Debug test

.github/actions/custom-build-and-push/action.yml

@@ -32,20 +32,16 @@ inputs:
     description: 'Cache destinations'
     required: false
   retry-wait-time:
-    description: 'Time to wait before attempt 2 in seconds'
+    description: 'Time to wait before retry in seconds'
     required: false
-    default: '60'
-  retry-wait-time-2:
-    description: 'Time to wait before attempt 3 in seconds'
-    required: false
-    default: '120'
+    default: '5'
 
 runs:
   using: "composite"
   steps:
-    - name: Build and push Docker image (Attempt 1 of 3)
+    - name: Build and push Docker image (First Attempt)
       id: buildx1
-      uses: docker/build-push-action@v6
+      uses: docker/build-push-action@v5
       continue-on-error: true
       with:
         context: ${{ inputs.context }}
@@ -58,17 +54,16 @@ runs:
         cache-from: ${{ inputs.cache-from }}
         cache-to: ${{ inputs.cache-to }}
 
-    - name: Wait before attempt 2
+    - name: Wait to retry
       if: steps.buildx1.outcome != 'success'
       run: |
         echo "First attempt failed. Waiting ${{ inputs.retry-wait-time }} seconds before retry..."
         sleep ${{ inputs.retry-wait-time }}
       shell: bash
 
-    - name: Build and push Docker image (Attempt 2 of 3)
-      id: buildx2
+    - name: Build and push Docker image (Retry Attempt)
       if: steps.buildx1.outcome != 'success'
-      uses: docker/build-push-action@v6
+      uses: docker/build-push-action@v5
       with:
         context: ${{ inputs.context }}
         file: ${{ inputs.file }}
@@ -79,31 +74,3 @@ runs:
         tags: ${{ inputs.tags }}
         cache-from: ${{ inputs.cache-from }}
         cache-to: ${{ inputs.cache-to }}
-
-    - name: Wait before attempt 3
-      if: steps.buildx1.outcome != 'success' && steps.buildx2.outcome != 'success'
-      run: |
-        echo "Second attempt failed. Waiting ${{ inputs.retry-wait-time-2 }} seconds before retry..."
-        sleep ${{ inputs.retry-wait-time-2 }}
-      shell: bash
-
-    - name: Build and push Docker image (Attempt 3 of 3)
-      id: buildx3
-      if: steps.buildx1.outcome != 'success' && steps.buildx2.outcome != 'success'
-      uses: docker/build-push-action@v6
-      with:
-        context: ${{ inputs.context }}
-        file: ${{ inputs.file }}
-        platforms: ${{ inputs.platforms }}
-        pull: ${{ inputs.pull }}
-        push: ${{ inputs.push }}
-        load: ${{ inputs.load }}
-        tags: ${{ inputs.tags }}
-        cache-from: ${{ inputs.cache-from }}
-        cache-to: ${{ inputs.cache-to }}
-
-    - name: Report failure
-      if: steps.buildx1.outcome != 'success' && steps.buildx2.outcome != 'success' && steps.buildx3.outcome != 'success'
-      run: |
-        echo "All attempts failed. Possible transient infrastucture issues? Try again later or inspect logs for details."
-      shell: bash

.github/pull_request_template.md

@@ -6,24 +6,20 @@
 [Describe the tests you ran to verify your changes]
 
 
-## Accepted Risk (provide if relevant)
-N/A
+## Accepted Risk
+[Any know risks or failure modes to point out to reviewers]
 
 
-## Related Issue(s) (provide if relevant)
-N/A
+## Related Issue(s)
+[If applicable, link to the issue(s) this PR addresses]
 
 
-## Mental Checklist:
-- All of the automated tests pass
-- All PR comments are addressed and marked resolved
-- If there are migrations, they have been rebased to latest main
-- If there are new dependencies, they are added to the requirements
-- If there are new environment variables, they are added to all of the deployment methods
-- If there are new APIs that don't require auth, they are added to PUBLIC_ENDPOINT_SPECS
-- Docker images build and basic functionalities work
-- Author has done a final read through of the PR right before merge
-
-## Backporting (check the box to trigger backport action)
-Note: You have to check that the action passes, otherwise resolve the conflicts manually and tag the patches.
-- [ ] This PR should be backported (make sure to check that the backport attempt succeeds)
+## Checklist:
+- [ ] All of the automated tests pass
+- [ ] All PR comments are addressed and marked resolved
+- [ ] If there are migrations, they have been rebased to latest main
+- [ ] If there are new dependencies, they are added to the requirements
+- [ ] If there are new environment variables, they are added to all of the deployment methods
+- [ ] If there are new APIs that don't require auth, they are added to PUBLIC_ENDPOINT_SPECS
+- [ ] Docker images build and basic functionalities work
+- [ ] Author has done a final read through of the PR right before merge

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

@@ -3,61 +3,52 @@ name: Build and Push Backend Image on Tag
 on:
   push:
     tags:
-      - "*"
+      - '*'
 
 env:
-  REGISTRY_IMAGE: ${{ contains(github.ref_name, 'cloud') && 'onyxdotapp/onyx-backend-cloud' || 'onyxdotapp/onyx-backend' }}
-  LATEST_TAG: ${{ contains(github.ref_name, 'latest') }}
+  REGISTRY_IMAGE: danswer/danswer-backend
 
 jobs:
   build-and-push:
-    # TODO: investigate a matrix build like the web container
-    # See https://runs-on.com/runners/linux/
-    runs-on: [runs-on, runner=8cpu-linux-x64, "run-id=${{ github.run_id }}"]
+    # TODO: make this a matrix build like the web containers
+    runs-on: 
+      group: amd64-image-builders
 
     steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
+    - name: Checkout code
+      uses: actions/checkout@v2
 
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
+    - name: Set up Docker Buildx
+      uses: docker/setup-buildx-action@v3
 
-      - name: Login to Docker Hub
-        uses: docker/login-action@v3
-        with:
-          username: ${{ secrets.DOCKER_USERNAME }}
-          password: ${{ secrets.DOCKER_TOKEN }}
+    - name: Login to Docker Hub
+      uses: docker/login-action@v3
+      with:
+        username: ${{ secrets.DOCKER_USERNAME }}
+        password: ${{ secrets.DOCKER_TOKEN }}
 
-      - name: Install build-essential
-        run: |
-          sudo apt-get update
-          sudo apt-get install -y build-essential
+    - name: Install build-essential
+      run: |
+        sudo apt-get update
+        sudo apt-get install -y build-essential
+        
+    - name: Backend Image Docker Build and Push
+      uses: docker/build-push-action@v5
+      with:
+        context: ./backend
+        file: ./backend/Dockerfile
+        platforms: linux/amd64,linux/arm64
+        push: true
+        tags: |
+          ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
+          ${{ env.REGISTRY_IMAGE }}:latest
+        build-args: |
+          DANSWER_VERSION=${{ github.ref_name }}
 
-      - name: Backend Image Docker Build and Push
-        uses: docker/build-push-action@v5
-        with:
-          context: ./backend
-          file: ./backend/Dockerfile
-          platforms: linux/amd64,linux/arm64
-          push: true
-          tags: |
-            ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
-            ${{ env.LATEST_TAG == 'true' && format('{0}:latest', env.REGISTRY_IMAGE) || '' }}
-          build-args: |
-            ONYX_VERSION=${{ github.ref_name }}
-
-      # trivy has their own rate limiting issues causing this action to flake
-      # we worked around it by hardcoding to different db repos in env
-      # can re-enable when they figure it out
-      # https://github.com/aquasecurity/trivy/discussions/7538
-      # https://github.com/aquasecurity/trivy-action/issues/389
-      - name: Run Trivy vulnerability scanner
-        uses: aquasecurity/trivy-action@master
-        env:
-          TRIVY_DB_REPOSITORY: "public.ecr.aws/aquasecurity/trivy-db:2"
-          TRIVY_JAVA_DB_REPOSITORY: "public.ecr.aws/aquasecurity/trivy-java-db:1"
-        with:
-          # To run locally: trivy image --severity HIGH,CRITICAL onyxdotapp/onyx-backend
-          image-ref: docker.io/${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
-          severity: "CRITICAL,HIGH"
-          trivyignores: ./backend/.trivyignore
+    - name: Run Trivy vulnerability scanner
+      uses: aquasecurity/trivy-action@master
+      with:
+        # To run locally: trivy image --severity HIGH,CRITICAL danswer/danswer-backend
+        image-ref: docker.io/${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
+        severity: 'CRITICAL,HIGH'
+        trivyignores: ./backend/.trivyignore

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

@@ -1,137 +0,0 @@
-name: Build and Push Cloud Web Image on Tag
-# Identical to the web container build, but with correct image tag and build args
-
-on:
-  push:
-    tags:
-      - "*"
-
-env:
-  REGISTRY_IMAGE: onyxdotapp/onyx-web-server-cloud
-  LATEST_TAG: ${{ contains(github.ref_name, 'latest') }}
-
-jobs:
-  build:
-    runs-on:
-      - runs-on
-      - runner=${{ matrix.platform == 'linux/amd64' && '8cpu-linux-x64' || '8cpu-linux-arm64' }}
-      - run-id=${{ github.run_id }}
-      - tag=platform-${{ matrix.platform }}
-    strategy:
-      fail-fast: false
-      matrix:
-        platform:
-          - linux/amd64
-          - linux/arm64
-
-    steps:
-      - name: Prepare
-        run: |
-          platform=${{ matrix.platform }}
-          echo "PLATFORM_PAIR=${platform//\//-}" >> $GITHUB_ENV
-
-      - name: Checkout
-        uses: actions/checkout@v4
-
-      - name: Docker meta
-        id: meta
-        uses: docker/metadata-action@v5
-        with:
-          images: ${{ env.REGISTRY_IMAGE }}
-          tags: |
-            type=raw,value=${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
-            type=raw,value=${{ env.LATEST_TAG == 'true' && format('{0}:latest', env.REGISTRY_IMAGE) || '' }}
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-
-      - name: Login to Docker Hub
-        uses: docker/login-action@v3
-        with:
-          username: ${{ secrets.DOCKER_USERNAME }}
-          password: ${{ secrets.DOCKER_TOKEN }}
-
-      - name: Build and push by digest
-        id: build
-        uses: docker/build-push-action@v5
-        with:
-          context: ./web
-          file: ./web/Dockerfile
-          platforms: ${{ matrix.platform }}
-          push: true
-          build-args: |
-            ONYX_VERSION=${{ github.ref_name }}
-            NEXT_PUBLIC_CLOUD_ENABLED=true
-            NEXT_PUBLIC_POSTHOG_KEY=${{ secrets.POSTHOG_KEY }}
-            NEXT_PUBLIC_POSTHOG_HOST=${{ secrets.POSTHOG_HOST }}
-            NEXT_PUBLIC_SENTRY_DSN=${{ secrets.SENTRY_DSN }}
-            NEXT_PUBLIC_GTM_ENABLED=true
-          # needed due to weird interactions with the builds for different platforms
-          no-cache: true
-          labels: ${{ steps.meta.outputs.labels }}
-          outputs: type=image,name=${{ env.REGISTRY_IMAGE }},push-by-digest=true,name-canonical=true,push=true
-
-      - name: Export digest
-        run: |
-          mkdir -p /tmp/digests
-          digest="${{ steps.build.outputs.digest }}"
-          touch "/tmp/digests/${digest#sha256:}"
-
-      - name: Upload digest
-        uses: actions/upload-artifact@v4
-        with:
-          name: digests-${{ env.PLATFORM_PAIR }}
-          path: /tmp/digests/*
-          if-no-files-found: error
-          retention-days: 1
-
-  merge:
-    runs-on: ubuntu-latest
-    needs:
-      - build
-    steps:
-      - name: Download digests
-        uses: actions/download-artifact@v4
-        with:
-          path: /tmp/digests
-          pattern: digests-*
-          merge-multiple: true
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-
-      - name: Docker meta
-        id: meta
-        uses: docker/metadata-action@v5
-        with:
-          images: ${{ env.REGISTRY_IMAGE }}
-
-      - name: Login to Docker Hub
-        uses: docker/login-action@v3
-        with:
-          username: ${{ secrets.DOCKER_USERNAME }}
-          password: ${{ secrets.DOCKER_TOKEN }}
-
-      - name: Create manifest list and push
-        working-directory: /tmp/digests
-        run: |
-          docker buildx imagetools create $(jq -cr '.tags | map("-t " + .) | join(" ")' <<< "$DOCKER_METADATA_OUTPUT_JSON") \
-            $(printf '${{ env.REGISTRY_IMAGE }}@sha256:%s ' *)
-
-      - name: Inspect image
-        run: |
-          docker buildx imagetools inspect ${{ env.REGISTRY_IMAGE }}:${{ steps.meta.outputs.version }}
-
-      # trivy has their own rate limiting issues causing this action to flake
-      # we worked around it by hardcoding to different db repos in env
-      # can re-enable when they figure it out
-      # https://github.com/aquasecurity/trivy/discussions/7538
-      # https://github.com/aquasecurity/trivy-action/issues/389
-      - name: Run Trivy vulnerability scanner
-        uses: aquasecurity/trivy-action@master
-        env:
-          TRIVY_DB_REPOSITORY: "public.ecr.aws/aquasecurity/trivy-db:2"
-          TRIVY_JAVA_DB_REPOSITORY: "public.ecr.aws/aquasecurity/trivy-java-db:1"
-        with:
-          image-ref: docker.io/${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
-          severity: "CRITICAL,HIGH"

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

@@ -3,121 +3,41 @@ name: Build and Push Model Server Image on Tag
 on:
   push:
     tags:
-      - "*"
-
-env:
-  REGISTRY_IMAGE: ${{ contains(github.ref_name, 'cloud') && 'onyxdotapp/onyx-model-server-cloud' || 'onyxdotapp/onyx-model-server' }}
-  LATEST_TAG: ${{ contains(github.ref_name, 'latest') }}
-  DOCKER_BUILDKIT: 1
-  BUILDKIT_PROGRESS: plain
+      - '*'
 
 jobs:
-  build-amd64:
-    runs-on:
-      [runs-on, runner=8cpu-linux-x64, "run-id=${{ github.run_id }}-amd64"]
+  build-and-push:
+    runs-on: 
+      group: amd64-image-builders
+
     steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
+    - name: Checkout code
+      uses: actions/checkout@v2
 
-      - name: System Info
-        run: |
-          df -h
-          free -h
-          docker system prune -af --volumes
+    - name: Set up Docker Buildx
+      uses: docker/setup-buildx-action@v3
 
-      - 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: Login to Docker Hub
-        uses: docker/login-action@v3
-        with:
-          username: ${{ secrets.DOCKER_USERNAME }}
-          password: ${{ secrets.DOCKER_TOKEN }}
+    - name: Model Server Image Docker Build and Push
+      uses: docker/build-push-action@v5
+      with:
+        context: ./backend
+        file: ./backend/Dockerfile.model_server
+        platforms: linux/amd64,linux/arm64
+        push: true
+        tags: |
+          danswer/danswer-model-server:${{ github.ref_name }}
+          danswer/danswer-model-server:latest
+        build-args: |
+          DANSWER_VERSION=${{ github.ref_name }}
 
-      - name: Build and Push AMD64
-        uses: docker/build-push-action@v5
-        with:
-          context: ./backend
-          file: ./backend/Dockerfile.model_server
-          platforms: linux/amd64
-          push: true
-          tags: ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}-amd64
-          build-args: |
-            DANSWER_VERSION=${{ github.ref_name }}
-          outputs: type=registry
-          provenance: false
-
-  build-arm64:
-    runs-on:
-      [runs-on, runner=8cpu-linux-x64, "run-id=${{ github.run_id }}-arm64"]
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-
-      - name: System Info
-        run: |
-          df -h
-          free -h
-          docker system prune -af --volumes
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-        with:
-          driver-opts: |
-            image=moby/buildkit:latest
-            network=host
-
-      - name: Login to Docker Hub
-        uses: docker/login-action@v3
-        with:
-          username: ${{ secrets.DOCKER_USERNAME }}
-          password: ${{ secrets.DOCKER_TOKEN }}
-
-      - name: Build and Push ARM64
-        uses: docker/build-push-action@v5
-        with:
-          context: ./backend
-          file: ./backend/Dockerfile.model_server
-          platforms: linux/arm64
-          push: true
-          tags: ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}-arm64
-          build-args: |
-            DANSWER_VERSION=${{ github.ref_name }}
-          outputs: type=registry
-          provenance: false
-
-  merge-and-scan:
-    needs: [build-amd64, build-arm64]
-    runs-on: ubuntu-latest
-    steps:
-      - name: Login to Docker Hub
-        uses: docker/login-action@v3
-        with:
-          username: ${{ secrets.DOCKER_USERNAME }}
-          password: ${{ secrets.DOCKER_TOKEN }}
-
-      - name: Create and Push Multi-arch Manifest
-        run: |
-          docker buildx create --use
-          docker buildx imagetools create -t ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }} \
-            ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}-amd64 \
-            ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}-arm64
-          if [[ "${{ env.LATEST_TAG }}" == "true" ]]; then
-            docker buildx imagetools create -t ${{ env.REGISTRY_IMAGE }}:latest \
-              ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}-amd64 \
-              ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}-arm64
-          fi
-
-      - name: Run Trivy vulnerability scanner
-        uses: aquasecurity/trivy-action@master
-        env:
-          TRIVY_DB_REPOSITORY: "public.ecr.aws/aquasecurity/trivy-db:2"
-          TRIVY_JAVA_DB_REPOSITORY: "public.ecr.aws/aquasecurity/trivy-java-db:1"
-        with:
-          image-ref: docker.io/onyxdotapp/onyx-model-server:${{ github.ref_name }}
-          severity: "CRITICAL,HIGH"
-          timeout: "10m"
+    - name: Run Trivy vulnerability scanner
+      uses: aquasecurity/trivy-action@master
+      with:
+        image-ref: docker.io/danswer/danswer-model-server:${{ github.ref_name }}
+        severity: 'CRITICAL,HIGH'

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

@@ -3,19 +3,15 @@ name: Build and Push Web Image on Tag
 on:
   push:
     tags:
-      - "*"
+      - '*'
 
 env:
-  REGISTRY_IMAGE: onyxdotapp/onyx-web-server
-  LATEST_TAG: ${{ contains(github.ref_name, 'latest') }}
+  REGISTRY_IMAGE: danswer/danswer-web-server
 
 jobs:
   build:
-    runs-on:
-      - runs-on
-      - runner=${{ matrix.platform == 'linux/amd64' && '8cpu-linux-x64' || '8cpu-linux-arm64' }}
-      - run-id=${{ github.run_id }}
-      - tag=platform-${{ matrix.platform }}
+    runs-on: 
+      group: ${{ matrix.platform == 'linux/amd64' && 'amd64-image-builders' || 'arm64-image-builders' }}
     strategy:
       fail-fast: false
       matrix:
@@ -27,11 +23,11 @@ jobs:
       - name: Prepare
         run: |
           platform=${{ 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
@@ -39,17 +35,17 @@ jobs:
           images: ${{ env.REGISTRY_IMAGE }}
           tags: |
             type=raw,value=${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
-            type=raw,value=${{ env.LATEST_TAG == 'true' && format('{0}:latest', env.REGISTRY_IMAGE) || '' }}
-
+            type=raw,value=${{ env.REGISTRY_IMAGE }}:latest
+      
       - 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 +55,18 @@ 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 +86,34 @@ 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
       - name: Run Trivy vulnerability scanner
         uses: aquasecurity/trivy-action@master
-        env:
-          TRIVY_DB_REPOSITORY: "public.ecr.aws/aquasecurity/trivy-db:2"
-          TRIVY_JAVA_DB_REPOSITORY: "public.ecr.aws/aquasecurity/trivy-java-db:1"
         with:
           image-ref: docker.io/${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
-          severity: "CRITICAL,HIGH"
+          severity: 'CRITICAL,HIGH'

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

@@ -1,37 +1,32 @@
-# This workflow is set up to be manually triggered via the GitHub Action tab.
-# Given a version, it will tag those backend and webserver images as "latest".
-
 name: Tag Latest Version
 
 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: ubuntu-latest
     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

@@ -1,171 +0,0 @@
-# This workflow is intended to be manually triggered via the GitHub Action tab.
-# Given a hotfix branch, it will attempt to open a PR to all release branches and
-# by default auto merge them
-
-name: Hotfix release branches
-
-on:
-  workflow_dispatch:
-    inputs:
-      hotfix_commit:
-        description: "Hotfix commit hash"
-        required: true
-      hotfix_suffix:
-        description: "Hotfix branch suffix (e.g. hotfix/v0.8-{suffix})"
-        required: true
-      release_branch_pattern:
-        description: "Release branch pattern (regex)"
-        required: true
-        default: "release/.*"
-      auto_merge:
-        description: "Automatically merge the hotfix PRs"
-        required: true
-        type: choice
-        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=${{ github.run_id }}"]
-    steps:
-      # needs RKUO_DEPLOY_KEY for write access to merge PR's
-      - name: Checkout Repository
-        uses: actions/checkout@v4
-        with:
-          ssh-key: "${{ 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"
-
-      - name: Fetch All Branches
-        run: |
-          git fetch --all --prune
-
-      - name: Verify Hotfix Commit Exists
-        run: |
-          git rev-parse --verify "${{ github.event.inputs.hotfix_commit }}" || { echo "Commit not found: ${{ github.event.inputs.hotfix_commit }}"; exit 1; }
-
-      - name: Get Release Branches
-        id: get_release_branches
-        run: |
-          BRANCHES=$(git branch -r | grep -E "${{ github.event.inputs.release_branch_pattern }}" | sed 's|origin/||' | tr -d ' ')
-          if [ -z "$BRANCHES" ]; then
-            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/,$//')
-
-          # Set the branches as an output
-          echo "branches=$BRANCHES_JOINED" >> $GITHUB_OUTPUT
-
-      # notes on all the vagaries of wiring up automated PR's
-      # https://github.com/peter-evans/create-pull-request/blob/main/docs/concepts-guidelines.md#triggering-further-workflow-runs
-      # we must use a custom token for GH_TOKEN to trigger the subsequent PR checks
-      - name: Create and Merge Pull Requests to Matching Release Branches
-        env:
-          HOTFIX_COMMIT: ${{ github.event.inputs.hotfix_commit }}
-          HOTFIX_SUFFIX: ${{ github.event.inputs.hotfix_suffix }}
-          AUTO_MERGE: ${{ github.event.inputs.auto_merge }}
-          GH_TOKEN: ${{ secrets.RKUO_PERSONAL_ACCESS_TOKEN }}
-        run: |
-          # Get the branches from the previous step
-          BRANCHES="${{ steps.get_release_branches.outputs.branches }}"
-
-          # Convert BRANCHES to an array
-          IFS=$',' read -ra BRANCH_ARRAY <<< "$BRANCHES"
-
-          # Loop through each release branch and create and merge a PR
-          for RELEASE_BRANCH in "${BRANCH_ARRAY[@]}"; do
-            echo "Processing $RELEASE_BRANCH..."
-            
-            # Parse out the release version by removing "release/" from the branch name
-            RELEASE_VERSION=${RELEASE_BRANCH#release/}
-            echo "Release version parsed: $RELEASE_VERSION"
-            
-            HOTFIX_BRANCH="hotfix/${RELEASE_VERSION}-${HOTFIX_SUFFIX}"
-            echo "Creating PR from $HOTFIX_BRANCH to $RELEASE_BRANCH"
-
-            # Checkout the release branch
-            echo "Checking out $RELEASE_BRANCH"
-            git checkout "$RELEASE_BRANCH"
-
-            # Create the new hotfix branch
-            if git rev-parse --verify "$HOTFIX_BRANCH" >/dev/null 2>&1; then
-              echo "Hotfix branch $HOTFIX_BRANCH already exists. Skipping branch creation."
-            else
-              echo "Branching $RELEASE_BRANCH to $HOTFIX_BRANCH"
-              git checkout -b "$HOTFIX_BRANCH"
-            fi
-            
-            # Check if the hotfix commit is a merge commit
-            if git rev-list --merges -n 1 "$HOTFIX_COMMIT" >/dev/null 2>&1; then
-              # -m 1 uses the target branch as the base (which is what we want)
-              echo "Hotfix commit $HOTFIX_COMMIT is a merge commit, using -m 1 for cherry-pick"
-              CHERRY_PICK_CMD="git cherry-pick -m 1 $HOTFIX_COMMIT"
-            else
-              CHERRY_PICK_CMD="git cherry-pick $HOTFIX_COMMIT"
-            fi
-
-            # Perform the cherry-pick
-            echo "Executing: $CHERRY_PICK_CMD"
-            eval "$CHERRY_PICK_CMD"
-
-            if [ $? -ne 0 ]; then
-              echo "Cherry-pick failed for $HOTFIX_COMMIT on $HOTFIX_BRANCH. Aborting..."
-              git cherry-pick --abort
-              continue
-            fi
-
-            # Push the hotfix branch to the remote
-            echo "Pushing $HOTFIX_BRANCH..."
-            git push origin "$HOTFIX_BRANCH"
-            echo "Hotfix branch $HOTFIX_BRANCH created and pushed."
-            
-            # Check if PR already exists
-            EXISTING_PR=$(gh pr list --head "$HOTFIX_BRANCH" --base "$RELEASE_BRANCH" --state open --json number --jq '.[0].number')
-
-            if [ -n "$EXISTING_PR" ]; then
-              echo "An open PR already exists: #$EXISTING_PR. Skipping..."
-              continue
-            fi
-            
-            # Create a new PR and capture the output
-            PR_OUTPUT=$(gh pr create --title "Merge $HOTFIX_BRANCH into $RELEASE_BRANCH" \
-              --body "Automated PR to merge \`$HOTFIX_BRANCH\` into \`$RELEASE_BRANCH\`." \
-              --head "$HOTFIX_BRANCH" --base "$RELEASE_BRANCH")
-
-            # Extract the URL from the output
-            PR_URL=$(echo "$PR_OUTPUT" | grep -Eo 'https://github.com/[^ ]+')
-            echo "Pull request created: $PR_URL"
-
-            # Extract PR number from URL
-            PR_NUMBER=$(basename "$PR_URL")
-            echo "Pull request created: $PR_NUMBER"
-
-            if [ "$AUTO_MERGE" == "true" ]; then
-              echo "Attempting to merge pull request #$PR_NUMBER"
-
-              # Attempt to merge the PR
-              gh pr merge "$PR_NUMBER" --merge --auto --delete-branch
-
-              if [ $? -eq 0 ]; then
-                echo "Pull request #$PR_NUMBER merged successfully."
-              else
-                # Optionally, handle the error or continue
-                echo "Failed to merge pull request #$PR_NUMBER."
-              fi
-            fi
-          done

.github/workflows/nightly-close-stale-issues.yml

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

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

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

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

@@ -1,124 +0,0 @@
-name: Backport on Merge
-
-# Note this workflow does not trigger the builds, be sure to manually tag the branches to trigger the builds
-
-on:
-  pull_request:
-    types: [closed] # Later we check for merge so only PRs that go in can get backported
-
-permissions:
-  contents: write
-  actions: write
-
-jobs:
-  backport:
-    if: github.event.pull_request.merged == true
-    runs-on: ubuntu-latest
-    env:
-      GITHUB_TOKEN: ${{ secrets.YUHONG_GH_ACTIONS }}
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-        with:
-          ssh-key: "${{ secrets.RKUO_DEPLOY_KEY }}"
-          fetch-depth: 0
-
-      - name: Set up Git user
-        run: |
-          git config user.name "Richard Kuo [bot]"
-          git config user.email "rkuo[bot]@onyx.app"
-          git fetch --prune
-
-      - name: Check for Backport Checkbox
-        id: checkbox-check
-        run: |
-          PR_BODY="${{ github.event.pull_request.body }}"
-          if [[ "$PR_BODY" == *"[x] This PR should be backported"* ]]; then
-            echo "backport=true" >> $GITHUB_OUTPUT
-          else
-            echo "backport=false" >> $GITHUB_OUTPUT
-          fi
-
-      - name: List and sort release branches
-        id: list-branches
-        run: |
-          git fetch --all --tags
-          BRANCHES=$(git for-each-ref --format='%(refname:short)' refs/remotes/origin/release/* | sed 's|origin/release/||' | sort -Vr)
-          BETA=$(echo "$BRANCHES" | head -n 1)
-          STABLE=$(echo "$BRANCHES" | head -n 2 | tail -n 1)
-          echo "beta=release/$BETA" >> $GITHUB_OUTPUT
-          echo "stable=release/$STABLE" >> $GITHUB_OUTPUT
-          # Fetch latest tags for beta and stable
-          LATEST_BETA_TAG=$(git tag -l "v[0-9]*.[0-9]*.[0-9]*-beta.[0-9]*" | grep -E "^v[0-9]+\.[0-9]+\.[0-9]+-beta\.[0-9]+$" | grep -v -- "-cloud" | sort -Vr | head -n 1)
-          LATEST_STABLE_TAG=$(git tag -l "v[0-9]*.[0-9]*.[0-9]*" | grep -E "^v[0-9]+\.[0-9]+\.[0-9]+$" | sort -Vr | head -n 1)
-
-          # Handle case where no beta tags exist
-          if [[ -z "$LATEST_BETA_TAG" ]]; then
-            NEW_BETA_TAG="v1.0.0-beta.1"
-          else
-            NEW_BETA_TAG=$(echo $LATEST_BETA_TAG | awk -F '[.-]' '{print $1 "." $2 "." $3 "-beta." ($NF+1)}')
-          fi
-
-          # Increment latest stable tag
-          NEW_STABLE_TAG=$(echo $LATEST_STABLE_TAG | awk -F '.' '{print $1 "." $2 "." ($3+1)}')
-          echo "latest_beta_tag=$LATEST_BETA_TAG" >> $GITHUB_OUTPUT
-          echo "latest_stable_tag=$LATEST_STABLE_TAG" >> $GITHUB_OUTPUT
-          echo "new_beta_tag=$NEW_BETA_TAG" >> $GITHUB_OUTPUT
-          echo "new_stable_tag=$NEW_STABLE_TAG" >> $GITHUB_OUTPUT
-
-      - name: Echo branch and tag information
-        run: |
-          echo "Beta branch: ${{ steps.list-branches.outputs.beta }}"
-          echo "Stable branch: ${{ steps.list-branches.outputs.stable }}"
-          echo "Latest beta tag: ${{ steps.list-branches.outputs.latest_beta_tag }}"
-          echo "Latest stable tag: ${{ steps.list-branches.outputs.latest_stable_tag }}"
-          echo "New beta tag: ${{ steps.list-branches.outputs.new_beta_tag }}"
-          echo "New stable tag: ${{ steps.list-branches.outputs.new_stable_tag }}"
-
-      - name: Trigger Backport
-        if: steps.checkbox-check.outputs.backport == 'true'
-        run: |
-          set -e
-          echo "Backporting to beta ${{ steps.list-branches.outputs.beta }} and stable ${{ steps.list-branches.outputs.stable }}"
-
-          # Echo the merge commit SHA
-          echo "Merge commit SHA: ${{ github.event.pull_request.merge_commit_sha }}"
-
-          # Fetch all history for all branches and tags
-          git fetch --prune
-
-          # Reset and prepare the beta branch
-          git checkout ${{ steps.list-branches.outputs.beta }}
-          echo "Last 5 commits on beta branch:"
-          git log -n 5 --pretty=format:"%H"
-          echo ""  # Newline for formatting
-
-          # Cherry-pick the merge commit from the merged PR
-          git cherry-pick -m 1 ${{ github.event.pull_request.merge_commit_sha }} || {
-            echo "Cherry-pick to beta failed due to conflicts."
-            exit 1
-          }
-
-          # Create new beta branch/tag
-          git tag ${{ steps.list-branches.outputs.new_beta_tag }}
-          # Push the changes and tag to the beta branch using PAT
-          git push origin ${{ steps.list-branches.outputs.beta }}
-          git push origin ${{ steps.list-branches.outputs.new_beta_tag }}
-
-          # Reset and prepare the stable branch
-          git checkout ${{ steps.list-branches.outputs.stable }}
-          echo "Last 5 commits on stable branch:"
-          git log -n 5 --pretty=format:"%H"
-          echo ""  # Newline for formatting
-
-          # Cherry-pick the merge commit from the merged PR
-          git cherry-pick -m 1 ${{ github.event.pull_request.merge_commit_sha }} || {
-            echo "Cherry-pick to stable failed due to conflicts."
-            exit 1
-          }
-
-          # Create new stable branch/tag
-          git tag ${{ steps.list-branches.outputs.new_stable_tag }}
-          # Push the changes and tag to the stable branch using PAT
-          git push origin ${{ steps.list-branches.outputs.stable }}
-          git push origin ${{ steps.list-branches.outputs.new_stable_tag }}

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

@@ -1,238 +0,0 @@
-name: Run Chromatic Tests
-concurrency:
-  group: Run-Chromatic-Tests-${{ github.workflow }}-${{ github.head_ref || github.event.workflow_run.head_branch || github.run_id }}
-  cancel-in-progress: true
-
-on: push
-
-env:
-  OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-  SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
-
-jobs:
-  playwright-tests:
-    name: Playwright Tests
-
-    # See https://runs-on.com/runners/linux/
-    runs-on:
-      [
-        runs-on,
-        runner=32cpu-linux-x64,
-        disk=large,
-        "run-id=${{ github.run_id }}",
-      ]
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.11"
-          cache: "pip"
-          cache-dependency-path: |
-            backend/requirements/default.txt
-            backend/requirements/dev.txt
-            backend/requirements/model_server.txt
-      - run: |
-          python -m pip install --upgrade pip
-          pip install --retries 5 --timeout 30 -r backend/requirements/default.txt
-          pip install --retries 5 --timeout 30 -r backend/requirements/dev.txt
-          pip install --retries 5 --timeout 30 -r backend/requirements/model_server.txt
-
-      - name: Setup node
-        uses: actions/setup-node@v4
-        with:
-          node-version: 22
-
-      - name: Install node dependencies
-        working-directory: ./web
-        run: npm ci
-
-      - name: Install playwright browsers
-        working-directory: ./web
-        run: npx playwright install --with-deps
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-
-      - name: Login to Docker Hub
-        uses: docker/login-action@v3
-        with:
-          username: ${{ secrets.DOCKER_USERNAME }}
-          password: ${{ secrets.DOCKER_TOKEN }}
-
-      # tag every docker image with "test" so that we can spin up the correct set
-      # of images during testing
-
-      # we use the runs-on cache for docker builds
-      # in conjunction with runs-on runners, it has better speed and unlimited caching
-      # https://runs-on.com/caching/s3-cache-for-github-actions/
-      # https://runs-on.com/caching/docker/
-      # https://github.com/moby/buildkit#s3-cache-experimental
-
-      # images are built and run locally for testing purposes. Not pushed.
-
-      - name: Build Web Docker image
-        uses: ./.github/actions/custom-build-and-push
-        with:
-          context: ./web
-          file: ./web/Dockerfile
-          platforms: linux/amd64
-          tags: onyxdotapp/onyx-web-server:test
-          push: false
-          load: true
-          cache-from: type=s3,prefix=cache/${{ github.repository }}/integration-tests/web-server/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }}
-          cache-to: type=s3,prefix=cache/${{ github.repository }}/integration-tests/web-server/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }},mode=max
-
-      - name: Build Backend Docker image
-        uses: ./.github/actions/custom-build-and-push
-        with:
-          context: ./backend
-          file: ./backend/Dockerfile
-          platforms: linux/amd64
-          tags: onyxdotapp/onyx-backend:test
-          push: false
-          load: true
-          cache-from: type=s3,prefix=cache/${{ github.repository }}/integration-tests/backend/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }}
-          cache-to: type=s3,prefix=cache/${{ github.repository }}/integration-tests/backend/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }},mode=max
-
-      - name: Build Model Server Docker image
-        uses: ./.github/actions/custom-build-and-push
-        with:
-          context: ./backend
-          file: ./backend/Dockerfile.model_server
-          platforms: linux/amd64
-          tags: onyxdotapp/onyx-model-server:test
-          push: false
-          load: true
-          cache-from: type=s3,prefix=cache/${{ github.repository }}/integration-tests/model-server/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }}
-          cache-to: type=s3,prefix=cache/${{ github.repository }}/integration-tests/model-server/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }},mode=max
-
-      - name: Start Docker containers
-        run: |
-          cd deployment/docker_compose
-          ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true \
-          AUTH_TYPE=basic \
-          GEN_AI_API_KEY=${{ secrets.OPENAI_API_KEY }} \
-          REQUIRE_EMAIL_VERIFICATION=false \
-          DISABLE_TELEMETRY=true \
-          IMAGE_TAG=test \
-          docker compose -f docker-compose.dev.yml -p danswer-stack up -d
-        id: start_docker
-
-      - name: Wait for service to be ready
-        run: |
-          echo "Starting wait-for-service script..."
-
-          docker logs -f danswer-stack-api_server-1 &
-
-          start_time=$(date +%s)
-          timeout=300  # 5 minutes in seconds
-
-          while true; do
-            current_time=$(date +%s)
-            elapsed_time=$((current_time - start_time))
-            
-            if [ $elapsed_time -ge $timeout ]; then
-              echo "Timeout reached. Service did not become ready in 5 minutes."
-              exit 1
-            fi
-            
-            # Use curl with error handling to ignore specific exit code 56
-            response=$(curl -s -o /dev/null -w "%{http_code}" http://localhost:8080/health || echo "curl_error")
-            
-            if [ "$response" = "200" ]; then
-              echo "Service is ready!"
-              break
-            elif [ "$response" = "curl_error" ]; then
-              echo "Curl encountered an error, possibly exit code 56. Continuing to retry..."
-            else
-              echo "Service not ready yet (HTTP status $response). Retrying in 5 seconds..."
-            fi
-            
-            sleep 5
-          done
-          echo "Finished waiting for service."
-
-      - name: Run pytest playwright test init
-        working-directory: ./backend
-        env:
-          PYTEST_IGNORE_SKIP: true
-        run: pytest -s tests/integration/tests/playwright/test_playwright.py
-
-      - name: Run Playwright tests
-        working-directory: ./web
-        run: npx playwright test
-
-      - uses: actions/upload-artifact@v4
-        if: always()
-        with:
-          # Chromatic automatically defaults to the test-results directory.
-          # Replace with the path to your custom directory and adjust the CHROMATIC_ARCHIVE_LOCATION environment variable accordingly.
-          name: test-results
-          path: ./web/test-results
-          retention-days: 30
-
-      # save before stopping the containers so the logs can be captured
-      - name: Save Docker logs
-        if: success() || failure()
-        run: |
-          cd deployment/docker_compose
-          docker compose -f docker-compose.dev.yml -p danswer-stack logs > docker-compose.log
-          mv docker-compose.log ${{ github.workspace }}/docker-compose.log
-
-      - name: Upload logs
-        if: success() || failure()
-        uses: actions/upload-artifact@v4
-        with:
-          name: docker-logs
-          path: ${{ github.workspace }}/docker-compose.log
-
-      - name: Stop Docker containers
-        run: |
-          cd deployment/docker_compose
-          docker compose -f docker-compose.dev.yml -p danswer-stack down -v
-
-  chromatic-tests:
-    name: Chromatic Tests
-
-    needs: playwright-tests
-    runs-on:
-      [
-        runs-on,
-        runner=32cpu-linux-x64,
-        disk=large,
-        "run-id=${{ github.run_id }}",
-      ]
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-
-      - name: Setup node
-        uses: actions/setup-node@v4
-        with:
-          node-version: 22
-
-      - name: Install node dependencies
-        working-directory: ./web
-        run: npm ci
-
-      - name: Download Playwright test results
-        uses: actions/download-artifact@v4
-        with:
-          name: test-results
-          path: ./web/test-results
-
-      - name: Run Chromatic
-        uses: chromaui/action@latest
-        with:
-          playwright: true
-          projectToken: ${{ secrets.CHROMATIC_PROJECT_TOKEN }}
-          workingDir: ./web
-        env:
-          CHROMATIC_ARCHIVE_LOCATION: ./test-results

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

@@ -1,72 +0,0 @@
-name: Helm - Lint and Test Charts
-
-on:
-  merge_group:
-  pull_request:
-    branches: [ main ]
-  workflow_dispatch:  # Allows manual triggering
-  
-jobs:
-  helm-chart-check:
-    # See https://runs-on.com/runners/linux/
-    runs-on: [runs-on,runner=8cpu-linux-x64,hdd=256,"run-id=${{ github.run_id }}"]
-
-    # fetch-depth 0 is required for helm/chart-testing-action
-    steps:
-    - name: Checkout code
-      uses: actions/checkout@v4
-      with:
-        fetch-depth: 0
-        
-    - name: Set up Helm
-      uses: azure/setup-helm@v4.2.0
-      with:
-        version: v3.14.4
-      
-    - name: Set up chart-testing
-      uses: helm/chart-testing-action@v2.6.1
-
-    # even though we specify chart-dirs in ct.yaml, it isn't used by ct for the list-changed command...
-    - name: Run chart-testing (list-changed)
-      id: list-changed
-      run: |
-        echo "default_branch: ${{ github.event.repository.default_branch }}"
-        changed=$(ct list-changed --remote origin --target-branch ${{ github.event.repository.default_branch }} --chart-dirs deployment/helm/charts)
-        echo "list-changed output: $changed"
-        if [[ -n "$changed" ]]; then
-          echo "changed=true" >> "$GITHUB_OUTPUT"
-        fi
-
-#     rkuo: I don't think we need python?
-#     - name: Set up Python
-#       uses: actions/setup-python@v5
-#       with:
-#         python-version: '3.11'
-#         cache: 'pip'
-#         cache-dependency-path: |
-#           backend/requirements/default.txt
-#           backend/requirements/dev.txt
-#           backend/requirements/model_server.txt
-#     - run: |
-#         python -m pip install --upgrade pip
-#         pip install --retries 5 --timeout 30 -r backend/requirements/default.txt
-#         pip install --retries 5 --timeout 30 -r backend/requirements/dev.txt
-#         pip install --retries 5 --timeout 30 -r backend/requirements/model_server.txt
-
-    # lint all charts if any changes were detected
-    - name: Run chart-testing (lint)
-      if: steps.list-changed.outputs.changed == 'true'
-      run: ct lint --config ct.yaml --all
-      # the following would lint only changed charts, but linting isn't expensive
-      # run: ct lint --config ct.yaml --target-branch ${{ github.event.repository.default_branch }}
-
-    - name: Create kind cluster
-      if: steps.list-changed.outputs.changed == 'true'
-      uses: helm/kind-action@v1.10.0
-
-    - name: Run chart-testing (install)
-      if: steps.list-changed.outputs.changed == 'true'
-      run: ct install --all --helm-extra-set-args="--set=nginx.enabled=false" --debug --config ct.yaml
-      # the following would install only changed charts, but we only have one chart so 
-      # don't worry about that for now
-      # run: ct install --target-branch ${{ github.event.repository.default_branch }}

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

@@ -0,0 +1,67 @@
+# This workflow is intentionally disabled while we're still working on it
+# It's close to ready, but a race condition needs to be fixed with
+# API server and Vespa startup, and it needs to have a way to build/test against
+# local containers
+
+name: Helm - Lint and Test Charts
+
+on:
+  merge_group:
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  lint-test:
+    runs-on: Amd64
+
+    # fetch-depth 0 is required for helm/chart-testing-action
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v3
+      with:
+        fetch-depth: 0
+        
+    - name: Set up Helm
+      uses: azure/setup-helm@v4.2.0
+      with:
+        version: v3.14.4
+      
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.11'
+        cache: 'pip'
+        cache-dependency-path: |
+          backend/requirements/default.txt
+          backend/requirements/dev.txt
+          backend/requirements/model_server.txt
+    - run: |
+        python -m pip install --upgrade pip
+        pip install --retries 5 --timeout 30 -r backend/requirements/default.txt
+        pip install --retries 5 --timeout 30 -r backend/requirements/dev.txt
+        pip install --retries 5 --timeout 30 -r backend/requirements/model_server.txt
+
+    - name: Set up chart-testing
+      uses: helm/chart-testing-action@v2.6.1
+
+    - name: Run chart-testing (list-changed)
+      id: list-changed
+      run: |
+        changed=$(ct list-changed --target-branch ${{ github.event.repository.default_branch }})
+        if [[ -n "$changed" ]]; then
+          echo "changed=true" >> "$GITHUB_OUTPUT"
+        fi
+
+    - name: Run chart-testing (lint)
+#       if: steps.list-changed.outputs.changed == 'true'
+      run: ct lint --all --config ct.yaml --target-branch ${{ github.event.repository.default_branch }}
+
+    - name: Create kind cluster
+#       if: steps.list-changed.outputs.changed == 'true'
+      uses: helm/kind-action@v1.10.0
+
+    - name: Run chart-testing (install)
+#       if: steps.list-changed.outputs.changed == 'true'
+      run: ct install --all --config ct.yaml
+#       run: ct install --target-branch ${{ github.event.repository.default_branch }}
+      

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

@@ -1,242 +0,0 @@
-name: Run Integration Tests v2
-concurrency:
-  group: Run-Integration-Tests-${{ github.workflow }}-${{ github.head_ref || github.event.workflow_run.head_branch || github.run_id }}
-  cancel-in-progress: true
-
-on:
-  merge_group:
-  pull_request:
-    branches:
-      - main
-      - "release/**"
-
-env:
-  OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-  SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
-  CONFLUENCE_TEST_SPACE_URL: ${{ secrets.CONFLUENCE_TEST_SPACE_URL }}
-  CONFLUENCE_USER_NAME: ${{ secrets.CONFLUENCE_USER_NAME }}
-  CONFLUENCE_ACCESS_TOKEN: ${{ secrets.CONFLUENCE_ACCESS_TOKEN }}
-
-jobs:
-  integration-tests:
-    # See https://runs-on.com/runners/linux/
-    runs-on: [runs-on, runner=32cpu-linux-x64, "run-id=${{ github.run_id }}"]
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-
-      - name: Login to Docker Hub
-        uses: docker/login-action@v3
-        with:
-          username: ${{ secrets.DOCKER_USERNAME }}
-          password: ${{ secrets.DOCKER_TOKEN }}
-
-      # tag every docker image with "test" so that we can spin up the correct set
-      # of images during testing
-
-      # We don't need to build the Web Docker image since it's not yet used
-      # in the integration tests. We have a separate action to verify that it builds
-      # successfully.
-      - name: Pull Web Docker image
-        run: |
-          docker pull onyxdotapp/onyx-web-server:latest
-          docker tag onyxdotapp/onyx-web-server:latest onyxdotapp/onyx-web-server:test
-
-      # we use the runs-on cache for docker builds
-      # in conjunction with runs-on runners, it has better speed and unlimited caching
-      # https://runs-on.com/caching/s3-cache-for-github-actions/
-      # https://runs-on.com/caching/docker/
-      # https://github.com/moby/buildkit#s3-cache-experimental
-
-      # images are built and run locally for testing purposes. Not pushed.
-      - name: Build Backend Docker image
-        uses: ./.github/actions/custom-build-and-push
-        with:
-          context: ./backend
-          file: ./backend/Dockerfile
-          platforms: linux/amd64
-          tags: onyxdotapp/onyx-backend:test
-          push: false
-          load: true
-          cache-from: type=s3,prefix=cache/${{ github.repository }}/integration-tests/backend/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }}
-          cache-to: type=s3,prefix=cache/${{ github.repository }}/integration-tests/backend/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }},mode=max
-
-      - name: Build Model Server Docker image
-        uses: ./.github/actions/custom-build-and-push
-        with:
-          context: ./backend
-          file: ./backend/Dockerfile.model_server
-          platforms: linux/amd64
-          tags: onyxdotapp/onyx-model-server:test
-          push: false
-          load: true
-          cache-from: type=s3,prefix=cache/${{ github.repository }}/integration-tests/model-server/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }}
-          cache-to: type=s3,prefix=cache/${{ github.repository }}/integration-tests/model-server/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }},mode=max
-
-      - name: Build integration test Docker image
-        uses: ./.github/actions/custom-build-and-push
-        with:
-          context: ./backend
-          file: ./backend/tests/integration/Dockerfile
-          platforms: linux/amd64
-          tags: onyxdotapp/onyx-integration:test
-          push: false
-          load: true
-          cache-from: type=s3,prefix=cache/${{ github.repository }}/integration-tests/integration/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }}
-          cache-to: type=s3,prefix=cache/${{ github.repository }}/integration-tests/integration/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }},mode=max
-
-      # Start containers for multi-tenant tests
-      - name: Start Docker containers for multi-tenant tests
-        run: |
-          cd deployment/docker_compose
-          ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true \
-          MULTI_TENANT=true \
-          AUTH_TYPE=basic \
-          REQUIRE_EMAIL_VERIFICATION=false \
-          DISABLE_TELEMETRY=true \
-          IMAGE_TAG=test \
-          docker compose -f docker-compose.dev.yml -p danswer-stack up -d
-        id: start_docker_multi_tenant
-
-      # In practice, `cloud` Auth type would require OAUTH credentials to be set.
-      - name: Run Multi-Tenant Integration Tests
-        run: |
-          echo "Running integration tests..."
-          docker run --rm --network danswer-stack_default \
-            --name test-runner \
-            -e POSTGRES_HOST=relational_db \
-            -e POSTGRES_USER=postgres \
-            -e POSTGRES_PASSWORD=password \
-            -e POSTGRES_DB=postgres \
-            -e VESPA_HOST=index \
-            -e REDIS_HOST=cache \
-            -e API_SERVER_HOST=api_server \
-            -e OPENAI_API_KEY=${OPENAI_API_KEY} \
-            -e SLACK_BOT_TOKEN=${SLACK_BOT_TOKEN} \
-            -e TEST_WEB_HOSTNAME=test-runner \
-            -e AUTH_TYPE=cloud \
-            -e MULTI_TENANT=true \
-            onyxdotapp/onyx-integration:test \
-            /app/tests/integration/multitenant_tests
-        continue-on-error: true
-        id: run_multitenant_tests
-
-      - name: Check multi-tenant test results
-        run: |
-          if [ ${{ steps.run_tests.outcome }} == 'failure' ]; then
-            echo "Integration tests failed. Exiting with error."
-            exit 1
-          else
-            echo "All integration tests passed successfully."
-          fi
-
-      - name: Stop multi-tenant Docker containers
-        run: |
-          cd deployment/docker_compose
-          docker compose -f docker-compose.dev.yml -p danswer-stack down -v
-
-      - name: Start Docker containers
-        run: |
-          cd deployment/docker_compose
-          ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true \
-          AUTH_TYPE=basic \
-          REQUIRE_EMAIL_VERIFICATION=false \
-          DISABLE_TELEMETRY=true \
-          IMAGE_TAG=test \
-          docker compose -f docker-compose.dev.yml -p danswer-stack up -d
-        id: start_docker
-
-      - name: Wait for service to be ready
-        run: |
-          echo "Starting wait-for-service script..."
-
-          docker logs -f danswer-stack-api_server-1 &
-
-          start_time=$(date +%s)
-          timeout=300  # 5 minutes in seconds
-
-          while true; do
-            current_time=$(date +%s)
-            elapsed_time=$((current_time - start_time))
-            
-            if [ $elapsed_time -ge $timeout ]; then
-              echo "Timeout reached. Service did not become ready in 5 minutes."
-              exit 1
-            fi
-            
-            # Use curl with error handling to ignore specific exit code 56
-            response=$(curl -s -o /dev/null -w "%{http_code}" http://localhost:8080/health || echo "curl_error")
-            
-            if [ "$response" = "200" ]; then
-              echo "Service is ready!"
-              break
-            elif [ "$response" = "curl_error" ]; then
-              echo "Curl encountered an error, possibly exit code 56. Continuing to retry..."
-            else
-              echo "Service not ready yet (HTTP status $response). Retrying in 5 seconds..."
-            fi
-            
-            sleep 5
-          done
-          echo "Finished waiting for service."
-
-      - name: Run Standard Integration Tests
-        run: |
-          echo "Running integration tests..."
-          docker run --rm --network danswer-stack_default \
-            --name test-runner \
-            -e POSTGRES_HOST=relational_db \
-            -e POSTGRES_USER=postgres \
-            -e POSTGRES_PASSWORD=password \
-            -e POSTGRES_DB=postgres \
-            -e VESPA_HOST=index \
-            -e REDIS_HOST=cache \
-            -e API_SERVER_HOST=api_server \
-            -e OPENAI_API_KEY=${OPENAI_API_KEY} \
-            -e SLACK_BOT_TOKEN=${SLACK_BOT_TOKEN} \
-            -e CONFLUENCE_TEST_SPACE_URL=${CONFLUENCE_TEST_SPACE_URL} \
-            -e CONFLUENCE_USER_NAME=${CONFLUENCE_USER_NAME} \
-            -e CONFLUENCE_ACCESS_TOKEN=${CONFLUENCE_ACCESS_TOKEN} \
-            -e TEST_WEB_HOSTNAME=test-runner \
-            onyxdotapp/onyx-integration:test \
-            /app/tests/integration/tests \
-            /app/tests/integration/connector_job_tests
-        continue-on-error: true
-        id: run_tests
-
-      - name: Check test results
-        run: |
-          if [ ${{ steps.run_tests.outcome }} == 'failure' ]; then
-            echo "Integration tests failed. Exiting with error."
-            exit 1
-          else
-            echo "All integration tests passed successfully."
-          fi
-
-      # save before stopping the containers so the logs can be captured
-      - name: Save Docker logs
-        if: success() || failure()
-        run: |
-          cd deployment/docker_compose
-          docker compose -f docker-compose.dev.yml -p danswer-stack logs > docker-compose.log
-          mv docker-compose.log ${{ github.workspace }}/docker-compose.log
-
-      - name: Stop Docker containers
-        run: |
-          cd deployment/docker_compose
-          docker compose -f docker-compose.dev.yml -p danswer-stack down -v
-
-      - name: Upload logs
-        if: success() || failure()
-        uses: actions/upload-artifact@v4
-        with:
-          name: docker-logs
-          path: ${{ github.workspace }}/docker-compose.log
-
-      - name: Stop Docker containers
-        run: |
-          cd deployment/docker_compose
-          docker compose -f docker-compose.dev.yml -p danswer-stack down -v

.github/workflows/pr-python-checks.yml

@@ -3,21 +3,18 @@ name: Python Checks
 on:
   merge_group:
   pull_request:
-    branches:
-      - main
-      - 'release/**'
+    branches: [ main ]
 
 jobs:
   mypy-check:
-    # See https://runs-on.com/runners/linux/
-    runs-on: [runs-on,runner=8cpu-linux-x64,"run-id=${{ github.run_id }}"]
+    runs-on: ubuntu-latest
 
     steps:
     - name: Checkout code
-      uses: actions/checkout@v4
+      uses: actions/checkout@v3
 
     - name: Set up Python
-      uses: actions/setup-python@v5
+      uses: actions/setup-python@v4
       with:
         python-version: '3.11'
         cache: 'pip'

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

@@ -15,22 +15,10 @@ env:
   CONFLUENCE_TEST_PAGE_ID: ${{ secrets.CONFLUENCE_TEST_PAGE_ID }}
   CONFLUENCE_USER_NAME: ${{ secrets.CONFLUENCE_USER_NAME }}
   CONFLUENCE_ACCESS_TOKEN: ${{ secrets.CONFLUENCE_ACCESS_TOKEN }}
-  # Jira
-  JIRA_USER_EMAIL: ${{ secrets.JIRA_USER_EMAIL }}
-  JIRA_API_TOKEN: ${{ secrets.JIRA_API_TOKEN }}
-  # Google
-  GOOGLE_DRIVE_SERVICE_ACCOUNT_JSON_STR: ${{ secrets.GOOGLE_DRIVE_SERVICE_ACCOUNT_JSON_STR }}
-  GOOGLE_DRIVE_OAUTH_CREDENTIALS_JSON_STR_TEST_USER_1: ${{ secrets.GOOGLE_DRIVE_OAUTH_CREDENTIALS_JSON_STR_TEST_USER_1 }}
-  GOOGLE_DRIVE_OAUTH_CREDENTIALS_JSON_STR: ${{ secrets.GOOGLE_DRIVE_OAUTH_CREDENTIALS_JSON_STR }}
-  GOOGLE_GMAIL_SERVICE_ACCOUNT_JSON_STR: ${{ secrets.GOOGLE_GMAIL_SERVICE_ACCOUNT_JSON_STR }}
-  GOOGLE_GMAIL_OAUTH_CREDENTIALS_JSON_STR: ${{ secrets.GOOGLE_GMAIL_OAUTH_CREDENTIALS_JSON_STR }}
-  # Slab
-  SLAB_BOT_TOKEN: ${{ secrets.SLAB_BOT_TOKEN }}
 
 jobs:
   connectors-check:
-    # See https://runs-on.com/runners/linux/
-    runs-on: [runs-on,runner=8cpu-linux-x64,"run-id=${{ github.run_id }}"]
+    runs-on: ubuntu-latest
 
     env:
       PYTHONPATH: ./backend
@@ -40,7 +28,7 @@ jobs:
         uses: actions/checkout@v4
 
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v4
         with:
           python-version: "3.11"
           cache: "pip"

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

@@ -1,58 +0,0 @@
-name: Connector Tests
-
-on:
-  schedule:
-    # This cron expression runs the job daily at 16:00 UTC (9am PT)
-    - cron: "0 16 * * *"
-
-env:
-  # Bedrock
-  AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
-  AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
-  AWS_REGION_NAME: ${{ secrets.AWS_REGION_NAME }}
-
-  # OpenAI
-  OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-
-jobs:
-  model-check:
-    # See https://runs-on.com/runners/linux/
-    runs-on: [runs-on,runner=8cpu-linux-x64,"run-id=${{ github.run_id }}"]
-
-    env:
-      PYTHONPATH: ./backend
-
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.11"
-          cache: "pip"
-          cache-dependency-path: |
-            backend/requirements/default.txt
-            backend/requirements/dev.txt
-
-      - name: Install Dependencies
-        run: |
-          python -m pip install --upgrade pip
-          pip install --retries 5 --timeout 30 -r backend/requirements/default.txt
-          pip install --retries 5 --timeout 30 -r backend/requirements/dev.txt
-
-      - name: Run Tests
-        shell: script -q -e -c "bash --noprofile --norc -eo pipefail {0}"
-        run: |
-          py.test -o junit_family=xunit2 -xv --ff backend/tests/daily/llm
-          py.test -o junit_family=xunit2 -xv --ff backend/tests/daily/embedding
-
-      - name: Alert on Failure
-        if: failure() && github.event_name == 'schedule'
-        env:
-          SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
-        run: |
-          curl -X POST \
-            -H 'Content-type: application/json' \
-            --data '{"text":"Scheduled Model Tests failed! Check the run at: https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}"}' \
-            $SLACK_WEBHOOK

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

@@ -3,14 +3,11 @@ name: Python Unit Tests
 on:
   merge_group:
   pull_request:
-    branches:
-      - main
-      - 'release/**'
+    branches: [ main ]
 
 jobs:
   backend-check:
-    # See https://runs-on.com/runners/linux/
-    runs-on: [runs-on,runner=8cpu-linux-x64,"run-id=${{ github.run_id }}"]
+    runs-on: ubuntu-latest
 
     env:
       PYTHONPATH: ./backend
@@ -21,7 +18,7 @@ jobs:
       uses: actions/checkout@v4
 
     - name: Set up Python
-      uses: actions/setup-python@v5
+      uses: actions/setup-python@v4
       with:
         python-version: '3.11'
         cache: 'pip'

.github/workflows/pr-quality-checks.yml

@@ -1,6 +1,6 @@
 name: Quality Checks PR
 concurrency:
-  group: Quality-Checks-PR-${{ github.workflow }}-${{ github.head_ref || github.event.workflow_run.head_branch || github.run_id }}
+  group: Quality-Checks-PR-${{ github.head_ref }}
   cancel-in-progress: true
 
 on:
@@ -9,8 +9,7 @@ on:
 
 jobs:
   quality-checks:
-    # See https://runs-on.com/runners/linux/
-    runs-on: [runs-on,runner=8cpu-linux-x64,"run-id=${{ github.run_id }}"]
+    runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
         with:
@@ -18,6 +17,6 @@ jobs:
       - uses: actions/setup-python@v5
         with:
           python-version: "3.11"
-      - uses: pre-commit/action@v3.0.1
+      - uses: pre-commit/action@v3.0.0
         with:
           extra_args: ${{ github.event_name == 'pull_request' && format('--from-ref {0} --to-ref {1}', github.event.pull_request.base.sha, github.event.pull_request.head.sha) || '' }}

.github/workflows/run-it.yml

@@ -0,0 +1,161 @@
+name: Run Integration Tests
+concurrency:
+  group: Run-Integration-Tests-${{ github.head_ref }}
+  cancel-in-progress: true
+
+on:
+  merge_group:
+  pull_request:
+    branches: [ main ]
+
+env:
+  OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+
+jobs:
+  integration-tests:
+    runs-on: Amd64
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - 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 }}
+
+      # NOTE: we don't need to build the Web Docker image since it's not used
+      # during the IT for now. We have a separate action to verify it builds 
+      # succesfully
+      - name: Pull Web Docker image
+        run: |
+          docker pull danswer/danswer-web-server:latest
+          docker tag danswer/danswer-web-server:latest danswer/danswer-web-server:it
+
+      - name: Build Backend Docker image
+        uses: ./.github/actions/custom-build-and-push
+        with:
+          context: ./backend
+          file: ./backend/Dockerfile
+          platforms: linux/amd64
+          tags: danswer/danswer-backend:it
+          cache-from: type=registry,ref=danswer/danswer-backend:it
+          cache-to: |
+            type=registry,ref=danswer/danswer-backend:it,mode=max
+            type=inline
+
+      - name: Build Model Server Docker image
+        uses: ./.github/actions/custom-build-and-push
+        with:
+          context: ./backend
+          file: ./backend/Dockerfile.model_server
+          platforms: linux/amd64
+          tags: danswer/danswer-model-server:it
+          cache-from: type=registry,ref=danswer/danswer-model-server:it
+          cache-to: |
+            type=registry,ref=danswer/danswer-model-server:it,mode=max
+            type=inline
+
+      - 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: danswer/integration-test-runner:it
+          cache-from: type=registry,ref=danswer/integration-test-runner:it
+          cache-to: |
+            type=registry,ref=danswer/integration-test-runner:it,mode=max
+            type=inline
+
+      - name: Start Docker containers
+        run: |
+          cd deployment/docker_compose
+          ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true \
+          AUTH_TYPE=basic \
+          REQUIRE_EMAIL_VERIFICATION=false \
+          DISABLE_TELEMETRY=true \
+          IMAGE_TAG=it \
+          docker compose -f docker-compose.dev.yml -p danswer-stack up -d
+        id: start_docker
+
+      - name: Wait for service to be ready
+        run: |
+          echo "Starting wait-for-service script..."
+          
+          docker logs -f danswer-stack-api_server-1 &
+
+          start_time=$(date +%s)
+          timeout=300  # 5 minutes in seconds
+          
+          while true; do
+            current_time=$(date +%s)
+            elapsed_time=$((current_time - start_time))
+            
+            if [ $elapsed_time -ge $timeout ]; then
+              echo "Timeout reached. Service did not become ready in 5 minutes."
+              exit 1
+            fi
+            
+            # Use curl with error handling to ignore specific exit code 56
+            response=$(curl -s -o /dev/null -w "%{http_code}" http://localhost:8080/health || echo "curl_error")
+            
+            if [ "$response" = "200" ]; then
+              echo "Service is ready!"
+              break
+            elif [ "$response" = "curl_error" ]; then
+              echo "Curl encountered an error, possibly exit code 56. Continuing to retry..."
+            else
+              echo "Service not ready yet (HTTP status $response). Retrying in 5 seconds..."
+            fi
+            
+            sleep 5
+          done
+          echo "Finished waiting for service."
+
+      - name: Run integration tests
+        run: |
+          echo "Running integration tests..."
+          docker run --rm --network danswer-stack_default \
+            -e POSTGRES_HOST=relational_db \
+            -e POSTGRES_USER=postgres \
+            -e POSTGRES_PASSWORD=password \
+            -e POSTGRES_DB=postgres \
+            -e VESPA_HOST=index \
+            -e REDIS_HOST=cache \
+            -e API_SERVER_HOST=api_server \
+            -e OPENAI_API_KEY=${OPENAI_API_KEY} \
+            danswer/integration-test-runner:it
+        continue-on-error: true
+        id: run_tests
+
+      - name: Check test results
+        run: |
+          if [ ${{ steps.run_tests.outcome }} == 'failure' ]; then
+            echo "Integration tests failed. Exiting with error."
+            exit 1
+          else
+            echo "All integration tests passed successfully."
+          fi
+
+      - name: Save Docker logs
+        if: success() || failure()
+        run: |
+          cd deployment/docker_compose
+          docker compose -f docker-compose.dev.yml -p danswer-stack logs > docker-compose.log
+          mv docker-compose.log ${{ github.workspace }}/docker-compose.log
+      
+      - name: Upload logs
+        if: success() || failure()
+        uses: actions/upload-artifact@v3
+        with:
+          name: docker-logs
+          path: ${{ github.workspace }}/docker-compose.log
+
+      - name: Stop Docker containers
+        run: |
+          cd deployment/docker_compose
+          docker compose -f docker-compose.dev.yml -p danswer-stack down -v

.github/workflows/tag-nightly.yml

@@ -1,53 +0,0 @@
-name: Nightly Tag Push
-
-on:
-  schedule:
-    - 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
-
-jobs:
-  create-and-push-tag:
-    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 }}"
-
-      - name: Set up Git user
-        run: |
-          git config user.name "Richard Kuo [bot]"
-          git config user.email "rkuo[bot]@onyx.app"
-
-      - name: Check for existing nightly tag
-        id: check_tag
-        run: |
-          if git tag --points-at HEAD --list "nightly-latest*" | grep -q .; then
-            echo "A tag starting with 'nightly-latest' already exists on HEAD."
-            echo "tag_exists=true" >> $GITHUB_OUTPUT
-          else
-            echo "No tag starting with 'nightly-latest' exists on HEAD."
-            echo "tag_exists=false" >> $GITHUB_OUTPUT
-          fi
-
-      # don't tag again if HEAD already has a nightly-latest tag on it
-      - name: Create Nightly Tag
-        if: steps.check_tag.outputs.tag_exists == 'false'
-        env:
-          DATE: ${{ github.run_id }}
-        run: |
-          TAG_NAME="nightly-latest-$(date +'%Y%m%d')"
-          echo "Creating tag: $TAG_NAME"
-          git tag $TAG_NAME
-
-      - name: Push Tag
-        if: steps.check_tag.outputs.tag_exists == 'false'
-        run: |
-          TAG_NAME="nightly-latest-$(date +'%Y%m%d')"
-          git push origin $TAG_NAME

.gitignore

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

.prettierignore

@@ -1 +0,0 @@
-backend/tests/integration/tests/pruning/website

.vscode/launch.template.jsonc

@@ -6,69 +6,19 @@
     // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
     "version": "0.2.0",
     "compounds": [
-		{
-			// Dummy entry used to label the group
-			"name": "--- Compound ---",
-		  	"configurations": [
-		  		"--- Individual ---"
-		  	],
-			"presentation": {
-				 "group": "1",
-			 }
-		},
         {
-            "name": "Run All Onyx Services",
+            "name": "Run All Danswer Services",
             "configurations": [
                 "Web Server",
                 "Model Server",
                 "API Server",
-                "Slack Bot",
-		  		"Celery primary", 
-		  		"Celery light", 
-		  		"Celery heavy", 
-		  		"Celery indexing", 
-		  		"Celery beat",
-            ],
-			"presentation": {
-				 "group": "1",
-			 }
-        },
-		{
-			"name": "Web / Model / API",
-		  	"configurations": [
-		  		"Web Server", 
-		  		"Model Server", 
-		  		"API Server",
-		  	],
-			"presentation": {
-				 "group": "1",
-			 }
-		},
-		{
-			"name": "Celery (all)",
-		  	"configurations": [
-		  		"Celery primary", 
-		  		"Celery light", 
-		  		"Celery heavy", 
-		  		"Celery indexing", 
-		  		"Celery beat"
-		  	],
-			"presentation": {
-				 "group": "1",
-			 }
-		}
+                "Indexing",
+                "Background Jobs",
+                "Slack Bot"
+            ]
+        }
     ],
     "configurations": [
-		{
-	    	// Dummy entry used to label the group
-			"name": "--- Individual ---",
-			"type": "node",
-			"request": "launch",
-			"presentation": {
-				"group": "2",
-				"order": 0
-			}
-		},
         {
             "name": "Web Server",
             "type": "node",
@@ -79,11 +29,7 @@
             "runtimeArgs": [
                 "run", "dev"
             ],
-            "presentation": {
-				 "group": "2",
-			 },
-            "console": "integratedTerminal",
-            "consoleTitle": "Web Server Console"
+            "console": "integratedTerminal"
         },
         {
             "name": "Model Server",
@@ -102,11 +48,7 @@
                 "--reload",
                 "--port",
                 "9000"
-            ],
-            "presentation": {
-				 "group": "2",
-			},
-            "consoleTitle": "Model Server Console"
+            ]
         },
         {
             "name": "API Server",
@@ -122,128 +64,18 @@
                 "PYTHONUNBUFFERED": "1"
             },
             "args": [
-                "onyx.main:app",
+                "danswer.main:app",
                 "--reload",
                 "--port",
                 "8080"
-            ],
-            "presentation": {
-				 "group": "2",
-			 },
-            "consoleTitle": "API Server Console"
-        },
-        // For the listener to access the Slack API,
-        // DANSWER_BOT_SLACK_APP_TOKEN & DANSWER_BOT_SLACK_BOT_TOKEN need to be set in .env file located in the root of the project
-        {
-            "name": "Slack Bot",
-            "consoleName": "Slack Bot",
-            "type": "debugpy",
-            "request": "launch",
-            "program": "onyx/onyxbot/slack/listener.py",
-            "cwd": "${workspaceFolder}/backend",
-            "envFile": "${workspaceFolder}/.vscode/.env",
-            "env": {
-                "LOG_LEVEL": "DEBUG",
-                "PYTHONUNBUFFERED": "1",
-                "PYTHONPATH": "."
-            },
-            "presentation": {
-				 "group": "2",
-			},
-            "consoleTitle": "Slack Bot Console"
+            ]
         },
         {
-            "name": "Celery primary",
+            "name": "Indexing",
+            "consoleName": "Indexing",
             "type": "debugpy",
             "request": "launch",
-            "module": "celery",
-            "cwd": "${workspaceFolder}/backend",
-            "envFile": "${workspaceFolder}/.vscode/.env",
-            "env": {
-                "LOG_LEVEL": "INFO",
-                "PYTHONUNBUFFERED": "1",
-                "PYTHONPATH": "."
-            },
-            "args": [
-                "-A",
-                "onyx.background.celery.versioned_apps.primary",
-                "worker",
-                "--pool=threads",
-                "--concurrency=4",
-                "--prefetch-multiplier=1",
-                "--loglevel=INFO",
-                "--hostname=primary@%n",
-                "-Q",
-                "celery",
-            ],
-            "presentation": {
-				 "group": "2",
-			 },
-            "consoleTitle": "Celery primary Console"
-        },
-        {
-            "name": "Celery light",
-            "type": "debugpy",
-            "request": "launch",
-            "module": "celery",
-            "cwd": "${workspaceFolder}/backend",
-            "envFile": "${workspaceFolder}/.vscode/.env",
-            "env": {
-                "LOG_LEVEL": "INFO",
-                "PYTHONUNBUFFERED": "1",
-                "PYTHONPATH": "."
-            },
-            "args": [
-                "-A",
-                "onyx.background.celery.versioned_apps.light",
-                "worker",
-                "--pool=threads",
-                "--concurrency=64",
-                "--prefetch-multiplier=8",
-                "--loglevel=INFO",
-                "--hostname=light@%n",
-                "-Q",
-                "vespa_metadata_sync,connector_deletion,doc_permissions_upsert",
-            ],
-            "presentation": {
-				 "group": "2",
-			 },
-            "consoleTitle": "Celery light Console"
-        },
-        {
-            "name": "Celery heavy",
-            "type": "debugpy",
-            "request": "launch",
-            "module": "celery",
-            "cwd": "${workspaceFolder}/backend",
-            "envFile": "${workspaceFolder}/.vscode/.env",
-            "env": {
-                "LOG_LEVEL": "INFO",
-                "PYTHONUNBUFFERED": "1",
-                "PYTHONPATH": "."
-            },
-            "args": [
-                "-A",
-                "onyx.background.celery.versioned_apps.heavy",
-                "worker",
-                "--pool=threads",
-                "--concurrency=4",
-                "--prefetch-multiplier=1",
-                "--loglevel=INFO",
-                "--hostname=heavy@%n",
-                "-Q",
-                "connector_pruning,connector_doc_permissions_sync,connector_external_group_sync",
-            ],
-            "presentation": {
-				 "group": "2",
-			 },
-            "consoleTitle": "Celery heavy Console"
-        },
-        {
-            "name": "Celery indexing",
-            "type": "debugpy",
-            "request": "launch",
-            "module": "celery",
+            "program": "danswer/background/update.py",
             "cwd": "${workspaceFolder}/backend",
             "envFile": "${workspaceFolder}/.vscode/.env",
             "env": {
@@ -251,46 +83,42 @@
                 "LOG_LEVEL": "DEBUG",
                 "PYTHONUNBUFFERED": "1",
                 "PYTHONPATH": "."
-            },
-            "args": [
-                "-A",
-                "onyx.background.celery.versioned_apps.indexing",
-                "worker",
-                "--pool=threads",
-                "--concurrency=1",
-                "--prefetch-multiplier=1",
-                "--loglevel=INFO",
-                "--hostname=indexing@%n",
-                "-Q",
-                "connector_indexing",
-            ],
-            "presentation": {
-				 "group": "2",
-			 },
-            "consoleTitle": "Celery indexing Console"
+            }
         },
+        // Celery and all async jobs, usually would include indexing as well but this is handled separately above for dev
         {
-            "name": "Celery beat",
+            "name": "Background Jobs",
+            "consoleName": "Background Jobs",
             "type": "debugpy",
             "request": "launch",
-            "module": "celery",
+            "program": "scripts/dev_run_background_jobs.py",
+            "cwd": "${workspaceFolder}/backend",
+            "envFile": "${workspaceFolder}/.vscode/.env",
+            "env": {
+                "LOG_DANSWER_MODEL_INTERACTIONS": "True",
+                "LOG_LEVEL": "DEBUG",
+                "PYTHONUNBUFFERED": "1",
+                "PYTHONPATH": "."
+            },
+            "args": [
+                "--no-indexing"
+            ]
+        },
+        // For the listner to access the Slack API,
+        // DANSWER_BOT_SLACK_APP_TOKEN & DANSWER_BOT_SLACK_BOT_TOKEN need to be set in .env file located in the root of the project
+        {
+            "name": "Slack Bot",
+            "consoleName": "Slack Bot",
+            "type": "debugpy",
+            "request": "launch",
+            "program": "danswer/danswerbot/slack/listener.py",
             "cwd": "${workspaceFolder}/backend",
             "envFile": "${workspaceFolder}/.vscode/.env",
             "env": {
                 "LOG_LEVEL": "DEBUG",
                 "PYTHONUNBUFFERED": "1",
                 "PYTHONPATH": "."
-            },
-            "args": [
-                "-A",
-                "onyx.background.celery.versioned_apps.beat",
-                "beat",
-                "--loglevel=INFO",
-            ],
-            "presentation": {
-				 "group": "2",
-			 },
-            "consoleTitle": "Celery beat Console"
+            }
         },
         {
             "name": "Pytest",
@@ -308,23 +136,9 @@
             "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"
-            ],
-            "presentation": {
-				 "group": "2",
-			 },
-            "consoleTitle": "Pytest Console"
+                //"tests/unit/danswer/llm/answering/test_prune_and_merge.py"
+            ]
         },
-		{
-	    	// Dummy entry used to label the group
-			"name": "--- Tasks ---",
-			"type": "node",
-			"request": "launch",
-			"presentation": {
-				"group": "3",
-				"order": 0
-			}
-		},
         {
             "name": "Clear and Restart External Volumes and Containers",
             "type": "node",
@@ -333,27 +147,7 @@
             "runtimeArgs": ["${workspaceFolder}/backend/scripts/restart_containers.sh"],
             "cwd": "${workspaceFolder}",
             "console": "integratedTerminal",
-            "stopOnEntry": true,
-            "presentation": {
-				 "group": "3",
-			 },
-        },
-        {
-	        // Celery jobs launched through a single background script (legacy)
-	        // Recommend using the "Celery (all)" compound launch instead.
-            "name": "Background Jobs",
-            "consoleName": "Background Jobs",
-            "type": "debugpy",
-            "request": "launch",
-            "program": "scripts/dev_run_background_jobs.py",
-            "cwd": "${workspaceFolder}/backend",
-            "envFile": "${workspaceFolder}/.vscode/.env",
-            "env": {
-                "LOG_DANSWER_MODEL_INTERACTIONS": "True",
-                "LOG_LEVEL": "DEBUG",
-                "PYTHONUNBUFFERED": "1",
-                "PYTHONPATH": "."
-            },
-        },
+            "stopOnEntry": true
+        }
     ]
 }

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-2afut44lv-Rw3kSWu6_OmdAXRpCv80DQ) / 
+[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

@@ -1,147 +1,129 @@
-<!-- DANSWER_METADATA={"link": "https://github.com/onyx-dot-app/onyx/blob/main/README.md"} -->
-
-<a name="readme-top"></a>
+<!-- DANSWER_METADATA={"link": "https://github.com/danswer-ai/danswer/blob/main/README.md"} -->
 
 <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-2lcmqw703-071hBuZBfNEOGUsLa5PXvQ" 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.
+* Multi-Model model support, chat with images, video etc.
+* Choosing between LLMs and parameters during chat session.
+* Tool calling and agent configurations options.
+* Organizational understanding and ability to locate and suggest experts from your team.
 
-- Chat/Prompt sharing with specific teammates and user groups.
-- Multimodal model support, chat with images, video etc.
-- Choosing between LLMs and parameters during chat session.
-- Tool calling and agent configurations options.
-- Organizational understanding and ability to locate and suggest experts from your team.
 
-## Other Notable Benefits of Onyx
+## Other Noteable Benefits of Danswer
+* User Authentication with document level access management.
+* Best in class Hybrid Search across all sources (BM-25 + prefix aware embedding models).
+* Admin Dashboard to configure connectors, document-sets, access, etc.
+* Custom deep learning models + learn from user feedback.
+* Easy deployment and ability to host Danswer anywhere of your choosing.
 
-- 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)
-
-## ✨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>
-
-<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
-    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
-        ↑ Back to Top ↑
-    </a>
-</p>

backend/Dockerfile

@@ -1,19 +1,18 @@
 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=${ONYX_VERSION} \
+# Default DANSWER_VERSION, typically overriden during builds by GitHub Actions.
+ARG DANSWER_VERSION=0.3-dev
+ENV DANSWER_VERSION=${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)
@@ -37,8 +36,6 @@ RUN apt-get update && \
     rm -rf /var/lib/apt/lists/* && \
     apt-get clean
 
-
-
 # Install Python dependencies
 # Remove py which is pulled in by retry, py is not needed and is a CVE
 COPY ./requirements/default.txt /tmp/requirements.txt
@@ -56,7 +53,7 @@ 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 \
@@ -73,11 +70,11 @@ RUN apt-get update && \
     rm -rf /var/lib/apt/lists/* && \
     rm -f /usr/local/lib/python3.11/site-packages/tornado/test/test.key
 
-
 # Pre-downloading models for setups with limited egress
 RUN python -c "from tokenizers import Tokenizer; \
 Tokenizer.from_pretrained('nomic-ai/nomic-embed-text-v1')"
 
+
 # Pre-downloading NLTK for setups with limited egress
 RUN python -c "import nltk; \
 nltk.download('stopwords', quiet=True); \
@@ -92,10 +89,9 @@ 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
 COPY ./alembic.ini /app/alembic.ini
 COPY supervisord.conf /usr/etc/supervisord.conf
 
@@ -105,7 +101,7 @@ COPY ./scripts/force_delete_connector_by_id.py /app/scripts/force_delete_connect
 # Put logo in assets
 COPY ./assets /app/assets
 
-ENV PYTHONPATH=/app
+ENV PYTHONPATH /app
 
 # Default command which does nothing
 # This container is used by api server and background which specify their own CMD

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=${ONYX_VERSION} \
+# Default DANSWER_VERSION, typically overriden during builds by GitHub Actions.
+ARG DANSWER_VERSION=0.3-dev
+ENV DANSWER_VERSION=${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; \
@@ -38,23 +38,23 @@ 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
 COPY ./model_server /app/model_server
 
-ENV PYTHONPATH=/app
+ENV PYTHONPATH /app
 
 CMD ["uvicorn", "model_server.main:app", "--host", "0.0.0.0", "--port", "9000"]

backend/alembic.ini

@@ -1,6 +1,6 @@
 # A generic, single database configuration.
 
-[DEFAULT]
+[alembic]
 # path to migration scripts
 script_location = alembic
 
@@ -47,8 +47,7 @@ prepend_sys_path = .
 # version_path_separator = :
 # version_path_separator = ;
 # version_path_separator = space
-version_path_separator = os  
-# Use os.pathsep. Default configuration used for new projects.
+version_path_separator = os  # Use os.pathsep. Default configuration used for new projects.
 
 # set to 'true' to search source files recursively
 # in each "version_locations" directory
@@ -107,12 +106,3 @@ formatter = generic
 [formatter_generic]
 format = %(levelname)-5.5s [%(name)s] %(message)s
 datefmt = %H:%M:%S
-
-
-[alembic]
-script_location = alembic
-version_locations = %(script_location)s/versions
-
-[schema_private]
-script_location = alembic_tenants
-version_locations = %(script_location)s/versions

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

@@ -1,215 +1,107 @@
-from sqlalchemy.engine.base import Connection
-from typing import Literal
 import asyncio
 from logging.config import fileConfig
-import logging
 
 from alembic import context
+from danswer.db.engine import build_connection_string
+from danswer.db.models import Base
 from sqlalchemy import pool
+from sqlalchemy.engine import Connection
 from sqlalchemy.ext.asyncio import create_async_engine
-from sqlalchemy.sql import text
-from sqlalchemy.sql.schema import SchemaItem
-
-from shared_configs.configs import MULTI_TENANT
-from onyx.db.engine import build_connection_string
-from onyx.db.models import Base
 from celery.backends.database.session import ResultModelBase  # type: ignore
-from onyx.db.engine import get_all_tenant_ids
-from shared_configs.configs import POSTGRES_DEFAULT_SCHEMA
+from sqlalchemy.schema import SchemaItem
 
-# Alembic Config object
+# this is the Alembic Config object, which provides
+# access to the values within the .ini file in use.
 config = context.config
 
 # Interpret the config file for Python logging.
+# This line sets up loggers basically.
 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
+# add your model's MetaData object here
+# for 'autogenerate' support
+# from myapp import mymodel
+# target_metadata = mymodel.Base.metadata
 target_metadata = [Base.metadata, ResultModelBase.metadata]
 
-EXCLUDE_TABLES = {"kombu_queue", "kombu_message"}
+# other values from the config, defined by the needs of env.py,
+# can be acquired:
+# my_important_option = config.get_main_option("my_important_option")
+# ... etc.
 
-# Set up logging
-logger = logging.getLogger(__name__)
+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:
-    """
-    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]:
+def run_migrations_offline() -> None:
+    """Run migrations in 'offline' mode.
+
+    This configures the context with just a URL
+    and not an Engine, though an Engine is acceptable
+    here as well.  By skipping the Engine creation
+    we don't even need a DBAPI to be available.
+
+    Calls to context.execute() here emit the given string to the
+    script output.
+
     """
-    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:
-        for pair in arg.split(","):
-            if "=" in pair:
-                key, value = pair.split("=", 1)
-                x_args[key.strip()] = value.strip()
-    schema_name = x_args.get("schema", POSTGRES_DEFAULT_SCHEMA)
-    create_schema = x_args.get("create_schema", "true").lower() == "true"
-    upgrade_all_tenants = x_args.get("upgrade_all_tenants", "false").lower() == "true"
-
-    if (
-        MULTI_TENANT
-        and schema_name == POSTGRES_DEFAULT_SCHEMA
-        and not upgrade_all_tenants
-    ):
-        raise ValueError(
-            "Cannot run default migrations in public schema when multi-tenancy is enabled. "
-            "Please specify a tenant-specific schema."
-        )
-
-    return schema_name, create_schema, upgrade_all_tenants
-
-
-def do_run_migrations(
-    connection: Connection, schema_name: str, create_schema: bool
-) -> None:
-    """
-    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}"'))
-
+    url = build_connection_string()
     context.configure(
-        connection=connection,
+        url=url,
         target_metadata=target_metadata,  # type: ignore
-        include_object=include_object,
-        version_table_schema=schema_name,
-        include_schemas=True,
-        compare_type=True,
-        compare_server_default=True,
-        script_location=config.get_main_option("script_location"),
+        literal_binds=True,
+        dialect_opts={"paramstyle": "named"},
     )
 
     with context.begin_transaction():
         context.run_migrations()
 
 
-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()
+def do_run_migrations(connection: Connection) -> None:
+    context.configure(
+        connection=connection,
+        target_metadata=target_metadata,  # type: ignore
+        include_object=include_object,
+    )  # type: ignore
 
-    engine = create_async_engine(
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+async def run_async_migrations() -> None:
+    """In this scenario we need to create an Engine
+    and associate a connection with the context.
+
+    """
+
+    connectable = create_async_engine(
         build_connection_string(),
         poolclass=pool.NullPool,
     )
 
-    if upgrade_all_tenants:
-        # Run migrations for all tenant schemas sequentially
-        tenant_schemas = get_all_tenant_ids()
+    async with connectable.connect() as connection:
+        await connection.run_sync(do_run_migrations)
 
-        for schema in tenant_schemas:
-            try:
-                logger.info(f"Migrating schema: {schema}")
-                async with engine.connect() as connection:
-                    await connection.run_sync(
-                        do_run_migrations,
-                        schema_name=schema,
-                        create_schema=create_schema,
-                    )
-            except Exception as e:
-                logger.error(f"Error migrating schema {schema}: {e}")
-                raise
-    else:
-        try:
-            logger.info(f"Migrating schema: {schema_name}")
-            async with engine.connect() as connection:
-                await connection.run_sync(
-                    do_run_migrations,
-                    schema_name=schema_name,
-                    create_schema=create_schema,
-                )
-        except Exception as e:
-            logger.error(f"Error migrating schema {schema_name}: {e}")
-            raise
-
-    await engine.dispose()
-
-
-def run_migrations_offline() -> None:
-    """
-    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)
-        tenant_schemas = get_all_tenant_ids()
-        engine.sync_engine.dispose()
-
-        for schema in tenant_schemas:
-            logger.info(f"Migrating schema: {schema}")
-            context.configure(
-                url=url,
-                target_metadata=target_metadata,  # type: ignore
-                literal_binds=True,
-                include_object=include_object,
-                version_table_schema=schema,
-                include_schemas=True,
-                script_location=config.get_main_option("script_location"),
-                dialect_opts={"paramstyle": "named"},
-            )
-
-            with context.begin_transaction():
-                context.run_migrations()
-    else:
-        logger.info(f"Migrating schema: {schema_name}")
-        context.configure(
-            url=url,
-            target_metadata=target_metadata,  # type: ignore
-            literal_binds=True,
-            include_object=include_object,
-            version_table_schema=schema_name,
-            include_schemas=True,
-            script_location=config.get_main_option("script_location"),
-            dialect_opts={"paramstyle": "named"},
-        )
-
-        with context.begin_transaction():
-            context.run_migrations()
+    await connectable.dispose()
 
 
 def run_migrations_online() -> None:
-    """
-    Runs migrations in 'online' mode using an asynchronous engine.
-    """
+    """Run migrations in 'online' mode."""
+
     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/177de57c21c9_display_custom_llm_models.py

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

backend/alembic/versions/1b10e1fda030_add_additional_data_to_notifications.py

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

backend/alembic/versions/1f60f60c3401_embedding_model_search_settings.py

@@ -10,7 +10,7 @@ from alembic import op
 import sqlalchemy as sa
 from sqlalchemy.dialects import postgresql
 
-from 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/26b931506ecb_default_chosen_assistants_to_none.py

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

backend/alembic/versions/2daa494a0851_add_group_sync_time.py

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

backend/alembic/versions/33cb72ea4d80_single_tool_call_per_message.py

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

backend/alembic/versions/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/46b7a812670f_fix_user__external_user_group_id_fk.py

@@ -1,46 +0,0 @@
-"""fix_user__external_user_group_id_fk
-
-Revision ID: 46b7a812670f
-Revises: f32615f71aeb
-Create Date: 2024-09-23 12:58:03.894038
-
-"""
-from alembic import op
-
-# revision identifiers, used by Alembic.
-revision = "46b7a812670f"
-down_revision = "f32615f71aeb"
-branch_labels = None
-depends_on = None
-
-
-def upgrade() -> None:
-    # Drop the existing primary key
-    op.drop_constraint(
-        "user__external_user_group_id_pkey",
-        "user__external_user_group_id",
-        type_="primary",
-    )
-
-    # Add the new composite primary key
-    op.create_primary_key(
-        "user__external_user_group_id_pkey",
-        "user__external_user_group_id",
-        ["user_id", "external_user_group_id", "cc_pair_id"],
-    )
-
-
-def downgrade() -> None:
-    # Drop the composite primary key
-    op.drop_constraint(
-        "user__external_user_group_id_pkey",
-        "user__external_user_group_id",
-        type_="primary",
-    )
-    # Delete all entries from the table
-    op.execute("DELETE FROM user__external_user_group_id")
-
-    # Recreate the original primary key on user_id
-    op.create_primary_key(
-        "user__external_user_group_id_pkey", "user__external_user_group_id", ["user_id"]
-    )

backend/alembic/versions/47e5bef3a1d7_add_persona_categories.py

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

backend/alembic/versions/4ee1287bd26a_add_multiple_slack_bot_support.py

@@ -1,280 +0,0 @@
-"""add_multiple_slack_bot_support
-
-Revision ID: 4ee1287bd26a
-Revises: 47e5bef3a1d7
-Create Date: 2024-11-06 13:15:53.302644
-
-"""
-import logging
-from typing import cast
-from alembic import op
-import sqlalchemy as sa
-from sqlalchemy.orm import Session
-from onyx.key_value_store.factory import get_kv_store
-from onyx.db.models import SlackBot
-from sqlalchemy.dialects import postgresql
-
-# revision identifiers, used by Alembic.
-revision = "4ee1287bd26a"
-down_revision = "47e5bef3a1d7"
-branch_labels: None = None
-depends_on: None = None
-
-# Configure logging
-logger = logging.getLogger("alembic.runtime.migration")
-logger.setLevel(logging.INFO)
-
-
-def upgrade() -> None:
-    logger.info(f"{revision}: create_table: slack_bot")
-    # Create new slack_bot table
-    op.create_table(
-        "slack_bot",
-        sa.Column("id", sa.Integer(), nullable=False),
-        sa.Column("name", sa.String(), nullable=False),
-        sa.Column("enabled", sa.Boolean(), nullable=False, server_default="true"),
-        sa.Column("bot_token", sa.LargeBinary(), nullable=False),
-        sa.Column("app_token", sa.LargeBinary(), nullable=False),
-        sa.PrimaryKeyConstraint("id"),
-        sa.UniqueConstraint("bot_token"),
-        sa.UniqueConstraint("app_token"),
-    )
-
-    # # Create new slack_channel_config table
-    op.create_table(
-        "slack_channel_config",
-        sa.Column("id", sa.Integer(), nullable=False),
-        sa.Column("slack_bot_id", sa.Integer(), nullable=True),
-        sa.Column("persona_id", sa.Integer(), nullable=True),
-        sa.Column("channel_config", postgresql.JSONB(), nullable=False),
-        sa.Column("response_type", sa.String(), nullable=False),
-        sa.Column(
-            "enable_auto_filters", sa.Boolean(), nullable=False, server_default="false"
-        ),
-        sa.ForeignKeyConstraint(
-            ["slack_bot_id"],
-            ["slack_bot.id"],
-        ),
-        sa.ForeignKeyConstraint(
-            ["persona_id"],
-            ["persona.id"],
-        ),
-        sa.PrimaryKeyConstraint("id"),
-    )
-
-    # Handle existing Slack bot tokens first
-    logger.info(f"{revision}: Checking for existing Slack bot.")
-    bot_token = None
-    app_token = None
-    first_row_id = None
-
-    try:
-        tokens = cast(dict, get_kv_store().load("slack_bot_tokens_config_key"))
-    except Exception:
-        logger.warning("No existing Slack bot tokens found.")
-        tokens = {}
-
-    bot_token = tokens.get("bot_token")
-    app_token = tokens.get("app_token")
-
-    if bot_token and app_token:
-        logger.info(f"{revision}: Found bot and app tokens.")
-
-        session = Session(bind=op.get_bind())
-        new_slack_bot = SlackBot(
-            name="Slack Bot (Migrated)",
-            enabled=True,
-            bot_token=bot_token,
-            app_token=app_token,
-        )
-        session.add(new_slack_bot)
-        session.commit()
-        first_row_id = new_slack_bot.id
-
-    # Create a default bot if none exists
-    # This is in case there are no slack tokens but there are channels configured
-    op.execute(
-        sa.text(
-            """
-            INSERT INTO slack_bot (name, enabled, bot_token, app_token)
-            SELECT 'Default Bot', true, '', ''
-            WHERE NOT EXISTS (SELECT 1 FROM slack_bot)
-            RETURNING id;
-            """
-        )
-    )
-
-    # Get the bot ID to use (either from existing migration or newly created)
-    bot_id_query = sa.text(
-        """
-        SELECT COALESCE(
-            :first_row_id,
-            (SELECT id FROM slack_bot ORDER BY id ASC LIMIT 1)
-        ) as bot_id;
-        """
-    )
-    result = op.get_bind().execute(bot_id_query, {"first_row_id": first_row_id})
-    bot_id = result.scalar()
-
-    # CTE (Common Table Expression) that transforms the old slack_bot_config table data
-    # This splits up the channel_names into their own rows
-    channel_names_cte = """
-        WITH channel_names AS (
-            SELECT
-                sbc.id as config_id,
-                sbc.persona_id,
-                sbc.response_type,
-                sbc.enable_auto_filters,
-                jsonb_array_elements_text(sbc.channel_config->'channel_names') as channel_name,
-                sbc.channel_config->>'respond_tag_only' as respond_tag_only,
-                sbc.channel_config->>'respond_to_bots' as respond_to_bots,
-                sbc.channel_config->'respond_member_group_list' as respond_member_group_list,
-                sbc.channel_config->'answer_filters' as answer_filters,
-                sbc.channel_config->'follow_up_tags' as follow_up_tags
-            FROM slack_bot_config sbc
-        )
-    """
-
-    # Insert the channel names into the new slack_channel_config table
-    insert_statement = """
-        INSERT INTO slack_channel_config (
-            slack_bot_id,
-            persona_id,
-            channel_config,
-            response_type,
-            enable_auto_filters
-        )
-        SELECT
-            :bot_id,
-            channel_name.persona_id,
-            jsonb_build_object(
-                'channel_name', channel_name.channel_name,
-                'respond_tag_only',
-                COALESCE((channel_name.respond_tag_only)::boolean, false),
-                'respond_to_bots',
-                COALESCE((channel_name.respond_to_bots)::boolean, false),
-                'respond_member_group_list',
-                COALESCE(channel_name.respond_member_group_list, '[]'::jsonb),
-                'answer_filters',
-                COALESCE(channel_name.answer_filters, '[]'::jsonb),
-                'follow_up_tags',
-                COALESCE(channel_name.follow_up_tags, '[]'::jsonb)
-            ),
-            channel_name.response_type,
-            channel_name.enable_auto_filters
-        FROM channel_names channel_name;
-    """
-
-    op.execute(sa.text(channel_names_cte + insert_statement).bindparams(bot_id=bot_id))
-
-    # Clean up old tokens if they existed
-    try:
-        if bot_token and app_token:
-            logger.info(f"{revision}: Removing old bot and app tokens.")
-            get_kv_store().delete("slack_bot_tokens_config_key")
-    except Exception:
-        logger.warning("tried to delete tokens in dynamic config but failed")
-    # Rename the table
-    op.rename_table(
-        "slack_bot_config__standard_answer_category",
-        "slack_channel_config__standard_answer_category",
-    )
-
-    # Rename the column
-    op.alter_column(
-        "slack_channel_config__standard_answer_category",
-        "slack_bot_config_id",
-        new_column_name="slack_channel_config_id",
-    )
-
-    # Drop the table with CASCADE to handle dependent objects
-    op.execute("DROP TABLE slack_bot_config CASCADE")
-
-    logger.info(f"{revision}: Migration complete.")
-
-
-def downgrade() -> None:
-    # Recreate the old slack_bot_config table
-    op.create_table(
-        "slack_bot_config",
-        sa.Column("id", sa.Integer(), nullable=False),
-        sa.Column("persona_id", sa.Integer(), nullable=True),
-        sa.Column("channel_config", postgresql.JSONB(), nullable=False),
-        sa.Column("response_type", sa.String(), nullable=False),
-        sa.Column("enable_auto_filters", sa.Boolean(), nullable=False),
-        sa.ForeignKeyConstraint(
-            ["persona_id"],
-            ["persona.id"],
-        ),
-        sa.PrimaryKeyConstraint("id"),
-    )
-
-    # Migrate data back to the old format
-    # Group by persona_id to combine channel names back into arrays
-    op.execute(
-        sa.text(
-            """
-            INSERT INTO slack_bot_config (
-                persona_id,
-                channel_config,
-                response_type,
-                enable_auto_filters
-            )
-            SELECT DISTINCT ON (persona_id)
-                persona_id,
-                jsonb_build_object(
-                    'channel_names', (
-                        SELECT jsonb_agg(c.channel_config->>'channel_name')
-                        FROM slack_channel_config c
-                        WHERE c.persona_id = scc.persona_id
-                    ),
-                    'respond_tag_only', (channel_config->>'respond_tag_only')::boolean,
-                    'respond_to_bots', (channel_config->>'respond_to_bots')::boolean,
-                    'respond_member_group_list', channel_config->'respond_member_group_list',
-                    'answer_filters', channel_config->'answer_filters',
-                    'follow_up_tags', channel_config->'follow_up_tags'
-                ),
-                response_type,
-                enable_auto_filters
-            FROM slack_channel_config scc
-            WHERE persona_id IS NOT NULL;
-            """
-        )
-    )
-
-    # Rename the table back
-    op.rename_table(
-        "slack_channel_config__standard_answer_category",
-        "slack_bot_config__standard_answer_category",
-    )
-
-    # Rename the column back
-    op.alter_column(
-        "slack_bot_config__standard_answer_category",
-        "slack_channel_config_id",
-        new_column_name="slack_bot_config_id",
-    )
-
-    # Try to save the first bot's tokens back to KV store
-    try:
-        first_bot = (
-            op.get_bind()
-            .execute(
-                sa.text(
-                    "SELECT bot_token, app_token FROM slack_bot ORDER BY id LIMIT 1"
-                )
-            )
-            .first()
-        )
-        if first_bot and first_bot.bot_token and first_bot.app_token:
-            tokens = {
-                "bot_token": first_bot.bot_token,
-                "app_token": first_bot.app_token,
-            }
-            get_kv_store().store("slack_bot_tokens_config_key", tokens)
-    except Exception:
-        logger.warning("Failed to save tokens back to KV store")
-
-    # Drop the new tables in reverse order
-    op.drop_table("slack_channel_config")
-    op.drop_table("slack_bot")

backend/alembic/versions/54a74a0417fc_danswerbot_onyxbot.py

@@ -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/5b29123cd710_nullable_search_settings_for_historic_.py

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

backend/alembic/versions/5d12a446f5c0_add_api_version_and_deployment_name_to_.py

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

backend/alembic/versions/6756efa39ada_id_uuid_for_chat_session.py

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

backend/alembic/versions/6d562f86c78b_remove_default_bot.py

@@ -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.dynamic_configs.factory import get_dynamic_config_store
 
 # revision identifiers, used by Alembic.
 revision = "703313b75876"
@@ -54,7 +54,9 @@ def upgrade() -> None:
     )
 
     try:
-        settings_json = cast(str, get_kv_store().load("token_budget_settings"))
+        settings_json = cast(
+            str, get_dynamic_config_store().load("token_budget_settings")
+        )
         settings = json.loads(settings_json)
 
         is_enabled = settings.get("enable_token_budget", False)
@@ -69,7 +71,7 @@ def upgrade() -> None:
             )
 
         # Delete the dynamic config
-        get_kv_store().delete("token_budget_settings")
+        get_dynamic_config_store().delete("token_budget_settings")
 
     except Exception:
         # Ignore if the dynamic config is not found

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

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

backend/alembic/versions/94dc3d0236f8_make_document_set_description_optional.py

@@ -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/9cf5c00f72fe_add_creator_to_cc_pair.py

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

backend/alembic/versions/9f696734098f_combine_search_and_chat.py

@@ -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/ac5eaac849f9_add_last_pruned_to_connector_table.py

@@ -1,27 +0,0 @@
-"""add last_pruned to the connector_credential_pair table
-
-Revision ID: ac5eaac849f9
-Revises: 52a219fb5233
-Create Date: 2024-09-10 15:04:26.437118
-
-"""
-from alembic import op
-import sqlalchemy as sa
-
-# revision identifiers, used by Alembic.
-revision = "ac5eaac849f9"
-down_revision = "46b7a812670f"
-branch_labels = None
-depends_on = None
-
-
-def upgrade() -> None:
-    # last pruned represents the last time the connector was pruned
-    op.add_column(
-        "connector_credential_pair",
-        sa.Column("last_pruned", sa.DateTime(timezone=True), nullable=True),
-    )
-
-
-def downgrade() -> None:
-    op.drop_column("connector_credential_pair", "last_pruned")

backend/alembic/versions/b082fec533f0_make_last_attempt_status_nullable.py

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

backend/alembic/versions/b156fa702355_chat_reworked.py

@@ -10,7 +10,7 @@ from alembic import op
 import sqlalchemy as sa
 from sqlalchemy.dialects import postgresql
 from sqlalchemy.dialects.postgresql import ENUM
-from onyx.configs.constants import DocumentSource
+from danswer.configs.constants import DocumentSource
 
 # revision identifiers, used by Alembic.
 revision = "b156fa702355"
@@ -288,15 +288,6 @@ def upgrade() -> None:
 
 
 def downgrade() -> None:
-    # NOTE: you will lose all chat history. This is to satisfy the non-nullable constraints
-    # below
-    op.execute("DELETE FROM chat_feedback")
-    op.execute("DELETE FROM chat_message__search_doc")
-    op.execute("DELETE FROM document_retrieval_feedback")
-    op.execute("DELETE FROM document_retrieval_feedback")
-    op.execute("DELETE FROM chat_message")
-    op.execute("DELETE FROM chat_session")
-
     op.drop_constraint(
         "chat_feedback__chat_message_fk", "chat_feedback", type_="foreignkey"
     )

backend/alembic/versions/b72ed7a5db0e_remove_description_from_starter_messages.py

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

backend/alembic/versions/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/c0fd6e4da83a_add_recent_assistants.py

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

backend/alembic/versions/c99d76fcd298_add_nullable_to_persona_id_in_chat_.py

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

backend/alembic/versions/da4c21c69164_chosen_assistants_changed_to_jsonb.py

@@ -20,7 +20,7 @@ depends_on: None = None
 def upgrade() -> None:
     conn = op.get_bind()
     existing_ids_and_chosen_assistants = conn.execute(
-        sa.text('select id, chosen_assistants from "user"')
+        sa.text("select id, chosen_assistants from public.user")
     )
     op.drop_column(
         "user",
@@ -37,7 +37,7 @@ def upgrade() -> None:
     for id, chosen_assistants in existing_ids_and_chosen_assistants:
         conn.execute(
             sa.text(
-                'update "user" set chosen_assistants = :chosen_assistants where id = :id'
+                "update public.user set chosen_assistants = :chosen_assistants where id = :id"
             ),
             {"chosen_assistants": json.dumps(chosen_assistants), "id": id},
         )
@@ -46,7 +46,7 @@ def upgrade() -> None:
 def downgrade() -> None:
     conn = op.get_bind()
     existing_ids_and_chosen_assistants = conn.execute(
-        sa.text('select id, chosen_assistants from "user"')
+        sa.text("select id, chosen_assistants from public.user")
     )
     op.drop_column(
         "user",
@@ -59,7 +59,7 @@ def downgrade() -> None:
     for id, chosen_assistants in existing_ids_and_chosen_assistants:
         conn.execute(
             sa.text(
-                'update "user" set chosen_assistants = :chosen_assistants where id = :id'
+                "update public.user set chosen_assistants = :chosen_assistants where id = :id"
             ),
             {"chosen_assistants": chosen_assistants, "id": id},
         )

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/dfbe9e93d3c7_extended_role_for_non_web.py

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

backend/alembic/versions/e4334d5b33ba_add_deployment_name_to_llmprovider.py

@@ -1,26 +0,0 @@
-"""add_deployment_name_to_llmprovider
-
-Revision ID: e4334d5b33ba
-Revises: ac5eaac849f9
-Create Date: 2024-10-04 09:52:34.896867
-
-"""
-from alembic import op
-import sqlalchemy as sa
-
-
-# revision identifiers, used by Alembic.
-revision = "e4334d5b33ba"
-down_revision = "ac5eaac849f9"
-branch_labels = None
-depends_on = None
-
-
-def upgrade() -> None:
-    op.add_column(
-        "llm_provider", sa.Column("deployment_name", sa.String(), nullable=True)
-    )
-
-
-def downgrade() -> None:
-    op.drop_column("llm_provider", "deployment_name")

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 +0,0 @@
-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.

backend/alembic_tenants/env.py

@@ -1,119 +0,0 @@
-import asyncio
-from logging.config import fileConfig
-from typing import Literal
-
-from sqlalchemy import pool
-from sqlalchemy.engine import Connection
-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
-
-# this is the Alembic Config object, which provides
-# access to the values within the .ini file in use.
-config = context.config
-
-# Interpret the config file for Python logging.
-# This line sets up loggers basically.
-if config.config_file_name is not None and config.attributes.get(
-    "configure_logger", True
-):
-    fileConfig(config.config_file_name)
-
-# add your model's MetaData object here
-# for 'autogenerate' support
-# from myapp import mymodel
-# target_metadata = mymodel.Base.metadata
-target_metadata = [PublicBase.metadata]
-
-# other values from the config, defined by the needs of env.py,
-# can be acquired:
-# my_important_option = config.get_main_option("my_important_option")
-# ... etc.
-
-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",
-    ],
-    reflected: bool,
-    compare_to: SchemaItem | None,
-) -> bool:
-    if type_ == "table" and name in EXCLUDE_TABLES:
-        return False
-    return True
-
-
-def run_migrations_offline() -> None:
-    """Run migrations in 'offline' mode.
-
-    This configures the context with just a URL
-    and not an Engine, though an Engine is acceptable
-    here as well.  By skipping the Engine creation
-    we don't even need a DBAPI to be available.
-
-    Calls to context.execute() here emit the given string to the
-    script output.
-
-    """
-    url = build_connection_string()
-    context.configure(
-        url=url,
-        target_metadata=target_metadata,  # type: ignore
-        literal_binds=True,
-        dialect_opts={"paramstyle": "named"},
-    )
-
-    with context.begin_transaction():
-        context.run_migrations()
-
-
-def do_run_migrations(connection: Connection) -> None:
-    context.configure(
-        connection=connection,
-        target_metadata=target_metadata,  # type: ignore
-        include_object=include_object,
-    )  # type: ignore
-
-    with context.begin_transaction():
-        context.run_migrations()
-
-
-async def run_async_migrations() -> None:
-    """In this scenario we need to create an Engine
-    and associate a connection with the context.
-
-    """
-
-    connectable = create_async_engine(
-        build_connection_string(),
-        poolclass=pool.NullPool,
-    )
-
-    async with connectable.connect() as connection:
-        await connection.run_sync(do_run_migrations)
-
-    await connectable.dispose()
-
-
-def run_migrations_online() -> None:
-    """Run migrations in 'online' mode."""
-
-    asyncio.run(run_async_migrations())
-
-
-if context.is_offline_mode():
-    run_migrations_offline()
-else:
-    run_migrations_online()

backend/alembic_tenants/script.py.mako

@@ -1,24 +0,0 @@
-"""${message}
-
-Revision ID: ${up_revision}
-Revises: ${down_revision | comma,n}
-Create Date: ${create_date}
-
-"""
-from alembic import op
-import sqlalchemy as sa
-${imports if imports else ""}
-
-# revision identifiers, used by Alembic.
-revision = ${repr(up_revision)}
-down_revision = ${repr(down_revision)}
-branch_labels = ${repr(branch_labels)}
-depends_on = ${repr(depends_on)}
-
-
-def upgrade() -> None:
-    ${upgrades if upgrades else "pass"}
-
-
-def downgrade() -> None:
-    ${downgrades if downgrades else "pass"}

backend/alembic_tenants/versions/14a83a331951_create_usertenantmapping_table.py

@@ -1,24 +0,0 @@
-import sqlalchemy as sa
-
-from alembic import op
-
-# revision identifiers, used by Alembic.
-revision = "14a83a331951"
-down_revision = None
-branch_labels = None
-depends_on = None
-
-
-def upgrade() -> None:
-    op.create_table(
-        "user_tenant_mapping",
-        sa.Column("email", sa.String(), nullable=False),
-        sa.Column("tenant_id", sa.String(), nullable=False),
-        sa.UniqueConstraint("email", "tenant_id", name="uq_user_tenant"),
-        sa.UniqueConstraint("email", name="uq_email"),
-        schema="public",
-    )
-
-
-def downgrade() -> None:
-    op.drop_table("user_tenant_mapping", schema="public")

backend/danswer/__init__.py

@@ -0,0 +1,3 @@
+import os
+
+__version__ = os.environ.get("DANSWER_VERSION", "") or "0.3-dev"

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)
@@ -12,53 +12,13 @@ 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
-
-    def to_dict(self) -> dict:
-        return {
-            "external_access": {
-                "external_user_emails": list(self.external_access.external_user_emails),
-                "external_user_group_ids": list(
-                    self.external_access.external_user_group_ids
-                ),
-                "is_public": self.external_access.is_public,
-            },
-            "doc_id": self.doc_id,
-        }
-
-    @classmethod
-    def from_dict(cls, data: dict) -> "DocExternalAccess":
-        external_access = ExternalAccess(
-            external_user_emails=set(
-                data["external_access"].get("external_user_emails", [])
-            ),
-            external_user_group_ids=set(
-                data["external_access"].get("external_user_group_ids", [])
-            ),
-            is_public=data["external_access"]["is_public"],
-        )
-        return cls(
-            external_access=external_access,
-            doc_id=data["doc_id"],
-        )
-
-
 @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]
@@ -110,12 +70,3 @@ class DocumentAccess(ExternalAccess):
             user_groups=set(user_groups),
             is_public=is_public,
         )
-
-
-default_public_access = DocumentAccess(
-    external_user_emails=set(),
-    external_user_group_ids=set(),
-    user_emails=set(),
-    user_groups=set(),
-    is_public=True,
-)

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/invited_users.py

@@ -0,0 +1,20 @@
+from typing import cast
+
+from danswer.configs.constants import KV_USER_STORE_KEY
+from danswer.dynamic_configs.factory import get_dynamic_config_store
+from danswer.dynamic_configs.interface import ConfigNotFoundError
+from danswer.dynamic_configs.interface import JSON_ro
+
+
+def get_invited_users() -> list[str]:
+    try:
+        store = get_dynamic_config_store()
+        return cast(list, store.load(KV_USER_STORE_KEY))
+    except ConfigNotFoundError:
+        return list()
+
+
+def write_invited_users(emails: list[str]) -> int:
+    store = get_dynamic_config_store()
+    store.store(KV_USER_STORE_KEY, cast(JSON_ro, emails))
+    return len(emails)

backend/danswer/auth/noauth_user.py

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

backend/danswer/auth/schemas.py

@@ -13,24 +13,12 @@ class UserRole(str, Enum):
         groups they are curators of
     - 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
-    - External permissioned users that have been picked up during the external permissions sync process but don't have a web login
     """
 
-    LIMITED = "limited"
     BASIC = "basic"
     ADMIN = "admin"
     CURATOR = "curator"
     GLOBAL_CURATOR = "global_curator"
-    SLACK_USER = "slack_user"
-    EXT_PERM_USER = "ext_perm_user"
-
-    def is_web_login(self) -> bool:
-        return self not in [
-            UserRole.SLACK_USER,
-            UserRole.EXT_PERM_USER,
-        ]
 
 
 class UserStatus(str, Enum):
@@ -45,8 +33,9 @@ class UserRead(schemas.BaseUser[uuid.UUID]):
 
 class UserCreate(schemas.BaseUserCreate):
     role: UserRole = UserRole.BASIC
-    tenant_id: str | None = None
+    has_web_login: bool | None = True
 
 
 class UserUpdate(schemas.BaseUserUpdate):
     role: UserRole
+    has_web_login: bool | None = True

backend/danswer/auth/users.py

@@ -0,0 +1,507 @@
+import smtplib
+import uuid
+from collections.abc import AsyncGenerator
+from datetime import datetime
+from datetime import timezone
+from email.mime.multipart import MIMEMultipart
+from email.mime.text import MIMEText
+from typing import Optional
+from typing import Tuple
+
+from email_validator import EmailNotValidError
+from email_validator import validate_email
+from fastapi import APIRouter
+from fastapi import Depends
+from fastapi import HTTPException
+from fastapi import Request
+from fastapi import Response
+from fastapi import status
+from fastapi.security import OAuth2PasswordRequestForm
+from fastapi_users import BaseUserManager
+from fastapi_users import exceptions
+from fastapi_users import FastAPIUsers
+from fastapi_users import models
+from fastapi_users import schemas
+from fastapi_users import UUIDIDMixin
+from fastapi_users.authentication import AuthenticationBackend
+from fastapi_users.authentication import CookieTransport
+from fastapi_users.authentication import Strategy
+from fastapi_users.authentication.strategy.db import AccessTokenDatabase
+from fastapi_users.authentication.strategy.db import DatabaseStrategy
+from fastapi_users.openapi import OpenAPIResponseType
+from fastapi_users_db_sqlalchemy import SQLAlchemyUserDatabase
+from sqlalchemy.orm import Session
+
+from danswer.auth.invited_users import get_invited_users
+from danswer.auth.schemas import UserCreate
+from danswer.auth.schemas import UserRole
+from danswer.auth.schemas import UserUpdate
+from danswer.configs.app_configs import AUTH_TYPE
+from danswer.configs.app_configs import DISABLE_AUTH
+from danswer.configs.app_configs import EMAIL_FROM
+from danswer.configs.app_configs import 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.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.engine import get_session
+from danswer.db.engine import get_sqlalchemy_engine
+from danswer.db.models import AccessToken
+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_versioned_implementation
+
+logger = setup_logger()
+
+
+def is_user_admin(user: User | None) -> bool:
+    if AUTH_TYPE == AuthType.DISABLED:
+        return True
+    if user and user.role == UserRole.ADMIN:
+        return True
+    return False
+
+
+def verify_auth_setting() -> None:
+    if AUTH_TYPE not in [AuthType.DISABLED, AuthType.BASIC, AuthType.GOOGLE_OAUTH]:
+        raise ValueError(
+            "User must choose a valid user authentication method: "
+            "disabled, basic, or google_oauth"
+        )
+    logger.notice(f"Using Auth Type: {AUTH_TYPE.value}")
+
+
+def get_display_email(email: str | None, space_less: bool = False) -> str:
+    if email and email.endswith(DANSWER_API_KEY_DUMMY_EMAIL_DOMAIN):
+        name = email.split("@")[0]
+        if name == DANSWER_API_KEY_PREFIX + UNNAMED_KEY_PLACEHOLDER:
+            return "Unnamed API Key"
+
+        if space_less:
+            return name
+
+        return name.replace("API_KEY__", "API Key: ")
+
+    return email or ""
+
+
+def user_needs_to_be_verified() -> bool:
+    # all other auth types besides basic should require users to be
+    # verified
+    return AUTH_TYPE != AuthType.BASIC or REQUIRE_EMAIL_VERIFICATION
+
+
+def verify_email_is_invited(email: str) -> None:
+    whitelist = get_invited_users()
+    if not whitelist:
+        return
+
+    if not email:
+        raise PermissionError("Email must be specified")
+
+    email_info = validate_email(email)  # can raise EmailNotValidError
+
+    for email_whitelist in whitelist:
+        try:
+            # normalized emails are now being inserted into the db
+            # we can remove this normalization on read after some time has passed
+            email_info_whitelist = validate_email(email_whitelist)
+        except EmailNotValidError:
+            continue
+
+        # oddly, normalization does not include lowercasing the user part of the
+        # email address ... which we want to allow
+        if email_info.normalized.lower() == email_info_whitelist.normalized.lower():
+            return
+
+    raise PermissionError("User not on allowed user whitelist")
+
+
+def verify_email_in_whitelist(email: str) -> None:
+    with Session(get_sqlalchemy_engine()) as db_session:
+        if not get_user_by_email(email, db_session):
+            verify_email_is_invited(email)
+
+
+def verify_email_domain(email: str) -> None:
+    if VALID_EMAIL_DOMAINS:
+        if email.count("@") != 1:
+            raise HTTPException(
+                status_code=status.HTTP_400_BAD_REQUEST,
+                detail="Email is not valid",
+            )
+        domain = email.split("@")[-1]
+        if domain not in VALID_EMAIL_DOMAINS:
+            raise HTTPException(
+                status_code=status.HTTP_400_BAD_REQUEST,
+                detail="Email domain is not valid",
+            )
+
+
+def send_user_verification_email(
+    user_email: str,
+    token: str,
+    mail_from: str = EMAIL_FROM,
+) -> None:
+    msg = MIMEMultipart()
+    msg["Subject"] = "Danswer Email Verification"
+    msg["To"] = user_email
+    if mail_from:
+        msg["From"] = mail_from
+
+    link = f"{WEB_DOMAIN}/auth/verify-email?token={token}"
+
+    body = MIMEText(f"Click the following link to verify your email address: {link}")
+    msg.attach(body)
+
+    with smtplib.SMTP(SMTP_SERVER, SMTP_PORT) as s:
+        s.starttls()
+        # If credentials fails with gmail, check (You need an app password, not just the basic email password)
+        # https://support.google.com/accounts/answer/185833?sjid=8512343437447396151-NA
+        s.login(SMTP_USER, SMTP_PASS)
+        s.send_message(msg)
+
+
+class UserManager(UUIDIDMixin, BaseUserManager[User, uuid.UUID]):
+    reset_password_token_secret = USER_AUTH_SECRET
+    verification_token_secret = USER_AUTH_SECRET
+
+    async def create(
+        self,
+        user_create: schemas.UC | UserCreate,
+        safe: bool = False,
+        request: Optional[Request] = None,
+    ) -> User:
+        verify_email_is_invited(user_create.email)
+        verify_email_domain(user_create.email)
+        if hasattr(user_create, "role"):
+            user_count = await get_user_count()
+            if user_count == 0 or user_create.email in get_default_admin_user_emails():
+                user_create.role = UserRole.ADMIN
+            else:
+                user_create.role = UserRole.BASIC
+        user = None
+        try:
+            user = await super().create(user_create, safe=safe, request=request)  # type: ignore
+        except exceptions.UserAlreadyExists:
+            user = await self.get_by_email(user_create.email)
+            # Handle case where user has used product outside of web and is now creating an account through web
+            if (
+                not user.has_web_login
+                and hasattr(user_create, "has_web_login")
+                and user_create.has_web_login
+            ):
+                user_update = UserUpdate(
+                    password=user_create.password,
+                    has_web_login=True,
+                    role=user_create.role,
+                    is_verified=user_create.is_verified,
+                )
+                user = await self.update(user_update, user)
+            else:
+                raise exceptions.UserAlreadyExists()
+        return user
+
+    async def oauth_callback(
+        self: "BaseUserManager[models.UOAP, models.ID]",
+        oauth_name: str,
+        access_token: str,
+        account_id: str,
+        account_email: str,
+        expires_at: Optional[int] = None,
+        refresh_token: Optional[str] = None,
+        request: Optional[Request] = None,
+        *,
+        associate_by_email: bool = False,
+        is_verified_by_default: bool = False,
+    ) -> models.UOAP:
+        verify_email_in_whitelist(account_email)
+        verify_email_domain(account_email)
+
+        user = await super().oauth_callback(  # type: ignore
+            oauth_name=oauth_name,
+            access_token=access_token,
+            account_id=account_id,
+            account_email=account_email,
+            expires_at=expires_at,
+            refresh_token=refresh_token,
+            request=request,
+            associate_by_email=associate_by_email,
+            is_verified_by_default=is_verified_by_default,
+        )
+
+        # NOTE: Most IdPs have very short expiry times, and we don't want to force the user to
+        # re-authenticate that frequently, so by default this is disabled
+        if expires_at and TRACK_EXTERNAL_IDP_EXPIRY:
+            oidc_expiry = datetime.fromtimestamp(expires_at, tz=timezone.utc)
+            await self.user_db.update(user, update_dict={"oidc_expiry": oidc_expiry})
+
+        # this is needed if an organization goes from `TRACK_EXTERNAL_IDP_EXPIRY=true` to `false`
+        # otherwise, the oidc expiry will always be old, and the user will never be able to login
+        if user.oidc_expiry and not TRACK_EXTERNAL_IDP_EXPIRY:
+            await self.user_db.update(user, update_dict={"oidc_expiry": None})
+
+        # Handle case where user has used product outside of web and is now creating an account through web
+        if not user.has_web_login:
+            await self.user_db.update(
+                user,
+                update_dict={
+                    "is_verified": is_verified_by_default,
+                    "has_web_login": True,
+                },
+            )
+            user.is_verified = is_verified_by_default
+            user.has_web_login = True
+
+        return user
+
+    async def on_after_register(
+        self, user: User, request: Optional[Request] = None
+    ) -> None:
+        logger.notice(f"User {user.id} has registered.")
+        optional_telemetry(
+            record_type=RecordType.SIGN_UP,
+            data={"action": "create"},
+            user_id=str(user.id),
+        )
+
+    async def on_after_forgot_password(
+        self, user: User, token: str, request: Optional[Request] = None
+    ) -> None:
+        logger.notice(f"User {user.id} has forgot their password. Reset token: {token}")
+
+    async def on_after_request_verify(
+        self, user: User, token: str, request: Optional[Request] = None
+    ) -> None:
+        verify_email_domain(user.email)
+
+        logger.notice(
+            f"Verification requested for user {user.id}. Verification token: {token}"
+        )
+
+        send_user_verification_email(user.email, token)
+
+    async def authenticate(
+        self, credentials: OAuth2PasswordRequestForm
+    ) -> Optional[User]:
+        try:
+            user = await self.get_by_email(credentials.username)
+        except exceptions.UserNotExists:
+            self.password_helper.hash(credentials.password)
+            return None
+
+        if not user.has_web_login:
+            raise HTTPException(
+                status_code=status.HTTP_403_FORBIDDEN,
+                detail="NO_WEB_LOGIN_AND_HAS_NO_PASSWORD",
+            )
+
+        verified, updated_password_hash = self.password_helper.verify_and_update(
+            credentials.password, user.hashed_password
+        )
+        if not verified:
+            return None
+
+        if updated_password_hash is not None:
+            await self.user_db.update(user, {"hashed_password": updated_password_hash})
+
+        return user
+
+
+async def get_user_manager(
+    user_db: SQLAlchemyUserDatabase = Depends(get_user_db),
+) -> AsyncGenerator[UserManager, None]:
+    yield UserManager(user_db)
+
+
+cookie_transport = CookieTransport(
+    cookie_max_age=SESSION_EXPIRE_TIME_SECONDS,
+    cookie_secure=WEB_DOMAIN.startswith("https"),
+)
+
+
+def get_database_strategy(
+    access_token_db: AccessTokenDatabase[AccessToken] = Depends(get_access_token_db),
+) -> DatabaseStrategy:
+    strategy = DatabaseStrategy(
+        access_token_db, lifetime_seconds=SESSION_EXPIRE_TIME_SECONDS  # type: ignore
+    )
+
+    return strategy
+
+
+auth_backend = AuthenticationBackend(
+    name="database",
+    transport=cookie_transport,
+    get_strategy=get_database_strategy,
+)
+
+
+class FastAPIUserWithLogoutRouter(FastAPIUsers[models.UP, models.ID]):
+    def get_logout_router(
+        self,
+        backend: AuthenticationBackend,
+        requires_verification: bool = REQUIRE_EMAIL_VERIFICATION,
+    ) -> APIRouter:
+        """
+        Provide a router for logout only for OAuth/OIDC Flows.
+        This way the login router does not need to be included
+        """
+        router = APIRouter()
+        get_current_user_token = self.authenticator.current_user_token(
+            active=True, verified=requires_verification
+        )
+        logout_responses: OpenAPIResponseType = {
+            **{
+                status.HTTP_401_UNAUTHORIZED: {
+                    "description": "Missing token or inactive user."
+                }
+            },
+            **backend.transport.get_openapi_logout_responses_success(),
+        }
+
+        @router.post(
+            "/logout", name=f"auth:{backend.name}.logout", responses=logout_responses
+        )
+        async def logout(
+            user_token: Tuple[models.UP, str] = Depends(get_current_user_token),
+            strategy: Strategy[models.UP, models.ID] = Depends(backend.get_strategy),
+        ) -> Response:
+            user, token = user_token
+            return await backend.logout(strategy, user, token)
+
+        return router
+
+
+fastapi_users = FastAPIUserWithLogoutRouter[User, uuid.UUID](
+    get_user_manager, [auth_backend]
+)
+
+
+# NOTE: verified=REQUIRE_EMAIL_VERIFICATION is not used here since we
+# take care of that in `double_check_user` ourself. This is needed, since
+# we want the /me endpoint to still return a user even if they are not
+# yet verified, so that the frontend knows they exist
+optional_fastapi_current_user = fastapi_users.current_user(active=True, optional=True)
+
+
+async def optional_user_(
+    request: Request,
+    user: User | None,
+    db_session: Session,
+) -> User | None:
+    """NOTE: `request` and `db_session` are not used here, but are included
+    for the EE version of this function."""
+    return user
+
+
+async def optional_user(
+    request: Request,
+    user: User | None = Depends(optional_fastapi_current_user),
+    db_session: Session = Depends(get_session),
+) -> User | None:
+    versioned_fetch_user = fetch_versioned_implementation(
+        "danswer.auth.users", "optional_user_"
+    )
+    return await versioned_fetch_user(request, user, db_session)
+
+
+async def double_check_user(
+    user: User | None,
+    optional: bool = DISABLE_AUTH,
+    include_expired: bool = False,
+) -> User | None:
+    if optional:
+        return None
+
+    if user is None:
+        raise HTTPException(
+            status_code=status.HTTP_403_FORBIDDEN,
+            detail="Access denied. User is not authenticated.",
+        )
+
+    if user_needs_to_be_verified() and not user.is_verified:
+        raise HTTPException(
+            status_code=status.HTTP_403_FORBIDDEN,
+            detail="Access denied. User is not verified.",
+        )
+
+    if (
+        user.oidc_expiry
+        and user.oidc_expiry < datetime.now(timezone.utc)
+        and not include_expired
+    ):
+        raise HTTPException(
+            status_code=status.HTTP_403_FORBIDDEN,
+            detail="Access denied. User's OIDC token has expired.",
+        )
+
+    return user
+
+
+async def current_user_with_expired_token(
+    user: User | None = Depends(optional_user),
+) -> User | None:
+    return await double_check_user(user, include_expired=True)
+
+
+async def current_user(
+    user: User | None = Depends(optional_user),
+) -> User | None:
+    return await double_check_user(user)
+
+
+async def current_curator_or_admin_user(
+    user: User | None = Depends(current_user),
+) -> User | None:
+    if DISABLE_AUTH:
+        return None
+
+    if not user or not hasattr(user, "role"):
+        raise HTTPException(
+            status_code=status.HTTP_403_FORBIDDEN,
+            detail="Access denied. User is not authenticated or lacks role information.",
+        )
+
+    allowed_roles = {UserRole.GLOBAL_CURATOR, UserRole.CURATOR, UserRole.ADMIN}
+    if user.role not in allowed_roles:
+        raise HTTPException(
+            status_code=status.HTTP_403_FORBIDDEN,
+            detail="Access denied. User is not a curator or admin.",
+        )
+
+    return user
+
+
+async def current_admin_user(user: User | None = Depends(current_user)) -> User | None:
+    if DISABLE_AUTH:
+        return None
+
+    if not user or not hasattr(user, "role") or user.role != UserRole.ADMIN:
+        raise HTTPException(
+            status_code=status.HTTP_403_FORBIDDEN,
+            detail="Access denied. User must be an admin to perform this action.",
+        )
+
+    return user
+
+
+def get_default_admin_user_emails_() -> list[str]:
+    # No default seeding available for Danswer MIT
+    return []

backend/danswer/background/celery/celery_redis.py

@@ -0,0 +1,361 @@
+# These are helper objects for tracking the keys we need to write in redis
+import time
+from abc import ABC
+from abc import abstractmethod
+from typing import cast
+from uuid import uuid4
+
+import redis
+from celery import Celery
+from redis import Redis
+from sqlalchemy.orm import Session
+
+from danswer.background.celery.celeryconfig import CELERY_SEPARATOR
+from danswer.configs.constants import CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT
+from danswer.configs.constants import DanswerCeleryPriority
+from danswer.configs.constants import DanswerCeleryQueues
+from danswer.db.connector_credential_pair import get_connector_credential_pair_from_id
+from danswer.db.document import construct_document_select_for_connector_credential_pair
+from danswer.db.document import (
+    construct_document_select_for_connector_credential_pair_by_needs_sync,
+)
+from danswer.db.document_set import construct_document_select_by_docset
+from danswer.utils.variable_functionality import fetch_versioned_implementation
+
+
+class RedisObjectHelper(ABC):
+    PREFIX = "base"
+    FENCE_PREFIX = PREFIX + "_fence"
+    TASKSET_PREFIX = PREFIX + "_taskset"
+
+    def __init__(self, id: int):
+        self._id: int = id
+
+    @property
+    def task_id_prefix(self) -> str:
+        return f"{self.PREFIX}_{self._id}"
+
+    @property
+    def fence_key(self) -> str:
+        # example: documentset_fence_1
+        return f"{self.FENCE_PREFIX}_{self._id}"
+
+    @property
+    def taskset_key(self) -> str:
+        # example: documentset_taskset_1
+        return f"{self.TASKSET_PREFIX}_{self._id}"
+
+    @staticmethod
+    def get_id_from_fence_key(key: str) -> int | None:
+        """
+        Extracts the object ID from a fence key in the format `PREFIX_fence_X`.
+
+        Args:
+            key (str): The fence key string.
+
+        Returns:
+            Optional[int]: The extracted ID if the key is in the correct format, otherwise None.
+        """
+        parts = key.split("_")
+        if len(parts) != 3:
+            return None
+
+        try:
+            object_id = int(parts[2])
+        except ValueError:
+            return None
+
+        return object_id
+
+    @staticmethod
+    def get_id_from_task_id(task_id: str) -> int | None:
+        """
+        Extracts the object ID from a task ID string.
+
+        This method assumes the task ID is formatted as `prefix_objectid_suffix`, where:
+        - `prefix` is an arbitrary string (e.g., the name of the task or entity),
+        - `objectid` is the ID you want to extract,
+        - `suffix` is another arbitrary string (e.g., a UUID).
+
+        Example:
+            If the input `task_id` is `documentset_1_cbfdc96a-80ca-4312-a242-0bb68da3c1dc`,
+            this method will return the string `"1"`.
+
+        Args:
+            task_id (str): The task ID string from which to extract the object ID.
+
+        Returns:
+            str | None: The extracted object ID if the task ID is in the correct format, otherwise None.
+        """
+        # example: task_id=documentset_1_cbfdc96a-80ca-4312-a242-0bb68da3c1dc
+        parts = task_id.split("_")
+        if len(parts) != 3:
+            return None
+
+        try:
+            object_id = int(parts[1])
+        except ValueError:
+            return None
+
+        return object_id
+
+    @abstractmethod
+    def generate_tasks(
+        self,
+        celery_app: Celery,
+        db_session: Session,
+        redis_client: Redis,
+        lock: redis.lock.Lock,
+    ) -> int | None:
+        pass
+
+
+class RedisDocumentSet(RedisObjectHelper):
+    PREFIX = "documentset"
+    FENCE_PREFIX = PREFIX + "_fence"
+    TASKSET_PREFIX = PREFIX + "_taskset"
+
+    def generate_tasks(
+        self,
+        celery_app: Celery,
+        db_session: Session,
+        redis_client: Redis,
+        lock: redis.lock.Lock,
+    ) -> int | None:
+        last_lock_time = time.monotonic()
+
+        async_results = []
+        stmt = construct_document_select_by_docset(self._id, current_only=False)
+        for doc in db_session.scalars(stmt).yield_per(1):
+            current_time = time.monotonic()
+            if current_time - last_lock_time >= (
+                CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT / 4
+            ):
+                lock.reacquire()
+                last_lock_time = current_time
+
+            # celery's default task id format is "dd32ded3-00aa-4884-8b21-42f8332e7fac"
+            # the key for the result is "celery-task-meta-dd32ded3-00aa-4884-8b21-42f8332e7fac"
+            # we prefix the task id so it's easier to keep track of who created the task
+            # aka "documentset_1_6dd32ded3-00aa-4884-8b21-42f8332e7fac"
+            custom_task_id = f"{self.task_id_prefix}_{uuid4()}"
+
+            # add to the set BEFORE creating the task.
+            redis_client.sadd(self.taskset_key, custom_task_id)
+
+            result = celery_app.send_task(
+                "vespa_metadata_sync_task",
+                kwargs=dict(document_id=doc.id),
+                queue=DanswerCeleryQueues.VESPA_METADATA_SYNC,
+                task_id=custom_task_id,
+                priority=DanswerCeleryPriority.LOW,
+            )
+
+            async_results.append(result)
+
+        return len(async_results)
+
+
+class RedisUserGroup(RedisObjectHelper):
+    PREFIX = "usergroup"
+    FENCE_PREFIX = PREFIX + "_fence"
+    TASKSET_PREFIX = PREFIX + "_taskset"
+
+    def generate_tasks(
+        self,
+        celery_app: Celery,
+        db_session: Session,
+        redis_client: Redis,
+        lock: redis.lock.Lock,
+    ) -> int | None:
+        last_lock_time = time.monotonic()
+
+        async_results = []
+
+        try:
+            construct_document_select_by_usergroup = fetch_versioned_implementation(
+                "danswer.db.user_group",
+                "construct_document_select_by_usergroup",
+            )
+        except ModuleNotFoundError:
+            return 0
+
+        stmt = construct_document_select_by_usergroup(self._id)
+        for doc in db_session.scalars(stmt).yield_per(1):
+            current_time = time.monotonic()
+            if current_time - last_lock_time >= (
+                CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT / 4
+            ):
+                lock.reacquire()
+                last_lock_time = current_time
+
+            # celery's default task id format is "dd32ded3-00aa-4884-8b21-42f8332e7fac"
+            # the key for the result is "celery-task-meta-dd32ded3-00aa-4884-8b21-42f8332e7fac"
+            # we prefix the task id so it's easier to keep track of who created the task
+            # aka "documentset_1_6dd32ded3-00aa-4884-8b21-42f8332e7fac"
+            custom_task_id = f"{self.task_id_prefix}_{uuid4()}"
+
+            # add to the set BEFORE creating the task.
+            redis_client.sadd(self.taskset_key, custom_task_id)
+
+            result = celery_app.send_task(
+                "vespa_metadata_sync_task",
+                kwargs=dict(document_id=doc.id),
+                queue=DanswerCeleryQueues.VESPA_METADATA_SYNC,
+                task_id=custom_task_id,
+                priority=DanswerCeleryPriority.LOW,
+            )
+
+            async_results.append(result)
+
+        return len(async_results)
+
+
+class RedisConnectorCredentialPair(RedisObjectHelper):
+    """This class differs from the default in that the taskset used spans
+    all connectors and is not per connector."""
+
+    PREFIX = "connectorsync"
+    FENCE_PREFIX = PREFIX + "_fence"
+    TASKSET_PREFIX = PREFIX + "_taskset"
+
+    @classmethod
+    def get_fence_key(cls) -> str:
+        return RedisConnectorCredentialPair.FENCE_PREFIX
+
+    @classmethod
+    def get_taskset_key(cls) -> str:
+        return RedisConnectorCredentialPair.TASKSET_PREFIX
+
+    @property
+    def taskset_key(self) -> str:
+        """Notice that this is intentionally reusing the same taskset for all
+        connector syncs"""
+        # example: connector_taskset
+        return f"{self.TASKSET_PREFIX}"
+
+    def generate_tasks(
+        self,
+        celery_app: Celery,
+        db_session: Session,
+        redis_client: Redis,
+        lock: redis.lock.Lock,
+    ) -> int | None:
+        last_lock_time = time.monotonic()
+
+        async_results = []
+        cc_pair = get_connector_credential_pair_from_id(self._id, db_session)
+        if not cc_pair:
+            return None
+
+        stmt = construct_document_select_for_connector_credential_pair_by_needs_sync(
+            cc_pair.connector_id, cc_pair.credential_id
+        )
+        for doc in db_session.scalars(stmt).yield_per(1):
+            current_time = time.monotonic()
+            if current_time - last_lock_time >= (
+                CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT / 4
+            ):
+                lock.reacquire()
+                last_lock_time = current_time
+
+            # celery's default task id format is "dd32ded3-00aa-4884-8b21-42f8332e7fac"
+            # the key for the result is "celery-task-meta-dd32ded3-00aa-4884-8b21-42f8332e7fac"
+            # we prefix the task id so it's easier to keep track of who created the task
+            # aka "documentset_1_6dd32ded3-00aa-4884-8b21-42f8332e7fac"
+            custom_task_id = f"{self.task_id_prefix}_{uuid4()}"
+
+            # add to the tracking taskset in redis BEFORE creating the celery task.
+            # note that for the moment we are using a single taskset key, not differentiated by cc_pair id
+            redis_client.sadd(
+                RedisConnectorCredentialPair.get_taskset_key(), custom_task_id
+            )
+
+            # Priority on sync's triggered by new indexing should be medium
+            result = celery_app.send_task(
+                "vespa_metadata_sync_task",
+                kwargs=dict(document_id=doc.id),
+                queue=DanswerCeleryQueues.VESPA_METADATA_SYNC,
+                task_id=custom_task_id,
+                priority=DanswerCeleryPriority.MEDIUM,
+            )
+
+            async_results.append(result)
+
+        return len(async_results)
+
+
+class RedisConnectorDeletion(RedisObjectHelper):
+    PREFIX = "connectordeletion"
+    FENCE_PREFIX = PREFIX + "_fence"
+    TASKSET_PREFIX = PREFIX + "_taskset"
+
+    def generate_tasks(
+        self,
+        celery_app: Celery,
+        db_session: Session,
+        redis_client: Redis,
+        lock: redis.lock.Lock,
+    ) -> int | None:
+        last_lock_time = time.monotonic()
+
+        async_results = []
+        cc_pair = get_connector_credential_pair_from_id(self._id, db_session)
+        if not cc_pair:
+            return None
+
+        stmt = construct_document_select_for_connector_credential_pair(
+            cc_pair.connector_id, cc_pair.credential_id
+        )
+        for doc in db_session.scalars(stmt).yield_per(1):
+            current_time = time.monotonic()
+            if current_time - last_lock_time >= (
+                CELERY_VESPA_SYNC_BEAT_LOCK_TIMEOUT / 4
+            ):
+                lock.reacquire()
+                last_lock_time = current_time
+
+            # celery's default task id format is "dd32ded3-00aa-4884-8b21-42f8332e7fac"
+            # the actual redis key is "celery-task-meta-dd32ded3-00aa-4884-8b21-42f8332e7fac"
+            # we prefix the task id so it's easier to keep track of who created the task
+            # aka "documentset_1_6dd32ded3-00aa-4884-8b21-42f8332e7fac"
+            custom_task_id = f"{self.task_id_prefix}_{uuid4()}"
+
+            # add to the tracking taskset in redis BEFORE creating the celery task.
+            # note that for the moment we are using a single taskset key, not differentiated by cc_pair id
+            redis_client.sadd(self.taskset_key, custom_task_id)
+
+            # Priority on sync's triggered by new indexing should be medium
+            result = celery_app.send_task(
+                "document_by_cc_pair_cleanup_task",
+                kwargs=dict(
+                    document_id=doc.id,
+                    connector_id=cc_pair.connector_id,
+                    credential_id=cc_pair.credential_id,
+                ),
+                queue=DanswerCeleryQueues.CONNECTOR_DELETION,
+                task_id=custom_task_id,
+                priority=DanswerCeleryPriority.MEDIUM,
+            )
+
+            async_results.append(result)
+
+        return len(async_results)
+
+
+def celery_get_queue_length(queue: str, r: Redis) -> int:
+    """This is a redis specific way to get the length of a celery queue.
+    It is priority aware and knows how to count across the multiple redis lists
+    used to implement task prioritization.
+    This operation is not atomic."""
+    total_length = 0
+    for i in range(len(DanswerCeleryPriority)):
+        queue_name = queue
+        if i > 0:
+            queue_name += CELERY_SEPARATOR
+            queue_name += str(i)
+
+        length = r.llen(queue_name)
+        total_length += cast(int, length)
+
+    return total_length

backend/danswer/background/celery/celery_run.py

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

backend/danswer/background/celery/celery_utils.py

@@ -0,0 +1,143 @@
+from datetime import datetime
+from datetime import timezone
+
+from sqlalchemy.orm import Session
+
+from danswer.background.celery.celery_redis import RedisConnectorDeletion
+from danswer.background.task_utils import name_cc_prune_task
+from danswer.configs.app_configs import ALLOW_SIMULTANEOUS_PRUNING
+from danswer.configs.app_configs import MAX_PRUNING_DOCUMENT_RETRIEVAL_PER_MINUTE
+from danswer.connectors.cross_connector_utils.rate_limit_wrapper import (
+    rate_limit_builder,
+)
+from danswer.connectors.interfaces import BaseConnector
+from danswer.connectors.interfaces import IdConnector
+from danswer.connectors.interfaces import LoadConnector
+from danswer.connectors.interfaces import PollConnector
+from danswer.connectors.models import Document
+from danswer.db.connector_credential_pair import get_connector_credential_pair
+from danswer.db.engine import get_db_current_time
+from danswer.db.enums import TaskStatus
+from danswer.db.models import Connector
+from danswer.db.models import Credential
+from danswer.db.models import TaskQueueState
+from danswer.db.tasks import check_task_is_live_and_not_timed_out
+from danswer.db.tasks import get_latest_task
+from danswer.db.tasks import get_latest_task_by_type
+from danswer.redis.redis_pool import RedisPool
+from danswer.server.documents.models import DeletionAttemptSnapshot
+from danswer.utils.logger import setup_logger
+
+logger = setup_logger()
+redis_pool = RedisPool()
+
+
+def _get_deletion_status(
+    connector_id: int, credential_id: int, db_session: Session
+) -> TaskQueueState | None:
+    """We no longer store TaskQueueState in the DB for a deletion attempt.
+    This function populates TaskQueueState by just checking redis.
+    """
+    cc_pair = get_connector_credential_pair(
+        connector_id=connector_id, credential_id=credential_id, db_session=db_session
+    )
+    if not cc_pair:
+        return None
+
+    rcd = RedisConnectorDeletion(cc_pair.id)
+
+    r = redis_pool.get_client()
+    if not r.exists(rcd.fence_key):
+        return None
+
+    return TaskQueueState(
+        task_id="", task_name=rcd.fence_key, status=TaskStatus.STARTED
+    )
+
+
+def get_deletion_attempt_snapshot(
+    connector_id: int, credential_id: int, db_session: Session
+) -> DeletionAttemptSnapshot | None:
+    deletion_task = _get_deletion_status(connector_id, credential_id, db_session)
+    if not deletion_task:
+        return None
+
+    return DeletionAttemptSnapshot(
+        connector_id=connector_id,
+        credential_id=credential_id,
+        status=deletion_task.status,
+    )
+
+
+def should_prune_cc_pair(
+    connector: Connector, credential: Credential, db_session: Session
+) -> bool:
+    if not connector.prune_freq:
+        return False
+
+    pruning_task_name = name_cc_prune_task(
+        connector_id=connector.id, credential_id=credential.id
+    )
+    last_pruning_task = get_latest_task(pruning_task_name, db_session)
+    current_db_time = get_db_current_time(db_session)
+
+    if not last_pruning_task:
+        time_since_initialization = current_db_time - connector.time_created
+        if time_since_initialization.total_seconds() >= connector.prune_freq:
+            return True
+        return False
+
+    if not ALLOW_SIMULTANEOUS_PRUNING:
+        pruning_type_task_name = name_cc_prune_task()
+        last_pruning_type_task = get_latest_task_by_type(
+            pruning_type_task_name, db_session
+        )
+
+        if last_pruning_type_task and check_task_is_live_and_not_timed_out(
+            last_pruning_type_task, db_session
+        ):
+            return False
+
+    if check_task_is_live_and_not_timed_out(last_pruning_task, db_session):
+        return False
+
+    if not last_pruning_task.start_time:
+        return False
+
+    time_since_last_pruning = current_db_time - last_pruning_task.start_time
+    return time_since_last_pruning.total_seconds() >= connector.prune_freq
+
+
+def document_batch_to_ids(doc_batch: list[Document]) -> set[str]:
+    return {doc.id for doc in doc_batch}
+
+
+def extract_ids_from_runnable_connector(runnable_connector: BaseConnector) -> set[str]:
+    """
+    If the PruneConnector hasnt been implemented for the given connector, just pull
+    all docs using the load_from_state and grab out the IDs
+    """
+    all_connector_doc_ids: set[str] = set()
+
+    doc_batch_generator = None
+    if isinstance(runnable_connector, IdConnector):
+        all_connector_doc_ids = runnable_connector.retrieve_all_source_ids()
+    elif isinstance(runnable_connector, LoadConnector):
+        doc_batch_generator = runnable_connector.load_from_state()
+    elif isinstance(runnable_connector, PollConnector):
+        start = datetime(1970, 1, 1, tzinfo=timezone.utc).timestamp()
+        end = datetime.now(timezone.utc).timestamp()
+        doc_batch_generator = runnable_connector.poll_source(start=start, end=end)
+    else:
+        raise RuntimeError("Pruning job could not find a valid runnable_connector.")
+
+    if doc_batch_generator:
+        doc_batch_processing_func = document_batch_to_ids
+        if MAX_PRUNING_DOCUMENT_RETRIEVAL_PER_MINUTE:
+            doc_batch_processing_func = rate_limit_builder(
+                max_calls=MAX_PRUNING_DOCUMENT_RETRIEVAL_PER_MINUTE, period=60
+            )(document_batch_to_ids)
+        for doc_batch in doc_batch_generator:
+            all_connector_doc_ids.update(doc_batch_processing_func(doc_batch))
+
+    return all_connector_doc_ids

backend/danswer/background/celery/celeryconfig.py

@@ -1,25 +1,20 @@
 # 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_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_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
 
 CELERY_SEPARATOR = ":"
 
 CELERY_PASSWORD_PART = ""
 if REDIS_PASSWORD:
-    CELERY_PASSWORD_PART = ":" + urllib.parse.quote(REDIS_PASSWORD, safe="") + "@"
+    CELERY_PASSWORD_PART = f":{REDIS_PASSWORD}@"
 
 REDIS_SCHEME = "redis"
 
@@ -31,51 +26,29 @@ if REDIS_SSL:
     if REDIS_SSL_CA_CERTS:
         SSL_QUERY_PARAMS += f"&ssl_ca_certs={REDIS_SSL_CA_CERTS}"
 
-# region Broker settings
 # example celery_broker_url: "redis://:password@localhost:6379/15"
 broker_url = f"{REDIS_SCHEME}://{CELERY_PASSWORD_PART}{REDIS_HOST}:{REDIS_PORT}/{REDIS_DB_NUMBER_CELERY}{SSL_QUERY_PARAMS}"
 
-broker_connection_retry_on_startup = True
-broker_pool_limit = CELERY_BROKER_POOL_LIMIT
+result_backend = f"{REDIS_SCHEME}://{CELERY_PASSWORD_PART}{REDIS_HOST}:{REDIS_PORT}/{REDIS_DB_NUMBER_CELERY_RESULT_BACKEND}{SSL_QUERY_PARAMS}"
+
+# NOTE: prefetch 4 is significantly faster than prefetch 1 for small tasks
+# however, prefetching is bad when tasks are lengthy as those tasks
+# can stall other tasks.
+worker_prefetch_multiplier = 4
 
-# 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,
-    "health_check_interval": REDIS_HEALTH_CHECK_INTERVAL,
-    "socket_keepalive": True,
-    "socket_keepalive_options": REDIS_SOCKET_KEEPALIVE_OPTIONS,
 }
-# endregion
 
-# redis backend settings
-# https://docs.celeryq.dev/en/stable/userguide/configuration.html#redis-backend-settings
-
-# there doesn't appear to be a way to set socket_keepalive_options on the redis result backend
-redis_socket_keepalive = True
-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
 # It's possible we don't even need celery's result backend, in which case all of the optimization below
 # might be irrelevant
-result_backend = f"{REDIS_SCHEME}://{CELERY_PASSWORD_PART}{REDIS_HOST}:{REDIS_PORT}/{REDIS_DB_NUMBER_CELERY_RESULT_BACKEND}{SSL_QUERY_PARAMS}"
 result_expires = CELERY_RESULT_EXPIRES  # 86400 seconds is the default
-# endregion
 
-# Leaving this to the default of True may cause double logging since both our own app
-# and celery think they are controlling the logger.
-# TODO: Configure celery's logger entirely manually and set this to False
-# worker_hijack_root_logger = False
-
-# region Notes on serialization performance
 # Option 0: Defaults (json serializer, no compression)
 # about 1.5 KB per queued task. 1KB in queue, 400B for result, 100 as a child entry in generator result
 
@@ -101,4 +74,3 @@ result_expires = CELERY_RESULT_EXPIRES  # 86400 seconds is the default
 # task_serializer = "pickle-bzip2"
 # result_serializer = "pickle-bzip2"
 # accept_content=["pickle", "pickle-bzip2"]
-# endregion

backend/danswer/background/connector_deletion.py

@@ -0,0 +1,110 @@
+"""
+To delete a connector / credential pair:
+(1) find all documents associated with connector / credential pair where there
+this the is only connector / credential pair that has indexed it
+(2) delete all documents from document stores
+(3) delete all entries from postgres
+(4) find all documents associated with connector / credential pair where there
+are multiple connector / credential pairs that have indexed it
+(5) update document store entries to remove access associated with the
+connector / credential pair from the access list
+(6) delete all relevant entries from postgres
+"""
+from sqlalchemy.orm import Session
+
+from danswer.access.access import get_access_for_documents
+from danswer.db.document import delete_documents_by_connector_credential_pair__no_commit
+from danswer.db.document import delete_documents_complete__no_commit
+from danswer.db.document import get_document_connector_counts
+from danswer.db.document import prepare_to_modify_documents
+from danswer.db.document_set import fetch_document_sets_for_documents
+from danswer.db.engine import get_sqlalchemy_engine
+from danswer.document_index.interfaces import DocumentIndex
+from danswer.document_index.interfaces import UpdateRequest
+from danswer.server.documents.models import ConnectorCredentialPairIdentifier
+from danswer.utils.logger import setup_logger
+
+logger = setup_logger()
+
+_DELETION_BATCH_SIZE = 1000
+
+
+def delete_connector_credential_pair_batch(
+    document_ids: list[str],
+    connector_id: int,
+    credential_id: int,
+    document_index: DocumentIndex,
+) -> None:
+    """
+    Removes a batch of documents ids from a cc-pair. If no other cc-pair uses a document anymore
+    it gets permanently deleted.
+    """
+    with Session(get_sqlalchemy_engine()) as db_session:
+        # acquire lock for all documents in this batch so that indexing can't
+        # override the deletion
+        with prepare_to_modify_documents(
+            db_session=db_session, document_ids=document_ids
+        ):
+            document_connector_counts = get_document_connector_counts(
+                db_session=db_session, document_ids=document_ids
+            )
+
+            # figure out which docs need to be completely deleted
+            document_ids_to_delete = [
+                document_id
+                for document_id, cnt in document_connector_counts
+                if cnt == 1
+            ]
+            logger.debug(f"Deleting documents: {document_ids_to_delete}")
+
+            document_index.delete(doc_ids=document_ids_to_delete)
+
+            delete_documents_complete__no_commit(
+                db_session=db_session,
+                document_ids=document_ids_to_delete,
+            )
+
+            # figure out which docs need to be updated
+            document_ids_to_update = [
+                document_id for document_id, cnt in document_connector_counts if cnt > 1
+            ]
+
+            # maps document id to list of document set names
+            new_doc_sets_for_documents: dict[str, set[str]] = {
+                document_id_and_document_set_names_tuple[0]: set(
+                    document_id_and_document_set_names_tuple[1]
+                )
+                for document_id_and_document_set_names_tuple in fetch_document_sets_for_documents(
+                    db_session=db_session,
+                    document_ids=document_ids_to_update,
+                )
+            }
+
+            # determine future ACLs for documents in batch
+            access_for_documents = get_access_for_documents(
+                document_ids=document_ids_to_update,
+                db_session=db_session,
+            )
+
+            # update Vespa
+            logger.debug(f"Updating documents: {document_ids_to_update}")
+            update_requests = [
+                UpdateRequest(
+                    document_ids=[document_id],
+                    access=access,
+                    document_sets=new_doc_sets_for_documents[document_id],
+                )
+                for document_id, access in access_for_documents.items()
+            ]
+            document_index.update(update_requests=update_requests)
+
+            # clean up Postgres
+            delete_documents_by_connector_credential_pair__no_commit(
+                db_session=db_session,
+                document_ids=document_ids_to_update,
+                connector_credential_pair_identifier=ConnectorCredentialPairIdentifier(
+                    connector_id=connector_id,
+                    credential_id=credential_id,
+                ),
+            )
+            db_session.commit()

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: