Make seeded personas default

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

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

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

@@ -7,7 +7,7 @@ on:
       - "*"
 
 env:
-  REGISTRY_IMAGE: onyxdotapp/onyx-web-server-cloud
+  REGISTRY_IMAGE: danswer/danswer-web-server-cloud
   LATEST_TAG: ${{ contains(github.ref_name, 'latest') }}
 
 jobs:
@@ -60,7 +60,7 @@ jobs:
           platforms: ${{ matrix.platform }}
           push: true
           build-args: |
-            ONYX_VERSION=${{ github.ref_name }}
+            DANSWER_VERSION=${{ github.ref_name }}
             NEXT_PUBLIC_CLOUD_ENABLED=true
             NEXT_PUBLIC_POSTHOG_KEY=${{ secrets.POSTHOG_KEY }}
             NEXT_PUBLIC_POSTHOG_HOST=${{ secrets.POSTHOG_HOST }}

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

@@ -6,31 +6,20 @@ on:
       - "*"
 
 env:
-  REGISTRY_IMAGE: ${{ contains(github.ref_name, 'cloud') && 'onyxdotapp/onyx-model-server-cloud' || 'onyxdotapp/onyx-model-server' }}
+  REGISTRY_IMAGE: ${{ contains(github.ref_name, 'cloud') && 'danswer/danswer-model-server-cloud' || 'danswer/danswer-model-server' }}
   LATEST_TAG: ${{ contains(github.ref_name, 'latest') }}
-  DOCKER_BUILDKIT: 1
-  BUILDKIT_PROGRESS: plain
 
 jobs:
-  build-amd64:
-    runs-on:
-      [runs-on, runner=8cpu-linux-x64, "run-id=${{ github.run_id }}-amd64"]
+  build-and-push:
+    # See https://runs-on.com/runners/linux/
+    runs-on: [runs-on, runner=8cpu-linux-x64, "run-id=${{ github.run_id }}"]
+
     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
@@ -38,86 +27,29 @@ jobs:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_TOKEN }}
 
-      - name: Build and Push AMD64
+      - 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
+          platforms: linux/amd64,linux/arm64
           push: true
-          tags: ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}-amd64
+          tags: |
+            ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
+            ${{ env.LATEST_TAG == 'true' && format('{0}:latest', env.REGISTRY_IMAGE) || '' }}
           build-args: |
             DANSWER_VERSION=${{ 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
 
+      # 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/onyxdotapp/onyx-model-server:${{ github.ref_name }}
+          image-ref: docker.io/danswer/danswer-model-server:${{ 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: onyxdotapp/onyx-web-server
+  REGISTRY_IMAGE: danswer/danswer-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: ${{ matrix.platform }}
           push: true
           build-args: |
-            ONYX_VERSION=${{ github.ref_name }}
-          # needed due to weird interactions with the builds for different platforms
+            DANSWER_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 onyxdotapp/onyx-web-server:latest onyxdotapp/onyx-web-server:${{ github.event.inputs.version }}
+    - name: Pull, Tag and Push Web Server Image
+      run: |
+        docker buildx imagetools create -t danswer/danswer-web-server:latest danswer/danswer-web-server:${{ github.event.inputs.version }}
 
-      - name: Pull, Tag and Push API Server Image
-        run: |
-          docker buildx imagetools create -t onyxdotapp/onyx-backend:latest onyxdotapp/onyx-backend:${{ github.event.inputs.version }}
+    - name: Pull, Tag and Push API Server Image
+      run: |
+        docker buildx imagetools create -t danswer/danswer-backend:latest danswer/danswer-backend:${{ github.event.inputs.version }}

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

@@ -8,42 +8,43 @@ 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]@onyx.app"
+          git config user.email "rkuo[bot]@danswer.ai"
 
       - name: Fetch All Branches
         run: |
@@ -61,10 +62,10 @@ 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/,$//')
 
@@ -168,4 +169,4 @@ jobs:
                 echo "Failed to merge pull request #$PR_NUMBER."
               fi
             fi
-          done
+          done

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

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

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

@@ -14,24 +14,18 @@ jobs:
     name: Playwright Tests
 
     # See https://runs-on.com/runners/linux/
-    runs-on:
-      [
-        runs-on,
-        runner=32cpu-linux-x64,
-        disk=large,
-        "run-id=${{ github.run_id }}",
-      ]
+    runs-on: [runs-on,runner=8cpu-linux-x64,ram=16,"run-id=${{ github.run_id }}"]
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
         with:
           fetch-depth: 0
-
+          
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
-          python-version: "3.11"
-          cache: "pip"
+          python-version: '3.11'
+          cache: 'pip'
           cache-dependency-path: |
             backend/requirements/default.txt
             backend/requirements/dev.txt
@@ -41,7 +35,7 @@ jobs:
           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:
@@ -54,7 +48,7 @@ jobs:
       - name: Install playwright browsers
         working-directory: ./web
         run: npx playwright install --with-deps
-
+        
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v3
 
@@ -66,13 +60,13 @@ jobs:
 
       # 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
@@ -81,7 +75,7 @@ jobs:
           context: ./web
           file: ./web/Dockerfile
           platforms: linux/amd64
-          tags: onyxdotapp/onyx-web-server:test
+          tags: danswer/danswer-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=${{ env.RUNS_ON_S3_BUCKET_CACHE }}
@@ -93,7 +87,7 @@ jobs:
           context: ./backend
           file: ./backend/Dockerfile
           platforms: linux/amd64
-          tags: onyxdotapp/onyx-backend:test
+          tags: danswer/danswer-backend:test
           push: false
           load: true
           cache-from: type=s3,prefix=cache/${{ github.repository }}/integration-tests/backend/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }}
@@ -105,7 +99,7 @@ jobs:
           context: ./backend
           file: ./backend/Dockerfile.model_server
           platforms: linux/amd64
-          tags: onyxdotapp/onyx-model-server:test
+          tags: danswer/danswer-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=${{ env.RUNS_ON_S3_BUCKET_CACHE }}
@@ -116,7 +110,6 @@ jobs:
           cd deployment/docker_compose
           ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true \
           AUTH_TYPE=basic \
-          GEN_AI_API_KEY=${{ secrets.OPENAI_API_KEY }} \
           REQUIRE_EMAIL_VERIFICATION=false \
           DISABLE_TELEMETRY=true \
           IMAGE_TAG=test \
@@ -126,12 +119,12 @@ 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))
@@ -159,7 +152,7 @@ jobs:
 
       - name: Run pytest playwright test init
         working-directory: ./backend
-        env:
+        env: 
           PYTEST_IGNORE_SKIP: true
         run: pytest -s tests/integration/tests/playwright/test_playwright.py
 
@@ -175,7 +168,7 @@ jobs:
           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()
@@ -183,7 +176,7 @@ jobs:
           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
@@ -198,41 +191,35 @@ jobs:
 
   chromatic-tests:
     name: Chromatic Tests
-
+    
     needs: playwright-tests
-    runs-on:
-      [
-        runs-on,
-        runner=32cpu-linux-x64,
-        disk=large,
-        "run-id=${{ github.run_id }}",
-      ]
+    runs-on: [runs-on,runner=8cpu-linux-x64,ram=16,"run-id=${{ github.run_id }}"]
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
         with:
           fetch-depth: 0
-
+          
       - 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:
+        env: 
           CHROMATIC_ARCHIVE_LOCATION: ./test-results

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

@@ -8,7 +8,7 @@ on:
   pull_request:
     branches:
       - main
-      - "release/**"
+      - 'release/**'
 
 env:
   OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
@@ -16,11 +16,11 @@ env:
   CONFLUENCE_TEST_SPACE_URL: ${{ secrets.CONFLUENCE_TEST_SPACE_URL }}
   CONFLUENCE_USER_NAME: ${{ secrets.CONFLUENCE_USER_NAME }}
   CONFLUENCE_ACCESS_TOKEN: ${{ secrets.CONFLUENCE_ACCESS_TOKEN }}
-
+  
 jobs:
   integration-tests:
     # See https://runs-on.com/runners/linux/
-    runs-on: [runs-on, runner=32cpu-linux-x64, "run-id=${{ github.run_id }}"]
+    runs-on: [runs-on,runner=8cpu-linux-x64,ram=16,"run-id=${{ github.run_id }}"]
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
@@ -36,21 +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 onyxdotapp/onyx-web-server:latest
-          docker tag onyxdotapp/onyx-web-server:latest onyxdotapp/onyx-web-server:test
+          docker pull danswer/danswer-web-server:latest
+          docker tag danswer/danswer-web-server:latest danswer/danswer-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
@@ -58,7 +58,7 @@ jobs:
           context: ./backend
           file: ./backend/Dockerfile
           platforms: linux/amd64
-          tags: onyxdotapp/onyx-backend:test
+          tags: danswer/danswer-backend:test
           push: false
           load: true
           cache-from: type=s3,prefix=cache/${{ github.repository }}/integration-tests/backend/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }}
@@ -70,19 +70,19 @@ jobs:
           context: ./backend
           file: ./backend/Dockerfile.model_server
           platforms: linux/amd64
-          tags: onyxdotapp/onyx-model-server:test
+          tags: danswer/danswer-model-server:test
           push: false
           load: true
           cache-from: type=s3,prefix=cache/${{ 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=${{ env.RUNS_ON_S3_BUCKET_CACHE }},mode=max
-
+      
       - name: Build integration test Docker image
         uses: ./.github/actions/custom-build-and-push
         with:
           context: ./backend
           file: ./backend/tests/integration/Dockerfile
           platforms: linux/amd64
-          tags: onyxdotapp/onyx-integration:test
+          tags: danswer/danswer-integration:test
           push: false
           load: true
           cache-from: type=s3,prefix=cache/${{ github.repository }}/integration-tests/integration/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }}
@@ -119,7 +119,7 @@ jobs:
             -e TEST_WEB_HOSTNAME=test-runner \
             -e AUTH_TYPE=cloud \
             -e MULTI_TENANT=true \
-            onyxdotapp/onyx-integration:test \
+            danswer/danswer-integration:test \
             /app/tests/integration/multitenant_tests
         continue-on-error: true
         id: run_multitenant_tests
@@ -131,14 +131,15 @@ jobs:
             exit 1
           else
             echo "All integration tests passed successfully."
-          fi
+          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
+
+      - name: Start Docker containers 
         run: |
           cd deployment/docker_compose
           ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true \
@@ -152,12 +153,12 @@ 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=$((current_time - start_time))
@@ -201,7 +202,7 @@ jobs:
             -e CONFLUENCE_USER_NAME=${CONFLUENCE_USER_NAME} \
             -e CONFLUENCE_ACCESS_TOKEN=${CONFLUENCE_ACCESS_TOKEN} \
             -e TEST_WEB_HOSTNAME=test-runner \
-            onyxdotapp/onyx-integration:test \
+            danswer/danswer-integration:test \
             /app/tests/integration/tests \
             /app/tests/integration/connector_job_tests
         continue-on-error: true
@@ -228,7 +229,7 @@ jobs:
         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-python-connector-tests.yml

@@ -24,8 +24,6 @@ env:
   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 }}
 
 jobs:
   connectors-check:

.github/workflows/tag-nightly.yml

@@ -2,52 +2,53 @@ 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]@onyx.app"
+    - name: Set up Git user
+      run: |
+        git config user.name "Richard Kuo [bot]"
+        git config user.email "rkuo[bot]@danswer.ai"
 
-      - 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: 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
 
-      # 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 $TAG_NAME
+    - name: Push Tag
+      if: steps.check_tag.outputs.tag_exists == 'false'
+      run: |
+        TAG_NAME="nightly-latest-$(date +'%Y%m%d')"
+        git push origin $TAG_NAME
+        

.vscode/launch.template.jsonc

@@ -17,7 +17,7 @@
 			 }
 		},
         {
-            "name": "Run All Onyx Services",
+            "name": "Run All Danswer Services",
             "configurations": [
                 "Web Server",
                 "Model Server",
@@ -122,7 +122,7 @@
                 "PYTHONUNBUFFERED": "1"
             },
             "args": [
-                "onyx.main:app",
+                "danswer.main:app",
                 "--reload",
                 "--port",
                 "8080"
@@ -139,7 +139,7 @@
             "consoleName": "Slack Bot",
             "type": "debugpy",
             "request": "launch",
-            "program": "onyx/onyxbot/slack/listener.py",
+            "program": "danswer/danswerbot/slack/listener.py",
             "cwd": "${workspaceFolder}/backend",
             "envFile": "${workspaceFolder}/.vscode/.env",
             "env": {
@@ -166,7 +166,7 @@
             },
             "args": [
                 "-A",
-                "onyx.background.celery.versioned_apps.primary",
+                "danswer.background.celery.versioned_apps.primary",
                 "worker",
                 "--pool=threads",
                 "--concurrency=4",
@@ -195,7 +195,7 @@
             },
             "args": [
                 "-A",
-                "onyx.background.celery.versioned_apps.light",
+                "danswer.background.celery.versioned_apps.light",
                 "worker",
                 "--pool=threads",
                 "--concurrency=64",
@@ -224,7 +224,7 @@
             },
             "args": [
                 "-A",
-                "onyx.background.celery.versioned_apps.heavy",
+                "danswer.background.celery.versioned_apps.heavy",
                 "worker",
                 "--pool=threads",
                 "--concurrency=4",
@@ -254,7 +254,7 @@
             },
             "args": [
                 "-A",
-                "onyx.background.celery.versioned_apps.indexing",
+                "danswer.background.celery.versioned_apps.indexing",
                 "worker",
                 "--pool=threads",
                 "--concurrency=1",
@@ -283,7 +283,7 @@
             },
             "args": [
                 "-A",
-                "onyx.background.celery.versioned_apps.beat",
+                "danswer.background.celery.versioned_apps.beat",
                 "beat",
                 "--loglevel=INFO",
             ],
@@ -308,7 +308,7 @@
             "args": [
                 "-v"
                 // Specify a sepcific module/test to run or provide nothing to run all tests
-                //"tests/unit/onyx/llm/answering/test_prune_and_merge.py"
+                //"tests/unit/danswer/llm/answering/test_prune_and_merge.py"
             ],
             "presentation": {
 				 "group": "2",

CONTRIBUTING.md

@@ -1,113 +1,105 @@
-<!-- DANSWER_METADATA={"link": "https://github.com/onyx-dot-app/onyx/blob/main/CONTRIBUTING.md"} -->
+<!-- DANSWER_METADATA={"link": "https://github.com/danswer-ai/danswer/blob/main/CONTRIBUTING.md"} -->
 
-# Contributing to Onyx
-
-Hey there! We are so excited that you're interested in Onyx.
+# Contributing to Danswer
+Hey there! We are so excited that you're interested in Danswer.
 
 As an open source project in a rapidly changing space, we welcome all contributions.
 
+
 ## 💃 Guidelines
-
 ### Contribution Opportunities
-
-The [GitHub Issues](https://github.com/onyx-dot-app/onyx/issues) page is a great place to start for contribution ideas.
+The [GitHub Issues](https://github.com/danswer-ai/danswer/issues) page is a great place to start for contribution ideas.
 
 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/onyx-dot-app/onyx/blob/main/backend/onyx/connectors/README.md).
+[README.md](https://github.com/danswer-ai/danswer/blob/main/backend/danswer/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 Onyx moves in the right direction.
+Your input is vital to making sure that Danswer 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-1w76msxmd-HJHLe3KNFIAIzk_0dSOKaQ) /
-[Discord](https://discord.gg/TDJ59cGV2X) directly about anything at all.
+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. 
+
 
 ### 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-1w76msxmd-HJHLe3KNFIAIzk_0dSOKaQ)
-and
+[Slack](https://join.slack.com/t/danswer/shared_invite/zt-2afut44lv-Rw3kSWu6_OmdAXRpCv80DQ)
+and 
 [Discord](https://discord.gg/TDJ59cGV2X).
 
 We would love to see you there!
 
+
 ## Get Started 🚀
-
-Onyx being a fully functional app, relies on some external software, specifically:
-
+Danswer 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 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.
+> 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.
+
 
 ### 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
 
+#### 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 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.
+> 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.
 
 _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 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
+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
 ```
 
 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
 ```
@@ -117,50 +109,42 @@ 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 `onyx/web` run:
-
+Once the above is done, navigate to `danswer/web` run:
 ```bash
 npm i
 ```
 
 #### Docker containers for external software
-
 You will need Docker installed to run these containers.
 
-First navigate to `onyx/deployment/docker_compose`, then start up Postgres/Vespa/Redis with:
-
+First navigate to `danswer/deployment/docker_compose`, then start up Postgres/Vespa/Redis with:
 ```bash
-docker compose -f docker-compose.dev.yml -p onyx-stack up -d index relational_db cache
+docker compose -f docker-compose.dev.yml -p danswer-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 `onyx/backend` and run:
-
+Navigate to `danswer/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 Onyx, you will need to run the DB migrations for Postgres.
+The first time running Danswer, 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 `onyx/backend` and with the venv active, run:
-
+Navigate to `danswer/backend` and with the venv active, run:
 ```bash
 alembic upgrade head
 ```
@@ -168,24 +152,21 @@ 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 `onyx/backend`, run:
-
+Still in `danswer/backend`, run:
 ```bash
 python ./scripts/dev_run_background_jobs.py
 ```
 
-To run the backend API server, navigate back to `onyx/backend` and run:
-
+To run the backend API server, navigate back to `danswer/backend` and run:
 ```bash
-AUTH_TYPE=disabled uvicorn onyx.main:app --reload --port 8080
+AUTH_TYPE=disabled uvicorn danswer.main:app --reload --port 8080
 ```
 
 _For Windows (for compatibility with both PowerShell and Command Prompt):_
-
 ```bash
 powershell -Command "
     $env:AUTH_TYPE='disabled'
-    uvicorn onyx.main:app --reload --port 8080
+    uvicorn danswer.main:app --reload --port 8080 
 "
 ```
 
@@ -201,61 +182,57 @@ You should now have 4 servers running:
 - Model server
 - Background jobs
 
-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.
+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.
 
-You've successfully set up a local Onyx instance! 🏁
+You've successfully set up a local Danswer instance! 🏁
 
-#### Running the Onyx application in a container
+#### Running the Danswer application in a container
 
-You can run the full Onyx application stack from pre-built images including all external software dependencies.
+You can run the full Danswer application stack from pre-built images including all external software dependencies.
 
-Navigate to `onyx/deployment/docker_compose` and run:
+Navigate to `danswer/deployment/docker_compose` and run:
 
 ```bash
-docker compose -f docker-compose.dev.yml -p onyx-stack up -d
+docker compose -f docker-compose.dev.yml -p danswer-stack up -d
 ```
 
-After Docker pulls and starts these containers, navigate to `http://localhost:3000` to use Onyx.
+After Docker pulls and starts these containers, navigate to `http://localhost:3000` to use Danswer.
 
-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:
+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:
 
 ```bash
-docker compose -f docker-compose.dev.yml -p onyx-stack up -d --build
+docker compose -f docker-compose.dev.yml -p danswer-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 `onyx/backend` directory, run:
-
+Then, from the `danswer/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.
+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 `onyx/web` directory.
-To run the formatter, use `npx prettier --write .` from the `onyx/web` directory.
+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
 
-Onyx loosely follows the SemVer versioning standard.
+### Release Process
+Danswer 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=onyx%2F).
+You can see the containers [here](https://hub.docker.com/search?q=danswer%2F).

CONTRIBUTING_MACOS.md

@@ -1,19 +1,15 @@
 ## Some additional notes for Mac Users
-
-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).
+The base instructions to set up the development environment are located in [CONTRIBUTING.md](https://github.com/danswer-ai/danswer/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"
 ```
@@ -21,16 +17,15 @@ 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
+### Setting up Docker
+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
 
+### 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
-```
+```

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 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.
+* 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.
 
 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

@@ -1,143 +1,142 @@
-<!-- DANSWER_METADATA={"link": "https://github.com/onyx-dot-app/onyx/blob/main/README.md"} -->
-
+<!-- DANSWER_METADATA={"link": "https://github.com/danswer-ai/danswer/blob/main/README.md"} -->
 <a name="readme-top"></a>
 
 <h2 align="center">
-<a href="https://www.onyx.app/"> <img width="50%" src="https://github.com/onyx-dot-app/onyx/blob/logo/LogoOnyx.png?raw=true)" /></a>
+<a href="https://www.danswer.ai/"> <img width="50%" src="https://github.com/danswer-owners/danswer/blob/1fabd9372d66cd54238847197c33f091a724803b/DanswerWithName.png?raw=true)" /></a>
 </h2>
 
 <p align="center">
-<p align="center">Open Source Gen-AI + Enterprise Search.</p>
+<p align="center">Open Source Gen-AI Chat + Unified Search.</p>
 
 <p align="center">
-<a href="https://docs.onyx.app/" target="_blank">
+<a href="https://docs.danswer.dev/" 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-1w76msxmd-HJHLe3KNFIAIzk_0dSOKaQ" target="_blank">
+<a href="https://join.slack.com/t/danswer/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/onyx-dot-app/onyx/blob/main/README.md" target="_blank">
+<a href="https://github.com/danswer-ai/danswer/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>[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.
+<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.
 
-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
+Danswer also serves as a Unified Search across all common workplace tools such as Slack, Google Drive, Confluence, etc.
+By combining LLMs and team specific knowledge, Danswer becomes a subject matter expert for the team. Imagine ChatGPT if
 it had access to your team's unique knowledge! It enables questions such as "A customer wants feature X, is this already
 supported?" or "Where's the pull request for feature Y?"
 
 <h3>Usage</h3>
 
-Onyx Web App:
+Danswer Web App:
 
-https://github.com/onyx-dot-app/onyx/assets/32520769/563be14c-9304-47b5-bf0a-9049c2b6f410
+https://github.com/danswer-ai/danswer/assets/32520769/563be14c-9304-47b5-bf0a-9049c2b6f410
 
-Or, plug Onyx into your existing Slack workflows (more integrations to come 😁):
 
-https://github.com/onyx-dot-app/onyx/assets/25087905/3e19739b-d178-4371-9a38-011430bdec1b
+Or, plug Danswer into your existing Slack workflows (more integrations to come 😁):
 
-For more details on the Admin UI to manage connectors and users, check out our
+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 
 <strong><a href="https://www.youtube.com/watch?v=geNzY1nbCnU">Full Video Demo</a></strong>!
 
 ## Deployment
 
-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.
+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.
 
-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).
+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).
 
-## 💃 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 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.
+## 💃 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.
+
 
 ## 🚧 Roadmap
+* Chat/Prompt sharing with specific teammates and user groups.
+* Multimodal model support, chat with images, video etc.
+* Choosing between LLMs and parameters during chat session.
+* Tool calling and agent configurations options.
+* Organizational understanding and ability to locate and suggest experts from your team.
 
-- Chat/Prompt sharing with specific teammates and user groups.
-- Multimodal model support, chat with images, video etc.
-- Choosing between LLMs and parameters during chat session.
-- Tool calling and agent configurations options.
-- Organizational understanding and ability to locate and suggest experts from your team.
 
-## Other Notable Benefits of Onyx
+## Other Notable Benefits of Danswer
+* User Authentication with document level access management.
+* Best in class Hybrid Search across all sources (BM-25 + prefix aware embedding models).
+* Admin Dashboard to configure connectors, document-sets, access, etc.
+* Custom deep learning models + learn from user feedback.
+* Easy deployment and ability to host Danswer anywhere of your choosing.
 
-- 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 Onyx:
+There are two editions of Danswer:
 
-- 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.
+  * Danswer Community Edition (CE) is available freely under the MIT Expat license. This version has ALL the core features discussed above. This is the version of Danswer you will get if you follow the Deployment guide above.
+  * Danswer Enterprise Edition (EE) includes extra features that are primarily useful for larger organizations. Specifically, this includes:
+    * Single Sign-On (SSO), with support for both SAML and OIDC
+    * Role-based access control
+    * Document permission inheritance from connected sources
+    * Usage analytics and query history accessible to admins
+    * Whitelabeling
+    * API key authentication
+    * Encryption of secrets
+    * Any many more! Checkout [our website](https://www.danswer.ai/) for the latest.
 
-To try the Onyx Enterprise Edition:
+To try the Danswer Enterprise Edition: 
 
-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).
+  1. Checkout our [Cloud product](https://app.danswer.ai/signup).
+  2. For self-hosting, contact us at [founders@danswer.ai](mailto:founders@danswer.ai) or book a call with us on our [Cal](https://cal.com/team/danswer/founders).
 
 ## 💡 Contributing
-
 Looking to contribute? Please check out the [Contribution Guide](CONTRIBUTING.md) for more details.
 
 ## ⭐Star History
 
-[![Star History Chart](https://api.star-history.com/svg?repos=onyx-dot-app/onyx&type=Date)](https://star-history.com/#onyx-dot-app/onyx&Date)
+[![Star History Chart](https://api.star-history.com/svg?repos=danswer-ai/danswer&type=Date)](https://star-history.com/#danswer-ai/danswer&Date)
 
 ## ✨Contributors
 
-<a href="https://github.com/onyx-dot-app/onyx/graphs/contributors">
-  <img alt="contributors" src="https://contrib.rocks/image?repo=onyx-dot-app/onyx"/>
+<a href="https://github.com/danswer-ai/danswer/graphs/contributors">
+  <img alt="contributors" src="https://contrib.rocks/image?repo=danswer-ai/danswer"/>
 </a>
 
 <p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">

backend/Dockerfile

@@ -1,19 +1,19 @@
 FROM python:3.11.7-slim-bookworm
 
-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 \
+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 \
 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@onyx.app for more information. Please visit https://github.com/onyx-dot-app/onyx"
+founders@danswer.ai for more information. Please visit https://github.com/danswer-ai/danswer"
 
-# Default ONYX_VERSION, typically overriden during builds by GitHub Actions.
-ARG ONYX_VERSION=0.8-dev
-ENV ONYX_VERSION=${ONYX_VERSION} \
+# Default DANSWER_VERSION, typically overriden during builds by GitHub Actions.
+ARG DANSWER_VERSION=0.8-dev
+ENV DANSWER_VERSION=${DANSWER_VERSION} \
     DANSWER_RUNNING_IN_DOCKER="true"
 
 
-RUN echo "ONYX_VERSION: ${ONYX_VERSION}"
+RUN echo "DANSWER_VERSION: ${DANSWER_VERSION}"
 # Install system dependencies
 # cmake needed for psycopg (postgres)
 # libpq-dev needed for psycopg (postgres)
@@ -56,7 +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 Onyx functionality
+# perl-base is part of the base Python Debian image but not needed for Danswer functionality
 # perl-base could only be removed with --allow-remove-essential
 RUN apt-get update && \
     apt-get remove -y --allow-remove-essential \
@@ -73,7 +73,6 @@ 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')"
@@ -92,7 +91,7 @@ COPY ./ee /app/ee
 COPY supervisord.conf /etc/supervisor/conf.d/supervisord.conf
 
 # Set up application files
-COPY ./onyx /app/onyx
+COPY ./danswer /app/danswer
 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@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."
+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."
 
-# Default ONYX_VERSION, typically overriden during builds by GitHub Actions.
-ARG ONYX_VERSION=0.8-dev
-ENV ONYX_VERSION=${ONYX_VERSION} \
+# Default DANSWER_VERSION, typically overriden during builds by GitHub Actions.
+ARG DANSWER_VERSION=0.8-dev
+ENV DANSWER_VERSION=${DANSWER_VERSION} \
     DANSWER_RUNNING_IN_DOCKER="true"
 
 
-RUN echo "ONYX_VERSION: ${ONYX_VERSION}"
+RUN echo "DANSWER_VERSION: ${DANSWER_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 Onyx model
+# Download tokenizers, distilbert for the Danswer 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 Onyx, don't overwrite it with the built in cache folder
+# running Danswer, 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 ./onyx/utils/logger.py /app/onyx/utils/logger.py
+COPY ./danswer/utils/logger.py /app/danswer/utils/logger.py
 
 # Place to fetch version information
-COPY ./onyx/__init__.py /app/onyx/__init__.py
+COPY ./danswer/__init__.py /app/danswer/__init__.py
 
-# Shared between Onyx Backend and Model Server
+# Shared between Danswer Backend and Model Server
 COPY ./shared_configs /app/shared_configs
 
 # Model Server main code

backend/alembic/README.md

@@ -1,22 +1,19 @@
-<!-- DANSWER_METADATA={"link": "https://github.com/onyx-dot-app/onyx/blob/main/backend/alembic/README.md"} -->
+<!-- DANSWER_METADATA={"link": "https://github.com/danswer-ai/danswer/blob/main/backend/alembic/README.md"} -->
 
 # Alembic DB Migrations
-
 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.
+Danswer migrations use a generic single-database configuration with an async dbapi.
 
-## To generate new migrations:
-
-run from onyx/backend:
+## To generate new migrations: 
+run from danswer/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

@@ -1,70 +1,56 @@
-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
-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
+from typing import Any
 import asyncio
-import logging
 from logging.config import fileConfig
+import logging
 
 from alembic import context
+from sqlalchemy import pool
 from sqlalchemy.ext.asyncio import create_async_engine
-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 sqlalchemy.sql import text
+
+from shared_configs.configs import MULTI_TENANT
+from danswer.db.engine import build_connection_string
+from danswer.db.models import Base
 from celery.backends.database.session import ResultModelBase  # type: ignore
+from danswer.db.engine import get_all_tenant_ids
+from shared_configs.configs import POSTGRES_DEFAULT_SCHEMA
 
 # Alembic Config object
 config = context.config
 
+# Interpret the config file for Python logging.
 if config.config_file_name is not None and config.attributes.get(
     "configure_logger", True
 ):
     fileConfig(config.config_file_name)
 
+# Add your model's MetaData object here for 'autogenerate' support
 target_metadata = [Base.metadata, ResultModelBase.metadata]
 
 EXCLUDE_TABLES = {"kombu_queue", "kombu_message"}
-logger = logging.getLogger(__name__)
 
-ssl_context: ssl.SSLContext | None = None
-if USE_IAM_AUTH:
-    if not os.path.exists(SSL_CERT_FILE):
-        raise FileNotFoundError(f"Expected {SSL_CERT_FILE} when USE_IAM_AUTH is true.")
-    ssl_context = ssl.create_default_context(cafile=SSL_CERT_FILE)
+# Set up logging
+logger = logging.getLogger(__name__)
 
 
 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,
+    object: Any, name: str, type_: str, reflected: bool, compare_to: Any
 ) -> bool:
+    """
+    Determines whether a database object should be included in migrations.
+    Excludes specified tables from migrations.
+    """
     if type_ == "table" and name in EXCLUDE_TABLES:
         return False
     return True
 
 
 def get_schema_options() -> tuple[str, bool, bool]:
+    """
+    Parses command-line options passed via '-x' in Alembic commands.
+    Recognizes 'schema', 'create_schema', and 'upgrade_all_tenants' options.
+    """
     x_args_raw = context.get_x_argument()
     x_args = {}
     for arg in x_args_raw:
@@ -92,12 +78,16 @@ def get_schema_options() -> tuple[str, bool, bool]:
 def do_run_migrations(
     connection: Connection, schema_name: str, create_schema: bool
 ) -> None:
+    """
+    Executes migrations in the specified schema.
+    """
     logger.info(f"About to migrate schema: {schema_name}")
 
     if create_schema:
         connection.execute(text(f'CREATE SCHEMA IF NOT EXISTS "{schema_name}"'))
         connection.execute(text("COMMIT"))
 
+    # Set search_path to the target schema
     connection.execute(text(f'SET search_path TO "{schema_name}"'))
 
     context.configure(
@@ -115,25 +105,11 @@ def do_run_migrations(
         context.run_migrations()
 
 
-def provide_iam_token_for_alembic(
-    dialect: Any, conn_rec: Any, cargs: Any, cparams: Any
-) -> None:
-    if USE_IAM_AUTH:
-        # Database connection settings
-        region = AWS_REGION
-        host = POSTGRES_HOST
-        port = POSTGRES_PORT
-        user = POSTGRES_USER
-
-        # Get IAM authentication token
-        token = get_iam_auth_token(host, port, user, region)
-
-        # For Alembic / SQLAlchemy in this context, set SSL and password
-        cparams["password"] = token
-        cparams["ssl"] = ssl_context
-
-
 async def run_async_migrations() -> None:
+    """
+    Determines whether to run migrations for a single schema or all schemas,
+    and executes migrations accordingly.
+    """
     schema_name, create_schema, upgrade_all_tenants = get_schema_options()
 
     engine = create_async_engine(
@@ -141,16 +117,10 @@ async def run_async_migrations() -> None:
         poolclass=pool.NullPool,
     )
 
-    if USE_IAM_AUTH:
-
-        @event.listens_for(engine.sync_engine, "do_connect")
-        def event_provide_iam_token_for_alembic(
-            dialect: Any, conn_rec: Any, cargs: Any, cparams: Any
-        ) -> None:
-            provide_iam_token_for_alembic(dialect, conn_rec, cargs, cparams)
-
     if upgrade_all_tenants:
+        # Run migrations for all tenant schemas sequentially
         tenant_schemas = get_all_tenant_ids()
+
         for schema in tenant_schemas:
             try:
                 logger.info(f"Migrating schema: {schema}")
@@ -180,20 +150,15 @@ async def run_async_migrations() -> None:
 
 
 def run_migrations_offline() -> None:
+    """
+    Run migrations in 'offline' mode.
+    """
     schema_name, _, upgrade_all_tenants = get_schema_options()
     url = build_connection_string()
 
     if upgrade_all_tenants:
+        # Run offline migrations for all tenant schemas
         engine = create_async_engine(url)
-
-        if USE_IAM_AUTH:
-
-            @event.listens_for(engine.sync_engine, "do_connect")
-            def event_provide_iam_token_for_alembic_offline(
-                dialect: Any, conn_rec: Any, cargs: Any, cparams: Any
-            ) -> None:
-                provide_iam_token_for_alembic(dialect, conn_rec, cargs, cparams)
-
         tenant_schemas = get_all_tenant_ids()
         engine.sync_engine.dispose()
 
@@ -230,6 +195,9 @@ def run_migrations_offline() -> None:
 
 
 def run_migrations_online() -> None:
+    """
+    Runs migrations in 'online' mode using an asynchronous engine.
+    """
     asyncio.run(run_async_migrations())
 
 

backend/alembic/versions/0a98909f2757_enable_encrypted_fields.py

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

backend/alembic/versions/15326fcec57e_introduce_danswer_apis.py

@@ -1,4 +1,4 @@
-"""Introduce Onyx APIs
+"""Introduce Danswer 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 onyx.configs.constants import DocumentSource
+from danswer.configs.constants import DocumentSource
 
 # revision identifiers, used by Alembic.
 revision = "15326fcec57e"

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 onyx.configs.chat_configs import NUM_POSTPROCESSED_RESULTS
+from danswer.configs.chat_configs import NUM_POSTPROCESSED_RESULTS
 
 # revision identifiers, used by Alembic.
 revision = "1f60f60c3401"

backend/alembic/versions/35e518e0ddf4_properly_cascade.py

@@ -1,121 +0,0 @@
-"""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/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/onyx-dot-app/onyx/pull/637
+    # https://github.com/danswer-ai/danswer/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/4ee1287bd26a_add_multiple_slack_bot_support.py

@@ -10,8 +10,8 @@ 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 danswer.key_value_store.factory import get_kv_store
+from danswer.db.models import SlackBot
 from sqlalchemy.dialects import postgresql
 
 # revision identifiers, used by Alembic.

backend/alembic/versions/54a74a0417fc_danswerbot_onyxbot.py

@@ -1,23 +0,0 @@
-"""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_danswerbot_explicitly.py

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

backend/alembic/versions/6d562f86c78b_remove_default_bot.py

@@ -1,45 +0,0 @@
-"""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/703313b75876_add_tokenratelimit_tables.py

@@ -9,7 +9,7 @@ import json
 from typing import cast
 from alembic import op
 import sqlalchemy as sa
-from onyx.key_value_store.factory import get_kv_store
+from danswer.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 onyx.db.models import IndexModelStatus
-from onyx.context.search.enums import RecencyBiasSetting
-from onyx.context.search.enums import SearchType
+from danswer.db.models import IndexModelStatus
+from danswer.search.enums import RecencyBiasSetting
+from danswer.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/onyx-dot-app/onyx/pull/397/files#diff-f05fb341f6373790b91852579631b64ca7645797a190837156a282b67e5b19c2
+    # https://github.com/danswer-ai/danswer/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

@@ -1,45 +0,0 @@
-"""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 onyx.configs.constants import DocumentSource
+from danswer.configs.constants import DocumentSource
 
 # revision identifiers, used by Alembic.
 revision = "91fd3b470d1a"

backend/alembic/versions/93560ba1b118_add_web_ui_option_to_slack_config.py

@@ -1,35 +0,0 @@
-"""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

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

backend/alembic/versions/94dc3d0236f8_make_document_set_description_optional.py

@@ -1,30 +0,0 @@
-"""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/9f696734098f_combine_search_and_chat.py

@@ -1,36 +0,0 @@
-"""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

@@ -1,27 +0,0 @@
-"""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

@@ -1,30 +0,0 @@
-"""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/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 onyx.configs.constants import DocumentSource
+from danswer.configs.constants import DocumentSource
 
 # revision identifiers, used by Alembic.
 revision = "b156fa702355"

backend/alembic/versions/bf7a81109301_delete_input_prompts.py

@@ -1,57 +0,0 @@
-"""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

@@ -1,87 +0,0 @@
-"""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/dab04867cd88_add_composite_index_to_document_by_.py

@@ -1,32 +0,0 @@
-"""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_danswer_custom_tool_flow.py

@@ -1,4 +1,4 @@
-"""Onyx Custom Tool Flow
+"""Danswer 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 onyx.db.search_settings import (
+from danswer.db.search_settings import (
     get_new_default_embedding_model,
     get_old_default_embedding_model,
     user_has_overridden_embedding_model,
 )
-from onyx.db.models import IndexModelStatus
+from danswer.db.models import IndexModelStatus
 
 # revision identifiers, used by Alembic.
 revision = "dbaa756c2ccf"

backend/alembic/versions/e50154680a5c_no_source_enum.py

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

backend/alembic/versions/f7a894b06d02_non_nullbale_slack_bot_id_in_channel_.py

@@ -1,40 +0,0 @@
-"""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_tenants/README.md

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

backend/alembic_tenants/env.py

@@ -1,6 +1,5 @@
 import asyncio
 from logging.config import fileConfig
-from typing import Literal
 
 from sqlalchemy import pool
 from sqlalchemy.engine import Connection
@@ -8,8 +7,8 @@ from sqlalchemy.ext.asyncio import create_async_engine
 from sqlalchemy.schema import SchemaItem
 
 from alembic import context
-from onyx.db.engine import build_connection_string
-from onyx.db.models import PublicBase
+from danswer.db.engine import build_connection_string
+from danswer.db.models import PublicBase
 
 # this is the Alembic Config object, which provides
 # access to the values within the .ini file in use.
@@ -38,15 +37,8 @@ EXCLUDE_TABLES = {"kombu_queue", "kombu_message"}
 
 def include_object(
     object: SchemaItem,
-    name: str | None,
-    type_: Literal[
-        "schema",
-        "table",
-        "column",
-        "index",
-        "unique_constraint",
-        "foreign_key_constraint",
-    ],
+    name: str,
+    type_: str,
     reflected: bool,
     compare_to: SchemaItem | None,
 ) -> bool:

backend/danswer/__init__.py

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

backend/danswer/access/access.py

@@ -1,12 +1,12 @@
 from sqlalchemy.orm import Session
 
-from onyx.access.models import DocumentAccess
-from onyx.access.utils import prefix_user_email
-from onyx.configs.constants import PUBLIC_DOC_PAT
-from onyx.db.document import get_access_info_for_document
-from onyx.db.document import get_access_info_for_documents
-from onyx.db.models import User
-from onyx.utils.variable_functionality import fetch_versioned_implementation
+from danswer.access.models import DocumentAccess
+from danswer.access.utils import prefix_user_email
+from danswer.configs.constants import PUBLIC_DOC_PAT
+from danswer.db.document import get_access_info_for_document
+from danswer.db.document import get_access_info_for_documents
+from danswer.db.models import User
+from danswer.utils.variable_functionality import fetch_versioned_implementation
 
 
 def _get_access_for_document(
@@ -32,7 +32,7 @@ def get_access_for_document(
     db_session: Session,
 ) -> DocumentAccess:
     versioned_get_access_for_document_fn = fetch_versioned_implementation(
-        "onyx.access.access", "_get_access_for_document"
+        "danswer.access.access", "_get_access_for_document"
     )
     return versioned_get_access_for_document_fn(document_id, db_session)  # type: ignore
 
@@ -83,7 +83,7 @@ def get_access_for_documents(
 ) -> dict[str, DocumentAccess]:
     """Fetches all access information for the given documents."""
     versioned_get_access_for_documents_fn = fetch_versioned_implementation(
-        "onyx.access.access", "_get_access_for_documents"
+        "danswer.access.access", "_get_access_for_documents"
     )
     return versioned_get_access_for_documents_fn(
         document_ids, db_session
@@ -103,6 +103,6 @@ def _get_acl_for_user(user: User | None, db_session: Session) -> set[str]:
 
 def get_acl_for_user(user: User | None, db_session: Session | None = None) -> set[str]:
     versioned_acl_for_user_fn = fetch_versioned_implementation(
-        "onyx.access.access", "_get_acl_for_user"
+        "danswer.access.access", "_get_acl_for_user"
     )
     return versioned_acl_for_user_fn(user, db_session)  # type: ignore

backend/danswer/access/models.py

@@ -1,9 +1,9 @@
 from dataclasses import dataclass
 
-from onyx.access.utils import prefix_external_group
-from onyx.access.utils import prefix_user_email
-from onyx.access.utils import prefix_user_group
-from onyx.configs.constants import PUBLIC_DOC_PAT
+from danswer.access.utils import prefix_external_group
+from danswer.access.utils import prefix_user_email
+from danswer.access.utils import prefix_user_group
+from danswer.configs.constants import PUBLIC_DOC_PAT
 
 
 @dataclass(frozen=True)
@@ -12,17 +12,12 @@ class ExternalAccess:
     external_user_emails: set[str]
     # Names or external IDs of groups with access to the doc
     external_user_group_ids: set[str]
-    # Whether the document is public in the external system or Onyx
+    # Whether the document is public in the external system or Danswer
     is_public: bool
 
 
 @dataclass(frozen=True)
 class DocExternalAccess:
-    """
-    This is just a class to wrap the external access and the document ID
-    together. It's used for syncing document permissions to Redis.
-    """
-
     external_access: ExternalAccess
     # The document ID
     doc_id: str
@@ -58,7 +53,7 @@ class DocExternalAccess:
 
 @dataclass(frozen=True)
 class DocumentAccess(ExternalAccess):
-    # User emails for Onyx users, None indicates admin
+    # User emails for Danswer users, None indicates admin
     user_emails: set[str | None]
     # Names of user groups associated with this document
     user_groups: set[str]

backend/danswer/access/utils.py

@@ -1,9 +1,9 @@
-from onyx.configs.constants import DocumentSource
+from danswer.configs.constants import DocumentSource
 
 
 def prefix_user_email(user_email: str) -> str:
     """Prefixes a user email to eliminate collision with group names.
-    This applies to both a Onyx user and an External user, this is to make the query time
+    This applies to both a Danswer user and an External user, this is to make the query time
     more efficient"""
     return f"user_email:{user_email}"
 
@@ -15,7 +15,7 @@ def prefix_user_group(user_group_name: str) -> str:
 
 
 def prefix_external_group(ext_group_name: str) -> str:
-    """Prefixes an external group name to eliminate collision with user emails / Onyx groups."""
+    """Prefixes an external group name to eliminate collision with user emails / Danswer groups."""
     return f"external_group:{ext_group_name}"
 
 

backend/danswer/auth/api_key.py

@@ -1,4 +1,3 @@
-import hashlib
 import secrets
 import uuid
 from urllib.parse import quote
@@ -8,8 +7,8 @@ from fastapi import Request
 from passlib.hash import sha256_crypt
 from pydantic import BaseModel
 
-from onyx.auth.schemas import UserRole
-from onyx.configs.app_configs import API_KEY_HASH_ROUNDS
+from danswer.auth.schemas import UserRole
+from danswer.configs.app_configs import API_KEY_HASH_ROUNDS
 
 
 _API_KEY_HEADER_NAME = "Authorization"
@@ -17,10 +16,9 @@ _API_KEY_HEADER_NAME = "Authorization"
 # to non-standard, experimental, or custom headers in HTTP or other protocols. It
 # indicates that the header is not part of the official standards defined by
 # organizations like the Internet Engineering Task Force (IETF).
-_API_KEY_HEADER_ALTERNATIVE_NAME = "X-Onyx-Authorization"
+_API_KEY_HEADER_ALTERNATIVE_NAME = "X-Danswer-Authorization"
 _BEARER_PREFIX = "Bearer "
-_API_KEY_PREFIX = "on_"
-_DEPRECATED_API_KEY_PREFIX = "dn_"
+_API_KEY_PREFIX = "dn_"
 _API_KEY_LEN = 192
 
 
@@ -54,9 +52,7 @@ def extract_tenant_from_api_key_header(request: Request) -> str | None:
 
     api_key = raw_api_key_header[len(_BEARER_PREFIX) :].strip()
 
-    if not api_key.startswith(_API_KEY_PREFIX) and not api_key.startswith(
-        _DEPRECATED_API_KEY_PREFIX
-    ):
+    if not api_key.startswith(_API_KEY_PREFIX):
         return None
 
     parts = api_key[len(_API_KEY_PREFIX) :].split(".", 1)
@@ -67,19 +63,10 @@ def extract_tenant_from_api_key_header(request: Request) -> str | None:
     return unquote(tenant_id) if tenant_id else None
 
 
-def _deprecated_hash_api_key(api_key: str) -> str:
-    return sha256_crypt.hash(api_key, salt="", rounds=API_KEY_HASH_ROUNDS)
-
-
 def hash_api_key(api_key: str) -> str:
     # NOTE: no salt is needed, as the API key is randomly generated
     # and overlaps are impossible
-    if api_key.startswith(_API_KEY_PREFIX):
-        return hashlib.sha256(api_key.encode("utf-8")).hexdigest()
-    elif api_key.startswith(_DEPRECATED_API_KEY_PREFIX):
-        return _deprecated_hash_api_key(api_key)
-    else:
-        raise ValueError(f"Invalid API key prefix: {api_key[:3]}")
+    return sha256_crypt.hash(api_key, salt="", rounds=API_KEY_HASH_ROUNDS)
 
 
 def build_displayable_api_key(api_key: str) -> str:

backend/danswer/auth/invited_users.py

@@ -1,14 +1,15 @@
 from typing import cast
 
-from onyx.configs.constants import KV_USER_STORE_KEY
-from onyx.key_value_store.factory import get_kv_store
-from onyx.key_value_store.interface import KvKeyNotFoundError
-from onyx.utils.special_types import JSON_ro
+from danswer.configs.constants import KV_USER_STORE_KEY
+from danswer.key_value_store.factory import get_kv_store
+from danswer.key_value_store.interface import KvKeyNotFoundError
+from danswer.utils.special_types import JSON_ro
 
 
 def get_invited_users() -> list[str]:
     try:
         store = get_kv_store()
+
         return cast(list, store.load(KV_USER_STORE_KEY))
     except KvKeyNotFoundError:
         return list()

backend/danswer/auth/noauth_user.py

@@ -2,14 +2,12 @@ from collections.abc import Mapping
 from typing import Any
 from typing import cast
 
-from onyx.auth.schemas import UserRole
-from onyx.configs.constants import KV_NO_AUTH_USER_PREFERENCES_KEY
-from onyx.configs.constants import NO_AUTH_USER_EMAIL
-from onyx.configs.constants import NO_AUTH_USER_ID
-from onyx.key_value_store.store import KeyValueStore
-from onyx.key_value_store.store import KvKeyNotFoundError
-from onyx.server.manage.models import UserInfo
-from onyx.server.manage.models import UserPreferences
+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(
@@ -25,15 +23,13 @@ def load_no_auth_user_preferences(store: KeyValueStore) -> UserPreferences:
         )
         return UserPreferences(**preferences_data)
     except KvKeyNotFoundError:
-        return UserPreferences(
-            chosen_assistants=None, default_model=None, auto_scroll=True
-        )
+        return UserPreferences(chosen_assistants=None, default_model=None)
 
 
 def fetch_no_auth_user(store: KeyValueStore) -> UserInfo:
     return UserInfo(
-        id=NO_AUTH_USER_ID,
-        email=NO_AUTH_USER_EMAIL,
+        id="__no_auth_user__",
+        email="anonymous@danswer.ai",
         is_active=True,
         is_superuser=False,
         is_verified=True,

backend/danswer/auth/schemas.py

@@ -14,7 +14,7 @@ class UserRole(str, Enum):
     - Global Curator can perform admin actions
         for all groups they are a member of
     - Limited can access a limited set of basic api endpoints
-    - Slack are users that have used onyx via slack but dont have a web login
+    - Slack are users that have used danswer via slack but dont have a web login
     - External permissioned users that have been picked up during the external permissions sync process but don't have a web login
     """
 

backend/danswer/auth/users.py

@@ -5,7 +5,6 @@ from datetime import datetime
 from datetime import timezone
 from email.mime.multipart import MIMEMultipart
 from email.mime.text import MIMEText
-from typing import cast
 from typing import Dict
 from typing import List
 from typing import Optional
@@ -50,52 +49,49 @@ from httpx_oauth.oauth2 import BaseOAuth2
 from httpx_oauth.oauth2 import OAuth2Token
 from pydantic import BaseModel
 from sqlalchemy import text
-from sqlalchemy.ext.asyncio import AsyncSession
+from sqlalchemy.orm import Session
 
-from onyx.auth.api_key import get_hashed_api_key_from_request
-from onyx.auth.invited_users import get_invited_users
-from onyx.auth.schemas import UserCreate
-from onyx.auth.schemas import UserRole
-from onyx.auth.schemas import UserUpdate
-from onyx.configs.app_configs import AUTH_TYPE
-from onyx.configs.app_configs import DISABLE_AUTH
-from onyx.configs.app_configs import EMAIL_FROM
-from onyx.configs.app_configs import REQUIRE_EMAIL_VERIFICATION
-from onyx.configs.app_configs import SESSION_EXPIRE_TIME_SECONDS
-from onyx.configs.app_configs import SMTP_PASS
-from onyx.configs.app_configs import SMTP_PORT
-from onyx.configs.app_configs import SMTP_SERVER
-from onyx.configs.app_configs import SMTP_USER
-from onyx.configs.app_configs import TRACK_EXTERNAL_IDP_EXPIRY
-from onyx.configs.app_configs import USER_AUTH_SECRET
-from onyx.configs.app_configs import VALID_EMAIL_DOMAINS
-from onyx.configs.app_configs import WEB_DOMAIN
-from onyx.configs.constants import AuthType
-from onyx.configs.constants import DANSWER_API_KEY_DUMMY_EMAIL_DOMAIN
-from onyx.configs.constants import DANSWER_API_KEY_PREFIX
-from onyx.configs.constants import MilestoneRecordType
-from onyx.configs.constants import PASSWORD_SPECIAL_CHARS
-from onyx.configs.constants import UNNAMED_KEY_PLACEHOLDER
-from onyx.db.api_key import fetch_user_for_api_key
-from onyx.db.auth import get_access_token_db
-from onyx.db.auth import get_default_admin_user_emails
-from onyx.db.auth import get_user_count
-from onyx.db.auth import get_user_db
-from onyx.db.auth import SQLAlchemyUserAdminDB
-from onyx.db.engine import get_async_session
-from onyx.db.engine import get_async_session_with_tenant
-from onyx.db.engine import get_session_with_tenant
-from onyx.db.models import AccessToken
-from onyx.db.models import OAuthAccount
-from onyx.db.models import User
-from onyx.db.users import get_user_by_email
-from onyx.server.utils import BasicAuthenticationError
-from onyx.utils.logger import setup_logger
-from onyx.utils.telemetry import create_milestone_and_report
-from onyx.utils.telemetry import optional_telemetry
-from onyx.utils.telemetry import RecordType
-from onyx.utils.variable_functionality import fetch_ee_implementation_or_noop
-from onyx.utils.variable_functionality import fetch_versioned_implementation
+from danswer.auth.api_key import get_hashed_api_key_from_request
+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 DISABLE_VERIFICATION
+from danswer.configs.app_configs import EMAIL_FROM
+from danswer.configs.app_configs import REQUIRE_EMAIL_VERIFICATION
+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.api_key import fetch_user_for_api_key
+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.models import AccessToken
+from danswer.db.models import OAuthAccount
+from danswer.db.models import User
+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_ee_implementation_or_noop
+from danswer.utils.variable_functionality import fetch_versioned_implementation
 from shared_configs.configs import async_return_default_schema
 from shared_configs.configs import MULTI_TENANT
 from shared_configs.contextvars import CURRENT_TENANT_ID_CONTEXTVAR
@@ -103,6 +99,11 @@ from shared_configs.contextvars import CURRENT_TENANT_ID_CONTEXTVAR
 logger = setup_logger()
 
 
+class BasicAuthenticationError(HTTPException):
+    def __init__(self, detail: str):
+        super().__init__(status_code=status.HTTP_403_FORBIDDEN, detail=detail)
+
+
 def is_user_admin(user: User | None) -> bool:
     if AUTH_TYPE == AuthType.DISABLED:
         return True
@@ -135,12 +136,11 @@ def get_display_email(email: str | None, space_less: bool = False) -> str:
 
 
 def user_needs_to_be_verified() -> bool:
-    if AUTH_TYPE == AuthType.BASIC or AUTH_TYPE == AuthType.CLOUD:
-        return REQUIRE_EMAIL_VERIFICATION
-
-    # For other auth types, if the user is authenticated it's assumed that
-    # the user is already verified via the external IDP
-    return False
+    # all other auth types besides basic should require users to be
+    # verified
+    return not DISABLE_VERIFICATION and (
+        AUTH_TYPE != AuthType.BASIC or REQUIRE_EMAIL_VERIFICATION
+    )
 
 
 def verify_email_is_invited(email: str) -> None:
@@ -199,7 +199,7 @@ def send_user_verification_email(
     mail_from: str = EMAIL_FROM,
 ) -> None:
     msg = MIMEMultipart()
-    msg["Subject"] = "Onyx Email Verification"
+    msg["Subject"] = "Danswer Email Verification"
     msg["To"] = user_email
     if mail_from:
         msg["From"] = mail_from
@@ -229,26 +229,17 @@ class UserManager(UUIDIDMixin, BaseUserManager[User, uuid.UUID]):
         safe: bool = False,
         request: Optional[Request] = None,
     ) -> User:
-        # We verify the password here to make sure it's valid before we proceed
-        await self.validate_password(
-            user_create.password, cast(schemas.UC, user_create)
-        )
-
-        user_count: int | None = None
-        referral_source = (
-            request.cookies.get("referral_source", None)
-            if request is not None
-            else None
-        )
+        referral_source = None
+        if request is not None:
+            referral_source = request.cookies.get("referral_source", None)
 
         tenant_id = await fetch_ee_implementation_or_noop(
-            "onyx.server.tenants.provisioning",
-            "get_or_provision_tenant",
+            "danswer.server.tenants.provisioning",
+            "get_or_create_tenant_id",
             async_return_default_schema,
         )(
             email=user_create.email,
             referral_source=referral_source,
-            request=request,
         )
 
         async with get_async_session_with_tenant(tenant_id) as db_session:
@@ -291,37 +282,7 @@ class UserManager(UUIDIDMixin, BaseUserManager[User, uuid.UUID]):
             finally:
                 CURRENT_TENANT_ID_CONTEXTVAR.reset(token)
 
-        return user
-
-    async def validate_password(self, password: str, _: schemas.UC | models.UP) -> None:
-        # Validate password according to basic security guidelines
-        if len(password) < 12:
-            raise exceptions.InvalidPasswordException(
-                reason="Password must be at least 12 characters long."
-            )
-        if len(password) > 64:
-            raise exceptions.InvalidPasswordException(
-                reason="Password must not exceed 64 characters."
-            )
-        if not any(char.isupper() for char in password):
-            raise exceptions.InvalidPasswordException(
-                reason="Password must contain at least one uppercase letter."
-            )
-        if not any(char.islower() for char in password):
-            raise exceptions.InvalidPasswordException(
-                reason="Password must contain at least one lowercase letter."
-            )
-        if not any(char.isdigit() for char in password):
-            raise exceptions.InvalidPasswordException(
-                reason="Password must contain at least one number."
-            )
-        if not any(char in PASSWORD_SPECIAL_CHARS for char in password):
-            raise exceptions.InvalidPasswordException(
-                reason="Password must contain at least one special character from the following set: "
-                f"{PASSWORD_SPECIAL_CHARS}."
-            )
-
-        return
+            return user
 
     async def oauth_callback(
         self,
@@ -336,18 +297,17 @@ class UserManager(UUIDIDMixin, BaseUserManager[User, uuid.UUID]):
         associate_by_email: bool = False,
         is_verified_by_default: bool = False,
     ) -> User:
-        referral_source = (
-            getattr(request.state, "referral_source", None) if request else None
-        )
+        referral_source = None
+        if request:
+            referral_source = getattr(request.state, "referral_source", None)
 
         tenant_id = await fetch_ee_implementation_or_noop(
-            "onyx.server.tenants.provisioning",
-            "get_or_provision_tenant",
+            "danswer.server.tenants.provisioning",
+            "get_or_create_tenant_id",
             async_return_default_schema,
         )(
             email=account_email,
             referral_source=referral_source,
-            request=request,
         )
 
         if not tenant_id:
@@ -409,7 +369,6 @@ class UserManager(UUIDIDMixin, BaseUserManager[User, uuid.UUID]):
 
                     # Add OAuth account
                     await self.user_db.add_oauth_account(user, oauth_account_dict)
-
                     await self.on_after_register(user, request)
 
             else:
@@ -463,39 +422,6 @@ class UserManager(UUIDIDMixin, BaseUserManager[User, uuid.UUID]):
     async def on_after_register(
         self, user: User, request: Optional[Request] = None
     ) -> None:
-        tenant_id = await fetch_ee_implementation_or_noop(
-            "onyx.server.tenants.provisioning",
-            "get_or_provision_tenant",
-            async_return_default_schema,
-        )(
-            email=user.email,
-            request=request,
-        )
-
-        token = CURRENT_TENANT_ID_CONTEXTVAR.set(tenant_id)
-        try:
-            user_count = await get_user_count()
-
-            with get_session_with_tenant(tenant_id=tenant_id) as db_session:
-                if user_count == 1:
-                    create_milestone_and_report(
-                        user=user,
-                        distinct_id=user.email,
-                        event_type=MilestoneRecordType.USER_SIGNED_UP,
-                        properties=None,
-                        db_session=db_session,
-                    )
-                else:
-                    create_milestone_and_report(
-                        user=user,
-                        distinct_id=user.email,
-                        event_type=MilestoneRecordType.MULTIPLE_USERS,
-                        properties=None,
-                        db_session=db_session,
-                    )
-        finally:
-            CURRENT_TENANT_ID_CONTEXTVAR.reset(token)
-
         logger.notice(f"User {user.id} has registered.")
         optional_telemetry(
             record_type=RecordType.SIGN_UP,
@@ -526,8 +452,8 @@ class UserManager(UUIDIDMixin, BaseUserManager[User, uuid.UUID]):
 
         # Get tenant_id from mapping table
         tenant_id = await fetch_ee_implementation_or_noop(
-            "onyx.server.tenants.provisioning",
-            "get_or_provision_tenant",
+            "danswer.server.tenants.provisioning",
+            "get_or_create_tenant_id",
             async_return_default_schema,
         )(
             email=email,
@@ -587,8 +513,8 @@ cookie_transport = CookieTransport(
 class TenantAwareJWTStrategy(JWTStrategy):
     async def _create_token_data(self, user: User, impersonate: bool = False) -> dict:
         tenant_id = await fetch_ee_implementation_or_noop(
-            "onyx.server.tenants.provisioning",
-            "get_or_provision_tenant",
+            "danswer.server.tenants.provisioning",
+            "get_or_create_tenant_id",
             async_return_default_schema,
         )(
             email=user.email,
@@ -683,7 +609,7 @@ optional_fastapi_current_user = fastapi_users.current_user(active=True, optional
 async def optional_user_(
     request: Request,
     user: User | None,
-    async_db_session: AsyncSession,
+    db_session: Session,
 ) -> User | None:
     """NOTE: `request` and `db_session` are not used here, but are included
     for the EE version of this function."""
@@ -692,21 +618,13 @@ async def optional_user_(
 
 async def optional_user(
     request: Request,
-    async_db_session: AsyncSession = Depends(get_async_session),
+    db_session: Session = Depends(get_session),
     user: User | None = Depends(optional_fastapi_current_user),
 ) -> User | None:
     versioned_fetch_user = fetch_versioned_implementation(
-        "onyx.auth.users", "optional_user_"
+        "danswer.auth.users", "optional_user_"
     )
-    user = await versioned_fetch_user(request, user, async_db_session)
-
-    # check if an API key is present
-    if user is None:
-        hashed_api_key = get_hashed_api_key_from_request(request)
-        if hashed_api_key:
-            user = await fetch_user_for_api_key(hashed_api_key, async_db_session)
-
-    return user
+    return await versioned_fetch_user(request, user, db_session)
 
 
 async def double_check_user(
@@ -798,7 +716,7 @@ async def current_admin_user(user: User | None = Depends(current_user)) -> User
 
 
 def get_default_admin_user_emails_() -> list[str]:
-    # No default seeding available for Onyx MIT
+    # No default seeding available for Danswer MIT
     return []
 
 
@@ -818,7 +736,7 @@ def generate_state_token(
 
 
 # refer to https://github.com/fastapi-users/fastapi-users/blob/42ddc241b965475390e2bce887b084152ae1a2cd/fastapi_users/fastapi_users.py#L91
-def create_onyx_oauth_router(
+def create_danswer_oauth_router(
     oauth_client: BaseOAuth2,
     backend: AuthenticationBackend,
     state_secret: SecretType,
@@ -992,8 +910,8 @@ def get_oauth_router(
     return router
 
 
-async def api_key_dep(
-    request: Request, async_db_session: AsyncSession = Depends(get_async_session)
+def api_key_dep(
+    request: Request, db_session: Session = Depends(get_session)
 ) -> User | None:
     if AUTH_TYPE == AuthType.DISABLED:
         return None
@@ -1003,7 +921,7 @@ async def api_key_dep(
         raise HTTPException(status_code=401, detail="Missing API key")
 
     if hashed_api_key:
-        user = await fetch_user_for_api_key(hashed_api_key, async_db_session)
+        user = fetch_user_for_api_key(hashed_api_key, db_session)
 
     if user is None:
         raise HTTPException(status_code=401, detail="Invalid API key")

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

@@ -3,44 +3,38 @@ import multiprocessing
 import time
 from typing import Any
 
+import requests
 import sentry_sdk
 from celery import Task
 from celery.app import trace
 from celery.exceptions import WorkerShutdown
-from celery.signals import task_postrun
-from celery.signals import task_prerun
 from celery.states import READY_STATES
 from celery.utils.log import get_task_logger
 from celery.worker import strategy  # type: ignore
-from redis.lock import Lock as RedisLock
 from sentry_sdk.integrations.celery import CeleryIntegration
 from sqlalchemy import text
 from sqlalchemy.orm import Session
 
-from onyx.background.celery.apps.task_formatters import CeleryTaskColoredFormatter
-from onyx.background.celery.apps.task_formatters import CeleryTaskPlainFormatter
-from onyx.background.celery.celery_utils import celery_is_worker_primary
-from onyx.configs.constants import OnyxRedisLocks
-from onyx.db.engine import get_sqlalchemy_engine
-from onyx.document_index.vespa.shared_utils.utils import get_vespa_http_client
-from onyx.document_index.vespa_constants import VESPA_CONFIG_SERVER_URL
-from onyx.redis.redis_connector import RedisConnector
-from onyx.redis.redis_connector_credential_pair import RedisConnectorCredentialPair
-from onyx.redis.redis_connector_delete import RedisConnectorDelete
-from onyx.redis.redis_connector_doc_perm_sync import RedisConnectorPermissionSync
-from onyx.redis.redis_connector_ext_group_sync import RedisConnectorExternalGroupSync
-from onyx.redis.redis_connector_prune import RedisConnectorPrune
-from onyx.redis.redis_document_set import RedisDocumentSet
-from onyx.redis.redis_pool import get_redis_client
-from onyx.redis.redis_usergroup import RedisUserGroup
-from onyx.utils.logger import ColoredFormatter
-from onyx.utils.logger import PlainFormatter
-from onyx.utils.logger import setup_logger
-from shared_configs.configs import MULTI_TENANT
-from shared_configs.configs import POSTGRES_DEFAULT_SCHEMA
+from danswer.background.celery.apps.task_formatters import CeleryTaskColoredFormatter
+from danswer.background.celery.apps.task_formatters import CeleryTaskPlainFormatter
+from danswer.background.celery.celery_utils import celery_is_worker_primary
+from danswer.configs.constants import DanswerRedisLocks
+from danswer.db.engine import get_sqlalchemy_engine
+from danswer.document_index.vespa_constants import VESPA_CONFIG_SERVER_URL
+from danswer.redis.redis_connector import RedisConnector
+from danswer.redis.redis_connector_credential_pair import RedisConnectorCredentialPair
+from danswer.redis.redis_connector_delete import RedisConnectorDelete
+from danswer.redis.redis_connector_doc_perm_sync import RedisConnectorPermissionSync
+from danswer.redis.redis_connector_ext_group_sync import RedisConnectorExternalGroupSync
+from danswer.redis.redis_connector_prune import RedisConnectorPrune
+from danswer.redis.redis_document_set import RedisDocumentSet
+from danswer.redis.redis_pool import get_redis_client
+from danswer.redis.redis_usergroup import RedisUserGroup
+from danswer.utils.logger import ColoredFormatter
+from danswer.utils.logger import PlainFormatter
+from danswer.utils.logger import setup_logger
 from shared_configs.configs import SENTRY_DSN
-from shared_configs.configs import TENANT_ID_PREFIX
-from shared_configs.contextvars import CURRENT_TENANT_ID_CONTEXTVAR
+
 
 logger = setup_logger()
 
@@ -61,8 +55,8 @@ def on_task_prerun(
     sender: Any | None = None,
     task_id: str | None = None,
     task: Task | None = None,
-    args: tuple[Any, ...] | None = None,
-    kwargs: dict[str, Any] | None = None,
+    args: tuple | None = None,
+    kwargs: dict | None = None,
     **kwds: Any,
 ) -> None:
     pass
@@ -262,8 +256,7 @@ def wait_for_vespa(sender: Any, **kwargs: Any) -> None:
     logger.info("Vespa: Readiness probe starting.")
     while True:
         try:
-            client = get_vespa_http_client()
-            response = client.get(f"{VESPA_CONFIG_SERVER_URL}/state/v1/health")
+            response = requests.get(f"{VESPA_CONFIG_SERVER_URL}/state/v1/health")
             response.raise_for_status()
 
             response_dict = response.json()
@@ -306,7 +299,7 @@ def on_secondary_worker_init(sender: Any, **kwargs: Any) -> None:
 
     logger.info("Waiting for primary worker to be ready...")
     while True:
-        if r.exists(OnyxRedisLocks.PRIMARY_WORKER):
+        if r.exists(DanswerRedisLocks.PRIMARY_WORKER):
             break
 
         time_elapsed = time.monotonic() - time_start
@@ -339,49 +332,39 @@ def on_worker_shutdown(sender: Any, **kwargs: Any) -> None:
         return
 
     logger.info("Releasing primary worker lock.")
-    lock: RedisLock = sender.primary_worker_lock
+    lock = sender.primary_worker_lock
     try:
         if lock.owned():
             try:
                 lock.release()
                 sender.primary_worker_lock = None
-            except Exception:
-                logger.exception("Failed to release primary worker lock")
-    except Exception:
-        logger.exception("Failed to check if primary worker lock is owned")
+            except Exception as e:
+                logger.error(f"Failed to release primary worker lock: {e}")
+    except Exception as e:
+        logger.error(f"Failed to check if primary worker lock is owned: {e}")
 
 
 def on_setup_logging(
-    loglevel: int,
-    logfile: str | None,
-    format: str,
-    colorize: bool,
-    **kwargs: Any,
+    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 the root logger
     root_logger = logging.getLogger()
-    root_logger.handlers = []
 
-    # Define the log format
-    log_format = (
-        "%(levelname)-8s %(asctime)s %(filename)15s:%(lineno)-4d: %(name)s %(message)s"
-    )
-
-    # Set up the root handler
-    root_handler = logging.StreamHandler()
+    root_handler = logging.StreamHandler()  # Set up a handler for the root logger
     root_formatter = ColoredFormatter(
-        log_format,
+        "%(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)
+    root_logger.addHandler(root_handler)  # Apply the handler to the root logger
 
     if logfile:
         root_file_handler = logging.FileHandler(logfile)
         root_file_formatter = PlainFormatter(
-            log_format,
+            "%(asctime)s %(filename)30s %(lineno)4s: %(message)s",
             datefmt="%m/%d/%Y %I:%M:%S %p",
         )
         root_file_handler.setFormatter(root_file_formatter)
@@ -389,23 +372,19 @@ def on_setup_logging(
 
     root_logger.setLevel(loglevel)
 
-    # Configure the task logger
-    task_logger.handlers = []
-
-    task_handler = logging.StreamHandler()
-    task_handler.addFilter(TenantContextFilter())
+    # reformats celery's task logger
     task_formatter = CeleryTaskColoredFormatter(
-        log_format,
+        "%(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)
+    task_logger.addHandler(task_handler)  # Apply the handler to the task logger
 
     if logfile:
         task_file_handler = logging.FileHandler(logfile)
-        task_file_handler.addFilter(TenantContextFilter())
         task_file_formatter = CeleryTaskPlainFormatter(
-            log_format,
+            "%(asctime)s %(filename)30s %(lineno)4s: %(message)s",
             datefmt="%m/%d/%Y %I:%M:%S %p",
         )
         task_file_handler.setFormatter(task_file_formatter)
@@ -414,55 +393,10 @@ def on_setup_logging(
     task_logger.setLevel(loglevel)
     task_logger.propagate = False
 
-    # Hide celery task received and succeeded/failed messages
+    # hide celery task received spam
+    # e.g. "Task check_for_pruning[a1e96171-0ba8-4e00-887b-9fbf7442eab3] received"
     strategy.logger.setLevel(logging.WARNING)
+
+    # hide celery task succeeded/failed spam
+    # e.g. "Task check_for_pruning[a1e96171-0ba8-4e00-887b-9fbf7442eab3] succeeded in 0.03137450001668185s: None"
     trace.logger.setLevel(logging.WARNING)
-
-
-class TenantContextFilter(logging.Filter):
-
-    """Logging filter to inject tenant ID into the logger's name."""
-
-    def filter(self, record: logging.LogRecord) -> bool:
-        if not MULTI_TENANT:
-            record.name = ""
-            return True
-
-        tenant_id = CURRENT_TENANT_ID_CONTEXTVAR.get()
-        if tenant_id:
-            tenant_id = tenant_id.split(TENANT_ID_PREFIX)[-1][:5]
-            record.name = f"[t:{tenant_id}]"
-        else:
-            record.name = ""
-        return True
-
-
-@task_prerun.connect
-def set_tenant_id(
-    sender: Any | None = None,
-    task_id: str | None = None,
-    task: Task | None = None,
-    args: tuple[Any, ...] | None = None,
-    kwargs: dict[str, Any] | None = None,
-    **other_kwargs: Any,
-) -> None:
-    """Signal handler to set tenant ID in context var before task starts."""
-    tenant_id = (
-        kwargs.get("tenant_id", POSTGRES_DEFAULT_SCHEMA)
-        if kwargs
-        else POSTGRES_DEFAULT_SCHEMA
-    )
-    CURRENT_TENANT_ID_CONTEXTVAR.set(tenant_id)
-
-
-@task_postrun.connect
-def reset_tenant_id(
-    sender: Any | None = None,
-    task_id: str | None = None,
-    task: Task | None = None,
-    args: tuple[Any, ...] | None = None,
-    kwargs: dict[str, Any] | None = None,
-    **other_kwargs: Any,
-) -> None:
-    """Signal handler to reset tenant ID in context var after task ends."""
-    CURRENT_TENANT_ID_CONTEXTVAR.set(POSTGRES_DEFAULT_SCHEMA)

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

@@ -6,18 +6,19 @@ from celery import signals
 from celery.beat import PersistentScheduler  # type: ignore
 from celery.signals import beat_init
 
-import onyx.background.celery.apps.app_base as app_base
-from onyx.configs.constants import POSTGRES_CELERY_BEAT_APP_NAME
-from onyx.db.engine import get_all_tenant_ids
-from onyx.db.engine import SqlEngine
-from onyx.utils.logger import setup_logger
-from onyx.utils.variable_functionality import fetch_versioned_implementation
+import danswer.background.celery.apps.app_base as app_base
+from danswer.configs.constants import POSTGRES_CELERY_BEAT_APP_NAME
+from danswer.db.engine import get_all_tenant_ids
+from danswer.db.engine import SqlEngine
+from danswer.utils.logger import setup_logger
+from danswer.utils.variable_functionality import fetch_versioned_implementation
 from shared_configs.configs import IGNORED_SYNCING_TENANT_LIST
+from shared_configs.configs import MULTI_TENANT
 
 logger = setup_logger(__name__)
 
 celery_app = Celery(__name__)
-celery_app.config_from_object("onyx.background.celery.configs.beat")
+celery_app.config_from_object("danswer.background.celery.configs.beat")
 
 
 class DynamicTenantScheduler(PersistentScheduler):
@@ -43,22 +44,22 @@ class DynamicTenantScheduler(PersistentScheduler):
             self._last_reload is None
             or (now - self._last_reload) > self._reload_interval
         ):
-            logger.info("Reload interval reached, initiating task update")
+            logger.info("Reload interval reached, initiating tenant task update")
             self._update_tenant_tasks()
             self._last_reload = now
-            logger.info("Task update completed, reset reload timer")
+            logger.info("Tenant task update completed, reset reload timer")
         return retval
 
     def _update_tenant_tasks(self) -> None:
-        logger.info("Starting task update process")
+        logger.info("Starting tenant task update process")
         try:
-            logger.info("Fetching all IDs")
+            logger.info("Fetching all tenant IDs")
             tenant_ids = get_all_tenant_ids()
-            logger.info(f"Found {len(tenant_ids)} IDs")
+            logger.info(f"Found {len(tenant_ids)} tenants")
 
             logger.info("Fetching tasks to schedule")
             tasks_to_schedule = fetch_versioned_implementation(
-                "onyx.background.celery.tasks.beat_schedule", "get_tasks_to_schedule"
+                "danswer.background.celery.tasks.beat_schedule", "get_tasks_to_schedule"
             )
 
             new_beat_schedule: dict[str, dict[str, Any]] = {}
@@ -69,7 +70,7 @@ class DynamicTenantScheduler(PersistentScheduler):
             for task_name, _ in current_schedule:
                 if "-" in task_name:
                     existing_tenants.add(task_name.split("-")[-1])
-            logger.info(f"Found {len(existing_tenants)} existing items in schedule")
+            logger.info(f"Found {len(existing_tenants)} existing tenants in schedule")
 
             for tenant_id in tenant_ids:
                 if (
@@ -82,7 +83,7 @@ class DynamicTenantScheduler(PersistentScheduler):
                     continue
 
                 if tenant_id not in existing_tenants:
-                    logger.info(f"Processing new item: {tenant_id}")
+                    logger.info(f"Processing new tenant: {tenant_id}")
 
                 for task in tasks_to_schedule():
                     task_name = f"{task['name']}-{tenant_id}"
@@ -128,10 +129,11 @@ class DynamicTenantScheduler(PersistentScheduler):
                 logger.info("Schedule update completed successfully")
             else:
                 logger.info("Schedule is up to date, no changes needed")
-        except (AttributeError, KeyError) as e:
-            logger.exception(f"Failed to process task configuration: {str(e)}")
-        except Exception as e:
-            logger.exception(f"Unexpected error updating tasks: {str(e)}")
+
+        except (AttributeError, KeyError):
+            logger.exception("Failed to process task configuration")
+        except Exception:
+            logger.exception("Unexpected error updating tenant tasks")
 
     def _should_update_schedule(
         self, current_schedule: dict, new_schedule: dict
@@ -153,6 +155,10 @@ 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)
 
+    # Startup checks are not needed in multi-tenant case
+    if MULTI_TENANT:
+        return
+
     app_base.wait_for_redis(sender, **kwargs)
 
 

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

@@ -9,17 +9,17 @@ from celery.signals import worker_init
 from celery.signals import worker_ready
 from celery.signals import worker_shutdown
 
-import onyx.background.celery.apps.app_base as app_base
-from onyx.configs.constants import POSTGRES_CELERY_WORKER_HEAVY_APP_NAME
-from onyx.db.engine import SqlEngine
-from onyx.utils.logger import setup_logger
+import danswer.background.celery.apps.app_base as app_base
+from danswer.configs.constants import POSTGRES_CELERY_WORKER_HEAVY_APP_NAME
+from danswer.db.engine import SqlEngine
+from danswer.utils.logger import setup_logger
 from shared_configs.configs import MULTI_TENANT
 
 
 logger = setup_logger()
 
 celery_app = Celery(__name__)
-celery_app.config_from_object("onyx.background.celery.configs.heavy")
+celery_app.config_from_object("danswer.background.celery.configs.heavy")
 
 
 @signals.task_prerun.connect
@@ -61,14 +61,13 @@ def on_worker_init(sender: Any, **kwargs: Any) -> None:
     SqlEngine.set_app_name(POSTGRES_CELERY_WORKER_HEAVY_APP_NAME)
     SqlEngine.init_engine(pool_size=4, max_overflow=12)
 
-    app_base.wait_for_redis(sender, **kwargs)
-    app_base.wait_for_db(sender, **kwargs)
-    app_base.wait_for_vespa(sender, **kwargs)
-
-    # Less startup checks in multi-tenant case
+    # Startup checks are not needed in multi-tenant case
     if MULTI_TENANT:
         return
 
+    app_base.wait_for_redis(sender, **kwargs)
+    app_base.wait_for_db(sender, **kwargs)
+    app_base.wait_for_vespa(sender, **kwargs)
     app_base.on_secondary_worker_init(sender, **kwargs)
 
 
@@ -91,8 +90,8 @@ def on_setup_logging(
 
 celery_app.autodiscover_tasks(
     [
-        "onyx.background.celery.tasks.pruning",
-        "onyx.background.celery.tasks.doc_permission_syncing",
-        "onyx.background.celery.tasks.external_group_syncing",
+        "danswer.background.celery.tasks.pruning",
+        "danswer.background.celery.tasks.doc_permission_syncing",
+        "danswer.background.celery.tasks.external_group_syncing",
     ]
 )

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

@@ -10,17 +10,17 @@ from celery.signals import worker_process_init
 from celery.signals import worker_ready
 from celery.signals import worker_shutdown
 
-import onyx.background.celery.apps.app_base as app_base
-from onyx.configs.constants import POSTGRES_CELERY_WORKER_INDEXING_APP_NAME
-from onyx.db.engine import SqlEngine
-from onyx.utils.logger import setup_logger
+import danswer.background.celery.apps.app_base as app_base
+from danswer.configs.constants import POSTGRES_CELERY_WORKER_INDEXING_APP_NAME
+from danswer.db.engine import SqlEngine
+from danswer.utils.logger import setup_logger
 from shared_configs.configs import MULTI_TENANT
 
 
 logger = setup_logger()
 
 celery_app = Celery(__name__)
-celery_app.config_from_object("onyx.background.celery.configs.indexing")
+celery_app.config_from_object("danswer.background.celery.configs.indexing")
 
 
 @signals.task_prerun.connect
@@ -62,14 +62,13 @@ def on_worker_init(sender: Any, **kwargs: Any) -> None:
     SqlEngine.set_app_name(POSTGRES_CELERY_WORKER_INDEXING_APP_NAME)
     SqlEngine.init_engine(pool_size=sender.concurrency, max_overflow=sender.concurrency)
 
-    app_base.wait_for_redis(sender, **kwargs)
-    app_base.wait_for_db(sender, **kwargs)
-    app_base.wait_for_vespa(sender, **kwargs)
-
-    # Less startup checks in multi-tenant case
+    # Startup checks are not needed in multi-tenant case
     if MULTI_TENANT:
         return
 
+    app_base.wait_for_redis(sender, **kwargs)
+    app_base.wait_for_db(sender, **kwargs)
+    app_base.wait_for_vespa(sender, **kwargs)
     app_base.on_secondary_worker_init(sender, **kwargs)
 
 
@@ -97,6 +96,6 @@ def on_setup_logging(
 
 celery_app.autodiscover_tasks(
     [
-        "onyx.background.celery.tasks.indexing",
+        "danswer.background.celery.tasks.indexing",
     ]
 )

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

@@ -9,17 +9,17 @@ from celery.signals import worker_init
 from celery.signals import worker_ready
 from celery.signals import worker_shutdown
 
-import onyx.background.celery.apps.app_base as app_base
-from onyx.configs.constants import POSTGRES_CELERY_WORKER_LIGHT_APP_NAME
-from onyx.db.engine import SqlEngine
-from onyx.utils.logger import setup_logger
+import danswer.background.celery.apps.app_base as app_base
+from danswer.configs.constants import POSTGRES_CELERY_WORKER_LIGHT_APP_NAME
+from danswer.db.engine import SqlEngine
+from danswer.utils.logger import setup_logger
 from shared_configs.configs import MULTI_TENANT
 
 
 logger = setup_logger()
 
 celery_app = Celery(__name__)
-celery_app.config_from_object("onyx.background.celery.configs.light")
+celery_app.config_from_object("danswer.background.celery.configs.light")
 
 
 @signals.task_prerun.connect
@@ -60,15 +60,13 @@ def on_worker_init(sender: Any, **kwargs: Any) -> None:
 
     SqlEngine.set_app_name(POSTGRES_CELERY_WORKER_LIGHT_APP_NAME)
     SqlEngine.init_engine(pool_size=sender.concurrency, max_overflow=8)
+    # Startup checks are not needed in multi-tenant case
+    if MULTI_TENANT:
+        return
 
     app_base.wait_for_redis(sender, **kwargs)
     app_base.wait_for_db(sender, **kwargs)
     app_base.wait_for_vespa(sender, **kwargs)
-
-    # Less startup checks in multi-tenant case
-    if MULTI_TENANT:
-        return
-
     app_base.on_secondary_worker_init(sender, **kwargs)
 
 
@@ -91,9 +89,9 @@ def on_setup_logging(
 
 celery_app.autodiscover_tasks(
     [
-        "onyx.background.celery.tasks.shared",
-        "onyx.background.celery.tasks.vespa",
-        "onyx.background.celery.tasks.connector_deletion",
-        "onyx.background.celery.tasks.doc_permission_syncing",
+        "danswer.background.celery.tasks.shared",
+        "danswer.background.celery.tasks.vespa",
+        "danswer.background.celery.tasks.connector_deletion",
+        "danswer.background.celery.tasks.doc_permission_syncing",
     ]
 )

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

@@ -11,38 +11,38 @@ from celery.signals import celeryd_init
 from celery.signals import worker_init
 from celery.signals import worker_ready
 from celery.signals import worker_shutdown
-from redis.lock import Lock as RedisLock
 
-import onyx.background.celery.apps.app_base as app_base
-from onyx.background.celery.apps.app_base import task_logger
-from onyx.background.celery.celery_utils import celery_is_worker_primary
-from onyx.background.celery.tasks.indexing.tasks import (
+import danswer.background.celery.apps.app_base as app_base
+from danswer.background.celery.apps.app_base import task_logger
+from danswer.background.celery.celery_utils import celery_is_worker_primary
+from danswer.background.celery.tasks.indexing.tasks import (
     get_unfenced_index_attempt_ids,
 )
-from onyx.configs.constants import CELERY_PRIMARY_WORKER_LOCK_TIMEOUT
-from onyx.configs.constants import OnyxRedisLocks
-from onyx.configs.constants import POSTGRES_CELERY_WORKER_PRIMARY_APP_NAME
-from onyx.db.engine import get_session_with_default_tenant
-from onyx.db.engine import SqlEngine
-from onyx.db.index_attempt import get_index_attempt
-from onyx.db.index_attempt import mark_attempt_canceled
-from onyx.redis.redis_connector_credential_pair import RedisConnectorCredentialPair
-from onyx.redis.redis_connector_delete import RedisConnectorDelete
-from onyx.redis.redis_connector_doc_perm_sync import RedisConnectorPermissionSync
-from onyx.redis.redis_connector_ext_group_sync import RedisConnectorExternalGroupSync
-from onyx.redis.redis_connector_index import RedisConnectorIndex
-from onyx.redis.redis_connector_prune import RedisConnectorPrune
-from onyx.redis.redis_connector_stop import RedisConnectorStop
-from onyx.redis.redis_document_set import RedisDocumentSet
-from onyx.redis.redis_pool import get_redis_client
-from onyx.redis.redis_usergroup import RedisUserGroup
-from onyx.utils.logger import setup_logger
+from danswer.configs.constants import CELERY_PRIMARY_WORKER_LOCK_TIMEOUT
+from danswer.configs.constants import DanswerRedisLocks
+from danswer.configs.constants import POSTGRES_CELERY_WORKER_PRIMARY_APP_NAME
+from danswer.db.engine import get_session_with_default_tenant
+from danswer.db.engine import SqlEngine
+from danswer.db.index_attempt import get_index_attempt
+from danswer.db.index_attempt import mark_attempt_failed
+from danswer.redis.redis_connector_credential_pair import RedisConnectorCredentialPair
+from danswer.redis.redis_connector_delete import RedisConnectorDelete
+from danswer.redis.redis_connector_doc_perm_sync import RedisConnectorPermissionSync
+from danswer.redis.redis_connector_ext_group_sync import RedisConnectorExternalGroupSync
+from danswer.redis.redis_connector_index import RedisConnectorIndex
+from danswer.redis.redis_connector_prune import RedisConnectorPrune
+from danswer.redis.redis_connector_stop import RedisConnectorStop
+from danswer.redis.redis_document_set import RedisDocumentSet
+from danswer.redis.redis_pool import get_redis_client
+from danswer.redis.redis_usergroup import RedisUserGroup
+from danswer.utils.logger import setup_logger
 from shared_configs.configs import MULTI_TENANT
 
+
 logger = setup_logger()
 
 celery_app = Celery(__name__)
-celery_app.config_from_object("onyx.background.celery.configs.primary")
+celery_app.config_from_object("danswer.background.celery.configs.primary")
 
 
 @signals.task_prerun.connect
@@ -84,14 +84,14 @@ def on_worker_init(sender: Any, **kwargs: Any) -> None:
     SqlEngine.set_app_name(POSTGRES_CELERY_WORKER_PRIMARY_APP_NAME)
     SqlEngine.init_engine(pool_size=8, max_overflow=0)
 
+    # Startup checks are not needed in multi-tenant case
+    if MULTI_TENANT:
+        return
+
     app_base.wait_for_redis(sender, **kwargs)
     app_base.wait_for_db(sender, **kwargs)
     app_base.wait_for_vespa(sender, **kwargs)
 
-    # Less startup checks in multi-tenant case
-    if MULTI_TENANT:
-        return
-
     logger.info("Running as the primary celery worker.")
 
     # This is singleton work that should be done on startup exactly once
@@ -110,19 +110,15 @@ def on_worker_init(sender: Any, **kwargs: Any) -> None:
     # 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(OnyxRedisLocks.PRIMARY_WORKER)
+    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.
-
-    # set thread_local=False since we don't control what thread the periodic task might
-    # reacquire the lock with
-    lock: RedisLock = r.lock(
-        OnyxRedisLocks.PRIMARY_WORKER,
+    lock = r.lock(
+        DanswerRedisLocks.PRIMARY_WORKER,
         timeout=CELERY_PRIMARY_WORKER_LOCK_TIMEOUT,
-        thread_local=False,
     )
 
     logger.info("Primary worker lock: Acquire starting.")
@@ -138,8 +134,8 @@ def on_worker_init(sender: Any, **kwargs: Any) -> None:
 
     # As currently designed, when this worker starts as "primary", we reinitialize redis
     # to a clean state (for our purposes, anyway)
-    r.delete(OnyxRedisLocks.CHECK_VESPA_SYNC_BEAT_LOCK)
-    r.delete(OnyxRedisLocks.MONITOR_VESPA_SYNC_BEAT_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())
@@ -169,13 +165,13 @@ def on_worker_init(sender: Any, **kwargs: Any) -> None:
                 continue
 
             failure_reason = (
-                f"Canceling leftover index attempt found on startup: "
+                f"Orphaned index attempt found on startup: "
                 f"index_attempt={attempt.id} "
                 f"cc_pair={attempt.connector_credential_pair_id} "
                 f"search_settings={attempt.search_settings_id}"
             )
             logger.warning(failure_reason)
-            mark_attempt_canceled(attempt.id, db_session, failure_reason)
+            mark_attempt_failed(attempt.id, db_session, failure_reason)
 
 
 @worker_ready.connect
@@ -231,7 +227,7 @@ class HubPeriodicTask(bootsteps.StartStopStep):
             if not hasattr(worker, "primary_worker_lock"):
                 return
 
-            lock: RedisLock = worker.primary_worker_lock
+            lock = worker.primary_worker_lock
 
             r = get_redis_client(tenant_id=None)
 
@@ -244,7 +240,7 @@ class HubPeriodicTask(bootsteps.StartStopStep):
                     "Reasons could be worker restart or lock expiration."
                 )
                 lock = r.lock(
-                    OnyxRedisLocks.PRIMARY_WORKER,
+                    DanswerRedisLocks.PRIMARY_WORKER,
                     timeout=CELERY_PRIMARY_WORKER_LOCK_TIMEOUT,
                 )
 
@@ -273,13 +269,13 @@ celery_app.steps["worker"].add(HubPeriodicTask)
 
 celery_app.autodiscover_tasks(
     [
-        "onyx.background.celery.tasks.connector_deletion",
-        "onyx.background.celery.tasks.indexing",
-        "onyx.background.celery.tasks.periodic",
-        "onyx.background.celery.tasks.doc_permission_syncing",
-        "onyx.background.celery.tasks.external_group_syncing",
-        "onyx.background.celery.tasks.pruning",
-        "onyx.background.celery.tasks.shared",
-        "onyx.background.celery.tasks.vespa",
+        "danswer.background.celery.tasks.connector_deletion",
+        "danswer.background.celery.tasks.indexing",
+        "danswer.background.celery.tasks.periodic",
+        "danswer.background.celery.tasks.doc_permission_syncing",
+        "danswer.background.celery.tasks.external_group_syncing",
+        "danswer.background.celery.tasks.pruning",
+        "danswer.background.celery.tasks.shared",
+        "danswer.background.celery.tasks.vespa",
     ]
 )

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

@@ -2,8 +2,8 @@ import logging
 
 from celery import current_task
 
-from onyx.utils.logger import ColoredFormatter
-from onyx.utils.logger import PlainFormatter
+from danswer.utils.logger import ColoredFormatter
+from danswer.utils.logger import PlainFormatter
 
 
 class CeleryTaskPlainFormatter(PlainFormatter):

backend/danswer/background/celery/celery_redis.py

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

backend/danswer/background/celery/celery_utils.py

@@ -4,22 +4,22 @@ from typing import Any
 
 from sqlalchemy.orm import Session
 
-from onyx.configs.app_configs import MAX_PRUNING_DOCUMENT_RETRIEVAL_PER_MINUTE
-from onyx.connectors.cross_connector_utils.rate_limit_wrapper import (
+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 onyx.connectors.interfaces import BaseConnector
-from onyx.connectors.interfaces import LoadConnector
-from onyx.connectors.interfaces import PollConnector
-from onyx.connectors.interfaces import SlimConnector
-from onyx.connectors.models import Document
-from onyx.db.connector_credential_pair import get_connector_credential_pair
-from onyx.db.enums import TaskStatus
-from onyx.db.models import TaskQueueState
-from onyx.indexing.indexing_heartbeat import IndexingHeartbeatInterface
-from onyx.redis.redis_connector import RedisConnector
-from onyx.server.documents.models import DeletionAttemptSnapshot
-from onyx.utils.logger import setup_logger
+from danswer.connectors.interfaces import BaseConnector
+from danswer.connectors.interfaces import LoadConnector
+from danswer.connectors.interfaces import PollConnector
+from danswer.connectors.interfaces import SlimConnector
+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.indexing.indexing_heartbeat import IndexingHeartbeatInterface
+from danswer.redis.redis_connector import RedisConnector
+from danswer.server.documents.models import DeletionAttemptSnapshot
+from danswer.utils.logger import setup_logger
 
 
 logger = setup_logger()

backend/danswer/background/celery/configs/base.py

@@ -1,19 +1,19 @@
 # docs: https://docs.celeryq.dev/en/stable/userguide/configuration.html
 import urllib.parse
 
-from onyx.configs.app_configs import CELERY_BROKER_POOL_LIMIT
-from onyx.configs.app_configs import CELERY_RESULT_EXPIRES
-from onyx.configs.app_configs import REDIS_DB_NUMBER_CELERY
-from onyx.configs.app_configs import REDIS_DB_NUMBER_CELERY_RESULT_BACKEND
-from onyx.configs.app_configs import REDIS_HEALTH_CHECK_INTERVAL
-from onyx.configs.app_configs import REDIS_HOST
-from onyx.configs.app_configs import REDIS_PASSWORD
-from onyx.configs.app_configs import REDIS_PORT
-from onyx.configs.app_configs import REDIS_SSL
-from onyx.configs.app_configs import REDIS_SSL_CA_CERTS
-from onyx.configs.app_configs import REDIS_SSL_CERT_REQS
-from onyx.configs.constants import OnyxCeleryPriority
-from onyx.configs.constants import REDIS_SOCKET_KEEPALIVE_OPTIONS
+from danswer.configs.app_configs import CELERY_BROKER_POOL_LIMIT
+from danswer.configs.app_configs import CELERY_RESULT_EXPIRES
+from danswer.configs.app_configs import REDIS_DB_NUMBER_CELERY
+from danswer.configs.app_configs import REDIS_DB_NUMBER_CELERY_RESULT_BACKEND
+from danswer.configs.app_configs import REDIS_HEALTH_CHECK_INTERVAL
+from danswer.configs.app_configs import REDIS_HOST
+from danswer.configs.app_configs import REDIS_PASSWORD
+from danswer.configs.app_configs import REDIS_PORT
+from danswer.configs.app_configs import REDIS_SSL
+from danswer.configs.app_configs import REDIS_SSL_CA_CERTS
+from danswer.configs.app_configs import REDIS_SSL_CERT_REQS
+from danswer.configs.constants import DanswerCeleryPriority
+from danswer.configs.constants import REDIS_SOCKET_KEEPALIVE_OPTIONS
 
 CELERY_SEPARATOR = ":"
 
@@ -41,7 +41,7 @@ broker_pool_limit = CELERY_BROKER_POOL_LIMIT
 # redis broker settings
 # https://docs.celeryq.dev/projects/kombu/en/stable/reference/kombu.transport.redis.html
 broker_transport_options = {
-    "priority_steps": list(range(len(OnyxCeleryPriority))),
+    "priority_steps": list(range(len(DanswerCeleryPriority))),
     "sep": CELERY_SEPARATOR,
     "queue_order_strategy": "priority",
     "retry_on_timeout": True,
@@ -60,7 +60,7 @@ redis_retry_on_timeout = True
 redis_backend_health_check_interval = REDIS_HEALTH_CHECK_INTERVAL
 
 
-task_default_priority = OnyxCeleryPriority.MEDIUM
+task_default_priority = DanswerCeleryPriority.MEDIUM
 task_acks_late = True
 
 # region Task result backend settings

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

@@ -1,5 +1,5 @@
 # docs: https://docs.celeryq.dev/en/stable/userguide/configuration.html
-import onyx.background.celery.configs.base as shared_config
+import danswer.background.celery.configs.base as shared_config
 
 broker_url = shared_config.broker_url
 broker_connection_retry_on_startup = shared_config.broker_connection_retry_on_startup

backend/danswer/background/celery/configs/heavy.py

@@ -1,4 +1,4 @@
-import onyx.background.celery.configs.base as shared_config
+import danswer.background.celery.configs.base as shared_config
 
 broker_url = shared_config.broker_url
 broker_connection_retry_on_startup = shared_config.broker_connection_retry_on_startup

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

@@ -1,5 +1,5 @@
-import onyx.background.celery.configs.base as shared_config
-from onyx.configs.app_configs import CELERY_WORKER_INDEXING_CONCURRENCY
+import danswer.background.celery.configs.base as shared_config
+from danswer.configs.app_configs import CELERY_WORKER_INDEXING_CONCURRENCY
 
 broker_url = shared_config.broker_url
 broker_connection_retry_on_startup = shared_config.broker_connection_retry_on_startup

backend/danswer/background/celery/configs/light.py

@@ -1,6 +1,6 @@
-import onyx.background.celery.configs.base as shared_config
-from onyx.configs.app_configs import CELERY_WORKER_LIGHT_CONCURRENCY
-from onyx.configs.app_configs import CELERY_WORKER_LIGHT_PREFETCH_MULTIPLIER
+import danswer.background.celery.configs.base as shared_config
+from danswer.configs.app_configs import CELERY_WORKER_LIGHT_CONCURRENCY
+from danswer.configs.app_configs import CELERY_WORKER_LIGHT_PREFETCH_MULTIPLIER
 
 broker_url = shared_config.broker_url
 broker_connection_retry_on_startup = shared_config.broker_connection_retry_on_startup

backend/danswer/background/celery/configs/primary.py

@@ -1,4 +1,4 @@
-import onyx.background.celery.configs.base as shared_config
+import danswer.background.celery.configs.base as shared_config
 
 broker_url = shared_config.broker_url
 broker_connection_retry_on_startup = shared_config.broker_connection_retry_on_startup

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

@@ -0,0 +1,60 @@
+from datetime import timedelta
+from typing import Any
+
+from danswer.configs.constants import DanswerCeleryPriority
+
+
+tasks_to_schedule = [
+    {
+        "name": "check-for-vespa-sync",
+        "task": "check_for_vespa_sync_task",
+        "schedule": timedelta(seconds=20),
+        "options": {"priority": DanswerCeleryPriority.HIGH},
+    },
+    {
+        "name": "check-for-connector-deletion",
+        "task": "check_for_connector_deletion_task",
+        "schedule": timedelta(seconds=20),
+        "options": {"priority": DanswerCeleryPriority.HIGH},
+    },
+    {
+        "name": "check-for-indexing",
+        "task": "check_for_indexing",
+        "schedule": timedelta(seconds=15),
+        "options": {"priority": DanswerCeleryPriority.HIGH},
+    },
+    {
+        "name": "check-for-prune",
+        "task": "check_for_pruning",
+        "schedule": timedelta(seconds=15),
+        "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},
+    },
+    {
+        "name": "check-for-doc-permissions-sync",
+        "task": "check_for_doc_permissions_sync",
+        "schedule": timedelta(seconds=30),
+        "options": {"priority": DanswerCeleryPriority.HIGH},
+    },
+    {
+        "name": "check-for-external-group-sync",
+        "task": "check_for_external_group_sync",
+        "schedule": timedelta(seconds=20),
+        "options": {"priority": DanswerCeleryPriority.HIGH},
+    },
+]
+
+
+def get_tasks_to_schedule() -> list[dict[str, Any]]:
+    return tasks_to_schedule

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

@@ -5,22 +5,22 @@ from celery import Celery
 from celery import shared_task
 from celery import Task
 from celery.exceptions import SoftTimeLimitExceeded
+from redis import Redis
 from redis.lock import Lock as RedisLock
 from sqlalchemy.orm import Session
 
-from onyx.background.celery.apps.app_base import task_logger
-from onyx.configs.app_configs import JOB_TIMEOUT
-from onyx.configs.constants import CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT
-from onyx.configs.constants import OnyxCeleryTask
-from onyx.configs.constants import OnyxRedisLocks
-from onyx.db.connector_credential_pair import get_connector_credential_pair_from_id
-from onyx.db.connector_credential_pair import get_connector_credential_pairs
-from onyx.db.engine import get_session_with_tenant
-from onyx.db.enums import ConnectorCredentialPairStatus
-from onyx.db.search_settings import get_all_search_settings
-from onyx.redis.redis_connector import RedisConnector
-from onyx.redis.redis_connector_delete import RedisConnectorDeletePayload
-from onyx.redis.redis_pool import get_redis_client
+from danswer.background.celery.apps.app_base import task_logger
+from danswer.configs.app_configs import JOB_TIMEOUT
+from danswer.configs.constants import CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT
+from danswer.configs.constants import DanswerRedisLocks
+from danswer.db.connector_credential_pair import get_connector_credential_pair_from_id
+from danswer.db.connector_credential_pair import get_connector_credential_pairs
+from danswer.db.engine import get_session_with_tenant
+from danswer.db.enums import ConnectorCredentialPairStatus
+from danswer.db.search_settings import get_all_search_settings
+from danswer.redis.redis_connector import RedisConnector
+from danswer.redis.redis_connector_delete import RedisConnectorDeletePayload
+from danswer.redis.redis_pool import get_redis_client
 
 
 class TaskDependencyError(RuntimeError):
@@ -29,7 +29,7 @@ class TaskDependencyError(RuntimeError):
 
 
 @shared_task(
-    name=OnyxCeleryTask.CHECK_FOR_CONNECTOR_DELETION,
+    name="check_for_connector_deletion_task",
     soft_time_limit=JOB_TIMEOUT,
     trail=False,
     bind=True,
@@ -37,8 +37,8 @@ class TaskDependencyError(RuntimeError):
 def check_for_connector_deletion_task(self: Task, *, tenant_id: str | None) -> None:
     r = get_redis_client(tenant_id=tenant_id)
 
-    lock_beat: RedisLock = r.lock(
-        OnyxRedisLocks.CHECK_CONNECTOR_DELETION_BEAT_LOCK,
+    lock_beat = r.lock(
+        DanswerRedisLocks.CHECK_CONNECTOR_DELETION_BEAT_LOCK,
         timeout=CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT,
     )
 
@@ -60,7 +60,7 @@ def check_for_connector_deletion_task(self: Task, *, tenant_id: str | None) -> N
                 redis_connector = RedisConnector(tenant_id, cc_pair_id)
                 try:
                     try_generate_document_cc_pair_cleanup_tasks(
-                        self.app, cc_pair_id, db_session, lock_beat, tenant_id
+                        self.app, cc_pair_id, db_session, r, lock_beat, tenant_id
                     )
                 except TaskDependencyError as e:
                     # this means we wanted to start deleting but dependent tasks were running
@@ -76,7 +76,7 @@ def check_for_connector_deletion_task(self: Task, *, tenant_id: str | None) -> N
             "Soft time limit exceeded, task is being terminated gracefully."
         )
     except Exception:
-        task_logger.exception("Unexpected exception during connector deletion check")
+        task_logger.exception(f"Unexpected exception: tenant={tenant_id}")
     finally:
         if lock_beat.owned():
             lock_beat.release()
@@ -86,6 +86,7 @@ def try_generate_document_cc_pair_cleanup_tasks(
     app: Celery,
     cc_pair_id: int,
     db_session: Session,
+    r: Redis,
     lock_beat: RedisLock,
     tenant_id: str | None,
 ) -> int | None:
@@ -131,14 +132,14 @@ def try_generate_document_cc_pair_cleanup_tasks(
             redis_connector_index = redis_connector.new_index(search_settings.id)
             if redis_connector_index.fenced:
                 raise TaskDependencyError(
-                    "Connector deletion - Delayed (indexing in progress): "
+                    f"Connector deletion - Delayed (indexing in progress): "
                     f"cc_pair={cc_pair_id} "
                     f"search_settings={search_settings.id}"
                 )
 
         if redis_connector.prune.fenced:
             raise TaskDependencyError(
-                "Connector deletion - Delayed (pruning in progress): "
+                f"Connector deletion - Delayed (pruning in progress): "
                 f"cc_pair={cc_pair_id}"
             )
 
@@ -175,7 +176,7 @@ def try_generate_document_cc_pair_cleanup_tasks(
         #     return 0
 
         task_logger.info(
-            "RedisConnectorDeletion.generate_tasks finished. "
+            f"RedisConnectorDeletion.generate_tasks finished. "
             f"cc_pair={cc_pair_id} tasks_generated={tasks_generated}"
         )
 

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

@@ -8,37 +8,34 @@ from celery import shared_task
 from celery import Task
 from celery.exceptions import SoftTimeLimitExceeded
 from redis import Redis
-from redis.lock import Lock as RedisLock
 
-from ee.onyx.db.connector_credential_pair import get_all_auto_sync_cc_pairs
-from ee.onyx.db.document import upsert_document_external_perms
-from ee.onyx.external_permissions.sync_params import DOC_PERMISSION_SYNC_PERIODS
-from ee.onyx.external_permissions.sync_params import DOC_PERMISSIONS_FUNC_MAP
-from onyx.access.models import DocExternalAccess
-from onyx.background.celery.apps.app_base import task_logger
-from onyx.configs.app_configs import JOB_TIMEOUT
-from onyx.configs.constants import CELERY_PERMISSIONS_SYNC_LOCK_TIMEOUT
-from onyx.configs.constants import CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT
-from onyx.configs.constants import DANSWER_REDIS_FUNCTION_LOCK_PREFIX
-from onyx.configs.constants import DocumentSource
-from onyx.configs.constants import OnyxCeleryPriority
-from onyx.configs.constants import OnyxCeleryQueues
-from onyx.configs.constants import OnyxCeleryTask
-from onyx.configs.constants import OnyxRedisLocks
-from onyx.db.connector_credential_pair import get_connector_credential_pair_from_id
-from onyx.db.document import upsert_document_by_connector_credential_pair
-from onyx.db.engine import get_session_with_tenant
-from onyx.db.enums import AccessType
-from onyx.db.enums import ConnectorCredentialPairStatus
-from onyx.db.models import ConnectorCredentialPair
-from onyx.db.users import batch_add_ext_perm_user_if_not_exists
-from onyx.redis.redis_connector import RedisConnector
-from onyx.redis.redis_connector_doc_perm_sync import (
-    RedisConnectorPermissionSyncPayload,
+from danswer.access.models import DocExternalAccess
+from danswer.background.celery.apps.app_base import task_logger
+from danswer.configs.app_configs import JOB_TIMEOUT
+from danswer.configs.constants import CELERY_PERMISSIONS_SYNC_LOCK_TIMEOUT
+from danswer.configs.constants import CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT
+from danswer.configs.constants import DANSWER_REDIS_FUNCTION_LOCK_PREFIX
+from danswer.configs.constants import DanswerCeleryPriority
+from danswer.configs.constants import DanswerCeleryQueues
+from danswer.configs.constants import DanswerRedisLocks
+from danswer.configs.constants import DocumentSource
+from danswer.db.connector_credential_pair import get_connector_credential_pair_from_id
+from danswer.db.engine import get_session_with_tenant
+from danswer.db.enums import AccessType
+from danswer.db.enums import ConnectorCredentialPairStatus
+from danswer.db.models import ConnectorCredentialPair
+from danswer.db.users import batch_add_ext_perm_user_if_not_exists
+from danswer.redis.redis_connector import RedisConnector
+from danswer.redis.redis_connector_doc_perm_sync import (
+    RedisConnectorPermissionSyncData,
 )
-from onyx.redis.redis_pool import get_redis_client
-from onyx.utils.logger import doc_permission_sync_ctx
-from onyx.utils.logger import setup_logger
+from danswer.redis.redis_pool import get_redis_client
+from danswer.utils.logger import doc_permission_sync_ctx
+from danswer.utils.logger import setup_logger
+from ee.danswer.db.connector_credential_pair import get_all_auto_sync_cc_pairs
+from ee.danswer.db.document import upsert_document_external_perms
+from ee.danswer.external_permissions.sync_params import DOC_PERMISSION_SYNC_PERIODS
+from ee.danswer.external_permissions.sync_params import DOC_PERMISSIONS_FUNC_MAP
 
 logger = setup_logger()
 
@@ -84,7 +81,7 @@ def _is_external_doc_permissions_sync_due(cc_pair: ConnectorCredentialPair) -> b
 
 
 @shared_task(
-    name=OnyxCeleryTask.CHECK_FOR_DOC_PERMISSIONS_SYNC,
+    name="check_for_doc_permissions_sync",
     soft_time_limit=JOB_TIMEOUT,
     bind=True,
 )
@@ -92,7 +89,7 @@ def check_for_doc_permissions_sync(self: Task, *, tenant_id: str | None) -> None
     r = get_redis_client(tenant_id=tenant_id)
 
     lock_beat = r.lock(
-        OnyxRedisLocks.CHECK_CONNECTOR_DOC_PERMISSIONS_SYNC_BEAT_LOCK,
+        DanswerRedisLocks.CHECK_CONNECTOR_DOC_PERMISSIONS_SYNC_BEAT_LOCK,
         timeout=CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT,
     )
 
@@ -141,7 +138,7 @@ def try_creating_permissions_sync_task(
 
     LOCK_TIMEOUT = 30
 
-    lock: RedisLock = r.lock(
+    lock = r.lock(
         DANSWER_REDIS_FUNCTION_LOCK_PREFIX + "try_generate_permissions_sync_tasks",
         timeout=LOCK_TIMEOUT,
     )
@@ -165,20 +162,20 @@ def try_creating_permissions_sync_task(
 
         custom_task_id = f"{redis_connector.permissions.generator_task_key}_{uuid4()}"
 
-        result = app.send_task(
-            OnyxCeleryTask.CONNECTOR_PERMISSION_SYNC_GENERATOR_TASK,
+        app.send_task(
+            "connector_permission_sync_generator_task",
             kwargs=dict(
                 cc_pair_id=cc_pair_id,
                 tenant_id=tenant_id,
             ),
-            queue=OnyxCeleryQueues.CONNECTOR_DOC_PERMISSIONS_SYNC,
+            queue=DanswerCeleryQueues.CONNECTOR_DOC_PERMISSIONS_SYNC,
             task_id=custom_task_id,
-            priority=OnyxCeleryPriority.HIGH,
+            priority=DanswerCeleryPriority.HIGH,
         )
 
         # set a basic fence to start
-        payload = RedisConnectorPermissionSyncPayload(
-            started=None, celery_task_id=result.id
+        payload = RedisConnectorPermissionSyncData(
+            started=None,
         )
 
         redis_connector.permissions.set_fence(payload)
@@ -193,7 +190,7 @@ def try_creating_permissions_sync_task(
 
 
 @shared_task(
-    name=OnyxCeleryTask.CONNECTOR_PERMISSION_SYNC_GENERATOR_TASK,
+    name="connector_permission_sync_generator_task",
     acks_late=False,
     soft_time_limit=JOB_TIMEOUT,
     track_started=True,
@@ -219,8 +216,8 @@ def connector_permission_sync_generator_task(
 
     r = get_redis_client(tenant_id=tenant_id)
 
-    lock: RedisLock = r.lock(
-        OnyxRedisLocks.CONNECTOR_DOC_PERMISSIONS_SYNC_LOCK_PREFIX
+    lock = r.lock(
+        DanswerRedisLocks.CONNECTOR_DOC_PERMISSIONS_SYNC_LOCK_PREFIX
         + f"_{redis_connector.id}",
         timeout=CELERY_PERMISSIONS_SYNC_LOCK_TIMEOUT,
     )
@@ -244,17 +241,13 @@ def connector_permission_sync_generator_task(
 
             doc_sync_func = DOC_PERMISSIONS_FUNC_MAP.get(source_type)
             if doc_sync_func is None:
-                raise ValueError(
-                    f"No doc sync func found for {source_type} with cc_pair={cc_pair_id}"
-                )
+                raise ValueError(f"No doc sync func found for {source_type}")
 
-            logger.info(f"Syncing docs for {source_type} with cc_pair={cc_pair_id}")
+            logger.info(f"Syncing docs for {source_type}")
 
-            payload = redis_connector.permissions.payload
-            if not payload:
-                raise ValueError(f"No fence payload found: cc_pair={cc_pair_id}")
-
-            payload.started = datetime.now(timezone.utc)
+            payload = RedisConnectorPermissionSyncData(
+                started=datetime.now(timezone.utc),
+            )
             redis_connector.permissions.set_fence(payload)
 
             document_external_accesses: list[DocExternalAccess] = doc_sync_func(cc_pair)
@@ -263,12 +256,7 @@ def connector_permission_sync_generator_task(
                 f"RedisConnector.permissions.generate_tasks starting. cc_pair={cc_pair_id}"
             )
             tasks_generated = redis_connector.permissions.generate_tasks(
-                celery_app=self.app,
-                lock=lock,
-                new_permissions=document_external_accesses,
-                source_string=source_type,
-                connector_id=cc_pair.connector.id,
-                credential_id=cc_pair.credential.id,
+                self.app, lock, document_external_accesses, source_type
             )
             if tasks_generated is None:
                 return None
@@ -293,7 +281,7 @@ def connector_permission_sync_generator_task(
 
 
 @shared_task(
-    name=OnyxCeleryTask.UPDATE_EXTERNAL_DOCUMENT_PERMISSIONS_TASK,
+    name="update_external_document_permissions_task",
     soft_time_limit=LIGHT_SOFT_TIME_LIMIT,
     time_limit=LIGHT_TIME_LIMIT,
     max_retries=DOCUMENT_PERMISSIONS_UPDATE_MAX_RETRIES,
@@ -304,8 +292,6 @@ def update_external_document_permissions_task(
     tenant_id: str | None,
     serialized_doc_external_access: dict,
     source_string: str,
-    connector_id: int,
-    credential_id: int,
 ) -> bool:
     document_external_access = DocExternalAccess.from_dict(
         serialized_doc_external_access
@@ -314,28 +300,18 @@ def update_external_document_permissions_task(
     external_access = document_external_access.external_access
     try:
         with get_session_with_tenant(tenant_id) as db_session:
-            # Add the users to the DB if they don't exist
+            # Then we build the update requests to update vespa
             batch_add_ext_perm_user_if_not_exists(
                 db_session=db_session,
                 emails=list(external_access.external_user_emails),
             )
-            # Then we upsert the document's external permissions in postgres
-            created_new_doc = upsert_document_external_perms(
+            upsert_document_external_perms(
                 db_session=db_session,
                 doc_id=doc_id,
                 external_access=external_access,
                 source_type=DocumentSource(source_string),
             )
 
-            if created_new_doc:
-                # If a new document was created, we associate it with the cc_pair
-                upsert_document_by_connector_credential_pair(
-                    db_session=db_session,
-                    connector_id=connector_id,
-                    credential_id=credential_id,
-                    document_ids=[doc_id],
-                )
-
             logger.debug(
                 f"Successfully synced postgres document permissions for {doc_id}"
             )

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

@@ -8,38 +8,29 @@ from celery import shared_task
 from celery import Task
 from celery.exceptions import SoftTimeLimitExceeded
 from redis import Redis
-from redis.lock import Lock as RedisLock
 
-from ee.onyx.db.connector_credential_pair import get_all_auto_sync_cc_pairs
-from ee.onyx.db.connector_credential_pair import get_cc_pairs_by_source
-from ee.onyx.db.external_perm import ExternalUserGroup
-from ee.onyx.db.external_perm import replace_user__ext_group_for_cc_pair
-from ee.onyx.external_permissions.sync_params import EXTERNAL_GROUP_SYNC_PERIODS
-from ee.onyx.external_permissions.sync_params import GROUP_PERMISSIONS_FUNC_MAP
-from ee.onyx.external_permissions.sync_params import (
-    GROUP_PERMISSIONS_IS_CC_PAIR_AGNOSTIC,
-)
-from onyx.background.celery.apps.app_base import task_logger
-from onyx.configs.app_configs import JOB_TIMEOUT
-from onyx.configs.constants import CELERY_EXTERNAL_GROUP_SYNC_LOCK_TIMEOUT
-from onyx.configs.constants import CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT
-from onyx.configs.constants import DANSWER_REDIS_FUNCTION_LOCK_PREFIX
-from onyx.configs.constants import OnyxCeleryPriority
-from onyx.configs.constants import OnyxCeleryQueues
-from onyx.configs.constants import OnyxCeleryTask
-from onyx.configs.constants import OnyxRedisLocks
-from onyx.db.connector import mark_cc_pair_as_external_group_synced
-from onyx.db.connector_credential_pair import get_connector_credential_pair_from_id
-from onyx.db.engine import get_session_with_tenant
-from onyx.db.enums import AccessType
-from onyx.db.enums import ConnectorCredentialPairStatus
-from onyx.db.models import ConnectorCredentialPair
-from onyx.redis.redis_connector import RedisConnector
-from onyx.redis.redis_connector_ext_group_sync import (
-    RedisConnectorExternalGroupSyncPayload,
-)
-from onyx.redis.redis_pool import get_redis_client
-from onyx.utils.logger import setup_logger
+from danswer.background.celery.apps.app_base import task_logger
+from danswer.configs.app_configs import JOB_TIMEOUT
+from danswer.configs.constants import CELERY_EXTERNAL_GROUP_SYNC_LOCK_TIMEOUT
+from danswer.configs.constants import CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT
+from danswer.configs.constants import DANSWER_REDIS_FUNCTION_LOCK_PREFIX
+from danswer.configs.constants import DanswerCeleryPriority
+from danswer.configs.constants import DanswerCeleryQueues
+from danswer.configs.constants import DanswerRedisLocks
+from danswer.db.connector import mark_cc_pair_as_external_group_synced
+from danswer.db.connector_credential_pair import get_connector_credential_pair_from_id
+from danswer.db.engine import get_session_with_tenant
+from danswer.db.enums import AccessType
+from danswer.db.enums import ConnectorCredentialPairStatus
+from danswer.db.models import ConnectorCredentialPair
+from danswer.redis.redis_connector import RedisConnector
+from danswer.redis.redis_pool import get_redis_client
+from danswer.utils.logger import setup_logger
+from ee.danswer.db.connector_credential_pair import get_all_auto_sync_cc_pairs
+from ee.danswer.db.external_perm import ExternalUserGroup
+from ee.danswer.db.external_perm import replace_user__ext_group_for_cc_pair
+from ee.danswer.external_permissions.sync_params import EXTERNAL_GROUP_SYNC_PERIODS
+from ee.danswer.external_permissions.sync_params import GROUP_PERMISSIONS_FUNC_MAP
 
 logger = setup_logger()
 
@@ -58,7 +49,7 @@ def _is_external_group_sync_due(cc_pair: ConnectorCredentialPair) -> bool:
     if cc_pair.access_type != AccessType.SYNC:
         return False
 
-    # skip external group sync if not active
+    # skip pruning if not active
     if cc_pair.status != ConnectorCredentialPairStatus.ACTIVE:
         return False
 
@@ -90,7 +81,7 @@ def _is_external_group_sync_due(cc_pair: ConnectorCredentialPair) -> bool:
 
 
 @shared_task(
-    name=OnyxCeleryTask.CHECK_FOR_EXTERNAL_GROUP_SYNC,
+    name="check_for_external_group_sync",
     soft_time_limit=JOB_TIMEOUT,
     bind=True,
 )
@@ -98,7 +89,7 @@ def check_for_external_group_sync(self: Task, *, tenant_id: str | None) -> None:
     r = get_redis_client(tenant_id=tenant_id)
 
     lock_beat = r.lock(
-        OnyxRedisLocks.CHECK_CONNECTOR_EXTERNAL_GROUP_SYNC_BEAT_LOCK,
+        DanswerRedisLocks.CHECK_CONNECTOR_EXTERNAL_GROUP_SYNC_BEAT_LOCK,
         timeout=CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT,
     )
 
@@ -111,28 +102,12 @@ def check_for_external_group_sync(self: Task, *, tenant_id: str | None) -> None:
         with get_session_with_tenant(tenant_id) as db_session:
             cc_pairs = get_all_auto_sync_cc_pairs(db_session)
 
-            # We only want to sync one cc_pair per source type in
-            # GROUP_PERMISSIONS_IS_CC_PAIR_AGNOSTIC
-            for source in GROUP_PERMISSIONS_IS_CC_PAIR_AGNOSTIC:
-                # These are ordered by cc_pair id so the first one is the one we want
-                cc_pairs_to_dedupe = get_cc_pairs_by_source(
-                    db_session, source, only_sync=True
-                )
-                # We only want to sync one cc_pair per source type
-                # in GROUP_PERMISSIONS_IS_CC_PAIR_AGNOSTIC so we dedupe here
-                for cc_pair_to_remove in cc_pairs_to_dedupe[1:]:
-                    cc_pairs = [
-                        cc_pair
-                        for cc_pair in cc_pairs
-                        if cc_pair.id != cc_pair_to_remove.id
-                    ]
-
             for cc_pair in cc_pairs:
                 if _is_external_group_sync_due(cc_pair):
                     cc_pair_ids_to_sync.append(cc_pair.id)
 
         for cc_pair_id in cc_pair_ids_to_sync:
-            tasks_created = try_creating_external_group_sync_task(
+            tasks_created = try_creating_permissions_sync_task(
                 self.app, cc_pair_id, r, tenant_id
             )
             if not tasks_created:
@@ -150,7 +125,7 @@ def check_for_external_group_sync(self: Task, *, tenant_id: str | None) -> None:
             lock_beat.release()
 
 
-def try_creating_external_group_sync_task(
+def try_creating_permissions_sync_task(
     app: Celery,
     cc_pair_id: int,
     r: Redis,
@@ -181,23 +156,18 @@ def try_creating_external_group_sync_task(
 
         custom_task_id = f"{redis_connector.external_group_sync.taskset_key}_{uuid4()}"
 
-        result = app.send_task(
-            OnyxCeleryTask.CONNECTOR_EXTERNAL_GROUP_SYNC_GENERATOR_TASK,
+        _ = app.send_task(
+            "connector_external_group_sync_generator_task",
             kwargs=dict(
                 cc_pair_id=cc_pair_id,
                 tenant_id=tenant_id,
             ),
-            queue=OnyxCeleryQueues.CONNECTOR_EXTERNAL_GROUP_SYNC,
+            queue=DanswerCeleryQueues.CONNECTOR_EXTERNAL_GROUP_SYNC,
             task_id=custom_task_id,
-            priority=OnyxCeleryPriority.HIGH,
+            priority=DanswerCeleryPriority.HIGH,
         )
-
-        payload = RedisConnectorExternalGroupSyncPayload(
-            started=datetime.now(timezone.utc),
-            celery_task_id=result.id,
-        )
-
-        redis_connector.external_group_sync.set_fence(payload)
+        # set a basic fence to start
+        redis_connector.external_group_sync.set_fence(True)
 
     except Exception:
         task_logger.exception(
@@ -212,7 +182,7 @@ def try_creating_external_group_sync_task(
 
 
 @shared_task(
-    name=OnyxCeleryTask.CONNECTOR_EXTERNAL_GROUP_SYNC_GENERATOR_TASK,
+    name="connector_external_group_sync_generator_task",
     acks_late=False,
     soft_time_limit=JOB_TIMEOUT,
     track_started=True,
@@ -225,7 +195,7 @@ def connector_external_group_sync_generator_task(
     tenant_id: str | None,
 ) -> None:
     """
-    Permission sync task that handles external group syncing for a given connector credential pair
+    Permission sync task that handles document permission syncing for a given connector credential pair
     This task assumes that the task has already been properly fenced
     """
 
@@ -233,8 +203,8 @@ def connector_external_group_sync_generator_task(
 
     r = get_redis_client(tenant_id=tenant_id)
 
-    lock: RedisLock = r.lock(
-        OnyxRedisLocks.CONNECTOR_EXTERNAL_GROUP_SYNC_LOCK_PREFIX
+    lock = r.lock(
+        DanswerRedisLocks.CONNECTOR_EXTERNAL_GROUP_SYNC_LOCK_PREFIX
         + f"_{redis_connector.id}",
         timeout=CELERY_EXTERNAL_GROUP_SYNC_LOCK_TIMEOUT,
     )
@@ -258,13 +228,9 @@ def connector_external_group_sync_generator_task(
 
             ext_group_sync_func = GROUP_PERMISSIONS_FUNC_MAP.get(source_type)
             if ext_group_sync_func is None:
-                raise ValueError(
-                    f"No external group sync func found for {source_type} for cc_pair: {cc_pair_id}"
-                )
+                raise ValueError(f"No external group sync func found for {source_type}")
 
-            logger.info(
-                f"Syncing external groups for {source_type} for cc_pair: {cc_pair_id}"
-            )
+            logger.info(f"Syncing docs for {source_type}")
 
             external_user_groups: list[ExternalUserGroup] = ext_group_sync_func(cc_pair)
 
@@ -283,6 +249,7 @@ def connector_external_group_sync_generator_task(
             )
 
             mark_cc_pair_as_external_group_synced(db_session, cc_pair.id)
+
     except Exception as e:
         task_logger.exception(
             f"Failed to run external group sync: cc_pair={cc_pair_id}"
@@ -293,6 +260,6 @@ def connector_external_group_sync_generator_task(
         raise e
     finally:
         # we always want to clear the fence after the task is done or failed so it doesn't get stuck
-        redis_connector.external_group_sync.set_fence(None)
+        redis_connector.external_group_sync.set_fence(False)
         if lock.owned():
             lock.release()

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

@@ -1,9 +1,7 @@
-import time
 from datetime import datetime
 from datetime import timezone
 from http import HTTPStatus
 from time import sleep
-from typing import Any
 
 import redis
 import sentry_sdk
@@ -16,50 +14,45 @@ from redis.exceptions import LockError
 from redis.lock import Lock as RedisLock
 from sqlalchemy.orm import Session
 
-from onyx.background.celery.apps.app_base import task_logger
-from onyx.background.celery.celery_redis import celery_find_task
-from onyx.background.indexing.job_client import SimpleJobClient
-from onyx.background.indexing.run_indexing import run_indexing_entrypoint
-from onyx.configs.app_configs import DISABLE_INDEX_UPDATE_ON_SWAP
-from onyx.configs.constants import CELERY_INDEXING_LOCK_TIMEOUT
-from onyx.configs.constants import CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT
-from onyx.configs.constants import DANSWER_REDIS_FUNCTION_LOCK_PREFIX
-from onyx.configs.constants import DocumentSource
-from onyx.configs.constants import OnyxCeleryPriority
-from onyx.configs.constants import OnyxCeleryQueues
-from onyx.configs.constants import OnyxCeleryTask
-from onyx.configs.constants import OnyxRedisLocks
-from onyx.db.connector import mark_ccpair_with_indexing_trigger
-from onyx.db.connector_credential_pair import fetch_connector_credential_pairs
-from onyx.db.connector_credential_pair import get_connector_credential_pair_from_id
-from onyx.db.engine import get_db_current_time
-from onyx.db.engine import get_session_with_tenant
-from onyx.db.enums import ConnectorCredentialPairStatus
-from onyx.db.enums import IndexingMode
-from onyx.db.enums import IndexingStatus
-from onyx.db.enums import IndexModelStatus
-from onyx.db.index_attempt import create_index_attempt
-from onyx.db.index_attempt import delete_index_attempt
-from onyx.db.index_attempt import get_all_index_attempts_by_status
-from onyx.db.index_attempt import get_index_attempt
-from onyx.db.index_attempt import get_last_attempt_for_cc_pair
-from onyx.db.index_attempt import mark_attempt_canceled
-from onyx.db.index_attempt import mark_attempt_failed
-from onyx.db.models import ConnectorCredentialPair
-from onyx.db.models import IndexAttempt
-from onyx.db.models import SearchSettings
-from onyx.db.search_settings import get_active_search_settings
-from onyx.db.search_settings import get_current_search_settings
-from onyx.db.swap_index import check_index_swap
-from onyx.indexing.indexing_heartbeat import IndexingHeartbeatInterface
-from onyx.natural_language_processing.search_nlp_models import EmbeddingModel
-from onyx.natural_language_processing.search_nlp_models import warm_up_bi_encoder
-from onyx.redis.redis_connector import RedisConnector
-from onyx.redis.redis_connector_index import RedisConnectorIndex
-from onyx.redis.redis_connector_index import RedisConnectorIndexPayload
-from onyx.redis.redis_pool import get_redis_client
-from onyx.utils.logger import setup_logger
-from onyx.utils.variable_functionality import global_version
+from danswer.background.celery.apps.app_base import task_logger
+from danswer.background.indexing.job_client import SimpleJobClient
+from danswer.background.indexing.run_indexing import run_indexing_entrypoint
+from danswer.configs.app_configs import DISABLE_INDEX_UPDATE_ON_SWAP
+from danswer.configs.constants import CELERY_INDEXING_LOCK_TIMEOUT
+from danswer.configs.constants import CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT
+from danswer.configs.constants import DANSWER_REDIS_FUNCTION_LOCK_PREFIX
+from danswer.configs.constants import DanswerCeleryPriority
+from danswer.configs.constants import DanswerCeleryQueues
+from danswer.configs.constants import DanswerRedisLocks
+from danswer.configs.constants import DocumentSource
+from danswer.db.connector_credential_pair import fetch_connector_credential_pairs
+from danswer.db.connector_credential_pair import get_connector_credential_pair_from_id
+from danswer.db.engine import get_db_current_time
+from danswer.db.engine import get_session_with_tenant
+from danswer.db.enums import ConnectorCredentialPairStatus
+from danswer.db.enums import IndexingStatus
+from danswer.db.enums import IndexModelStatus
+from danswer.db.index_attempt import create_index_attempt
+from danswer.db.index_attempt import delete_index_attempt
+from danswer.db.index_attempt import get_all_index_attempts_by_status
+from danswer.db.index_attempt import get_index_attempt
+from danswer.db.index_attempt import get_last_attempt_for_cc_pair
+from danswer.db.index_attempt import mark_attempt_failed
+from danswer.db.models import ConnectorCredentialPair
+from danswer.db.models import IndexAttempt
+from danswer.db.models import SearchSettings
+from danswer.db.search_settings import get_current_search_settings
+from danswer.db.search_settings import get_secondary_search_settings
+from danswer.db.swap_index import check_index_swap
+from danswer.indexing.indexing_heartbeat import IndexingHeartbeatInterface
+from danswer.natural_language_processing.search_nlp_models import EmbeddingModel
+from danswer.natural_language_processing.search_nlp_models import warm_up_bi_encoder
+from danswer.redis.redis_connector import RedisConnector
+from danswer.redis.redis_connector_index import RedisConnectorIndex
+from danswer.redis.redis_connector_index import RedisConnectorIndexPayload
+from danswer.redis.redis_pool import get_redis_client
+from danswer.utils.logger import setup_logger
+from danswer.utils.variable_functionality import global_version
 from shared_configs.configs import INDEXING_MODEL_SERVER_HOST
 from shared_configs.configs import INDEXING_MODEL_SERVER_PORT
 from shared_configs.configs import MULTI_TENANT
@@ -84,7 +77,7 @@ class IndexingCallback(IndexingHeartbeatInterface):
         self.started: datetime = datetime.now(timezone.utc)
         self.redis_lock.reacquire()
 
-        self.last_tag: str = "IndexingCallback.__init__"
+        self.last_tag: str = ""
         self.last_lock_reacquire: datetime = datetime.now(timezone.utc)
 
     def should_stop(self) -> bool:
@@ -160,25 +153,17 @@ def get_unfenced_index_attempt_ids(db_session: Session, r: redis.Redis) -> list[
 
 
 @shared_task(
-    name=OnyxCeleryTask.CHECK_FOR_INDEXING,
+    name="check_for_indexing",
     soft_time_limit=300,
     bind=True,
 )
 def check_for_indexing(self: Task, *, tenant_id: str | None) -> int | None:
-    """a lightweight task used to kick off indexing tasks.
-    Occcasionally does some validation of existing state to clear up error conditions"""
-    time_start = time.monotonic()
-
     tasks_created = 0
-    locked = False
-    redis_client = get_redis_client(tenant_id=tenant_id)
 
-    # we need to use celery's redis client to access its redis data
-    # (which lives on a different db number)
-    # redis_client_celery: Redis = self.app.broker_connection().channel().client  # type: ignore
+    r = get_redis_client(tenant_id=tenant_id)
 
-    lock_beat: RedisLock = redis_client.lock(
-        OnyxRedisLocks.CHECK_INDEXING_BEAT_LOCK,
+    lock_beat: RedisLock = r.lock(
+        DanswerRedisLocks.CHECK_INDEXING_BEAT_LOCK,
         timeout=CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT,
     )
 
@@ -187,8 +172,6 @@ def check_for_indexing(self: Task, *, tenant_id: str | None) -> int | None:
         if not lock_beat.acquire(blocking=False):
             return None
 
-        locked = True
-
         # check for search settings swap
         with get_session_with_tenant(tenant_id=tenant_id) as db_session:
             old_search_settings = check_index_swap(db_session=db_session)
@@ -222,10 +205,17 @@ def check_for_indexing(self: Task, *, tenant_id: str | None) -> int | None:
 
             redis_connector = RedisConnector(tenant_id, cc_pair_id)
             with get_session_with_tenant(tenant_id) as db_session:
-                search_settings_list: list[SearchSettings] = get_active_search_settings(
-                    db_session
-                )
-                for search_settings_instance in search_settings_list:
+                # Get the primary search settings
+                primary_search_settings = get_current_search_settings(db_session)
+                search_settings = [primary_search_settings]
+
+                # Check for secondary search settings
+                secondary_search_settings = get_secondary_search_settings(db_session)
+                if secondary_search_settings is not None:
+                    # If secondary settings exist, add them to the list
+                    search_settings.append(secondary_search_settings)
+
+                for search_settings_instance in search_settings:
                     redis_connector_index = redis_connector.new_index(
                         search_settings_instance.id
                     )
@@ -241,48 +231,24 @@ def check_for_indexing(self: Task, *, tenant_id: str | None) -> int | None:
                     last_attempt = get_last_attempt_for_cc_pair(
                         cc_pair.id, search_settings_instance.id, db_session
                     )
-
-                    search_settings_primary = False
-                    if search_settings_instance.id == search_settings_list[0].id:
-                        search_settings_primary = True
-
                     if not _should_index(
                         cc_pair=cc_pair,
                         last_index=last_attempt,
                         search_settings_instance=search_settings_instance,
-                        search_settings_primary=search_settings_primary,
-                        secondary_index_building=len(search_settings_list) > 1,
+                        secondary_index_building=len(search_settings) > 1,
                         db_session=db_session,
                     ):
                         continue
 
-                    reindex = False
-                    if search_settings_instance.id == search_settings_list[0].id:
-                        # the indexing trigger is only checked and cleared with the primary search settings
-                        if cc_pair.indexing_trigger is not None:
-                            if cc_pair.indexing_trigger == IndexingMode.REINDEX:
-                                reindex = True
-
-                            task_logger.info(
-                                f"Connector indexing manual trigger detected: "
-                                f"cc_pair={cc_pair.id} "
-                                f"search_settings={search_settings_instance.id} "
-                                f"indexing_mode={cc_pair.indexing_trigger}"
-                            )
-
-                            mark_ccpair_with_indexing_trigger(
-                                cc_pair.id, None, db_session
-                            )
-
                     # using a task queue and only allowing one task per cc_pair/search_setting
                     # prevents us from starving out certain attempts
                     attempt_id = try_creating_indexing_task(
                         self.app,
                         cc_pair,
                         search_settings_instance,
-                        reindex,
+                        False,
                         db_session,
-                        redis_client,
+                        r,
                         tenant_id,
                     )
                     if attempt_id:
@@ -290,16 +256,14 @@ def check_for_indexing(self: Task, *, tenant_id: str | None) -> int | None:
                             f"Connector indexing queued: "
                             f"index_attempt={attempt_id} "
                             f"cc_pair={cc_pair.id} "
-                            f"search_settings={search_settings_instance.id}"
+                            f"search_settings={search_settings_instance.id} "
                         )
                         tasks_created += 1
 
         # Fail any index attempts in the DB that don't have fences
         # This shouldn't ever happen!
         with get_session_with_tenant(tenant_id) as db_session:
-            unfenced_attempt_ids = get_unfenced_index_attempt_ids(
-                db_session, redis_client
-            )
+            unfenced_attempt_ids = get_unfenced_index_attempt_ids(db_session, r)
             for attempt_id in unfenced_attempt_ids:
                 lock_beat.reacquire()
 
@@ -318,229 +282,28 @@ def check_for_indexing(self: Task, *, tenant_id: str | None) -> int | None:
                     attempt.id, db_session, failure_reason=failure_reason
                 )
 
-        # rkuo: The following code logically appears to work, but the celery inspect code may be unstable
-        # turning off for the moment to see if it helps cloud stability
-
-        # we want to run this less frequently than the overall task
-        # if not redis_client.exists(OnyxRedisSignals.VALIDATE_INDEXING_FENCES):
-        #     # clear any indexing fences that don't have associated celery tasks in progress
-        #     # tasks can be in the queue in redis, in reserved tasks (prefetched by the worker),
-        #     # or be currently executing
-        #     try:
-        #         task_logger.info("Validating indexing fences...")
-        #         validate_indexing_fences(
-        #             tenant_id, self.app, redis_client, redis_client_celery, lock_beat
-        #         )
-        #     except Exception:
-        #         task_logger.exception("Exception while validating indexing fences")
-
-        #     redis_client.set(OnyxRedisSignals.VALIDATE_INDEXING_FENCES, 1, ex=60)
-
     except SoftTimeLimitExceeded:
         task_logger.info(
             "Soft time limit exceeded, task is being terminated gracefully."
         )
     except Exception:
-        task_logger.exception("Unexpected exception during indexing check")
+        task_logger.exception(f"Unexpected exception: tenant={tenant_id}")
     finally:
-        if locked:
-            if lock_beat.owned():
-                lock_beat.release()
-            else:
-                task_logger.error(
-                    "check_for_indexing - Lock not owned on completion: "
-                    f"tenant={tenant_id}"
-                )
+        if lock_beat.owned():
+            lock_beat.release()
+        else:
+            task_logger.error(
+                "check_for_indexing - Lock not owned on completion: "
+                f"tenant={tenant_id}"
+            )
 
-    time_elapsed = time.monotonic() - time_start
-    task_logger.info(f"check_for_indexing finished: elapsed={time_elapsed:.2f}")
     return tasks_created
 
 
-def validate_indexing_fences(
-    tenant_id: str | None,
-    celery_app: Celery,
-    r: Redis,
-    r_celery: Redis,
-    lock_beat: RedisLock,
-) -> None:
-    reserved_indexing_tasks: set[str] = set()
-    active_indexing_tasks: set[str] = set()
-    indexing_worker_names: list[str] = []
-
-    # filter for and create an indexing specific inspect object
-    inspect = celery_app.control.inspect()
-    workers: dict[str, Any] = inspect.ping()  # type: ignore
-    if not workers:
-        raise ValueError("No workers found!")
-
-    for worker_name in list(workers.keys()):
-        if "indexing" in worker_name:
-            indexing_worker_names.append(worker_name)
-
-    if len(indexing_worker_names) == 0:
-        raise ValueError("No indexing workers found!")
-
-    inspect_indexing = celery_app.control.inspect(destination=indexing_worker_names)
-
-    # NOTE: each dict entry is a map of worker name to a list of tasks
-    # we want sets for reserved task and active task id's to optimize
-    # subsequent validation lookups
-
-    # get the list of reserved tasks
-    reserved_tasks: dict[str, list] | None = inspect_indexing.reserved()  # type: ignore
-    if reserved_tasks is None:
-        raise ValueError("inspect_indexing.reserved() returned None!")
-
-    for _, task_list in reserved_tasks.items():
-        for task in task_list:
-            reserved_indexing_tasks.add(task["id"])
-
-    # get the list of active tasks
-    active_tasks: dict[str, list] | None = inspect_indexing.active()  # type: ignore
-    if active_tasks is None:
-        raise ValueError("inspect_indexing.active() returned None!")
-
-    for _, task_list in active_tasks.items():
-        for task in task_list:
-            active_indexing_tasks.add(task["id"])
-
-    # validate all existing indexing jobs
-    for key_bytes in r.scan_iter(RedisConnectorIndex.FENCE_PREFIX + "*"):
-        lock_beat.reacquire()
-        with get_session_with_tenant(tenant_id) as db_session:
-            validate_indexing_fence(
-                tenant_id,
-                key_bytes,
-                reserved_indexing_tasks,
-                active_indexing_tasks,
-                r_celery,
-                db_session,
-            )
-    return
-
-
-def validate_indexing_fence(
-    tenant_id: str | None,
-    key_bytes: bytes,
-    reserved_tasks: set[str],
-    active_tasks: set[str],
-    r_celery: Redis,
-    db_session: Session,
-) -> None:
-    """Checks for the error condition where an indexing fence is set but the associated celery tasks don't exist.
-    This can happen if the indexing worker hard crashes or is terminated.
-    Being in this bad state means the fence will never clear without help, so this function
-    gives the help.
-
-    How this works:
-    1. Active signal is renewed with a 5 minute TTL
-    1.1 When the fence is created
-    1.2. When the task is seen in the redis queue
-    1.3. When the task is seen in the reserved or active list for a worker
-    2. The TTL allows us to get through the transitions on fence startup
-    and when the task starts executing.
-
-    More TTL clarification: it is seemingly impossible to exactly query Celery for
-    whether a task is in the queue or currently executing.
-    1. An unknown task id is always returned as state PENDING.
-    2. Redis can be inspected for the task id, but the task id is gone between the time a worker receives the task
-    and the time it actually starts on the worker.
-    """
-    # if the fence doesn't exist, there's nothing to do
-    fence_key = key_bytes.decode("utf-8")
-    composite_id = RedisConnector.get_id_from_fence_key(fence_key)
-    if composite_id is None:
-        task_logger.warning(
-            f"validate_indexing_fence - could not parse composite_id from {fence_key}"
-        )
-        return
-
-    # parse out metadata and initialize the helper class with it
-    parts = composite_id.split("/")
-    if len(parts) != 2:
-        return
-
-    cc_pair_id = int(parts[0])
-    search_settings_id = int(parts[1])
-
-    redis_connector = RedisConnector(tenant_id, cc_pair_id)
-    redis_connector_index = redis_connector.new_index(search_settings_id)
-    if not redis_connector_index.fenced:
-        return
-
-    payload = redis_connector_index.payload
-    if not payload:
-        return
-
-    # OK, there's actually something for us to validate
-
-    if payload.celery_task_id is None:
-        # the fence is just barely set up.
-        if redis_connector_index.active():
-            return
-
-        # it would be odd to get here as there isn't that much that can go wrong during
-        # initial fence setup, but it's still worth making sure we can recover
-        logger.info(
-            f"validate_indexing_fence - Resetting fence in basic state without any activity: fence={fence_key}"
-        )
-        redis_connector_index.reset()
-        return
-
-    found = celery_find_task(
-        payload.celery_task_id, OnyxCeleryQueues.CONNECTOR_INDEXING, r_celery
-    )
-    if found:
-        # the celery task exists in the redis queue
-        redis_connector_index.set_active()
-        return
-
-    if payload.celery_task_id in reserved_tasks:
-        # the celery task was prefetched and is reserved within the indexing worker
-        redis_connector_index.set_active()
-        return
-
-    if payload.celery_task_id in active_tasks:
-        # the celery task is active (aka currently executing)
-        redis_connector_index.set_active()
-        return
-
-    # we may want to enable this check if using the active task list somehow isn't good enough
-    # if redis_connector_index.generator_locked():
-    #     logger.info(f"{payload.celery_task_id} is currently executing.")
-
-    # we didn't find any direct indication that associated celery tasks exist, but they still might be there
-    # due to gaps in our ability to check states during transitions
-    # Rely on the active signal (which has a duration that allows us to bridge those gaps)
-    if redis_connector_index.active():
-        return
-
-    # celery tasks don't exist and the active signal has expired, possibly due to a crash. Clean it up.
-    logger.warning(
-        f"validate_indexing_fence - Resetting fence because no associated celery tasks were found: fence={fence_key}"
-    )
-    if payload.index_attempt_id:
-        try:
-            mark_attempt_failed(
-                payload.index_attempt_id,
-                db_session,
-                "validate_indexing_fence - Canceling index attempt due to missing celery tasks",
-            )
-        except Exception:
-            logger.exception(
-                "validate_indexing_fence - Exception while marking index attempt as failed."
-            )
-
-    redis_connector_index.reset()
-    return
-
-
 def _should_index(
     cc_pair: ConnectorCredentialPair,
     last_index: IndexAttempt | None,
     search_settings_instance: SearchSettings,
-    search_settings_primary: bool,
     secondary_index_building: bool,
     db_session: Session,
 ) -> bool:
@@ -605,11 +368,6 @@ def _should_index(
     ):
         return False
 
-    if search_settings_primary:
-        if cc_pair.indexing_trigger is not None:
-            # if a manual indexing trigger is on the cc pair, honor it for primary search settings
-            return True
-
     # if no attempt has ever occurred, we should index regardless of refresh_freq
     if not last_index:
         return True
@@ -682,7 +440,6 @@ def try_creating_indexing_task(
             celery_task_id=None,
         )
 
-        redis_connector_index.set_active()
         redis_connector_index.set_fence(payload)
 
         # create the index attempt for tracking purposes
@@ -701,29 +458,28 @@ def try_creating_indexing_task(
         # when the task is sent, we have yet to finish setting up the fence
         # therefore, the task must contain code that blocks until the fence is ready
         result = celery_app.send_task(
-            OnyxCeleryTask.CONNECTOR_INDEXING_PROXY_TASK,
+            "connector_indexing_proxy_task",
             kwargs=dict(
                 index_attempt_id=index_attempt_id,
                 cc_pair_id=cc_pair.id,
                 search_settings_id=search_settings.id,
                 tenant_id=tenant_id,
             ),
-            queue=OnyxCeleryQueues.CONNECTOR_INDEXING,
+            queue=DanswerCeleryQueues.CONNECTOR_INDEXING,
             task_id=custom_task_id,
-            priority=OnyxCeleryPriority.MEDIUM,
+            priority=DanswerCeleryPriority.MEDIUM,
         )
         if not result:
             raise RuntimeError("send_task for connector_indexing_proxy_task failed.")
 
         # now fill out the fence with the rest of the data
-        redis_connector_index.set_active()
-
         payload.index_attempt_id = index_attempt_id
         payload.celery_task_id = result.id
         redis_connector_index.set_fence(payload)
     except Exception:
         task_logger.exception(
             f"try_creating_indexing_task - Unexpected exception: "
+            f"tenant={tenant_id} "
             f"cc_pair={cc_pair.id} "
             f"search_settings={search_settings.id}"
         )
@@ -739,14 +495,8 @@ def try_creating_indexing_task(
     return index_attempt_id
 
 
-@shared_task(
-    name=OnyxCeleryTask.CONNECTOR_INDEXING_PROXY_TASK,
-    bind=True,
-    acks_late=False,
-    track_started=True,
-)
+@shared_task(name="connector_indexing_proxy_task", acks_late=False, track_started=True)
 def connector_indexing_proxy_task(
-    self: Task,
     index_attempt_id: int,
     cc_pair_id: int,
     search_settings_id: int,
@@ -755,13 +505,10 @@ def connector_indexing_proxy_task(
     """celery tasks are forked, but forking is unstable.  This proxies work to a spawned task."""
     task_logger.info(
         f"Indexing watchdog - starting: attempt={index_attempt_id} "
+        f"tenant={tenant_id} "
         f"cc_pair={cc_pair_id} "
         f"search_settings={search_settings_id}"
     )
-
-    if not self.request.id:
-        task_logger.error("self.request.id is None!")
-
     client = SimpleJobClient()
 
     job = client.submit(
@@ -777,122 +524,51 @@ def connector_indexing_proxy_task(
     if not job:
         task_logger.info(
             f"Indexing watchdog - spawn failed: attempt={index_attempt_id} "
+            f"tenant={tenant_id} "
             f"cc_pair={cc_pair_id} "
             f"search_settings={search_settings_id}"
         )
         return
 
     task_logger.info(
-        f"Indexing proxy - spawn succeeded: attempt={index_attempt_id} "
         f"Indexing watchdog - spawn succeeded: attempt={index_attempt_id} "
+        f"tenant={tenant_id} "
         f"cc_pair={cc_pair_id} "
         f"search_settings={search_settings_id}"
     )
 
-    redis_connector = RedisConnector(tenant_id, cc_pair_id)
-    redis_connector_index = redis_connector.new_index(search_settings_id)
-
     while True:
-        sleep(5)
-
-        if self.request.id and redis_connector_index.terminating(self.request.id):
-            task_logger.warning(
-                "Indexing watchdog - termination signal detected: "
-                f"attempt={index_attempt_id} "
-                f"cc_pair={cc_pair_id} "
-                f"search_settings={search_settings_id}"
-            )
-
-            try:
-                with get_session_with_tenant(tenant_id) as db_session:
-                    mark_attempt_canceled(
-                        index_attempt_id,
-                        db_session,
-                        "Connector termination signal detected",
-                    )
-            except Exception:
-                # if the DB exceptions, we'll just get an unfriendly failure message
-                # in the UI instead of the cancellation message
-                logger.exception(
-                    "Indexing watchdog - transient exception marking index attempt as canceled: "
-                    f"attempt={index_attempt_id} "
-                    f"tenant={tenant_id} "
-                    f"cc_pair={cc_pair_id} "
-                    f"search_settings={search_settings_id}"
-                )
-
-                job.cancel()
-
-            break
+        sleep(10)
 
+        # do nothing for ongoing jobs that haven't been stopped
         if not job.done():
-            # if the spawned task is still running, restart the check once again
-            # if the index attempt is not in a finished status
-            try:
-                with get_session_with_tenant(tenant_id) as db_session:
-                    index_attempt = get_index_attempt(
-                        db_session=db_session, index_attempt_id=index_attempt_id
-                    )
-
-                    if not index_attempt:
-                        continue
-
-                    if not index_attempt.is_finished():
-                        continue
-            except Exception:
-                # if the DB exceptioned, just restart the check.
-                # polling the index attempt status doesn't need to be strongly consistent
-                logger.exception(
-                    "Indexing watchdog - transient exception looking up index attempt: "
-                    f"attempt={index_attempt_id} "
-                    f"tenant={tenant_id} "
-                    f"cc_pair={cc_pair_id} "
-                    f"search_settings={search_settings_id}"
+            with get_session_with_tenant(tenant_id) as db_session:
+                index_attempt = get_index_attempt(
+                    db_session=db_session, index_attempt_id=index_attempt_id
                 )
-                continue
+
+                if not index_attempt:
+                    continue
+
+                if not index_attempt.is_finished():
+                    continue
 
         if job.status == "error":
-            ignore_exitcode = False
-
-            exit_code: int | None = None
-            if job.process:
-                exit_code = job.process.exitcode
-
-            # seeing odd behavior where spawned tasks usually return exit code 1 in the cloud,
-            # even though logging clearly indicates that they completed successfully
-            # to work around this, we ignore the job error state if the completion signal is OK
-            status_int = redis_connector_index.get_completion()
-            if status_int:
-                status_enum = HTTPStatus(status_int)
-                if status_enum == HTTPStatus.OK:
-                    ignore_exitcode = True
-
-            if ignore_exitcode:
-                task_logger.warning(
-                    "Indexing watchdog - spawned task has non-zero exit code "
-                    "but completion signal is OK. Continuing...: "
-                    f"attempt={index_attempt_id} "
-                    f"tenant={tenant_id} "
-                    f"cc_pair={cc_pair_id} "
-                    f"search_settings={search_settings_id} "
-                    f"exit_code={exit_code}"
-                )
-            else:
-                task_logger.error(
-                    "Indexing watchdog - spawned task exceptioned: "
-                    f"attempt={index_attempt_id} "
-                    f"tenant={tenant_id} "
-                    f"cc_pair={cc_pair_id} "
-                    f"search_settings={search_settings_id} "
-                    f"exit_code={exit_code} "
-                    f"error={job.exception()}"
-                )
+            task_logger.error(
+                f"Indexing watchdog - spawned task exceptioned: "
+                f"attempt={index_attempt_id} "
+                f"tenant={tenant_id} "
+                f"cc_pair={cc_pair_id} "
+                f"search_settings={search_settings_id} "
+                f"error={job.exception()}"
+            )
 
         job.release()
         break
 
     task_logger.info(
         f"Indexing watchdog - finished: attempt={index_attempt_id} "
+        f"tenant={tenant_id} "
         f"cc_pair={cc_pair_id} "
         f"search_settings={search_settings_id}"
     )
@@ -1027,12 +703,9 @@ def connector_indexing_task(
         )
         break
 
-    # set thread_local=False since we don't control what thread the indexing/pruning
-    # might run our callback with
     lock: RedisLock = r.lock(
         redis_connector_index.generator_lock_key,
         timeout=CELERY_INDEXING_LOCK_TIMEOUT,
-        thread_local=False,
     )
 
     acquired = lock.acquire(blocking=False)
@@ -1088,7 +761,6 @@ def connector_indexing_task(
             f"search_settings={search_settings_id}"
         )
 
-        # This is where the heavy/real work happens
         run_indexing_entrypoint(
             index_attempt_id,
             tenant_id,
@@ -1118,6 +790,7 @@ def connector_indexing_task(
 
     logger.info(
         f"Indexing spawned task finished: attempt={index_attempt_id} "
+        f"tenant={tenant_id} "
         f"cc_pair={cc_pair_id} "
         f"search_settings={search_settings_id}"
     )

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

@@ -11,15 +11,14 @@ from sqlalchemy import inspect
 from sqlalchemy import text
 from sqlalchemy.orm import Session
 
-from onyx.background.celery.apps.app_base import task_logger
-from onyx.configs.app_configs import JOB_TIMEOUT
-from onyx.configs.constants import OnyxCeleryTask
-from onyx.configs.constants import PostgresAdvisoryLocks
-from onyx.db.engine import get_session_with_tenant
+from danswer.background.celery.apps.app_base import task_logger
+from danswer.configs.app_configs import JOB_TIMEOUT
+from danswer.configs.constants import PostgresAdvisoryLocks
+from danswer.db.engine import get_session_with_tenant
 
 
 @shared_task(
-    name=OnyxCeleryTask.KOMBU_MESSAGE_CLEANUP_TASK,
+    name="kombu_message_cleanup_task",
     soft_time_limit=JOB_TIMEOUT,
     bind=True,
     base=AbortableTask,

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

@@ -8,34 +8,32 @@ from celery import shared_task
 from celery import Task
 from celery.exceptions import SoftTimeLimitExceeded
 from redis import Redis
-from redis.lock import Lock as RedisLock
 from sqlalchemy.orm import Session
 
-from onyx.background.celery.apps.app_base import task_logger
-from onyx.background.celery.celery_utils import extract_ids_from_runnable_connector
-from onyx.background.celery.tasks.indexing.tasks import IndexingCallback
-from onyx.configs.app_configs import ALLOW_SIMULTANEOUS_PRUNING
-from onyx.configs.app_configs import JOB_TIMEOUT
-from onyx.configs.constants import CELERY_PRUNING_LOCK_TIMEOUT
-from onyx.configs.constants import CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT
-from onyx.configs.constants import DANSWER_REDIS_FUNCTION_LOCK_PREFIX
-from onyx.configs.constants import OnyxCeleryPriority
-from onyx.configs.constants import OnyxCeleryQueues
-from onyx.configs.constants import OnyxCeleryTask
-from onyx.configs.constants import OnyxRedisLocks
-from onyx.connectors.factory import instantiate_connector
-from onyx.connectors.models import InputType
-from onyx.db.connector_credential_pair import get_connector_credential_pair
-from onyx.db.connector_credential_pair import get_connector_credential_pair_from_id
-from onyx.db.connector_credential_pair import get_connector_credential_pairs
-from onyx.db.document import get_documents_for_connector_credential_pair
-from onyx.db.engine import get_session_with_tenant
-from onyx.db.enums import ConnectorCredentialPairStatus
-from onyx.db.models import ConnectorCredentialPair
-from onyx.redis.redis_connector import RedisConnector
-from onyx.redis.redis_pool import get_redis_client
-from onyx.utils.logger import pruning_ctx
-from onyx.utils.logger import setup_logger
+from danswer.background.celery.apps.app_base import task_logger
+from danswer.background.celery.celery_utils import extract_ids_from_runnable_connector
+from danswer.background.celery.tasks.indexing.tasks import IndexingCallback
+from danswer.configs.app_configs import ALLOW_SIMULTANEOUS_PRUNING
+from danswer.configs.app_configs import JOB_TIMEOUT
+from danswer.configs.constants import CELERY_PRUNING_LOCK_TIMEOUT
+from danswer.configs.constants import CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT
+from danswer.configs.constants import DANSWER_REDIS_FUNCTION_LOCK_PREFIX
+from danswer.configs.constants import DanswerCeleryPriority
+from danswer.configs.constants import DanswerCeleryQueues
+from danswer.configs.constants import 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_pair_from_id
+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_connector import RedisConnector
+from danswer.redis.redis_pool import get_redis_client
+from danswer.utils.logger import pruning_ctx
+from danswer.utils.logger import setup_logger
 
 logger = setup_logger()
 
@@ -77,7 +75,7 @@ def _is_pruning_due(cc_pair: ConnectorCredentialPair) -> bool:
 
 
 @shared_task(
-    name=OnyxCeleryTask.CHECK_FOR_PRUNING,
+    name="check_for_pruning",
     soft_time_limit=JOB_TIMEOUT,
     bind=True,
 )
@@ -85,7 +83,7 @@ def check_for_pruning(self: Task, *, tenant_id: str | None) -> None:
     r = get_redis_client(tenant_id=tenant_id)
 
     lock_beat = r.lock(
-        OnyxRedisLocks.CHECK_PRUNE_BEAT_LOCK,
+        DanswerRedisLocks.CHECK_PRUNE_BEAT_LOCK,
         timeout=CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT,
     )
 
@@ -122,7 +120,7 @@ def check_for_pruning(self: Task, *, tenant_id: str | None) -> None:
             "Soft time limit exceeded, task is being terminated gracefully."
         )
     except Exception:
-        task_logger.exception("Unexpected exception during pruning check")
+        task_logger.exception(f"Unexpected exception: tenant={tenant_id}")
     finally:
         if lock_beat.owned():
             lock_beat.release()
@@ -186,16 +184,16 @@ def try_creating_prune_generator_task(
         custom_task_id = f"{redis_connector.prune.generator_task_key}_{uuid4()}"
 
         celery_app.send_task(
-            OnyxCeleryTask.CONNECTOR_PRUNING_GENERATOR_TASK,
+            "connector_pruning_generator_task",
             kwargs=dict(
                 cc_pair_id=cc_pair.id,
                 connector_id=cc_pair.connector_id,
                 credential_id=cc_pair.credential_id,
                 tenant_id=tenant_id,
             ),
-            queue=OnyxCeleryQueues.CONNECTOR_PRUNING,
+            queue=DanswerCeleryQueues.CONNECTOR_PRUNING,
             task_id=custom_task_id,
-            priority=OnyxCeleryPriority.LOW,
+            priority=DanswerCeleryPriority.LOW,
         )
 
         # set this only after all tasks have been added
@@ -211,7 +209,7 @@ def try_creating_prune_generator_task(
 
 
 @shared_task(
-    name=OnyxCeleryTask.CONNECTOR_PRUNING_GENERATOR_TASK,
+    name="connector_pruning_generator_task",
     acks_late=False,
     soft_time_limit=JOB_TIMEOUT,
     track_started=True,
@@ -240,12 +238,9 @@ def connector_pruning_generator_task(
 
     r = get_redis_client(tenant_id=tenant_id)
 
-    # set thread_local=False since we don't control what thread the indexing/pruning
-    # might run our callback with
-    lock: RedisLock = r.lock(
-        OnyxRedisLocks.PRUNING_LOCK_PREFIX + f"_{redis_connector.id}",
+    lock = r.lock(
+        DanswerRedisLocks.PRUNING_LOCK_PREFIX + f"_{redis_connector.id}",
         timeout=CELERY_PRUNING_LOCK_TIMEOUT,
-        thread_local=False,
     )
 
     acquired = lock.acquire(blocking=False)
@@ -308,7 +303,7 @@ def connector_pruning_generator_task(
             doc_ids_to_remove = list(all_indexed_document_ids - all_connector_doc_ids)
 
             task_logger.info(
-                "Pruning set collected: "
+                f"Pruning set collected: "
                 f"cc_pair={cc_pair_id} "
                 f"connector_source={cc_pair.connector.source} "
                 f"docs_to_remove={len(doc_ids_to_remove)}"
@@ -324,7 +319,7 @@ def connector_pruning_generator_task(
                 return None
 
             task_logger.info(
-                "RedisConnector.prune.generate_tasks finished. "
+                f"RedisConnector.prune.generate_tasks finished. "
                 f"cc_pair={cc_pair_id} tasks_generated={tasks_generated}"
             )
 

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

@@ -4,8 +4,8 @@ from tenacity import retry_if_exception_type
 from tenacity import stop_after_delay
 from tenacity import wait_random_exponential
 
-from onyx.document_index.interfaces import DocumentIndex
-from onyx.document_index.interfaces import VespaDocumentFields
+from danswer.document_index.interfaces import DocumentIndex
+from danswer.document_index.interfaces import VespaDocumentFields
 
 
 class RetryDocumentIndex:

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

@@ -6,22 +6,21 @@ from celery import Task
 from celery.exceptions import SoftTimeLimitExceeded
 from tenacity import RetryError
 
-from onyx.access.access import get_access_for_document
-from onyx.background.celery.apps.app_base import task_logger
-from onyx.background.celery.tasks.shared.RetryDocumentIndex import RetryDocumentIndex
-from onyx.configs.constants import OnyxCeleryTask
-from onyx.db.document import delete_document_by_connector_credential_pair__no_commit
-from onyx.db.document import delete_documents_complete__no_commit
-from onyx.db.document import get_document
-from onyx.db.document import get_document_connector_count
-from onyx.db.document import mark_document_as_modified
-from onyx.db.document import mark_document_as_synced
-from onyx.db.document_set import fetch_document_sets_for_document
-from onyx.db.engine import get_session_with_tenant
-from onyx.document_index.document_index_utils import get_both_index_names
-from onyx.document_index.factory import get_default_document_index
-from onyx.document_index.interfaces import VespaDocumentFields
-from onyx.server.documents.models import ConnectorCredentialPairIdentifier
+from danswer.access.access import get_access_for_document
+from danswer.background.celery.apps.app_base import task_logger
+from danswer.background.celery.tasks.shared.RetryDocumentIndex import RetryDocumentIndex
+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_modified
+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
 
 DOCUMENT_BY_CC_PAIR_CLEANUP_MAX_RETRIES = 3
 
@@ -32,7 +31,7 @@ LIGHT_TIME_LIMIT = LIGHT_SOFT_TIME_LIMIT + 15
 
 
 @shared_task(
-    name=OnyxCeleryTask.DOCUMENT_BY_CC_PAIR_CLEANUP_TASK,
+    name="document_by_cc_pair_cleanup_task",
     soft_time_limit=LIGHT_SOFT_TIME_LIMIT,
     time_limit=LIGHT_TIME_LIMIT,
     max_retries=DOCUMENT_BY_CC_PAIR_CLEANUP_MAX_RETRIES,
@@ -60,7 +59,7 @@ def document_by_cc_pair_cleanup_task(
     connector / credential pair from the access list
     (6) delete all relevant entries from postgres
     """
-    task_logger.debug(f"Task start: doc={document_id}")
+    task_logger.debug(f"Task start: tenant={tenant_id} doc={document_id}")
 
     try:
         with get_session_with_tenant(tenant_id) as db_session:
@@ -129,13 +128,16 @@ def document_by_cc_pair_cleanup_task(
             db_session.commit()
 
             task_logger.info(
+                f"tenant={tenant_id} "
                 f"doc={document_id} "
                 f"action={action} "
                 f"refcount={count} "
                 f"chunks={chunks_affected}"
             )
     except SoftTimeLimitExceeded:
-        task_logger.info(f"SoftTimeLimitExceeded exception. doc={document_id}")
+        task_logger.info(
+            f"SoftTimeLimitExceeded exception. tenant={tenant_id} doc={document_id}"
+        )
         return False
     except Exception as ex:
         if isinstance(ex, RetryError):
@@ -154,12 +156,15 @@ def document_by_cc_pair_cleanup_task(
             if e.response.status_code == HTTPStatus.BAD_REQUEST:
                 task_logger.exception(
                     f"Non-retryable HTTPStatusError: "
+                    f"tenant={tenant_id} "
                     f"doc={document_id} "
                     f"status={e.response.status_code}"
                 )
             return False
 
-        task_logger.exception(f"Unexpected exception: doc={document_id}")
+        task_logger.exception(
+            f"Unexpected exception: tenant={tenant_id} doc={document_id}"
+        )
 
         if self.request.retries < DOCUMENT_BY_CC_PAIR_CLEANUP_MAX_RETRIES:
             # Still retrying. Exponential backoff from 2^4 to 2^6 ... i.e. 16, 32, 64
@@ -170,7 +175,7 @@ def document_by_cc_pair_cleanup_task(
             # eventually gets fixed out of band via stale document reconciliation
             task_logger.warning(
                 f"Max celery task retries reached. Marking doc as dirty for reconciliation: "
-                f"doc={document_id}"
+                f"tenant={tenant_id} doc={document_id}"
             )
             with get_session_with_tenant(tenant_id) as db_session:
                 # delete the cc pair relationship now and let reconciliation clean it up

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

@@ -1,4 +1,3 @@
-import time
 import traceback
 from datetime import datetime
 from datetime import timezone
@@ -17,64 +16,62 @@ from redis.lock import Lock as RedisLock
 from sqlalchemy.orm import Session
 from tenacity import RetryError
 
-from onyx.access.access import get_access_for_document
-from onyx.background.celery.apps.app_base import task_logger
-from onyx.background.celery.celery_redis import celery_get_queue_length
-from onyx.background.celery.tasks.shared.RetryDocumentIndex import RetryDocumentIndex
-from onyx.background.celery.tasks.shared.tasks import LIGHT_SOFT_TIME_LIMIT
-from onyx.background.celery.tasks.shared.tasks import LIGHT_TIME_LIMIT
-from onyx.configs.app_configs import JOB_TIMEOUT
-from onyx.configs.constants import CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT
-from onyx.configs.constants import OnyxCeleryQueues
-from onyx.configs.constants import OnyxCeleryTask
-from onyx.configs.constants import OnyxRedisLocks
-from onyx.db.connector import fetch_connector_by_id
-from onyx.db.connector import mark_cc_pair_as_permissions_synced
-from onyx.db.connector import mark_ccpair_as_pruned
-from onyx.db.connector_credential_pair import add_deletion_failure_message
-from onyx.db.connector_credential_pair import (
+from danswer.access.access import get_access_for_document
+from danswer.background.celery.apps.app_base import task_logger
+from danswer.background.celery.celery_redis import celery_get_queue_length
+from danswer.background.celery.tasks.shared.RetryDocumentIndex import RetryDocumentIndex
+from danswer.background.celery.tasks.shared.tasks import LIGHT_SOFT_TIME_LIMIT
+from danswer.background.celery.tasks.shared.tasks import LIGHT_TIME_LIMIT
+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_cc_pair_as_permissions_synced
+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 onyx.db.connector_credential_pair import get_connector_credential_pair_from_id
-from onyx.db.connector_credential_pair import get_connector_credential_pairs
-from onyx.db.document import count_documents_by_needs_sync
-from onyx.db.document import get_document
-from onyx.db.document import get_document_ids_for_connector_credential_pair
-from onyx.db.document import mark_document_as_synced
-from onyx.db.document_set import delete_document_set
-from onyx.db.document_set import delete_document_set_cc_pair_relationship__no_commit
-from onyx.db.document_set import fetch_document_sets
-from onyx.db.document_set import fetch_document_sets_for_document
-from onyx.db.document_set import get_document_set_by_id
-from onyx.db.document_set import mark_document_set_as_synced
-from onyx.db.engine import get_session_with_tenant
-from onyx.db.enums import IndexingStatus
-from onyx.db.index_attempt import delete_index_attempts
-from onyx.db.index_attempt import get_index_attempt
-from onyx.db.index_attempt import mark_attempt_failed
-from onyx.db.models import DocumentSet
-from onyx.document_index.document_index_utils import get_both_index_names
-from onyx.document_index.factory import get_default_document_index
-from onyx.document_index.interfaces import VespaDocumentFields
-from onyx.redis.redis_connector import RedisConnector
-from onyx.redis.redis_connector_credential_pair import RedisConnectorCredentialPair
-from onyx.redis.redis_connector_delete import RedisConnectorDelete
-from onyx.redis.redis_connector_doc_perm_sync import RedisConnectorPermissionSync
-from onyx.redis.redis_connector_doc_perm_sync import (
-    RedisConnectorPermissionSyncPayload,
+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 get_document_ids_for_connector_credential_pair
+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.index_attempt import delete_index_attempts
+from danswer.db.index_attempt import get_index_attempt
+from danswer.db.index_attempt import mark_attempt_failed
+from danswer.db.models import DocumentSet
+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.redis.redis_connector import RedisConnector
+from danswer.redis.redis_connector_credential_pair import RedisConnectorCredentialPair
+from danswer.redis.redis_connector_delete import RedisConnectorDelete
+from danswer.redis.redis_connector_doc_perm_sync import RedisConnectorPermissionSync
+from danswer.redis.redis_connector_doc_perm_sync import (
+    RedisConnectorPermissionSyncData,
 )
-from onyx.redis.redis_connector_index import RedisConnectorIndex
-from onyx.redis.redis_connector_prune import RedisConnectorPrune
-from onyx.redis.redis_document_set import RedisDocumentSet
-from onyx.redis.redis_pool import get_redis_client
-from onyx.redis.redis_usergroup import RedisUserGroup
-from onyx.utils.logger import setup_logger
-from onyx.utils.variable_functionality import fetch_versioned_implementation
-from onyx.utils.variable_functionality import (
+from danswer.redis.redis_connector_index import RedisConnectorIndex
+from danswer.redis.redis_connector_prune import RedisConnectorPrune
+from danswer.redis.redis_document_set import RedisDocumentSet
+from danswer.redis.redis_pool import get_redis_client
+from danswer.redis.redis_usergroup import RedisUserGroup
+from danswer.utils.logger import setup_logger
+from danswer.utils.variable_functionality import fetch_versioned_implementation
+from danswer.utils.variable_functionality import (
     fetch_versioned_implementation_with_fallback,
 )
-from onyx.utils.variable_functionality import global_version
-from onyx.utils.variable_functionality import noop_fallback
+from danswer.utils.variable_functionality import global_version
+from danswer.utils.variable_functionality import noop_fallback
 
 logger = setup_logger()
 
@@ -82,7 +79,7 @@ logger = setup_logger()
 # celery auto associates tasks created inside another task,
 # which bloats the result metadata considerably. trail=False prevents this.
 @shared_task(
-    name=OnyxCeleryTask.CHECK_FOR_VESPA_SYNC_TASK,
+    name="check_for_vespa_sync_task",
     soft_time_limit=JOB_TIMEOUT,
     trail=False,
     bind=True,
@@ -90,12 +87,11 @@ logger = setup_logger()
 def check_for_vespa_sync_task(self: 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."""
-    time_start = time.monotonic()
 
     r = get_redis_client(tenant_id=tenant_id)
 
-    lock_beat: RedisLock = r.lock(
-        OnyxRedisLocks.CHECK_VESPA_SYNC_BEAT_LOCK,
+    lock_beat = r.lock(
+        DanswerRedisLocks.CHECK_VESPA_SYNC_BEAT_LOCK,
         timeout=CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT,
     )
 
@@ -131,7 +127,7 @@ def check_for_vespa_sync_task(self: Task, *, tenant_id: str | None) -> None:
         if global_version.is_ee_version():
             try:
                 fetch_user_groups = fetch_versioned_implementation(
-                    "onyx.db.user_group", "fetch_user_groups"
+                    "danswer.db.user_group", "fetch_user_groups"
                 )
             except ModuleNotFoundError:
                 # Always exceptions on the MIT version, which is expected
@@ -158,15 +154,11 @@ def check_for_vespa_sync_task(self: Task, *, tenant_id: str | None) -> None:
             "Soft time limit exceeded, task is being terminated gracefully."
         )
     except Exception:
-        task_logger.exception("Unexpected exception during vespa metadata sync")
+        task_logger.exception(f"Unexpected exception: tenant={tenant_id}")
     finally:
         if lock_beat.owned():
             lock_beat.release()
 
-    time_elapsed = time.monotonic() - time_start
-    task_logger.info(f"check_for_vespa_sync_task finished: elapsed={time_elapsed:.2f}")
-    return
-
 
 def try_generate_stale_document_sync_tasks(
     celery_app: Celery,
@@ -298,7 +290,7 @@ def try_generate_user_group_sync_tasks(
 
     # race condition with the monitor/cleanup function if we use a cached result!
     fetch_user_group = fetch_versioned_implementation(
-        "onyx.db.user_group", "fetch_user_group"
+        "danswer.db.user_group", "fetch_user_group"
     )
 
     usergroup = fetch_user_group(db_session, usergroup_id)
@@ -482,7 +474,7 @@ def monitor_connector_deletion_taskset(
 
             # user groups
             cleanup_user_groups = fetch_versioned_implementation_with_fallback(
-                "onyx.db.user_group",
+                "danswer.db.user_group",
                 "delete_user_group_cc_pair_relationship__no_commit",
                 noop_fallback,
             )
@@ -596,7 +588,7 @@ def monitor_ccpair_permissions_taskset(
     if remaining > 0:
         return
 
-    payload: RedisConnectorPermissionSyncPayload | None = (
+    payload: RedisConnectorPermissionSyncData | None = (
         redis_connector.permissions.payload
     )
     start_time: datetime | None = payload.started if payload else None
@@ -604,7 +596,9 @@ def monitor_ccpair_permissions_taskset(
     mark_cc_pair_as_permissions_synced(db_session, int(cc_pair_id), start_time)
     task_logger.info(f"Successfully synced permissions for cc_pair={cc_pair_id}")
 
-    redis_connector.permissions.reset()
+    redis_connector.permissions.taskset_clear()
+    redis_connector.permissions.generator_clear()
+    redis_connector.permissions.set_fence(None)
 
 
 def monitor_ccpair_indexing_taskset(
@@ -661,52 +655,33 @@ def monitor_ccpair_indexing_taskset(
     # outer = result.state in READY state
     status_int = redis_connector_index.get_completion()
     if status_int is None:  # inner signal not set ... possible error
-        task_state = result.state
+        result_state = result.state
         if (
-            task_state in READY_STATES
+            result_state in READY_STATES
         ):  # outer signal in terminal state ... possible error
             # Now double check!
             if redis_connector_index.get_completion() is None:
                 # inner signal still not set (and cannot change when outer result_state is READY)
                 # Task is finished but generator complete isn't set.
                 # We have a problem! Worker may have crashed.
-                task_result = str(result.result)
-                task_traceback = str(result.traceback)
 
                 msg = (
                     f"Connector indexing aborted or exceptioned: "
                     f"attempt={payload.index_attempt_id} "
                     f"celery_task={payload.celery_task_id} "
+                    f"result_state={result_state} "
                     f"cc_pair={cc_pair_id} "
                     f"search_settings={search_settings_id} "
-                    f"elapsed_submitted={elapsed_submitted.total_seconds():.2f} "
-                    f"result.state={task_state} "
-                    f"result.result={task_result} "
-                    f"result.traceback={task_traceback}"
+                    f"elapsed_submitted={elapsed_submitted.total_seconds():.2f}"
                 )
                 task_logger.warning(msg)
 
-                try:
-                    index_attempt = get_index_attempt(
-                        db_session, payload.index_attempt_id
-                    )
-                    if index_attempt:
-                        if (
-                            index_attempt.status != IndexingStatus.CANCELED
-                            and index_attempt.status != IndexingStatus.FAILED
-                        ):
-                            mark_attempt_failed(
-                                index_attempt_id=payload.index_attempt_id,
-                                db_session=db_session,
-                                failure_reason=msg,
-                            )
-                except Exception:
-                    task_logger.exception(
-                        "monitor_ccpair_indexing_taskset - transient exception marking index attempt as failed: "
-                        f"attempt={payload.index_attempt_id} "
-                        f"tenant={tenant_id} "
-                        f"cc_pair={cc_pair_id} "
-                        f"search_settings={search_settings_id}"
+                index_attempt = get_index_attempt(db_session, payload.index_attempt_id)
+                if index_attempt:
+                    mark_attempt_failed(
+                        index_attempt_id=payload.index_attempt_id,
+                        db_session=db_session,
+                        failure_reason=msg,
                     )
 
                 redis_connector_index.reset()
@@ -717,7 +692,6 @@ def monitor_ccpair_indexing_taskset(
     task_logger.info(
         f"Connector indexing finished: cc_pair={cc_pair_id} "
         f"search_settings={search_settings_id} "
-        f"progress={progress} "
         f"status={status_enum.name} "
         f"elapsed_submitted={elapsed_submitted.total_seconds():.2f}"
     )
@@ -725,7 +699,7 @@ def monitor_ccpair_indexing_taskset(
     redis_connector_index.reset()
 
 
-@shared_task(name=OnyxCeleryTask.MONITOR_VESPA_SYNC, soft_time_limit=300, bind=True)
+@shared_task(name="monitor_vespa_sync", soft_time_limit=300, bind=True)
 def monitor_vespa_sync(self: Task, tenant_id: str | None) -> bool:
     """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.
@@ -736,11 +710,10 @@ def monitor_vespa_sync(self: Task, tenant_id: str | None) -> bool:
 
     Returns True if the task actually did work, False if it exited early to prevent overlap
     """
-    time_start = time.monotonic()
     r = get_redis_client(tenant_id=tenant_id)
 
     lock_beat: RedisLock = r.lock(
-        OnyxRedisLocks.MONITOR_VESPA_SYNC_BEAT_LOCK,
+        DanswerRedisLocks.MONITOR_VESPA_SYNC_BEAT_LOCK,
         timeout=CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT,
     )
 
@@ -751,19 +724,21 @@ def monitor_vespa_sync(self: Task, tenant_id: str | None) -> bool:
 
         # print current queue lengths
         r_celery = self.app.broker_connection().channel().client  # type: ignore
-        n_celery = celery_get_queue_length("celery", r_celery)
+        n_celery = celery_get_queue_length("celery", r)
         n_indexing = celery_get_queue_length(
-            OnyxCeleryQueues.CONNECTOR_INDEXING, r_celery
+            DanswerCeleryQueues.CONNECTOR_INDEXING, r_celery
+        )
+        n_sync = celery_get_queue_length(
+            DanswerCeleryQueues.VESPA_METADATA_SYNC, r_celery
         )
-        n_sync = celery_get_queue_length(OnyxCeleryQueues.VESPA_METADATA_SYNC, r_celery)
         n_deletion = celery_get_queue_length(
-            OnyxCeleryQueues.CONNECTOR_DELETION, r_celery
+            DanswerCeleryQueues.CONNECTOR_DELETION, r_celery
         )
         n_pruning = celery_get_queue_length(
-            OnyxCeleryQueues.CONNECTOR_PRUNING, r_celery
+            DanswerCeleryQueues.CONNECTOR_PRUNING, r_celery
         )
         n_permissions_sync = celery_get_queue_length(
-            OnyxCeleryQueues.CONNECTOR_DOC_PERMISSIONS_SYNC, r_celery
+            DanswerCeleryQueues.CONNECTOR_DOC_PERMISSIONS_SYNC, r_celery
         )
 
         task_logger.info(
@@ -794,7 +769,7 @@ def monitor_vespa_sync(self: Task, tenant_id: str | None) -> bool:
         for key_bytes in r.scan_iter(RedisUserGroup.FENCE_PREFIX + "*"):
             lock_beat.reacquire()
             monitor_usergroup_taskset = fetch_versioned_implementation_with_fallback(
-                "onyx.background.celery.tasks.vespa.tasks",
+                "danswer.background.celery.tasks.vespa.tasks",
                 "monitor_usergroup_taskset",
                 noop_fallback,
             )
@@ -821,8 +796,8 @@ def monitor_vespa_sync(self: Task, tenant_id: str | None) -> bool:
 
         # uncomment for debugging if needed
         # r_celery = celery_app.broker_connection().channel().client
-        # length = celery_get_queue_length(OnyxCeleryQueues.VESPA_METADATA_SYNC, r_celery)
-        # task_logger.warning(f"queue={OnyxCeleryQueues.VESPA_METADATA_SYNC} length={length}")
+        # 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."
@@ -831,13 +806,11 @@ def monitor_vespa_sync(self: Task, tenant_id: str | None) -> bool:
         if lock_beat.owned():
             lock_beat.release()
 
-    time_elapsed = time.monotonic() - time_start
-    task_logger.info(f"monitor_vespa_sync finished: elapsed={time_elapsed:.2f}")
     return True
 
 
 @shared_task(
-    name=OnyxCeleryTask.VESPA_METADATA_SYNC_TASK,
+    name="vespa_metadata_sync_task",
     bind=True,
     soft_time_limit=LIGHT_SOFT_TIME_LIMIT,
     time_limit=LIGHT_TIME_LIMIT,
@@ -882,9 +855,13 @@ def vespa_metadata_sync_task(
             # the sync might repeat again later
             mark_document_as_synced(document_id, db_session)
 
-            task_logger.info(f"doc={document_id} action=sync chunks={chunks_affected}")
+            task_logger.info(
+                f"tenant={tenant_id} doc={document_id} action=sync chunks={chunks_affected}"
+            )
     except SoftTimeLimitExceeded:
-        task_logger.info(f"SoftTimeLimitExceeded exception. doc={document_id}")
+        task_logger.info(
+            f"SoftTimeLimitExceeded exception. tenant={tenant_id} doc={document_id}"
+        )
     except Exception as ex:
         if isinstance(ex, RetryError):
             task_logger.warning(
@@ -902,13 +879,14 @@ def vespa_metadata_sync_task(
             if e.response.status_code == HTTPStatus.BAD_REQUEST:
                 task_logger.exception(
                     f"Non-retryable HTTPStatusError: "
+                    f"tenant={tenant_id} "
                     f"doc={document_id} "
                     f"status={e.response.status_code}"
                 )
             return False
 
         task_logger.exception(
-            f"Unexpected exception during vespa metadata sync: doc={document_id}"
+            f"Unexpected exception: tenant={tenant_id} doc={document_id}"
         )
 
         # Exponential backoff from 2^4 to 2^6 ... i.e. 16, 32, 64

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

@@ -0,0 +1,6 @@
+"""Factory stub for running celery worker / celery beat."""
+from danswer.background.celery.apps.beat import celery_app
+from danswer.utils.variable_functionality import set_is_ee_based_on_env_variable
+
+set_is_ee_based_on_env_variable()
+app = celery_app

backend/danswer/background/celery/versioned_apps/heavy.py

@@ -3,13 +3,13 @@ This code is different from the primary/beat stubs because there is no EE versio
 fetch. Port over the code in those files if we add an EE version of this worker."""
 from celery import Celery
 
-from onyx.utils.variable_functionality import set_is_ee_based_on_env_variable
+from danswer.utils.variable_functionality import set_is_ee_based_on_env_variable
 
 set_is_ee_based_on_env_variable()
 
 
 def get_app() -> Celery:
-    from onyx.background.celery.apps.heavy import celery_app
+    from danswer.background.celery.apps.heavy import celery_app
 
     return celery_app
 

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

@@ -3,13 +3,13 @@ This code is different from the primary/beat stubs because there is no EE versio
 fetch. Port over the code in those files if we add an EE version of this worker."""
 from celery import Celery
 
-from onyx.utils.variable_functionality import set_is_ee_based_on_env_variable
+from danswer.utils.variable_functionality import set_is_ee_based_on_env_variable
 
 set_is_ee_based_on_env_variable()
 
 
 def get_app() -> Celery:
-    from onyx.background.celery.apps.indexing import celery_app
+    from danswer.background.celery.apps.indexing import celery_app
 
     return celery_app
 

backend/danswer/background/celery/versioned_apps/light.py

@@ -3,13 +3,13 @@ This code is different from the primary/beat stubs because there is no EE versio
 fetch. Port over the code in those files if we add an EE version of this worker."""
 from celery import Celery
 
-from onyx.utils.variable_functionality import set_is_ee_based_on_env_variable
+from danswer.utils.variable_functionality import set_is_ee_based_on_env_variable
 
 set_is_ee_based_on_env_variable()
 
 
 def get_app() -> Celery:
-    from onyx.background.celery.apps.light import celery_app
+    from danswer.background.celery.apps.light import celery_app
 
     return celery_app
 

backend/danswer/background/celery/versioned_apps/primary.py

@@ -0,0 +1,8 @@
+"""Factory stub 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()
+app = fetch_versioned_implementation(
+    "danswer.background.celery.apps.primary", "celery_app"
+)

backend/danswer/background/indexing/checkpointing.py

@@ -3,9 +3,9 @@ into a series of checkpoints to better handle intermittent failures
 / jobs being killed by cloud providers."""
 import datetime
 
-from onyx.configs.app_configs import EXPERIMENTAL_CHECKPOINTING_ENABLED
-from onyx.configs.constants import DocumentSource
-from onyx.connectors.cross_connector_utils.miscellaneous_utils import datetime_to_utc
+from danswer.configs.app_configs import EXPERIMENTAL_CHECKPOINTING_ENABLED
+from danswer.configs.constants import DocumentSource
+from danswer.connectors.cross_connector_utils.miscellaneous_utils import datetime_to_utc
 
 
 def _2010_dt() -> datetime.datetime:

backend/danswer/background/indexing/dask_utils.py

@@ -4,7 +4,7 @@ import psutil
 from dask.distributed import WorkerPlugin
 from distributed import Worker
 
-from onyx.utils.logger import setup_logger
+from danswer.utils.logger import setup_logger
 
 logger = setup_logger()
 

backend/danswer/background/indexing/job_client.py

@@ -11,9 +11,9 @@ from typing import Any
 from typing import Literal
 from typing import Optional
 
-from onyx.configs.constants import POSTGRES_CELERY_WORKER_INDEXING_CHILD_APP_NAME
-from onyx.db.engine import SqlEngine
-from onyx.utils.logger import setup_logger
+from danswer.configs.constants import POSTGRES_CELERY_WORKER_INDEXING_CHILD_APP_NAME
+from danswer.db.engine import SqlEngine
+from danswer.utils.logger import setup_logger
 
 logger = setup_logger()
 
@@ -82,7 +82,7 @@ class SimpleJob:
             return "running"
         elif self.process.exitcode is None:
             return "cancelled"
-        elif self.process.exitcode != 0:
+        elif self.process.exitcode > 0:
             return "error"
         else:
             return "finished"
@@ -123,8 +123,7 @@ class SimpleJobClient:
         self._cleanup_completed_jobs()
         if len(self.jobs) >= self.n_workers:
             logger.debug(
-                f"No available workers to run job. "
-                f"Currently running '{len(self.jobs)}' jobs, with a limit of '{self.n_workers}'."
+                f"No available workers to run job. Currently running '{len(self.jobs)}' jobs, with a limit of '{self.n_workers}'."
             )
             return None
 

backend/danswer/background/indexing/run_indexing.py

@@ -6,37 +6,34 @@ from datetime import timezone
 
 from sqlalchemy.orm import Session
 
-from onyx.background.indexing.checkpointing import get_time_windows_for_index_attempt
-from onyx.background.indexing.tracer import OnyxTracer
-from onyx.configs.app_configs import INDEXING_SIZE_WARNING_THRESHOLD
-from onyx.configs.app_configs import INDEXING_TRACER_INTERVAL
-from onyx.configs.app_configs import POLL_CONNECTOR_OFFSET
-from onyx.configs.constants import MilestoneRecordType
-from onyx.connectors.connector_runner import ConnectorRunner
-from onyx.connectors.factory import instantiate_connector
-from onyx.connectors.models import IndexAttemptMetadata
-from onyx.db.connector_credential_pair import get_connector_credential_pair_from_id
-from onyx.db.connector_credential_pair import get_last_successful_attempt_time
-from onyx.db.connector_credential_pair import update_connector_credential_pair
-from onyx.db.engine import get_session_with_tenant
-from onyx.db.enums import ConnectorCredentialPairStatus
-from onyx.db.index_attempt import mark_attempt_canceled
-from onyx.db.index_attempt import mark_attempt_failed
-from onyx.db.index_attempt import mark_attempt_partially_succeeded
-from onyx.db.index_attempt import mark_attempt_succeeded
-from onyx.db.index_attempt import transition_attempt_to_in_progress
-from onyx.db.index_attempt import update_docs_indexed
-from onyx.db.models import IndexAttempt
-from onyx.db.models import IndexingStatus
-from onyx.db.models import IndexModelStatus
-from onyx.document_index.factory import get_default_document_index
-from onyx.indexing.embedder import DefaultIndexingEmbedder
-from onyx.indexing.indexing_heartbeat import IndexingHeartbeatInterface
-from onyx.indexing.indexing_pipeline import build_indexing_pipeline
-from onyx.utils.logger import setup_logger
-from onyx.utils.logger import TaskAttemptSingleton
-from onyx.utils.telemetry import create_milestone_and_report
-from onyx.utils.variable_functionality import global_version
+from danswer.background.indexing.checkpointing import get_time_windows_for_index_attempt
+from danswer.background.indexing.tracer import DanswerTracer
+from danswer.configs.app_configs import INDEXING_SIZE_WARNING_THRESHOLD
+from danswer.configs.app_configs import INDEXING_TRACER_INTERVAL
+from danswer.configs.app_configs import POLL_CONNECTOR_OFFSET
+from danswer.connectors.connector_runner import ConnectorRunner
+from danswer.connectors.factory import instantiate_connector
+from danswer.connectors.models import IndexAttemptMetadata
+from danswer.db.connector_credential_pair import get_connector_credential_pair_from_id
+from danswer.db.connector_credential_pair import get_last_successful_attempt_time
+from danswer.db.connector_credential_pair import update_connector_credential_pair
+from danswer.db.engine import get_session_with_tenant
+from danswer.db.enums import ConnectorCredentialPairStatus
+from danswer.db.index_attempt import mark_attempt_failed
+from danswer.db.index_attempt import mark_attempt_partially_succeeded
+from danswer.db.index_attempt import mark_attempt_succeeded
+from danswer.db.index_attempt import transition_attempt_to_in_progress
+from danswer.db.index_attempt import update_docs_indexed
+from danswer.db.models import IndexAttempt
+from danswer.db.models import IndexingStatus
+from danswer.db.models import IndexModelStatus
+from danswer.document_index.factory import get_default_document_index
+from danswer.indexing.embedder import DefaultIndexingEmbedder
+from danswer.indexing.indexing_heartbeat import IndexingHeartbeatInterface
+from danswer.indexing.indexing_pipeline import build_indexing_pipeline
+from danswer.utils.logger import setup_logger
+from danswer.utils.logger import TaskAttemptSingleton
+from danswer.utils.variable_functionality import global_version
 
 logger = setup_logger()
 
@@ -90,10 +87,6 @@ def _get_connector_runner(
     )
 
 
-class ConnectorStopSignal(Exception):
-    """A custom exception used to signal a stop in processing."""
-
-
 def _run_indexing(
     db_session: Session,
     index_attempt: IndexAttempt,
@@ -167,7 +160,7 @@ def _run_indexing(
 
     if INDEXING_TRACER_INTERVAL > 0:
         logger.debug(f"Memory tracer starting: interval={INDEXING_TRACER_INTERVAL}")
-        tracer = OnyxTracer()
+        tracer = DanswerTracer()
         tracer.start()
         tracer.snap()
 
@@ -215,7 +208,9 @@ def _run_indexing(
                 # contents still need to be initially pulled.
                 if callback:
                     if callback.should_stop():
-                        raise ConnectorStopSignal("Connector stop signal detected")
+                        raise RuntimeError(
+                            "_run_indexing: Connector stop signal detected"
+                        )
 
                 # TODO: should we move this into the above callback instead?
                 db_session.refresh(db_cc_pair)
@@ -309,16 +304,26 @@ def _run_indexing(
                 )
         except Exception as e:
             logger.exception(
-                f"Connector run exceptioned after elapsed time: {time.time() - start_time} seconds"
+                f"Connector run ran into exception after elapsed time: {time.time() - start_time} seconds"
             )
-
-            if isinstance(e, ConnectorStopSignal):
-                mark_attempt_canceled(
+            # Only mark the attempt as a complete failure if this is the first indexing window.
+            # Otherwise, some progress was made - the next run will not start from the beginning.
+            # In this case, it is not accurate to mark it as a failure. When the next run begins,
+            # if that fails immediately, it will be marked as a failure.
+            #
+            # NOTE: if the connector is manually disabled, we should mark it as a failure regardless
+            # to give better clarity in the UI, as the next run will never happen.
+            if (
+                ind == 0
+                or not db_cc_pair.status.is_active()
+                or index_attempt.status != IndexingStatus.IN_PROGRESS
+            ):
+                mark_attempt_failed(
                     index_attempt.id,
                     db_session,
-                    reason=str(e),
+                    failure_reason=str(e),
+                    full_exception_trace=traceback.format_exc(),
                 )
-
                 if is_primary:
                     update_connector_credential_pair(
                         db_session=db_session,
@@ -330,37 +335,6 @@ def _run_indexing(
                 if INDEXING_TRACER_INTERVAL > 0:
                     tracer.stop()
                 raise e
-            else:
-                # Only mark the attempt as a complete failure if this is the first indexing window.
-                # Otherwise, some progress was made - the next run will not start from the beginning.
-                # In this case, it is not accurate to mark it as a failure. When the next run begins,
-                # if that fails immediately, it will be marked as a failure.
-                #
-                # NOTE: if the connector is manually disabled, we should mark it as a failure regardless
-                # to give better clarity in the UI, as the next run will never happen.
-                if (
-                    ind == 0
-                    or not db_cc_pair.status.is_active()
-                    or index_attempt.status != IndexingStatus.IN_PROGRESS
-                ):
-                    mark_attempt_failed(
-                        index_attempt.id,
-                        db_session,
-                        failure_reason=str(e),
-                        full_exception_trace=traceback.format_exc(),
-                    )
-
-                    if is_primary:
-                        update_connector_credential_pair(
-                            db_session=db_session,
-                            connector_id=db_connector.id,
-                            credential_id=db_credential.id,
-                            net_docs=net_doc_change,
-                        )
-
-                    if INDEXING_TRACER_INTERVAL > 0:
-                        tracer.stop()
-                    raise e
 
             # break => similar to success case. As mentioned above, if the next run fails for the same
             # reason it will then be marked as a failure
@@ -398,15 +372,6 @@ def _run_indexing(
 
     if index_attempt_md.num_exceptions == 0:
         mark_attempt_succeeded(index_attempt, db_session)
-
-        create_milestone_and_report(
-            user=None,
-            distinct_id=tenant_id or "N/A",
-            event_type=MilestoneRecordType.CONNECTOR_SUCCEEDED,
-            properties=None,
-            db_session=db_session,
-        )
-
         logger.info(
             f"Connector succeeded: "
             f"docs={document_count} chunks={chunk_count} elapsed={elapsed_time:.2f}s"

backend/danswer/background/indexing/tracer.py

@@ -1,13 +1,13 @@
 import tracemalloc
 
-from onyx.utils.logger import setup_logger
+from danswer.utils.logger import setup_logger
 
 logger = setup_logger()
 
 DANSWER_TRACEMALLOC_FRAMES = 10
 
 
-class OnyxTracer:
+class DanswerTracer:
     def __init__(self) -> None:
         self.snapshot_first: tracemalloc.Snapshot | None = None
         self.snapshot_prev: tracemalloc.Snapshot | None = None
@@ -68,10 +68,10 @@ class OnyxTracer:
         if not self.snapshot or not self.snapshot_prev:
             return
 
-        OnyxTracer.log_diff(self.snapshot, self.snapshot_prev, numEntries)
+        DanswerTracer.log_diff(self.snapshot, self.snapshot_prev, numEntries)
 
     def log_first_diff(self, numEntries: int) -> None:
         if not self.snapshot or not self.snapshot_first:
             return
 
-        OnyxTracer.log_diff(self.snapshot, self.snapshot_first, numEntries)
+        DanswerTracer.log_diff(self.snapshot, self.snapshot_first, numEntries)

backend/danswer/background/task_utils.py

@@ -8,10 +8,10 @@ from celery import Task
 from celery.result import AsyncResult
 from sqlalchemy.orm import Session
 
-from onyx.db.engine import get_sqlalchemy_engine
-from onyx.db.tasks import mark_task_finished
-from onyx.db.tasks import mark_task_start
-from onyx.db.tasks import register_task
+from danswer.db.engine import get_sqlalchemy_engine
+from danswer.db.tasks import mark_task_finished
+from danswer.db.tasks import mark_task_start
+from danswer.db.tasks import register_task
 
 
 T = TypeVar("T", bound=Callable)

backend/danswer/chat/chat_utils.py

@@ -2,79 +2,20 @@ import re
 from typing import cast
 from uuid import UUID
 
-from fastapi import HTTPException
 from fastapi.datastructures import Headers
 from sqlalchemy.orm import Session
 
-from onyx.auth.users import is_user_admin
-from onyx.chat.models import CitationInfo
-from onyx.chat.models import LlmDoc
-from onyx.chat.models import PersonaOverrideConfig
-from onyx.chat.models import ThreadMessage
-from onyx.configs.constants import DEFAULT_PERSONA_ID
-from onyx.configs.constants import MessageType
-from onyx.context.search.models import InferenceSection
-from onyx.context.search.models import RerankingDetails
-from onyx.context.search.models import RetrievalDetails
-from onyx.db.chat import create_chat_session
-from onyx.db.chat import get_chat_messages_by_session
-from onyx.db.llm import fetch_existing_doc_sets
-from onyx.db.llm import fetch_existing_tools
-from onyx.db.models import ChatMessage
-from onyx.db.models import Persona
-from onyx.db.models import Prompt
-from onyx.db.models import Tool
-from onyx.db.models import User
-from onyx.db.persona import get_prompts_by_ids
-from onyx.llm.models import PreviousMessage
-from onyx.natural_language_processing.utils import BaseTokenizer
-from onyx.server.query_and_chat.models import CreateChatMessageRequest
-from onyx.tools.tool_implementations.custom.custom_tool import (
-    build_custom_tools_from_openapi_schema_and_headers,
-)
-from onyx.utils.logger import setup_logger
+from danswer.chat.models import CitationInfo
+from danswer.chat.models import LlmDoc
+from danswer.db.chat import get_chat_messages_by_session
+from danswer.db.models import ChatMessage
+from danswer.llm.answering.models import PreviousMessage
+from danswer.search.models import InferenceSection
+from danswer.utils.logger import setup_logger
 
 logger = setup_logger()
 
 
-def prepare_chat_message_request(
-    message_text: str,
-    user: User | None,
-    persona_id: int | None,
-    # Does the question need to have a persona override
-    persona_override_config: PersonaOverrideConfig | None,
-    prompt: Prompt | None,
-    message_ts_to_respond_to: str | None,
-    retrieval_details: RetrievalDetails | None,
-    rerank_settings: RerankingDetails | None,
-    db_session: Session,
-) -> CreateChatMessageRequest:
-    # Typically used for one shot flows like SlackBot or non-chat API endpoint use cases
-    new_chat_session = create_chat_session(
-        db_session=db_session,
-        description=None,
-        user_id=user.id if user else None,
-        # If using an override, this id will be ignored later on
-        persona_id=persona_id or DEFAULT_PERSONA_ID,
-        onyxbot_flow=True,
-        slack_thread_id=message_ts_to_respond_to,
-    )
-
-    return CreateChatMessageRequest(
-        chat_session_id=new_chat_session.id,
-        parent_message_id=None,  # It's a standalone chat session each time
-        message=message_text,
-        file_descriptors=[],  # Currently SlackBot/answer api do not support files in the context
-        prompt_id=prompt.id if prompt else None,
-        # Can always override the persona for the single query, if it's a normal persona
-        # then it will be treated the same
-        persona_override_config=persona_override_config,
-        search_doc_ids=None,
-        retrieval_options=retrieval_details,
-        rerank_settings=rerank_settings,
-    )
-
-
 def llm_doc_from_inference_section(inference_section: InferenceSection) -> LlmDoc:
     return LlmDoc(
         document_id=inference_section.center_chunk.document_id,
@@ -90,49 +31,9 @@ def llm_doc_from_inference_section(inference_section: InferenceSection) -> LlmDo
         if inference_section.center_chunk.source_links
         else None,
         source_links=inference_section.center_chunk.source_links,
-        match_highlights=inference_section.center_chunk.match_highlights,
     )
 
 
-def combine_message_thread(
-    messages: list[ThreadMessage],
-    max_tokens: int | None,
-    llm_tokenizer: BaseTokenizer,
-) -> str:
-    """Used to create a single combined message context from threads"""
-    if not messages:
-        return ""
-
-    message_strs: list[str] = []
-    total_token_count = 0
-
-    for message in reversed(messages):
-        if message.role == MessageType.USER:
-            role_str = message.role.value.upper()
-            if message.sender:
-                role_str += " " + message.sender
-            else:
-                # Since other messages might have the user identifying information
-                # better to use Unknown for symmetry
-                role_str += " Unknown"
-        else:
-            role_str = message.role.value.upper()
-
-        msg_str = f"{role_str}:\n{message.message}"
-        message_token_count = len(llm_tokenizer.encode(msg_str))
-
-        if (
-            max_tokens is not None
-            and total_token_count + message_token_count > max_tokens
-        ):
-            break
-
-        message_strs.insert(0, msg_str)
-        total_token_count += message_token_count
-
-    return "\n\n".join(message_strs)
-
-
 def create_chat_chain(
     chat_session_id: UUID,
     db_session: Session,
@@ -295,71 +196,3 @@ def extract_headers(
             if lowercase_key in headers:
                 extracted_headers[lowercase_key] = headers[lowercase_key]
     return extracted_headers
-
-
-def create_temporary_persona(
-    persona_config: PersonaOverrideConfig, db_session: Session, user: User | None = None
-) -> Persona:
-    if not is_user_admin(user):
-        raise HTTPException(
-            status_code=403,
-            detail="User is not authorized to create a persona in one shot queries",
-        )
-
-    """Create a temporary Persona object from the provided configuration."""
-    persona = Persona(
-        name=persona_config.name,
-        description=persona_config.description,
-        num_chunks=persona_config.num_chunks,
-        llm_relevance_filter=persona_config.llm_relevance_filter,
-        llm_filter_extraction=persona_config.llm_filter_extraction,
-        recency_bias=persona_config.recency_bias,
-        llm_model_provider_override=persona_config.llm_model_provider_override,
-        llm_model_version_override=persona_config.llm_model_version_override,
-    )
-
-    if persona_config.prompts:
-        persona.prompts = [
-            Prompt(
-                name=p.name,
-                description=p.description,
-                system_prompt=p.system_prompt,
-                task_prompt=p.task_prompt,
-                include_citations=p.include_citations,
-                datetime_aware=p.datetime_aware,
-            )
-            for p in persona_config.prompts
-        ]
-    elif persona_config.prompt_ids:
-        persona.prompts = get_prompts_by_ids(
-            db_session=db_session, prompt_ids=persona_config.prompt_ids
-        )
-
-    persona.tools = []
-    if persona_config.custom_tools_openapi:
-        for schema in persona_config.custom_tools_openapi:
-            tools = cast(
-                list[Tool],
-                build_custom_tools_from_openapi_schema_and_headers(schema),
-            )
-            persona.tools.extend(tools)
-
-    if persona_config.tools:
-        tool_ids = [tool.id for tool in persona_config.tools]
-        persona.tools.extend(
-            fetch_existing_tools(db_session=db_session, tool_ids=tool_ids)
-        )
-
-    if persona_config.tool_ids:
-        persona.tools.extend(
-            fetch_existing_tools(
-                db_session=db_session, tool_ids=persona_config.tool_ids
-            )
-        )
-
-    fetched_docs = fetch_existing_doc_sets(
-        db_session=db_session, doc_ids=persona_config.document_set_ids
-    )
-    persona.document_sets = fetched_docs
-
-    return persona