worker_ready signal received.")
-
-
-@worker_shutdown.connect
-def on_worker_shutdown(sender: Any, **kwargs: Any) -> None:
-    if not celery_is_worker_primary(sender):
-        return
-
-    if not sender.primary_worker_lock:
-        return
-
-    logger.info("Releasing primary worker lock.")
-    lock = sender.primary_worker_lock
-    if lock.owned():
-        lock.release()
-        sender.primary_worker_lock = None
-
-
-class CeleryTaskPlainFormatter(PlainFormatter):
-    def format(self, record: logging.LogRecord) -> str:
-        task = current_task
-        if task and task.request:
-            record.__dict__.update(task_id=task.request.id, task_name=task.name)
-            record.msg = f"[{task.name}({task.request.id})] {record.msg}"
-
-        return super().format(record)
-
-
-class CeleryTaskColoredFormatter(ColoredFormatter):
-    def format(self, record: logging.LogRecord) -> str:
-        task = current_task
-        if task and task.request:
-            record.__dict__.update(task_id=task.request.id, task_name=task.name)
-            record.msg = f"[{task.name}({task.request.id})] {record.msg}"
-
-        return super().format(record)
-
-
-@signals.setup_logging.connect
-def on_setup_logging(
-    loglevel: Any, logfile: Any, format: Any, colorize: Any, **kwargs: Any
-) -> None:
-    # TODO: could unhardcode format and colorize and accept these as options from
-    # celery's config
-
-    # reformats celery's worker logger
-    root_logger = logging.getLogger()
-
-    root_handler = logging.StreamHandler()  # Set up a handler for the root logger
-    root_formatter = ColoredFormatter(
-        "%(asctime)s %(filename)30s %(lineno)4s: %(message)s",
-        datefmt="%m/%d/%Y %I:%M:%S %p",
-    )
-    root_handler.setFormatter(root_formatter)
-    root_logger.addHandler(root_handler)  # Apply the handler to the root logger
-
-    if logfile:
-        root_file_handler = logging.FileHandler(logfile)
-        root_file_formatter = PlainFormatter(
-            "%(asctime)s %(filename)30s %(lineno)4s: %(message)s",
-            datefmt="%m/%d/%Y %I:%M:%S %p",
-        )
-        root_file_handler.setFormatter(root_file_formatter)
-        root_logger.addHandler(root_file_handler)
-
-    root_logger.setLevel(loglevel)
-
-    # reformats celery's task logger
-    task_formatter = CeleryTaskColoredFormatter(
-        "%(asctime)s %(filename)30s %(lineno)4s: %(message)s",
-        datefmt="%m/%d/%Y %I:%M:%S %p",
-    )
-    task_handler = logging.StreamHandler()  # Set up a handler for the task logger
-    task_handler.setFormatter(task_formatter)
-    task_logger.addHandler(task_handler)  # Apply the handler to the task logger
-
-    if logfile:
-        task_file_handler = logging.FileHandler(logfile)
-        task_file_formatter = CeleryTaskPlainFormatter(
-            "%(asctime)s %(filename)30s %(lineno)4s: %(message)s",
-            datefmt="%m/%d/%Y %I:%M:%S %p",
-        )
-        task_file_handler.setFormatter(task_file_formatter)
-        task_logger.addHandler(task_file_handler)
-
-    task_logger.setLevel(loglevel)
-    task_logger.propagate = False
-
-
-class HubPeriodicTask(bootsteps.StartStopStep):
-    """Regularly reacquires the primary worker lock outside of the task queue.
-    Use the task_logger in this class to avoid double logging.
-
-    This cannot be done inside a regular beat task because it must run on schedule and
-    a queue of existing work would starve the task from running.
-    """
-
-    # it's unclear to me whether using the hub's timer or the bootstep timer is better
-    requires = {"celery.worker.components:Hub"}
-
-    def __init__(self, worker: Any, **kwargs: Any) -> None:
-        self.interval = CELERY_PRIMARY_WORKER_LOCK_TIMEOUT / 8  # Interval in seconds
-        self.task_tref = None
-
-    def start(self, worker: Any) -> None:
-        if not celery_is_worker_primary(worker):
-            return
-
-        # Access the worker's event loop (hub)
-        hub = worker.consumer.controller.hub
-
-        # Schedule the periodic task
-        self.task_tref = hub.call_repeatedly(
-            self.interval, self.run_periodic_task, worker
-        )
-        task_logger.info("Scheduled periodic task with hub.")
-
-    def run_periodic_task(self, worker: Any) -> None:
-        try:
-            if not worker.primary_worker_lock:
-                return
-
-            if not hasattr(worker, "primary_worker_lock"):
-                return
-
-            r = get_redis_client()
-
-            lock: redis.lock.Lock = worker.primary_worker_lock
-
-            if lock.owned():
-                task_logger.debug("Reacquiring primary worker lock.")
-                lock.reacquire()
-            else:
-                task_logger.warning(
-                    "Full acquisition of primary worker lock. "
-                    "Reasons could be computer sleep or a clock change."
-                )
-                lock = r.lock(
-                    DanswerRedisLocks.PRIMARY_WORKER,
-                    timeout=CELERY_PRIMARY_WORKER_LOCK_TIMEOUT,
-                )
-
-                task_logger.info("Primary worker lock: Acquire starting.")
-                acquired = lock.acquire(
-                    blocking_timeout=CELERY_PRIMARY_WORKER_LOCK_TIMEOUT / 2
-                )
-                if acquired:
-                    task_logger.info("Primary worker lock: Acquire succeeded.")
-                else:
-                    task_logger.error("Primary worker lock: Acquire failed!")
-                    raise TimeoutError("Primary worker lock could not be acquired!")
-
-                worker.primary_worker_lock = lock
-        except Exception:
-            task_logger.exception("HubPeriodicTask.run_periodic_task exceptioned.")
-
-    def stop(self, worker: Any) -> None:
-        # Cancel the scheduled task when the worker stops
-        if self.task_tref:
-            self.task_tref.cancel()
-            task_logger.info("Canceled periodic task with hub.")
-
-
-celery_app.steps["worker"].add(HubPeriodicTask)
-
-celery_app.autodiscover_tasks(
-    [
-        "danswer.background.celery.tasks.connector_deletion",
-        "danswer.background.celery.tasks.periodic",
-        "danswer.background.celery.tasks.pruning",
-        "danswer.background.celery.tasks.shared",
-        "danswer.background.celery.tasks.vespa",
-    ]
-)
-
-#####
-# Celery Beat (Periodic Tasks) Settings
-#####
-
-tenant_ids = get_all_tenant_ids()
-
-tasks_to_schedule = [
-    {
-        "name": "check-for-vespa-sync",
-        "task": "check_for_vespa_sync_task",
-        "schedule": timedelta(seconds=5),
-        "options": {"priority": DanswerCeleryPriority.HIGH},
-    },
-    {
-        "name": "check-for-connector-deletion",
-        "task": "check_for_connector_deletion_task",
-        "schedule": timedelta(seconds=60),
-        "options": {"priority": DanswerCeleryPriority.HIGH},
-    },
-    {
-        "name": "check-for-prune",
-        "task": "check_for_prune_task_2",
-        "schedule": timedelta(seconds=10),
-        "options": {"priority": DanswerCeleryPriority.HIGH},
-    },
-    {
-        "name": "kombu-message-cleanup",
-        "task": "kombu_message_cleanup_task",
-        "schedule": timedelta(seconds=3600),
-        "options": {"priority": DanswerCeleryPriority.LOWEST},
-    },
-    {
-        "name": "monitor-vespa-sync",
-        "task": "monitor_vespa_sync",
-        "schedule": timedelta(seconds=5),
-        "options": {"priority": DanswerCeleryPriority.HIGH},
-    },
-]
-
-# Build the celery beat schedule dynamically
-beat_schedule = {}
-
-for tenant_id in tenant_ids:
-    for task in tasks_to_schedule:
-        task_name = f"{task['name']}-{tenant_id}"  # Unique name for each scheduled task
-        beat_schedule[task_name] = {
-            "task": task["task"],
-            "schedule": task["schedule"],
-            "options": task["options"],
-            "args": (tenant_id,),  # Must pass tenant_id as an argument
-        }
-
-# Include any existing beat schedules
-existing_beat_schedule = celery_app.conf.beat_schedule or {}
-beat_schedule.update(existing_beat_schedule)
-
-# Update the Celery app configuration once
-celery_app.conf.beat_schedule = beat_schedule

backend/danswer/background/celery/celery_redis.py

@@ -1,492 +0,0 @@
-# These are helper objects for tracking the keys we need to write in redis
-import time
-from abc import ABC
-from abc import abstractmethod
-from typing import cast
-from uuid import uuid4
-
-import redis
-from celery import Celery
-from redis import Redis
-from sqlalchemy.orm import Session
-
-from danswer.background.celery.celeryconfig import CELERY_SEPARATOR
-from danswer.configs.constants import CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT
-from danswer.configs.constants import DanswerCeleryPriority
-from danswer.configs.constants import DanswerCeleryQueues
-from danswer.db.connector_credential_pair import get_connector_credential_pair_from_id
-from danswer.db.document import construct_document_select_for_connector_credential_pair
-from danswer.db.document import (
-    construct_document_select_for_connector_credential_pair_by_needs_sync,
-)
-from danswer.db.document_set import construct_document_select_by_docset
-from danswer.utils.variable_functionality import fetch_versioned_implementation
-from danswer.utils.variable_functionality import global_version
-
-
-class RedisObjectHelper(ABC):
-    PREFIX = "base"
-    FENCE_PREFIX = PREFIX + "_fence"
-    TASKSET_PREFIX = PREFIX + "_taskset"
-
-    def __init__(self, id: int):
-        self._id: int = id
-
-    @property
-    def task_id_prefix(self) -> str:
-        return f"{self.PREFIX}_{self._id}"
-
-    @property
-    def fence_key(self) -> str:
-        # example: documentset_fence_1
-        return f"{self.FENCE_PREFIX}_{self._id}"
-
-    @property
-    def taskset_key(self) -> str:
-        # example: documentset_taskset_1
-        return f"{self.TASKSET_PREFIX}_{self._id}"
-
-    @staticmethod
-    def get_id_from_fence_key(key: str) -> int | None:
-        """
-        Extracts the object ID from a fence key in the format `PREFIX_fence_X`.
-
-        Args:
-            key (str): The fence key string.
-
-        Returns:
-            Optional[int]: The extracted ID if the key is in the correct format, otherwise None.
-        """
-        parts = key.split("_")
-        if len(parts) != 3:
-            return None
-
-        try:
-            object_id = int(parts[2])
-        except ValueError:
-            return None
-
-        return object_id
-
-    @staticmethod
-    def get_id_from_task_id(task_id: str) -> int | None:
-        """
-        Extracts the object ID from a task ID string.
-
-        This method assumes the task ID is formatted as `prefix_objectid_suffix`, where:
-        - `prefix` is an arbitrary string (e.g., the name of the task or entity),
-        - `objectid` is the ID you want to extract,
-        - `suffix` is another arbitrary string (e.g., a UUID).
-
-        Example:
-            If the input `task_id` is `documentset_1_cbfdc96a-80ca-4312-a242-0bb68da3c1dc`,
-            this method will return the string `"1"`.
-
-        Args:
-            task_id (str): The task ID string from which to extract the object ID.
-
-        Returns:
-            str | None: The extracted object ID if the task ID is in the correct format, otherwise None.
-        """
-        # example: task_id=documentset_1_cbfdc96a-80ca-4312-a242-0bb68da3c1dc
-        parts = task_id.split("_")
-        if len(parts) != 3:
-            return None
-
-        try:
-            object_id = int(parts[1])
-        except ValueError:
-            return None
-
-        return object_id
-
-    @abstractmethod
-    def generate_tasks(
-        self,
-        celery_app: Celery,
-        db_session: Session,
-        redis_client: Redis,
-        lock: redis.lock.Lock,
-        tenant_id: str | None,
-    ) -> int | None:
-        pass
-
-
-class RedisDocumentSet(RedisObjectHelper):
-    PREFIX = "documentset"
-    FENCE_PREFIX = PREFIX + "_fence"
-    TASKSET_PREFIX = PREFIX + "_taskset"
-
-    def generate_tasks(
-        self,
-        celery_app: Celery,
-        db_session: Session,
-        redis_client: Redis,
-        lock: redis.lock.Lock,
-        tenant_id: str | None,
-    ) -> int | None:
-        last_lock_time = time.monotonic()
-
-        async_results = []
-        stmt = construct_document_select_by_docset(self._id, current_only=False)
-        for doc in db_session.scalars(stmt).yield_per(1):
-            current_time = time.monotonic()
-            if current_time - last_lock_time >= (
-                CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT / 4
-            ):
-                lock.reacquire()
-                last_lock_time = current_time
-
-            # celery's default task id format is "dd32ded3-00aa-4884-8b21-42f8332e7fac"
-            # the key for the result is "celery-task-meta-dd32ded3-00aa-4884-8b21-42f8332e7fac"
-            # we prefix the task id so it's easier to keep track of who created the task
-            # aka "documentset_1_6dd32ded3-00aa-4884-8b21-42f8332e7fac"
-            custom_task_id = f"{self.task_id_prefix}_{uuid4()}"
-
-            # add to the set BEFORE creating the task.
-            redis_client.sadd(self.taskset_key, custom_task_id)
-
-            result = celery_app.send_task(
-                "vespa_metadata_sync_task",
-                kwargs=dict(document_id=doc.id, tenant_id=tenant_id),
-                queue=DanswerCeleryQueues.VESPA_METADATA_SYNC,
-                task_id=custom_task_id,
-                priority=DanswerCeleryPriority.LOW,
-            )
-
-            async_results.append(result)
-
-        return len(async_results)
-
-
-class RedisUserGroup(RedisObjectHelper):
-    PREFIX = "usergroup"
-    FENCE_PREFIX = PREFIX + "_fence"
-    TASKSET_PREFIX = PREFIX + "_taskset"
-
-    def generate_tasks(
-        self,
-        celery_app: Celery,
-        db_session: Session,
-        redis_client: Redis,
-        lock: redis.lock.Lock,
-        tenant_id: str | None,
-    ) -> int | None:
-        last_lock_time = time.monotonic()
-
-        async_results = []
-
-        if not global_version.is_ee_version():
-            return 0
-
-        try:
-            construct_document_select_by_usergroup = fetch_versioned_implementation(
-                "danswer.db.user_group",
-                "construct_document_select_by_usergroup",
-            )
-        except ModuleNotFoundError:
-            return 0
-
-        stmt = construct_document_select_by_usergroup(self._id)
-        for doc in db_session.scalars(stmt).yield_per(1):
-            current_time = time.monotonic()
-            if current_time - last_lock_time >= (
-                CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT / 4
-            ):
-                lock.reacquire()
-                last_lock_time = current_time
-
-            # celery's default task id format is "dd32ded3-00aa-4884-8b21-42f8332e7fac"
-            # the key for the result is "celery-task-meta-dd32ded3-00aa-4884-8b21-42f8332e7fac"
-            # we prefix the task id so it's easier to keep track of who created the task
-            # aka "documentset_1_6dd32ded3-00aa-4884-8b21-42f8332e7fac"
-            custom_task_id = f"{self.task_id_prefix}_{uuid4()}"
-
-            # add to the set BEFORE creating the task.
-            redis_client.sadd(self.taskset_key, custom_task_id)
-
-            result = celery_app.send_task(
-                "vespa_metadata_sync_task",
-                kwargs=dict(document_id=doc.id, tenant_id=tenant_id),
-                queue=DanswerCeleryQueues.VESPA_METADATA_SYNC,
-                task_id=custom_task_id,
-                priority=DanswerCeleryPriority.LOW,
-            )
-
-            async_results.append(result)
-
-        return len(async_results)
-
-
-class RedisConnectorCredentialPair(RedisObjectHelper):
-    """This class differs from the default in that the taskset used spans
-    all connectors and is not per connector."""
-
-    PREFIX = "connectorsync"
-    FENCE_PREFIX = PREFIX + "_fence"
-    TASKSET_PREFIX = PREFIX + "_taskset"
-
-    @classmethod
-    def get_fence_key(cls) -> str:
-        return RedisConnectorCredentialPair.FENCE_PREFIX
-
-    @classmethod
-    def get_taskset_key(cls) -> str:
-        return RedisConnectorCredentialPair.TASKSET_PREFIX
-
-    @property
-    def taskset_key(self) -> str:
-        """Notice that this is intentionally reusing the same taskset for all
-        connector syncs"""
-        # example: connector_taskset
-        return f"{self.TASKSET_PREFIX}"
-
-    def generate_tasks(
-        self,
-        celery_app: Celery,
-        db_session: Session,
-        redis_client: Redis,
-        lock: redis.lock.Lock,
-        tenant_id: str | None,
-    ) -> int | None:
-        last_lock_time = time.monotonic()
-
-        async_results = []
-        cc_pair = get_connector_credential_pair_from_id(self._id, db_session)
-        if not cc_pair:
-            return None
-
-        stmt = construct_document_select_for_connector_credential_pair_by_needs_sync(
-            cc_pair.connector_id, cc_pair.credential_id
-        )
-        for doc in db_session.scalars(stmt).yield_per(1):
-            current_time = time.monotonic()
-            if current_time - last_lock_time >= (
-                CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT / 4
-            ):
-                lock.reacquire()
-                last_lock_time = current_time
-
-            # celery's default task id format is "dd32ded3-00aa-4884-8b21-42f8332e7fac"
-            # the key for the result is "celery-task-meta-dd32ded3-00aa-4884-8b21-42f8332e7fac"
-            # we prefix the task id so it's easier to keep track of who created the task
-            # aka "documentset_1_6dd32ded3-00aa-4884-8b21-42f8332e7fac"
-            custom_task_id = f"{self.task_id_prefix}_{uuid4()}"
-
-            # add to the tracking taskset in redis BEFORE creating the celery task.
-            # note that for the moment we are using a single taskset key, not differentiated by cc_pair id
-            redis_client.sadd(
-                RedisConnectorCredentialPair.get_taskset_key(), custom_task_id
-            )
-
-            # Priority on sync's triggered by new indexing should be medium
-            result = celery_app.send_task(
-                "vespa_metadata_sync_task",
-                kwargs=dict(document_id=doc.id, tenant_id=tenant_id),
-                queue=DanswerCeleryQueues.VESPA_METADATA_SYNC,
-                task_id=custom_task_id,
-                priority=DanswerCeleryPriority.MEDIUM,
-            )
-
-            async_results.append(result)
-
-        return len(async_results)
-
-
-class RedisConnectorDeletion(RedisObjectHelper):
-    PREFIX = "connectordeletion"
-    FENCE_PREFIX = PREFIX + "_fence"
-    TASKSET_PREFIX = PREFIX + "_taskset"
-
-    def generate_tasks(
-        self,
-        celery_app: Celery,
-        db_session: Session,
-        redis_client: Redis,
-        lock: redis.lock.Lock,
-        tenant_id: str | None,
-    ) -> int | None:
-        last_lock_time = time.monotonic()
-
-        async_results = []
-        cc_pair = get_connector_credential_pair_from_id(self._id, db_session)
-        if not cc_pair:
-            return None
-
-        stmt = construct_document_select_for_connector_credential_pair(
-            cc_pair.connector_id, cc_pair.credential_id
-        )
-        for doc in db_session.scalars(stmt).yield_per(1):
-            current_time = time.monotonic()
-            if current_time - last_lock_time >= (
-                CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT / 4
-            ):
-                lock.reacquire()
-                last_lock_time = current_time
-
-            # celery's default task id format is "dd32ded3-00aa-4884-8b21-42f8332e7fac"
-            # the actual redis key is "celery-task-meta-dd32ded3-00aa-4884-8b21-42f8332e7fac"
-            # we prefix the task id so it's easier to keep track of who created the task
-            # aka "documentset_1_6dd32ded3-00aa-4884-8b21-42f8332e7fac"
-            custom_task_id = f"{self.task_id_prefix}_{uuid4()}"
-
-            # add to the tracking taskset in redis BEFORE creating the celery task.
-            # note that for the moment we are using a single taskset key, not differentiated by cc_pair id
-            redis_client.sadd(self.taskset_key, custom_task_id)
-
-            # Priority on sync's triggered by new indexing should be medium
-            result = celery_app.send_task(
-                "document_by_cc_pair_cleanup_task",
-                kwargs=dict(
-                    document_id=doc.id,
-                    connector_id=cc_pair.connector_id,
-                    credential_id=cc_pair.credential_id,
-                    tenant_id=tenant_id,
-                ),
-                queue=DanswerCeleryQueues.CONNECTOR_DELETION,
-                task_id=custom_task_id,
-                priority=DanswerCeleryPriority.MEDIUM,
-            )
-
-            async_results.append(result)
-
-        return len(async_results)
-
-
-class RedisConnectorPruning(RedisObjectHelper):
-    """Celery will kick off a long running generator task to crawl the connector and
-    find any missing docs, which will each then get a new cleanup task. The progress of
-    those tasks will then be monitored to completion.
-
-    Example rough happy path order:
-    Check connectorpruning_fence_1
-    Send generator task with id connectorpruning+generator_1_{uuid}
-
-    generator runs connector with callbacks that increment connectorpruning_generator_progress_1
-    generator creates many subtasks with id connectorpruning+sub_1_{uuid}
-      in taskset connectorpruning_taskset_1
-    on completion, generator sets connectorpruning_generator_complete_1
-
-    celery postrun removes subtasks from taskset
-    monitor beat task cleans up when taskset reaches 0 items
-    """
-
-    PREFIX = "connectorpruning"
-    FENCE_PREFIX = PREFIX + "_fence"  # a fence for the entire pruning process
-    GENERATOR_TASK_PREFIX = PREFIX + "+generator"
-
-    TASKSET_PREFIX = PREFIX + "_taskset"  # stores a list of prune tasks id's
-    SUBTASK_PREFIX = PREFIX + "+sub"
-
-    GENERATOR_PROGRESS_PREFIX = (
-        PREFIX + "_generator_progress"
-    )  # a signal that contains generator progress
-    GENERATOR_COMPLETE_PREFIX = (
-        PREFIX + "_generator_complete"
-    )  # a signal that the generator has finished
-
-    def __init__(self, id: int) -> None:
-        """id: the cc_pair_id of the connector credential pair"""
-
-        super().__init__(id)
-        self.documents_to_prune: set[str] = set()
-
-    @property
-    def generator_task_id_prefix(self) -> str:
-        return f"{self.GENERATOR_TASK_PREFIX}_{self._id}"
-
-    @property
-    def generator_progress_key(self) -> str:
-        # example: connectorpruning_generator_progress_1
-        return f"{self.GENERATOR_PROGRESS_PREFIX}_{self._id}"
-
-    @property
-    def generator_complete_key(self) -> str:
-        # example: connectorpruning_generator_complete_1
-        return f"{self.GENERATOR_COMPLETE_PREFIX}_{self._id}"
-
-    @property
-    def subtask_id_prefix(self) -> str:
-        return f"{self.SUBTASK_PREFIX}_{self._id}"
-
-    def generate_tasks(
-        self,
-        celery_app: Celery,
-        db_session: Session,
-        redis_client: Redis,
-        lock: redis.lock.Lock | None,
-        tenant_id: str | None,
-    ) -> int | None:
-        last_lock_time = time.monotonic()
-
-        async_results = []
-        cc_pair = get_connector_credential_pair_from_id(self._id, db_session)
-        if not cc_pair:
-            return None
-
-        for doc_id in self.documents_to_prune:
-            current_time = time.monotonic()
-            if lock and current_time - last_lock_time >= (
-                CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT / 4
-            ):
-                lock.reacquire()
-                last_lock_time = current_time
-
-            # celery's default task id format is "dd32ded3-00aa-4884-8b21-42f8332e7fac"
-            # the actual redis key is "celery-task-meta-dd32ded3-00aa-4884-8b21-42f8332e7fac"
-            # we prefix the task id so it's easier to keep track of who created the task
-            # aka "documentset_1_6dd32ded3-00aa-4884-8b21-42f8332e7fac"
-            custom_task_id = f"{self.subtask_id_prefix}_{uuid4()}"
-
-            # add to the tracking taskset in redis BEFORE creating the celery task.
-            # note that for the moment we are using a single taskset key, not differentiated by cc_pair id
-            redis_client.sadd(self.taskset_key, custom_task_id)
-
-            # Priority on sync's triggered by new indexing should be medium
-            result = celery_app.send_task(
-                "document_by_cc_pair_cleanup_task",
-                kwargs=dict(
-                    document_id=doc_id,
-                    connector_id=cc_pair.connector_id,
-                    credential_id=cc_pair.credential_id,
-                    tenant_id=tenant_id,
-                ),
-                queue=DanswerCeleryQueues.CONNECTOR_DELETION,
-                task_id=custom_task_id,
-                priority=DanswerCeleryPriority.MEDIUM,
-            )
-
-            async_results.append(result)
-
-        return len(async_results)
-
-    def is_pruning(self, db_session: Session, redis_client: Redis) -> bool:
-        """A single example of a helper method being refactored into the redis helper"""
-        cc_pair = get_connector_credential_pair_from_id(
-            cc_pair_id=self._id, db_session=db_session
-        )
-        if not cc_pair:
-            raise ValueError(f"cc_pair_id {self._id} does not exist.")
-
-        if redis_client.exists(self.fence_key):
-            return True
-
-        return False
-
-
-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/celery_run.py

@@ -1,9 +0,0 @@
-"""Entry point for running celery worker / celery beat."""
-from danswer.utils.variable_functionality import fetch_versioned_implementation
-from danswer.utils.variable_functionality import set_is_ee_based_on_env_variable
-
-
-set_is_ee_based_on_env_variable()
-celery_app = fetch_versioned_implementation(
-    "danswer.background.celery.celery_app", "celery_app"
-)

backend/danswer/background/celery/celery_utils.py

@@ -1,133 +0,0 @@
-from collections.abc import Callable
-from datetime import datetime
-from datetime import timezone
-from typing import Any
-
-from sqlalchemy.orm import Session
-
-from danswer.background.celery.celery_redis import RedisConnectorDeletion
-from danswer.configs.app_configs import MAX_PRUNING_DOCUMENT_RETRIEVAL_PER_MINUTE
-from danswer.connectors.cross_connector_utils.rate_limit_wrapper import (
-    rate_limit_builder,
-)
-from danswer.connectors.interfaces import BaseConnector
-from danswer.connectors.interfaces import IdConnector
-from danswer.connectors.interfaces import LoadConnector
-from danswer.connectors.interfaces import PollConnector
-from danswer.connectors.models import Document
-from danswer.db.connector_credential_pair import get_connector_credential_pair
-from danswer.db.enums import TaskStatus
-from danswer.db.models import TaskQueueState
-from danswer.redis.redis_pool import get_redis_client
-from danswer.server.documents.models import DeletionAttemptSnapshot
-from danswer.utils.logger import setup_logger
-
-
-logger = setup_logger()
-
-
-def _get_deletion_status(
-    connector_id: int, credential_id: int, db_session: Session
-) -> TaskQueueState | None:
-    """We no longer store TaskQueueState in the DB for a deletion attempt.
-    This function populates TaskQueueState by just checking redis.
-    """
-    cc_pair = get_connector_credential_pair(
-        connector_id=connector_id, credential_id=credential_id, db_session=db_session
-    )
-    if not cc_pair:
-        return None
-
-    rcd = RedisConnectorDeletion(cc_pair.id)
-
-    r = get_redis_client()
-    if not r.exists(rcd.fence_key):
-        return None
-
-    return TaskQueueState(
-        task_id="", task_name=rcd.fence_key, status=TaskStatus.STARTED
-    )
-
-
-def get_deletion_attempt_snapshot(
-    connector_id: int, credential_id: int, db_session: Session
-) -> DeletionAttemptSnapshot | None:
-    deletion_task = _get_deletion_status(connector_id, credential_id, db_session)
-    if not deletion_task:
-        return None
-
-    return DeletionAttemptSnapshot(
-        connector_id=connector_id,
-        credential_id=credential_id,
-        status=deletion_task.status,
-    )
-
-
-def document_batch_to_ids(doc_batch: list[Document]) -> set[str]:
-    return {doc.id for doc in doc_batch}
-
-
-def extract_ids_from_runnable_connector(
-    runnable_connector: BaseConnector,
-    progress_callback: Callable[[int], None] | None = None,
-) -> set[str]:
-    """
-    If the PruneConnector hasnt been implemented for the given connector, just pull
-    all docs using the load_from_state and grab out the IDs.
-
-    Optionally, a callback can be passed to handle the length of each document batch.
-    """
-    all_connector_doc_ids: set[str] = set()
-
-    doc_batch_generator = None
-    if isinstance(runnable_connector, IdConnector):
-        all_connector_doc_ids = runnable_connector.retrieve_all_source_ids()
-    elif isinstance(runnable_connector, LoadConnector):
-        doc_batch_generator = runnable_connector.load_from_state()
-    elif isinstance(runnable_connector, PollConnector):
-        start = datetime(1970, 1, 1, tzinfo=timezone.utc).timestamp()
-        end = datetime.now(timezone.utc).timestamp()
-        doc_batch_generator = runnable_connector.poll_source(start=start, end=end)
-    else:
-        raise RuntimeError("Pruning job could not find a valid runnable_connector.")
-
-    if doc_batch_generator:
-        doc_batch_processing_func = document_batch_to_ids
-        if MAX_PRUNING_DOCUMENT_RETRIEVAL_PER_MINUTE:
-            doc_batch_processing_func = rate_limit_builder(
-                max_calls=MAX_PRUNING_DOCUMENT_RETRIEVAL_PER_MINUTE, period=60
-            )(document_batch_to_ids)
-        for doc_batch in doc_batch_generator:
-            if progress_callback:
-                progress_callback(len(doc_batch))
-            all_connector_doc_ids.update(doc_batch_processing_func(doc_batch))
-
-    return all_connector_doc_ids
-
-
-def celery_is_listening_to_queue(worker: Any, name: str) -> bool:
-    """Checks to see if we're listening to the named queue"""
-
-    # how to get a list of queues this worker is listening to
-    # https://stackoverflow.com/questions/29790523/how-to-determine-which-queues-a-celery-worker-is-consuming-at-runtime
-    queue_names = list(worker.app.amqp.queues.consume_from.keys())
-    for queue_name in queue_names:
-        if queue_name == name:
-            return True
-
-    return False
-
-
-def celery_is_worker_primary(worker: Any) -> bool:
-    """There are multiple approaches that could be taken to determine if a celery worker
-    is 'primary', as defined by us. But the way we do it is to check the hostname set
-    for the celery worker, which can be done either in celeryconfig.py or on the
-    command line with '--hostname'."""
-    hostname = worker.hostname
-    if hostname.startswith("light"):
-        return False
-
-    if hostname.startswith("heavy"):
-        return False
-
-    return True

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

@@ -1,113 +0,0 @@
-import redis
-from celery import shared_task
-from celery.exceptions import SoftTimeLimitExceeded
-from redis import Redis
-from sqlalchemy.orm import Session
-from sqlalchemy.orm.exc import ObjectDeletedError
-
-from danswer.background.celery.celery_app import celery_app
-from danswer.background.celery.celery_app import task_logger
-from danswer.background.celery.celery_redis import RedisConnectorDeletion
-from danswer.configs.app_configs import JOB_TIMEOUT
-from danswer.configs.constants import CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT
-from danswer.configs.constants import DanswerRedisLocks
-from danswer.db.connector_credential_pair import get_connector_credential_pairs
-from danswer.db.engine import get_sqlalchemy_engine
-from danswer.db.enums import ConnectorCredentialPairStatus
-from danswer.db.models import ConnectorCredentialPair
-from danswer.redis.redis_pool import get_redis_client
-
-
-@shared_task(
-    name="check_for_connector_deletion_task",
-    soft_time_limit=JOB_TIMEOUT,
-    trail=False,
-)
-def check_for_connector_deletion_task(tenant_id: str | None) -> None:
-    r = get_redis_client()
-
-    lock_beat = 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
-
-        with Session(get_sqlalchemy_engine()) as db_session:
-            cc_pairs = get_connector_credential_pairs(db_session)
-            for cc_pair in cc_pairs:
-                try_generate_document_cc_pair_cleanup_tasks(
-                    cc_pair, db_session, r, lock_beat, tenant_id
-                )
-    except SoftTimeLimitExceeded:
-        task_logger.info(
-            "Soft time limit exceeded, task is being terminated gracefully."
-        )
-    except Exception:
-        task_logger.exception("Unexpected exception")
-    finally:
-        if lock_beat.owned():
-            lock_beat.release()
-
-
-def try_generate_document_cc_pair_cleanup_tasks(
-    cc_pair: ConnectorCredentialPair,
-    db_session: Session,
-    r: Redis,
-    lock_beat: redis.lock.Lock,
-    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.
-    """
-
-    lock_beat.reacquire()
-
-    rcd = RedisConnectorDeletion(cc_pair.id)
-
-    # don't generate sync tasks if tasks are still pending
-    if r.exists(rcd.fence_key):
-        return None
-
-    # we need to refresh the state of the object inside the fence
-    # to avoid a race condition with db.commit/fence deletion
-    # at the end of this taskset
-    try:
-        db_session.refresh(cc_pair)
-    except ObjectDeletedError:
-        return None
-
-    if cc_pair.status != ConnectorCredentialPairStatus.DELETING:
-        return None
-
-    # add tasks to celery and build up the task set to monitor in redis
-    r.delete(rcd.taskset_key)
-
-    # Add all documents that need to be updated into the queue
-    task_logger.info(
-        f"RedisConnectorDeletion.generate_tasks starting. cc_pair_id={cc_pair.id}"
-    )
-    tasks_generated = rcd.generate_tasks(
-        celery_app, db_session, r, lock_beat, tenant_id
-    )
-    if tasks_generated is None:
-        return None
-
-    # 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_id={cc_pair.id} tasks_generated={tasks_generated}"
-    )
-
-    # set this only after all tasks have been added
-    r.set(rcd.fence_key, tasks_generated)
-    return tasks_generated

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

@@ -1,251 +0,0 @@
-from datetime import datetime
-from datetime import timedelta
-from datetime import timezone
-from uuid import uuid4
-
-import redis
-from celery import shared_task
-from celery.exceptions import SoftTimeLimitExceeded
-from redis import Redis
-from sqlalchemy.orm import Session
-
-from danswer.background.celery.celery_app import celery_app
-from danswer.background.celery.celery_app import task_logger
-from danswer.background.celery.celery_redis import RedisConnectorPruning
-from danswer.background.celery.celery_utils import extract_ids_from_runnable_connector
-from danswer.configs.app_configs import ALLOW_SIMULTANEOUS_PRUNING
-from danswer.configs.app_configs import JOB_TIMEOUT
-from danswer.configs.constants import CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT
-from danswer.configs.constants import DanswerCeleryPriority
-from danswer.configs.constants import DanswerCeleryQueues
-from danswer.configs.constants import DanswerRedisLocks
-from danswer.connectors.factory import instantiate_connector
-from danswer.connectors.models import InputType
-from danswer.db.connector_credential_pair import get_connector_credential_pair
-from danswer.db.connector_credential_pair import get_connector_credential_pairs
-from danswer.db.document import get_documents_for_connector_credential_pair
-from danswer.db.engine import get_session_with_tenant
-from danswer.db.enums import ConnectorCredentialPairStatus
-from danswer.db.models import ConnectorCredentialPair
-from danswer.redis.redis_pool import get_redis_client
-from danswer.utils.logger import setup_logger
-
-
-logger = setup_logger()
-
-
-@shared_task(
-    name="check_for_prune_task_2",
-    soft_time_limit=JOB_TIMEOUT,
-)
-def check_for_prune_task_2(tenant_id: str | None) -> None:
-    r = get_redis_client()
-
-    lock_beat = r.lock(
-        DanswerRedisLocks.CHECK_PRUNE_BEAT_LOCK,
-        timeout=CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT,
-    )
-
-    try:
-        # these tasks should never overlap
-        if not lock_beat.acquire(blocking=False):
-            return
-
-        with get_session_with_tenant(tenant_id) as db_session:
-            cc_pairs = get_connector_credential_pairs(db_session)
-            for cc_pair in cc_pairs:
-                tasks_created = ccpair_pruning_generator_task_creation_helper(
-                    cc_pair, db_session, tenant_id, r, lock_beat
-                )
-                if not tasks_created:
-                    continue
-
-                task_logger.info(f"Pruning started: cc_pair_id={cc_pair.id}")
-    except SoftTimeLimitExceeded:
-        task_logger.info(
-            "Soft time limit exceeded, task is being terminated gracefully."
-        )
-    except Exception:
-        task_logger.exception("Unexpected exception")
-    finally:
-        if lock_beat.owned():
-            lock_beat.release()
-
-
-def ccpair_pruning_generator_task_creation_helper(
-    cc_pair: ConnectorCredentialPair,
-    db_session: Session,
-    tenant_id: str | None,
-    r: Redis,
-    lock_beat: redis.lock.Lock,
-) -> int | None:
-    """Returns an int if pruning is triggered.
-    The int represents the number of prune tasks generated (in this case, only one
-    because the task is a long running generator task.)
-    Returns None if no pruning is triggered (due to not being needed or
-    other reasons such as simultaneous pruning restrictions.
-
-    Checks for scheduling related conditions, then delegates the rest of the checks to
-    try_creating_prune_generator_task.
-    """
-
-    lock_beat.reacquire()
-
-    # skip pruning if no prune frequency is set
-    # pruning can still be forced via the API which will run a pruning task directly
-    if not cc_pair.connector.prune_freq:
-        return None
-
-    # skip pruning if the next scheduled prune time hasn't been reached yet
-    last_pruned = cc_pair.last_pruned
-    if not last_pruned:
-        # if never pruned, use the connector time created as the last_pruned time
-        last_pruned = cc_pair.connector.time_created
-
-    next_prune = last_pruned + timedelta(seconds=cc_pair.connector.prune_freq)
-    if datetime.now(timezone.utc) < next_prune:
-        return None
-
-    return try_creating_prune_generator_task(cc_pair, db_session, r, tenant_id)
-
-
-def try_creating_prune_generator_task(
-    cc_pair: ConnectorCredentialPair,
-    db_session: Session,
-    r: Redis,
-    tenant_id: str | None,
-) -> int | None:
-    """Checks for any conditions that should block the pruning generator task from being
-    created, then creates the task.
-
-    Does not check for scheduling related conditions as this function
-    is used to trigger prunes immediately.
-    """
-
-    if not ALLOW_SIMULTANEOUS_PRUNING:
-        for key in r.scan_iter(RedisConnectorPruning.FENCE_PREFIX + "*"):
-            return None
-
-    rcp = RedisConnectorPruning(cc_pair.id)
-
-    # skip pruning if already pruning
-    if r.exists(rcp.fence_key):
-        return None
-
-    # skip pruning if the cc_pair is deleting
-    db_session.refresh(cc_pair)
-    if cc_pair.status == ConnectorCredentialPairStatus.DELETING:
-        return None
-
-    # add a long running generator task to the queue
-    r.delete(rcp.generator_complete_key)
-    r.delete(rcp.taskset_key)
-
-    custom_task_id = f"{rcp.generator_task_id_prefix}_{uuid4()}"
-
-    celery_app.send_task(
-        "connector_pruning_generator_task",
-        kwargs=dict(
-            connector_id=cc_pair.connector_id,
-            credential_id=cc_pair.credential_id,
-            tenant_id=tenant_id,
-        ),
-        queue=DanswerCeleryQueues.CONNECTOR_PRUNING,
-        task_id=custom_task_id,
-        priority=DanswerCeleryPriority.LOW,
-    )
-
-    # set this only after all tasks have been added
-    r.set(rcp.fence_key, 1)
-    return 1
-
-
-@shared_task(name="connector_pruning_generator_task", soft_time_limit=JOB_TIMEOUT)
-def connector_pruning_generator_task(
-    connector_id: int, credential_id: int, tenant_id: str | None
-) -> None:
-    """connector pruning 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"""
-
-    r = get_redis_client()
-
-    with get_session_with_tenant(tenant_id) as db_session:
-        try:
-            cc_pair = get_connector_credential_pair(
-                db_session=db_session,
-                connector_id=connector_id,
-                credential_id=credential_id,
-            )
-
-            if not cc_pair:
-                task_logger.warning(
-                    f"ccpair not found for {connector_id} {credential_id}"
-                )
-                return
-
-            rcp = RedisConnectorPruning(cc_pair.id)
-
-            # Define the callback function
-            def redis_increment_callback(amount: int) -> None:
-                r.incrby(rcp.generator_progress_key, amount)
-
-            runnable_connector = instantiate_connector(
-                db_session,
-                cc_pair.connector.source,
-                InputType.PRUNE,
-                cc_pair.connector.connector_specific_config,
-                cc_pair.credential,
-            )
-
-            # a list of docs in the source
-            all_connector_doc_ids: set[str] = extract_ids_from_runnable_connector(
-                runnable_connector, redis_increment_callback
-            )
-
-            # a list of docs in our local index
-            all_indexed_document_ids = {
-                doc.id
-                for doc in get_documents_for_connector_credential_pair(
-                    db_session=db_session,
-                    connector_id=connector_id,
-                    credential_id=credential_id,
-                )
-            }
-
-            # generate list of docs to remove (no longer in the source)
-            doc_ids_to_remove = list(all_indexed_document_ids - all_connector_doc_ids)
-
-            task_logger.info(
-                f"Pruning set collected: "
-                f"cc_pair_id={cc_pair.id} "
-                f"docs_to_remove={len(doc_ids_to_remove)} "
-                f"doc_source={cc_pair.connector.source}"
-            )
-
-            rcp.documents_to_prune = set(doc_ids_to_remove)
-
-            task_logger.info(
-                f"RedisConnectorPruning.generate_tasks starting. cc_pair_id={cc_pair.id}"
-            )
-            tasks_generated = rcp.generate_tasks(
-                celery_app, db_session, r, None, tenant_id
-            )
-            if tasks_generated is None:
-                return None
-
-            task_logger.info(
-                f"RedisConnectorPruning.generate_tasks finished. "
-                f"cc_pair_id={cc_pair.id} tasks_generated={tasks_generated}"
-            )
-
-            r.set(rcp.generator_complete_key, tasks_generated)
-        except Exception as e:
-            task_logger.exception(
-                f"Failed to run pruning for connector id {connector_id}."
-            )
-
-            r.delete(rcp.generator_progress_key)
-            r.delete(rcp.taskset_key)
-            r.delete(rcp.fence_key)
-            raise e

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

@@ -1,126 +0,0 @@
-from celery import shared_task
-from celery import Task
-from celery.exceptions import SoftTimeLimitExceeded
-
-from danswer.access.access import get_access_for_document
-from danswer.background.celery.celery_app import task_logger
-from danswer.db.document import delete_document_by_connector_credential_pair__no_commit
-from danswer.db.document import delete_documents_complete__no_commit
-from danswer.db.document import get_document
-from danswer.db.document import get_document_connector_count
-from danswer.db.document import mark_document_as_synced
-from danswer.db.document_set import fetch_document_sets_for_document
-from danswer.db.engine import get_session_with_tenant
-from danswer.document_index.document_index_utils import get_both_index_names
-from danswer.document_index.factory import get_default_document_index
-from danswer.document_index.interfaces import VespaDocumentFields
-from danswer.server.documents.models import ConnectorCredentialPairIdentifier
-
-
-@shared_task(
-    name="document_by_cc_pair_cleanup_task",
-    bind=True,
-    soft_time_limit=45,
-    time_limit=60,
-    max_retries=3,
-)
-def document_by_cc_pair_cleanup_task(
-    self: Task,
-    document_id: str,
-    connector_id: int,
-    credential_id: int,
-    tenant_id: str | None,
-) -> bool:
-    """A lightweight subtask used to clean up document to cc pair relationships.
-    Created by connection deletion and connector pruning parent tasks."""
-
-    """
-    To delete a connector / credential pair:
-    (1) find all documents associated with connector / credential pair where there
-    this the is only connector / credential pair that has indexed it
-    (2) delete all documents from document stores
-    (3) delete all entries from postgres
-    (4) find all documents associated with connector / credential pair where there
-    are multiple connector / credential pairs that have indexed it
-    (5) update document store entries to remove access associated with the
-    connector / credential pair from the access list
-    (6) delete all relevant entries from postgres
-    """
-    try:
-        with get_session_with_tenant(tenant_id) as db_session:
-            action = "skip"
-            chunks_affected = 0
-
-            curr_ind_name, sec_ind_name = get_both_index_names(db_session)
-            document_index = get_default_document_index(
-                primary_index_name=curr_ind_name, secondary_index_name=sec_ind_name
-            )
-
-            count = get_document_connector_count(db_session, document_id)
-            if count == 1:
-                # count == 1 means this is the only remaining cc_pair reference to the doc
-                # delete it from vespa and the db
-                action = "delete"
-
-                chunks_affected = document_index.delete_single(document_id)
-                delete_documents_complete__no_commit(
-                    db_session=db_session,
-                    document_ids=[document_id],
-                )
-            elif count > 1:
-                action = "update"
-
-                # count > 1 means the document still has cc_pair references
-                doc = get_document(document_id, db_session)
-                if not doc:
-                    return False
-
-                # the below functions do not include cc_pairs being deleted.
-                # i.e. they will correctly omit access for the current cc_pair
-                doc_access = get_access_for_document(
-                    document_id=document_id, db_session=db_session
-                )
-
-                doc_sets = fetch_document_sets_for_document(document_id, db_session)
-                update_doc_sets: set[str] = set(doc_sets)
-
-                fields = VespaDocumentFields(
-                    document_sets=update_doc_sets,
-                    access=doc_access,
-                    boost=doc.boost,
-                    hidden=doc.hidden,
-                )
-
-                # update Vespa. OK if doc doesn't exist. Raises exception otherwise.
-                chunks_affected = document_index.update_single(
-                    document_id, fields=fields
-                )
-
-                # there are still other cc_pair references to the doc, so just resync to Vespa
-                delete_document_by_connector_credential_pair__no_commit(
-                    db_session=db_session,
-                    document_id=document_id,
-                    connector_credential_pair_identifier=ConnectorCredentialPairIdentifier(
-                        connector_id=connector_id,
-                        credential_id=credential_id,
-                    ),
-                )
-
-                mark_document_as_synced(document_id, db_session)
-            else:
-                pass
-
-            task_logger.info(
-                f"document_id={document_id} refcount={count} action={action} chunks={chunks_affected}"
-            )
-            db_session.commit()
-    except SoftTimeLimitExceeded:
-        task_logger.info(f"SoftTimeLimitExceeded exception. doc_id={document_id}")
-    except Exception as e:
-        task_logger.exception("Unexpected exception")
-
-        # Exponential backoff from 2^4 to 2^6 ... i.e. 16, 32, 64
-        countdown = 2 ** (self.request.retries + 4)
-        self.retry(exc=e, countdown=countdown)
-
-    return True

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

@@ -1,621 +0,0 @@
-import traceback
-from typing import cast
-
-import redis
-from celery import shared_task
-from celery import Task
-from celery.exceptions import SoftTimeLimitExceeded
-from redis import Redis
-from sqlalchemy.orm import Session
-
-from danswer.access.access import get_access_for_document
-from danswer.background.celery.celery_app import celery_app
-from danswer.background.celery.celery_app import task_logger
-from danswer.background.celery.celery_redis import celery_get_queue_length
-from danswer.background.celery.celery_redis import RedisConnectorCredentialPair
-from danswer.background.celery.celery_redis import RedisConnectorDeletion
-from danswer.background.celery.celery_redis import RedisConnectorPruning
-from danswer.background.celery.celery_redis import RedisDocumentSet
-from danswer.background.celery.celery_redis import RedisUserGroup
-from danswer.configs.app_configs import JOB_TIMEOUT
-from danswer.configs.constants import CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT
-from danswer.configs.constants import DanswerCeleryQueues
-from danswer.configs.constants import DanswerRedisLocks
-from danswer.db.connector import fetch_connector_by_id
-from danswer.db.connector import mark_ccpair_as_pruned
-from danswer.db.connector_credential_pair import add_deletion_failure_message
-from danswer.db.connector_credential_pair import (
-    delete_connector_credential_pair__no_commit,
-)
-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.document import count_documents_by_needs_sync
-from danswer.db.document import get_document
-from danswer.db.document import mark_document_as_synced
-from danswer.db.document_set import delete_document_set
-from danswer.db.document_set import delete_document_set_cc_pair_relationship__no_commit
-from danswer.db.document_set import fetch_document_sets
-from danswer.db.document_set import fetch_document_sets_for_document
-from danswer.db.document_set import get_document_set_by_id
-from danswer.db.document_set import mark_document_set_as_synced
-from danswer.db.engine import get_session_with_tenant
-from danswer.db.engine import get_sqlalchemy_engine
-from danswer.db.index_attempt import delete_index_attempts
-from danswer.db.models import DocumentSet
-from danswer.db.models import UserGroup
-from danswer.document_index.document_index_utils import get_both_index_names
-from danswer.document_index.factory import get_default_document_index
-from danswer.document_index.interfaces import UpdateRequest
-from danswer.redis.redis_pool import get_redis_client
-from danswer.utils.variable_functionality import fetch_versioned_implementation
-from danswer.utils.variable_functionality import (
-    fetch_versioned_implementation_with_fallback,
-)
-from danswer.utils.variable_functionality import global_version
-from danswer.utils.variable_functionality import noop_fallback
-
-
-# celery auto associates tasks created inside another task,
-# which bloats the result metadata considerably. trail=False prevents this.
-@shared_task(
-    name="check_for_vespa_sync_task",
-    soft_time_limit=JOB_TIMEOUT,
-    trail=False,
-)
-def check_for_vespa_sync_task(tenant_id: str | None) -> None:
-    """Runs periodically to check if any document needs syncing.
-    Generates sets of tasks for Celery if syncing is needed."""
-
-    r = get_redis_client()
-
-    lock_beat = r.lock(
-        DanswerRedisLocks.CHECK_VESPA_SYNC_BEAT_LOCK,
-        timeout=CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT,
-    )
-
-    try:
-        # these tasks should never overlap
-        if not lock_beat.acquire(blocking=False):
-            return
-
-        with get_session_with_tenant(tenant_id) as db_session:
-            try_generate_stale_document_sync_tasks(db_session, r, lock_beat, tenant_id)
-
-            # check if any document sets are not synced
-            document_set_info = fetch_document_sets(
-                user_id=None, db_session=db_session, include_outdated=True
-            )
-            for document_set, _ in document_set_info:
-                try_generate_document_set_sync_tasks(
-                    document_set, db_session, r, lock_beat, tenant_id
-                )
-
-            # check if any user groups are not synced
-            if global_version.is_ee_version():
-                try:
-                    fetch_user_groups = fetch_versioned_implementation(
-                        "danswer.db.user_group", "fetch_user_groups"
-                    )
-
-                    user_groups = fetch_user_groups(
-                        db_session=db_session, only_up_to_date=False
-                    )
-                    for usergroup in user_groups:
-                        try_generate_user_group_sync_tasks(
-                            usergroup, db_session, r, lock_beat, tenant_id
-                        )
-                except ModuleNotFoundError:
-                    # Always exceptions on the MIT version, which is expected
-                    # We shouldn't actually get here if the ee version check works
-                    pass
-
-    except SoftTimeLimitExceeded:
-        task_logger.info(
-            "Soft time limit exceeded, task is being terminated gracefully."
-        )
-    except Exception:
-        task_logger.exception("Unexpected exception")
-    finally:
-        if lock_beat.owned():
-            lock_beat.release()
-
-
-def try_generate_stale_document_sync_tasks(
-    db_session: Session, r: Redis, lock_beat: redis.lock.Lock, tenant_id: str | None
-) -> int | None:
-    # the fence is up, do nothing
-    if r.exists(RedisConnectorCredentialPair.get_fence_key()):
-        return None
-
-    r.delete(RedisConnectorCredentialPair.get_taskset_key())  # delete the taskset
-
-    # add tasks to celery and build up the task set to monitor in redis
-    stale_doc_count = count_documents_by_needs_sync(db_session)
-    if stale_doc_count == 0:
-        return None
-
-    task_logger.info(
-        f"Stale documents found (at least {stale_doc_count}). Generating sync tasks by cc pair."
-    )
-
-    task_logger.info("RedisConnector.generate_tasks starting by cc_pair.")
-
-    # rkuo: we could technically sync all stale docs in one big pass.
-    # but I feel it's more understandable to group the docs by cc_pair
-    total_tasks_generated = 0
-    cc_pairs = get_connector_credential_pairs(db_session)
-    for cc_pair in cc_pairs:
-        rc = RedisConnectorCredentialPair(cc_pair.id)
-        tasks_generated = rc.generate_tasks(
-            celery_app, db_session, r, lock_beat, tenant_id
-        )
-
-        if tasks_generated is None:
-            continue
-
-        if tasks_generated == 0:
-            continue
-
-        task_logger.info(
-            f"RedisConnector.generate_tasks finished for single cc_pair. "
-            f"cc_pair_id={cc_pair.id} tasks_generated={tasks_generated}"
-        )
-
-        total_tasks_generated += tasks_generated
-
-    task_logger.info(
-        f"RedisConnector.generate_tasks finished for all cc_pairs. total_tasks_generated={total_tasks_generated}"
-    )
-
-    r.set(RedisConnectorCredentialPair.get_fence_key(), total_tasks_generated)
-    return total_tasks_generated
-
-
-def try_generate_document_set_sync_tasks(
-    document_set: DocumentSet,
-    db_session: Session,
-    r: Redis,
-    lock_beat: redis.lock.Lock,
-    tenant_id: str | None,
-) -> int | None:
-    lock_beat.reacquire()
-
-    rds = RedisDocumentSet(document_set.id)
-
-    # don't generate document set sync tasks if tasks are still pending
-    if r.exists(rds.fence_key):
-        return None
-
-    # don't generate sync tasks if we're up to date
-    # race condition with the monitor/cleanup function if we use a cached result!
-    db_session.refresh(document_set)
-    if document_set.is_up_to_date:
-        return None
-
-    # add tasks to celery and build up the task set to monitor in redis
-    r.delete(rds.taskset_key)
-
-    task_logger.info(
-        f"RedisDocumentSet.generate_tasks starting. document_set_id={document_set.id}"
-    )
-
-    # Add all documents that need to be updated into the queue
-    tasks_generated = rds.generate_tasks(
-        celery_app, db_session, r, lock_beat, tenant_id
-    )
-    if tasks_generated is None:
-        return None
-
-    # 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"RedisDocumentSet.generate_tasks finished. "
-        f"document_set_id={document_set.id} tasks_generated={tasks_generated}"
-    )
-
-    # set this only after all tasks have been added
-    r.set(rds.fence_key, tasks_generated)
-    return tasks_generated
-
-
-def try_generate_user_group_sync_tasks(
-    usergroup: UserGroup,
-    db_session: Session,
-    r: Redis,
-    lock_beat: redis.lock.Lock,
-    tenant_id: str | None,
-) -> int | None:
-    lock_beat.reacquire()
-
-    rug = RedisUserGroup(usergroup.id)
-
-    # don't generate sync tasks if tasks are still pending
-    if r.exists(rug.fence_key):
-        return None
-
-    # race condition with the monitor/cleanup function if we use a cached result!
-    db_session.refresh(usergroup)
-    if usergroup.is_up_to_date:
-        return None
-
-    # add tasks to celery and build up the task set to monitor in redis
-    r.delete(rug.taskset_key)
-
-    # Add all documents that need to be updated into the queue
-    task_logger.info(
-        f"RedisUserGroup.generate_tasks starting. usergroup_id={usergroup.id}"
-    )
-    tasks_generated = rug.generate_tasks(
-        celery_app, db_session, r, lock_beat, tenant_id
-    )
-    if tasks_generated is None:
-        return None
-
-    # 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"RedisUserGroup.generate_tasks finished. "
-        f"usergroup_id={usergroup.id} tasks_generated={tasks_generated}"
-    )
-
-    # set this only after all tasks have been added
-    r.set(rug.fence_key, tasks_generated)
-    return tasks_generated
-
-
-def monitor_connector_taskset(r: Redis) -> None:
-    fence_value = r.get(RedisConnectorCredentialPair.get_fence_key())
-    if fence_value is None:
-        return
-
-    try:
-        initial_count = int(cast(int, fence_value))
-    except ValueError:
-        task_logger.error("The value is not an integer.")
-        return
-
-    count = r.scard(RedisConnectorCredentialPair.get_taskset_key())
-    task_logger.info(
-        f"Stale document sync progress: remaining={count} initial={initial_count}"
-    )
-    if count == 0:
-        r.delete(RedisConnectorCredentialPair.get_taskset_key())
-        r.delete(RedisConnectorCredentialPair.get_fence_key())
-        task_logger.info(f"Successfully synced stale documents. count={initial_count}")
-
-
-def monitor_document_set_taskset(
-    key_bytes: bytes, r: Redis, db_session: Session
-) -> None:
-    fence_key = key_bytes.decode("utf-8")
-    document_set_id = RedisDocumentSet.get_id_from_fence_key(fence_key)
-    if document_set_id is None:
-        task_logger.warning(f"could not parse document set id from {fence_key}")
-        return
-
-    rds = RedisDocumentSet(document_set_id)
-
-    fence_value = r.get(rds.fence_key)
-    if fence_value is None:
-        return
-
-    try:
-        initial_count = int(cast(int, fence_value))
-    except ValueError:
-        task_logger.error("The value is not an integer.")
-        return
-
-    count = cast(int, r.scard(rds.taskset_key))
-    task_logger.info(
-        f"Document set sync progress: document_set_id={document_set_id} remaining={count} initial={initial_count}"
-    )
-    if count > 0:
-        return
-
-    document_set = cast(
-        DocumentSet,
-        get_document_set_by_id(db_session=db_session, document_set_id=document_set_id),
-    )  # casting since we "know" a document set with this ID exists
-    if document_set:
-        if not document_set.connector_credential_pairs:
-            # if there are no connectors, then delete the document set.
-            delete_document_set(document_set_row=document_set, db_session=db_session)
-            task_logger.info(
-                f"Successfully deleted document set with ID: '{document_set_id}'!"
-            )
-        else:
-            mark_document_set_as_synced(document_set_id, db_session)
-            task_logger.info(
-                f"Successfully synced document set with ID: '{document_set_id}'!"
-            )
-
-    r.delete(rds.taskset_key)
-    r.delete(rds.fence_key)
-
-
-def monitor_connector_deletion_taskset(key_bytes: bytes, r: Redis) -> None:
-    fence_key = key_bytes.decode("utf-8")
-    cc_pair_id = RedisConnectorDeletion.get_id_from_fence_key(fence_key)
-    if cc_pair_id is None:
-        task_logger.warning(f"could not parse cc_pair_id from {fence_key}")
-        return
-
-    rcd = RedisConnectorDeletion(cc_pair_id)
-
-    fence_value = r.get(rcd.fence_key)
-    if fence_value is None:
-        return
-
-    try:
-        initial_count = int(cast(int, fence_value))
-    except ValueError:
-        task_logger.error("The value is not an integer.")
-        return
-
-    count = cast(int, r.scard(rcd.taskset_key))
-    task_logger.info(
-        f"Connector deletion progress: cc_pair_id={cc_pair_id} remaining={count} initial={initial_count}"
-    )
-    if count > 0:
-        return
-
-    with Session(get_sqlalchemy_engine()) as db_session:
-        cc_pair = get_connector_credential_pair_from_id(cc_pair_id, db_session)
-        if not cc_pair:
-            task_logger.warning(
-                f"monitor_connector_deletion_taskset - cc_pair_id not found: cc_pair_id={cc_pair_id}"
-            )
-            return
-
-        try:
-            # clean up the rest of the related Postgres entities
-            # index attempts
-            delete_index_attempts(
-                db_session=db_session,
-                cc_pair_id=cc_pair.id,
-            )
-
-            # document sets
-            delete_document_set_cc_pair_relationship__no_commit(
-                db_session=db_session,
-                connector_id=cc_pair.connector_id,
-                credential_id=cc_pair.credential_id,
-            )
-
-            # user groups
-            cleanup_user_groups = fetch_versioned_implementation_with_fallback(
-                "danswer.db.user_group",
-                "delete_user_group_cc_pair_relationship__no_commit",
-                noop_fallback,
-            )
-            cleanup_user_groups(
-                cc_pair_id=cc_pair.id,
-                db_session=db_session,
-            )
-
-            # finally, delete the cc-pair
-            delete_connector_credential_pair__no_commit(
-                db_session=db_session,
-                connector_id=cc_pair.connector_id,
-                credential_id=cc_pair.credential_id,
-            )
-            # if there are no credentials left, delete the connector
-            connector = fetch_connector_by_id(
-                db_session=db_session,
-                connector_id=cc_pair.connector_id,
-            )
-            if not connector or not len(connector.credentials):
-                task_logger.info(
-                    "Found no credentials left for connector, deleting connector"
-                )
-                db_session.delete(connector)
-            db_session.commit()
-        except Exception as e:
-            stack_trace = traceback.format_exc()
-            error_message = f"Error: {str(e)}\n\nStack Trace:\n{stack_trace}"
-            add_deletion_failure_message(db_session, cc_pair.id, error_message)
-            task_logger.exception(
-                f"Failed to run connector_deletion. "
-                f"cc_pair_id={cc_pair_id} connector_id={cc_pair.connector_id} credential_id={cc_pair.credential_id}"
-            )
-            raise e
-
-    task_logger.info(
-        f"Successfully deleted cc_pair: "
-        f"cc_pair_id={cc_pair_id} "
-        f"connector_id={cc_pair.connector_id} "
-        f"credential_id={cc_pair.credential_id} "
-        f"docs_deleted={initial_count}"
-    )
-
-    r.delete(rcd.taskset_key)
-    r.delete(rcd.fence_key)
-
-
-def monitor_ccpair_pruning_taskset(
-    key_bytes: bytes, r: Redis, db_session: Session
-) -> None:
-    fence_key = key_bytes.decode("utf-8")
-    cc_pair_id = RedisConnectorPruning.get_id_from_fence_key(fence_key)
-    if cc_pair_id is None:
-        task_logger.warning(
-            f"monitor_connector_pruning_taskset: could not parse cc_pair_id from {fence_key}"
-        )
-        return
-
-    rcp = RedisConnectorPruning(cc_pair_id)
-
-    fence_value = r.get(rcp.fence_key)
-    if fence_value is None:
-        return
-
-    generator_value = r.get(rcp.generator_complete_key)
-    if generator_value is None:
-        return
-
-    try:
-        initial_count = int(cast(int, generator_value))
-    except ValueError:
-        task_logger.error("The value is not an integer.")
-        return
-
-    count = cast(int, r.scard(rcp.taskset_key))
-    task_logger.info(
-        f"Connector pruning progress: cc_pair_id={cc_pair_id} remaining={count} initial={initial_count}"
-    )
-    if count > 0:
-        return
-
-    mark_ccpair_as_pruned(cc_pair_id, db_session)
-    task_logger.info(
-        f"Successfully pruned connector credential pair. cc_pair_id={cc_pair_id}"
-    )
-
-    r.delete(rcp.taskset_key)
-    r.delete(rcp.generator_progress_key)
-    r.delete(rcp.generator_complete_key)
-    r.delete(rcp.fence_key)
-
-
-@shared_task(name="monitor_vespa_sync", soft_time_limit=300, bind=True)
-def monitor_vespa_sync(self: Task, tenant_id: str | None) -> None:
-    """This is a celery beat task that monitors and finalizes metadata sync tasksets.
-    It scans for fence values and then gets the counts of any associated tasksets.
-    If the count is 0, that means all tasks finished and we should clean up.
-
-    This task lock timeout is CELERY_METADATA_SYNC_BEAT_LOCK_TIMEOUT seconds, so don't
-    do anything too expensive in this function!
-    """
-    r = get_redis_client()
-
-    lock_beat: redis.lock.Lock = r.lock(
-        DanswerRedisLocks.MONITOR_VESPA_SYNC_BEAT_LOCK,
-        timeout=CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT,
-    )
-
-    try:
-        # prevent overlapping tasks
-        if not lock_beat.acquire(blocking=False):
-            return
-
-        # print current queue lengths
-        r_celery = self.app.broker_connection().channel().client  # type: ignore
-        n_celery = celery_get_queue_length("celery", r)
-        n_sync = celery_get_queue_length(
-            DanswerCeleryQueues.VESPA_METADATA_SYNC, r_celery
-        )
-        n_deletion = celery_get_queue_length(
-            DanswerCeleryQueues.CONNECTOR_DELETION, r_celery
-        )
-        n_pruning = celery_get_queue_length(
-            DanswerCeleryQueues.CONNECTOR_PRUNING, r_celery
-        )
-
-        task_logger.info(
-            f"Queue lengths: celery={n_celery} sync={n_sync} deletion={n_deletion} pruning={n_pruning}"
-        )
-
-        lock_beat.reacquire()
-        if r.exists(RedisConnectorCredentialPair.get_fence_key()):
-            monitor_connector_taskset(r)
-
-        lock_beat.reacquire()
-        for key_bytes in r.scan_iter(RedisConnectorDeletion.FENCE_PREFIX + "*"):
-            monitor_connector_deletion_taskset(key_bytes, r)
-
-        with get_session_with_tenant(tenant_id) as db_session:
-            lock_beat.reacquire()
-            for key_bytes in r.scan_iter(RedisDocumentSet.FENCE_PREFIX + "*"):
-                monitor_document_set_taskset(key_bytes, r, db_session)
-
-            lock_beat.reacquire()
-            for key_bytes in r.scan_iter(RedisUserGroup.FENCE_PREFIX + "*"):
-                monitor_usergroup_taskset = (
-                    fetch_versioned_implementation_with_fallback(
-                        "danswer.background.celery.tasks.vespa.tasks",
-                        "monitor_usergroup_taskset",
-                        noop_fallback,
-                    )
-                )
-                monitor_usergroup_taskset(key_bytes, r, db_session)
-
-            lock_beat.reacquire()
-            for key_bytes in r.scan_iter(RedisConnectorPruning.FENCE_PREFIX + "*"):
-                monitor_ccpair_pruning_taskset(key_bytes, r, db_session)
-
-        # uncomment for debugging if needed
-        # r_celery = celery_app.broker_connection().channel().client
-        # length = celery_get_queue_length(DanswerCeleryQueues.VESPA_METADATA_SYNC, r_celery)
-        # task_logger.warning(f"queue={DanswerCeleryQueues.VESPA_METADATA_SYNC} length={length}")
-    except SoftTimeLimitExceeded:
-        task_logger.info(
-            "Soft time limit exceeded, task is being terminated gracefully."
-        )
-    finally:
-        if lock_beat.owned():
-            lock_beat.release()
-
-
-@shared_task(
-    name="vespa_metadata_sync_task",
-    bind=True,
-    soft_time_limit=45,
-    time_limit=60,
-    max_retries=3,
-)
-def vespa_metadata_sync_task(
-    self: Task, document_id: str, tenant_id: str | None
-) -> bool:
-    task_logger.info(f"document_id={document_id}")
-
-    try:
-        with get_session_with_tenant(tenant_id) as db_session:
-            curr_ind_name, sec_ind_name = get_both_index_names(db_session)
-            document_index = get_default_document_index(
-                primary_index_name=curr_ind_name, secondary_index_name=sec_ind_name
-            )
-
-            doc = get_document(document_id, db_session)
-            if not doc:
-                return False
-
-            # document set sync
-            doc_sets = fetch_document_sets_for_document(document_id, db_session)
-            update_doc_sets: set[str] = set(doc_sets)
-
-            # User group sync
-            doc_access = get_access_for_document(
-                document_id=document_id, db_session=db_session
-            )
-            update_request = UpdateRequest(
-                document_ids=[document_id],
-                document_sets=update_doc_sets,
-                access=doc_access,
-                boost=doc.boost,
-                hidden=doc.hidden,
-            )
-
-            # update Vespa
-            document_index.update(update_requests=[update_request])
-
-            # update db last. Worst case = we crash right before this and
-            # the sync might repeat again later
-            mark_document_as_synced(document_id, db_session)
-    except SoftTimeLimitExceeded:
-        task_logger.info(f"SoftTimeLimitExceeded exception. doc_id={document_id}")
-    except Exception as e:
-        task_logger.exception("Unexpected exception")
-
-        # Exponential backoff from 2^4 to 2^6 ... i.e. 16, 32, 64
-        countdown = 2 ** (self.request.retries + 4)
-        self.retry(exc=e, countdown=countdown)
-
-    return True