k

* early work in progress

* rename utility script

* move actual data seeding to a shareable function

* add test

* make the test pass with the fix

* fix comment

---------

Co-authored-by: Richard Kuo (Danswer) <rkuo@onyx.app>

.github/CODEOWNERS

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

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

@@ -0,0 +1,109 @@
+name: 'Build and Push Docker Image with Retry'
+description: 'Attempts to build and push a Docker image, with a retry on failure'
+inputs:
+  context:
+    description: 'Build context'
+    required: true
+  file:
+    description: 'Dockerfile location'
+    required: true
+  platforms:
+    description: 'Target platforms'
+    required: true
+  pull:
+    description: 'Always attempt to pull a newer version of the image'
+    required: false
+    default: 'true'
+  push:
+    description: 'Push the image to registry'
+    required: false
+    default: 'true'
+  load:
+    description: 'Load the image into Docker daemon'
+    required: false
+    default: 'true'
+  tags:
+    description: 'Image tags'
+    required: true
+  cache-from:
+    description: 'Cache sources'
+    required: false
+  cache-to:
+    description: 'Cache destinations'
+    required: false
+  retry-wait-time:
+    description: 'Time to wait before attempt 2 in seconds'
+    required: false
+    default: '60'
+  retry-wait-time-2:
+    description: 'Time to wait before attempt 3 in seconds'
+    required: false
+    default: '120'
+
+runs:
+  using: "composite"
+  steps:
+    - name: Build and push Docker image (Attempt 1 of 3)
+      id: buildx1
+      uses: docker/build-push-action@v6
+      continue-on-error: true
+      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: Wait before attempt 2
+      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
+      if: steps.buildx1.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: 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

@@ -0,0 +1,14 @@
+## Description
+
+[Provide a brief description of the changes in this PR]
+
+## How Has This Been Tested?
+
+[Describe the tests you ran to verify your changes]
+
+## Backporting (check the box to trigger backport action)
+
+Note: You have to check that the action passes, otherwise resolve the conflicts manually and tag the patches.
+
+- [ ] This PR should be backported (make sure to check that the backport attempt succeeds)
+- [ ] [Optional] Override Linear Check

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

@@ -3,42 +3,61 @@ 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') }}
 
 jobs:
   build-and-push:
-    runs-on: ubuntu-latest
+    # 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 }}"]
 
     steps:
-    - name: Checkout code
-      uses: actions/checkout@v2
+      - name: Checkout code
+        uses: actions/checkout@v4
 
-    - name: Set up Docker Buildx
-      uses: docker/setup-buildx-action@v1
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
 
-    - 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@v3
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_TOKEN }}
 
-    - name: Backend Image Docker Build and Push
-      uses: docker/build-push-action@v2
-      with:
-        context: ./backend
-        file: ./backend/Dockerfile
-        platforms: linux/amd64,linux/arm64
-        push: true
-        tags: |
-          danswer/danswer-backend:${{ github.ref_name }}
-          danswer/danswer-backend:latest
-        build-args: |
-          DANSWER_VERSION=${{ github.ref_name }}
+      - name: Install build-essential
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y build-essential
 
-    - 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/danswer/danswer-backend:${{ github.ref_name }}
-        severity: 'CRITICAL,HIGH'
-        trivyignores: ./backend/.trivyignore
+      - name: Backend Image Docker Build and Push
+        uses: docker/build-push-action@v5
+        with:
+          context: ./backend
+          file: ./backend/Dockerfile
+          platforms: linux/amd64,linux/arm64
+          push: true
+          tags: |
+            ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
+            ${{ env.LATEST_TAG == 'true' && format('{0}:latest', env.REGISTRY_IMAGE) || '' }}
+          build-args: |
+            ONYX_VERSION=${{ github.ref_name }}
+
+      # trivy has their own rate limiting issues causing this action to flake
+      # we worked around it by hardcoding to different db repos in env
+      # can re-enable when they figure it out
+      # https://github.com/aquasecurity/trivy/discussions/7538
+      # https://github.com/aquasecurity/trivy-action/issues/389
+      - name: Run Trivy vulnerability scanner
+        uses: aquasecurity/trivy-action@master
+        env:
+          TRIVY_DB_REPOSITORY: "public.ecr.aws/aquasecurity/trivy-db:2"
+          TRIVY_JAVA_DB_REPOSITORY: "public.ecr.aws/aquasecurity/trivy-java-db:1"
+        with:
+          # To run locally: trivy image --severity HIGH,CRITICAL onyxdotapp/onyx-backend
+          image-ref: docker.io/${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
+          severity: "CRITICAL,HIGH"
+          trivyignores: ./backend/.trivyignore

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

@@ -0,0 +1,141 @@
+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=${{ secrets.SENTRY_DSN }}
+            NEXT_PUBLIC_STRIPE_PUBLISHABLE_KEY=${{ secrets.STRIPE_PUBLISHABLE_KEY }}
+            NEXT_PUBLIC_GTM_ENABLED=true
+            NEXT_PUBLIC_FORGOT_PASSWORD_ENABLED=true
+            NEXT_PUBLIC_INCLUDE_ERROR_POPUP_SUPPORT_LINK=true
+            NODE_OPTIONS=--max-old-space-size=8192
+          # needed due to weird interactions with the builds for different platforms
+          no-cache: true
+          labels: ${{ steps.meta.outputs.labels }}
+          outputs: type=image,name=${{ 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

@@ -3,40 +3,149 @@ 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-and-push:
+  # 1) Preliminary job to check if the changed files are relevant
+  check_model_server_changes:
     runs-on: ubuntu-latest
-
+    outputs:
+      changed: ${{ steps.check.outputs.changed }}
     steps:
-    - name: Checkout code
-      uses: actions/checkout@v2
+      - name: Checkout code
+        uses: actions/checkout@v4
 
-    - name: Set up Docker Buildx
-      uses: docker/setup-buildx-action@v1
+      - name: Check if relevant files changed
+        id: check
+        run: |
+          # Default to "false"
+          echo "changed=false" >> $GITHUB_OUTPUT
 
-    - name: Login to Docker Hub
-      uses: docker/login-action@v1
-      with:
-        username: ${{ secrets.DOCKER_USERNAME }}
-        password: ${{ secrets.DOCKER_TOKEN }}
+          # Compare the previous commit (github.event.before) to the current one (github.sha)
+          # If any file in backend/model_server/** or backend/Dockerfile.model_server is changed,
+          # set changed=true
+          if git diff --name-only ${{ github.event.before }} ${{ github.sha }} \
+             | grep -E '^backend/model_server/|^backend/Dockerfile.model_server'; then
+            echo "changed=true" >> $GITHUB_OUTPUT
+          fi
 
-    - name: Model Server Image Docker Build and Push
-      uses: docker/build-push-action@v2
-      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 }}
+  build-amd64:
+    needs: [check_model_server_changes]
+    if: needs.check_model_server_changes.outputs.changed == 'true'
+    runs-on:
+      [runs-on, runner=8cpu-linux-x64, "run-id=${{ github.run_id }}-amd64"]
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
 
-    - name: Run Trivy vulnerability scanner
-      uses: aquasecurity/trivy-action@master
-      with:
-        image-ref: docker.io/danswer/danswer-model-server:${{ github.ref_name }}
-        severity: 'CRITICAL,HIGH'
+      - 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 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=${{ github.ref_name }}
+          outputs: type=registry
+          provenance: false
+
+  build-arm64:
+    needs: [check_model_server_changes]
+    if: needs.check_model_server_changes.outputs.changed == 'true'
+    runs-on:
+      [runs-on, runner=8cpu-linux-x64, "run-id=${{ github.run_id }}-arm64"]
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: System Info
+        run: |
+          df -h
+          free -h
+          docker system prune -af --volumes
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+        with:
+          driver-opts: |
+            image=moby/buildkit:latest
+            network=host
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_TOKEN }}
+
+      - name: Build and Push ARM64
+        uses: docker/build-push-action@v5
+        with:
+          context: ./backend
+          file: ./backend/Dockerfile.model_server
+          platforms: linux/arm64
+          push: true
+          tags: ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}-arm64
+          build-args: |
+            DANSWER_VERSION=${{ github.ref_name }}
+          outputs: type=registry
+          provenance: false
+
+  merge-and-scan:
+    needs: [build-amd64, build-arm64, check_model_server_changes]
+    if: needs.check_model_server_changes.outputs.changed == 'true'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_TOKEN }}
+
+      - name: Create and Push Multi-arch Manifest
+        run: |
+          docker buildx create --use
+          docker buildx imagetools create -t ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }} \
+            ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}-amd64 \
+            ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}-arm64
+          if [[ "${{ env.LATEST_TAG }}" == "true" ]]; then
+            docker buildx imagetools create -t ${{ env.REGISTRY_IMAGE }}:latest \
+              ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}-amd64 \
+              ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}-arm64
+          fi
+
+      - name: Run Trivy vulnerability scanner
+        uses: aquasecurity/trivy-action@master
+        env:
+          TRIVY_DB_REPOSITORY: "public.ecr.aws/aquasecurity/trivy-db:2"
+          TRIVY_JAVA_DB_REPOSITORY: "public.ecr.aws/aquasecurity/trivy-java-db:1"
+        with:
+          image-ref: docker.io/${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
+          severity: "CRITICAL,HIGH"
+          timeout: "10m"

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

@@ -3,40 +3,131 @@ 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') }}
 
 jobs:
-  build-and-push:
-    runs-on: ubuntu-latest
+  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: Checkout code
-      uses: actions/checkout@v2
+      - name: Prepare
+        run: |
+          platform=${{ matrix.platform }}
+          echo "PLATFORM_PAIR=${platform//\//-}" >> $GITHUB_ENV
 
-    - name: Set up Docker Buildx
-      uses: docker/setup-buildx-action@v1
+      - name: Checkout
+        uses: actions/checkout@v4
 
-    - name: Login to Docker Hub
-      uses: docker/login-action@v1
-      with:
-        username: ${{ secrets.DOCKER_USERNAME }}
-        password: ${{ secrets.DOCKER_TOKEN }}
+      - 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: Web Image Docker Build and Push
-      uses: docker/build-push-action@v2
-      with:
-        context: ./web
-        file: ./web/Dockerfile
-        platforms: linux/amd64,linux/arm64
-        push: true
-        tags: |
-          danswer/danswer-web-server:${{ github.ref_name }}
-          danswer/danswer-web-server:latest
-        build-args: |
-          DANSWER_VERSION=${{ github.ref_name }}
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
 
-    - name: Run Trivy vulnerability scanner
-      uses: aquasecurity/trivy-action@master
-      with:
-        image-ref: docker.io/danswer/danswer-web-server:${{ github.ref_name }}
-        severity: 'CRITICAL,HIGH'
+      - 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 }}
+            NODE_OPTIONS=--max-old-space-size=8192
+
+          # needed due to weird interactions with the builds for different platforms
+          no-cache: true
+          labels: ${{ steps.meta.outputs.labels }}
+          outputs: type=image,name=${{ 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-tag-latest.yml

@@ -1,32 +1,37 @@
+# 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:
-    runs-on: ubuntu-latest
+    # 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:
-    - name: Set up Docker Buildx
-      uses: docker/setup-buildx-action@v1
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v1
 
-    - name: Login to Docker Hub
-      uses: docker/login-action@v1
-      with:
-        username: ${{ secrets.DOCKER_USERNAME }}
-        password: ${{ secrets.DOCKER_TOKEN }}
+      - name: Login to Docker Hub
+        uses: docker/login-action@v1
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_TOKEN }}
 
-    - name: Enable Docker CLI experimental features
-      run: echo "DOCKER_CLI_EXPERIMENTAL=enabled" >> $GITHUB_ENV
+      - name: Enable Docker CLI experimental features
+        run: echo "DOCKER_CLI_EXPERIMENTAL=enabled" >> $GITHUB_ENV
 
-    - name: Pull, Tag and Push Web Server Image
-      run: |
-        docker buildx imagetools create -t danswer/danswer-web-server:latest danswer/danswer-web-server:${{ github.event.inputs.version }}
+      - name: Pull, Tag and Push Web Server Image
+        run: |
+          docker buildx imagetools create -t onyxdotapp/onyx-web-server:latest onyxdotapp/onyx-web-server:${{ github.event.inputs.version }}
 
-    - name: Pull, Tag and Push API Server Image
-      run: |
-        docker buildx imagetools create -t danswer/danswer-backend:latest danswer/danswer-backend:${{ github.event.inputs.version }}
+      - name: Pull, Tag and Push API Server Image
+        run: |
+          docker buildx imagetools create -t onyxdotapp/onyx-backend:latest onyxdotapp/onyx-backend:${{ github.event.inputs.version }}

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

@@ -0,0 +1,171 @@
+# 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

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

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

@@ -0,0 +1,142 @@
+# 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
+
+        # be careful enabling the sarif and upload as it may spam the security tab
+        # with a huge amount of items. Work out the issues before enabling upload.       
+#       - name: Run Trivy vulnerability scanner in repo mode
+#         if: always()
+#         uses: aquasecurity/trivy-action@0.29.0
+#         with:
+#           scan-type: fs
+#           scan-ref: .
+#           scanners: license
+#           format: table
+#           severity: HIGH,CRITICAL
+# #           format: sarif
+# #           output: trivy-results.sarif
+# 
+# #       - name: Upload Trivy scan results to GitHub Security tab
+# #         uses: github/codeql-action/upload-sarif@v3
+# #         with:
+# #           sarif_file: trivy-results.sarif
+
+  scan-trivy:
+    # See https://runs-on.com/runners/linux/
+    runs-on: [runs-on,runner=2cpu-linux-x64,"run-id=${{ github.run_id }}"]
+      
+    steps:
+    - name: Set up Docker Buildx
+      uses: docker/setup-buildx-action@v3
+
+    - name: Login to Docker Hub
+      uses: docker/login-action@v3
+      with:
+        username: ${{ secrets.DOCKER_USERNAME }}
+        password: ${{ secrets.DOCKER_TOKEN }}
+
+    # Backend
+    - name: Pull backend docker image
+      run: docker pull onyxdotapp/onyx-backend:latest
+
+    - name: Run Trivy vulnerability scanner on backend
+      uses: aquasecurity/trivy-action@0.29.0
+      env:
+        TRIVY_DB_REPOSITORY: 'public.ecr.aws/aquasecurity/trivy-db:2'
+        TRIVY_JAVA_DB_REPOSITORY: 'public.ecr.aws/aquasecurity/trivy-java-db:1'
+      with:
+        image-ref: onyxdotapp/onyx-backend:latest
+        scanners: license
+        severity: HIGH,CRITICAL
+        vuln-type: library
+        exit-code: 0  # Set to 1 if we want a failed scan to fail the workflow
+
+    # Web server
+    - name: Pull web server docker image
+      run: docker pull onyxdotapp/onyx-web-server:latest
+          
+    - name: Run Trivy vulnerability scanner on web server
+      uses: aquasecurity/trivy-action@0.29.0
+      env:
+        TRIVY_DB_REPOSITORY: 'public.ecr.aws/aquasecurity/trivy-db:2'
+        TRIVY_JAVA_DB_REPOSITORY: 'public.ecr.aws/aquasecurity/trivy-java-db:1'
+      with:
+        image-ref: onyxdotapp/onyx-web-server:latest
+        scanners: license
+        severity: HIGH,CRITICAL
+        vuln-type: library
+        exit-code: 0
+
+    # Model server
+    - name: Pull model server docker image
+      run: docker pull onyxdotapp/onyx-model-server:latest
+
+    - name: Run Trivy vulnerability scanner
+      uses: aquasecurity/trivy-action@0.29.0
+      env:
+        TRIVY_DB_REPOSITORY: 'public.ecr.aws/aquasecurity/trivy-db:2'
+        TRIVY_JAVA_DB_REPOSITORY: 'public.ecr.aws/aquasecurity/trivy-java-db:1'
+      with:
+        image-ref: onyxdotapp/onyx-model-server:latest
+        scanners: license
+        severity: HIGH,CRITICAL
+        vuln-type: library
+        exit-code: 0

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

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

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

@@ -0,0 +1,56 @@
+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: v3.17.0
+      
+    - name: Set up chart-testing
+      uses: helm/chart-testing-action@v2.7.0
+
+    # even though we specify chart-dirs in ct.yaml, it isn't used by ct for the list-changed command...
+    - name: Run chart-testing (list-changed)
+      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
+
+    # 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@v1.12.0
+
+    - 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-integration-tests.yml

@@ -0,0 +1,268 @@
+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=${{ env.RUNS_ON_S3_BUCKET_CACHE }},mode=max
+
+      # Start containers for multi-tenant tests
+      - name: Start Docker containers for multi-tenant tests
+        run: |
+          cd deployment/docker_compose
+          ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true \
+          MULTI_TENANT=true \
+          AUTH_TYPE=cloud \
+          REQUIRE_EMAIL_VERIFICATION=false \
+          DISABLE_TELEMETRY=true \
+          IMAGE_TAG=test \
+          DEV_MODE=true \
+          docker compose -f docker-compose.multitenant-dev.yml -p onyx-stack up -d
+        id: start_docker_multi_tenant
+
+      # In practice, `cloud` Auth type would require OAUTH credentials to be set.
+      - name: Run Multi-Tenant Integration Tests
+        run: |
+          echo "Waiting for 3 minutes to ensure API server is ready..."
+          sleep 180
+          echo "Running integration tests..."
+          docker run --rm --network onyx-stack_default \
+            --name test-runner \
+            -e POSTGRES_HOST=relational_db \
+            -e POSTGRES_USER=postgres \
+            -e POSTGRES_PASSWORD=password \
+            -e POSTGRES_DB=postgres \
+            -e POSTGRES_USE_NULL_POOL=true \
+            -e VESPA_HOST=index \
+            -e REDIS_HOST=cache \
+            -e API_SERVER_HOST=api_server \
+            -e OPENAI_API_KEY=${OPENAI_API_KEY} \
+            -e SLACK_BOT_TOKEN=${SLACK_BOT_TOKEN} \
+            -e TEST_WEB_HOSTNAME=test-runner \
+            -e AUTH_TYPE=cloud \
+            -e MULTI_TENANT=true \
+            -e REQUIRE_EMAIL_VERIFICATION=false \
+            -e DISABLE_TELEMETRY=true \
+            -e IMAGE_TAG=test \
+            -e DEV_MODE=true \
+            onyxdotapp/onyx-integration:test \
+            /app/tests/integration/multitenant_tests
+        continue-on-error: true
+        id: run_multitenant_tests
+
+      - name: Check multi-tenant test results
+        run: |
+          if [ ${{ steps.run_multitenant_tests.outcome }} == 'failure' ]; then
+            echo "Multi-tenant integration tests failed. Exiting with error."
+            exit 1
+          else
+            echo "All multi-tenant integration tests passed successfully."
+          fi
+
+      - name: Stop multi-tenant Docker containers
+        run: |
+          cd deployment/docker_compose
+          docker compose -f docker-compose.multitenant-dev.yml -p onyx-stack down -v
+
+      # NOTE: Use pre-ping/null pool to reduce flakiness due to dropped connections
+      - name: Start Docker containers
+        run: |
+          cd deployment/docker_compose
+          ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true \
+          AUTH_TYPE=basic \
+          POSTGRES_POOL_PRE_PING=true \
+          POSTGRES_USE_NULL_POOL=true \
+          REQUIRE_EMAIL_VERIFICATION=false \
+          DISABLE_TELEMETRY=true \
+          IMAGE_TAG=test \
+          INTEGRATION_TESTS_MODE=true \
+          docker compose -f docker-compose.dev.yml -p onyx-stack up -d
+        id: start_docker
+
+      - name: Wait for service to be ready
+        run: |
+          echo "Starting wait-for-service script..."
+
+          docker logs -f onyx-stack-api_server-1 &
+
+          start_time=$(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 $response). Retrying in 5 seconds..."
+            fi
+            
+            sleep 5
+          done
+          echo "Finished waiting for service."
+
+      - name: Start Mock Services
+        run: |
+          cd backend/tests/integration/mock_services
+          docker compose -f docker-compose.mock-it-services.yml \
+            -p mock-it-services-stack up -d
+
+      # NOTE: Use pre-ping/null to reduce flakiness due to dropped connections
+      - name: Run Standard Integration Tests
+        run: |
+          echo "Running integration tests..."
+          docker run --rm --network onyx-stack_default \
+            --name test-runner \
+            -e POSTGRES_HOST=relational_db \
+            -e POSTGRES_USER=postgres \
+            -e POSTGRES_PASSWORD=password \
+            -e POSTGRES_DB=postgres \
+            -e POSTGRES_POOL_PRE_PING=true \
+            -e POSTGRES_USE_NULL_POOL=true \
+            -e VESPA_HOST=index \
+            -e REDIS_HOST=cache \
+            -e API_SERVER_HOST=api_server \
+            -e OPENAI_API_KEY=${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 \
+            -e MOCK_CONNECTOR_SERVER_HOST=mock_connector_server \
+            -e MOCK_CONNECTOR_SERVER_PORT=8001 \
+            onyxdotapp/onyx-integration:test \
+            /app/tests/integration/tests \
+            /app/tests/integration/connector_job_tests
+        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
+
+      # ------------------------------------------------------------
+      # Always gather logs BEFORE "down":
+      - name: Dump API server logs
+        if: always()
+        run: |
+          cd deployment/docker_compose
+          docker compose -f docker-compose.dev.yml -p onyx-stack logs --no-color api_server > $GITHUB_WORKSPACE/api_server.log || true
+
+      - name: Dump all-container logs (optional)
+        if: always()
+        run: |
+          cd deployment/docker_compose
+          docker compose -f docker-compose.dev.yml -p onyx-stack logs --no-color > $GITHUB_WORKSPACE/docker-compose.log || true
+
+      - name: Upload logs
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: docker-all-logs
+          path: ${{ github.workspace }}/docker-compose.log
+      # ------------------------------------------------------------
+
+      - name: Stop Docker containers
+        if: always()
+        run: |
+          cd deployment/docker_compose
+          docker compose -f docker-compose.dev.yml -p onyx-stack down -v

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

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

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

@@ -0,0 +1,244 @@
+name: Run Playwright Tests
+concurrency:
+  group: Run-Playwright-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 }}
+  GEN_AI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+  MOCK_LLM_RESPONSE: true
+
+jobs:
+  playwright-tests:
+    name: Playwright Tests
+
+    # See https://runs-on.com/runners/linux/
+    runs-on:
+      [
+        runs-on,
+        runner=32cpu-linux-x64,
+        disk=large,
+        "run-id=${{ 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: ${{ github.workspace }}/docker-compose.log
+
+      - name: Stop Docker containers
+        run: |
+          cd deployment/docker_compose
+          docker compose -f docker-compose.dev.yml -p danswer-stack down -v
+
+# NOTE: Chromatic UI diff testing is currently disabled.
+# We are using Playwright for local and CI testing without visual regression checks.
+# Chromatic may be reintroduced in the future for UI diff testing if needed.
+
+# chromatic-tests:
+#   name: Chromatic Tests
+
+#   needs: playwright-tests
+#   runs-on:
+#     [
+#       runs-on,
+#       runner=32cpu-linux-x64,
+#       disk=large,
+#       "run-id=${{ 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-python-checks.yml

@@ -1,19 +1,23 @@
 name: Python Checks
 
 on:
+  merge_group:
   pull_request:
-    branches: [ main ]
+    branches:
+      - main
+      - 'release/**'
 
 jobs:
   mypy-check:
-    runs-on: ubuntu-latest
+    # See https://runs-on.com/runners/linux/
+    runs-on: [runs-on,runner=8cpu-linux-x64,"run-id=${{ github.run_id }}"]
 
     steps:
     - name: Checkout code
-      uses: actions/checkout@v3
+      uses: actions/checkout@v4
 
     - name: Set up Python
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
       with:
         python-version: '3.11'
         cache: 'pip'
@@ -23,9 +27,9 @@ jobs:
           backend/requirements/model_server.txt
     - run: |
         python -m pip install --upgrade pip
-        pip install -r backend/requirements/default.txt
-        pip install -r backend/requirements/dev.txt
-        pip install -r backend/requirements/model_server.txt
+        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: Run MyPy
       run: |

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

@@ -0,0 +1,92 @@
+name: Connector Tests
+
+on:
+  pull_request:
+    branches: [main]
+  schedule:
+    # This cron expression runs the job daily at 16:00 UTC (9am PT)
+    - cron: "0 16 * * *"
+
+env:
+  # Confluence
+  CONFLUENCE_TEST_SPACE_URL: ${{ secrets.CONFLUENCE_TEST_SPACE_URL }}
+  CONFLUENCE_TEST_SPACE: ${{ secrets.CONFLUENCE_TEST_SPACE }}
+  CONFLUENCE_IS_CLOUD: ${{ secrets.CONFLUENCE_IS_CLOUD }}
+  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 }}
+  # Zendesk
+  ZENDESK_SUBDOMAIN: ${{ secrets.ZENDESK_SUBDOMAIN }}
+  ZENDESK_EMAIL: ${{ secrets.ZENDESK_EMAIL }}
+  ZENDESK_TOKEN: ${{ secrets.ZENDESK_TOKEN }}
+  # Salesforce
+  SF_USERNAME: ${{ secrets.SF_USERNAME }}
+  SF_PASSWORD: ${{ secrets.SF_PASSWORD }}
+  SF_SECURITY_TOKEN: ${{ secrets.SF_SECURITY_TOKEN }}
+  # Airtable
+  AIRTABLE_TEST_BASE_ID: ${{ secrets.AIRTABLE_TEST_BASE_ID }}
+  AIRTABLE_TEST_TABLE_ID: ${{ secrets.AIRTABLE_TEST_TABLE_ID }}
+  AIRTABLE_TEST_TABLE_NAME: ${{ secrets.AIRTABLE_TEST_TABLE_NAME }}
+  AIRTABLE_ACCESS_TOKEN: ${{ secrets.AIRTABLE_ACCESS_TOKEN }}
+  # Sharepoint
+  SHAREPOINT_CLIENT_ID: ${{ secrets.SHAREPOINT_CLIENT_ID }}
+  SHAREPOINT_CLIENT_SECRET: ${{ secrets.SHAREPOINT_CLIENT_SECRET }}
+  SHAREPOINT_CLIENT_DIRECTORY_ID: ${{ secrets.SHAREPOINT_CLIENT_DIRECTORY_ID }}
+  SHAREPOINT_SITE: ${{ secrets.SHAREPOINT_SITE }}
+  # Gitbook
+  GITBOOK_SPACE_ID: ${{ secrets.GITBOOK_SPACE_ID }}
+  GITBOOK_API_KEY: ${{ secrets.GITBOOK_API_KEY }}
+
+jobs:
+  connectors-check:
+    # See https://runs-on.com/runners/linux/
+    runs-on: [runs-on,runner=8cpu-linux-x64,"run-id=${{ 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
+          playwright install chromium
+          playwright install-deps chromium
+          
+      - name: Run Tests
+        shell: script -q -e -c "bash --noprofile --norc -eo pipefail {0}"
+        run: py.test -o junit_family=xunit2 -xv --ff backend/tests/daily/connectors
+
+      - name: Alert on Failure
+        if: failure() && github.event_name == 'schedule'
+        env:
+          SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+        run: |
+          curl -X POST \
+            -H 'Content-type: application/json' \
+            --data '{"text":"Scheduled Connector Tests failed! Check the run at: https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}"}' \
+            $SLACK_WEBHOOK

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

@@ -0,0 +1,149 @@
+name: Model Server Tests
+
+on:
+  schedule:
+    # This cron expression runs the job daily at 16:00 UTC (9am PT)
+    - cron: "0 16 * * *"
+  workflow_dispatch:
+    inputs:
+      branch:
+        description: 'Branch to run the workflow on'
+        required: false
+        default: 'main'
+        
+env:
+  # Bedrock
+  AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
+  AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+  AWS_REGION_NAME: ${{ secrets.AWS_REGION_NAME }}
+
+  # API keys for testing
+  COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
+  LITELLM_API_KEY: ${{ secrets.LITELLM_API_KEY }}
+  LITELLM_API_URL: ${{ secrets.LITELLM_API_URL }}
+  OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+  AZURE_API_KEY: ${{ secrets.AZURE_API_KEY }}
+  AZURE_API_URL: ${{ secrets.AZURE_API_URL }}
+
+jobs:
+  model-check:
+    # See https://runs-on.com/runners/linux/
+    runs-on: [runs-on,runner=8cpu-linux-x64,"run-id=${{ github.run_id }}"]
+
+    env:
+      PYTHONPATH: ./backend
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_TOKEN }}
+
+      # tag every docker image with "test" so that we can spin up the correct set
+      # of images during testing
+
+      # We don't need to build the Web Docker image since it's not yet used
+      # in the integration tests. We have a separate action to verify that it builds
+      # successfully.
+      - name: Pull Model Server Docker image
+        run: |
+          docker pull onyxdotapp/onyx-model-server:latest
+          docker tag onyxdotapp/onyx-model-server:latest onyxdotapp/onyx-model-server:test
+          
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+          cache: "pip"
+          cache-dependency-path: |
+            backend/requirements/default.txt
+            backend/requirements/dev.txt
+
+      - name: Install Dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install --retries 5 --timeout 30 -r backend/requirements/default.txt
+          pip install --retries 5 --timeout 30 -r backend/requirements/dev.txt
+
+      - name: Start Docker containers
+        run: |
+          cd deployment/docker_compose
+          ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true \
+          AUTH_TYPE=basic \
+          REQUIRE_EMAIL_VERIFICATION=false \
+          DISABLE_TELEMETRY=true \
+          IMAGE_TAG=test \
+          docker compose -f docker-compose.model-server-test.yml -p onyx-stack up -d indexing_model_server
+        id: start_docker
+
+      - name: Wait for service to be ready
+        run: |
+          echo "Starting wait-for-service script..."
+
+          start_time=$(date +%s)
+          timeout=300  # 5 minutes in seconds
+
+          while true; do
+            current_time=$(date +%s)
+            elapsed_time=$((current_time - start_time))
+            
+            if [ $elapsed_time -ge $timeout ]; then
+              echo "Timeout reached. Service did not become ready in 5 minutes."
+              exit 1
+            fi
+            
+            # Use curl with error handling to ignore specific exit code 56
+            response=$(curl -s -o /dev/null -w "%{http_code}" http://localhost:9000/api/health || echo "curl_error")
+            
+            if [ "$response" = "200" ]; then
+              echo "Service is ready!"
+              break
+            elif [ "$response" = "curl_error" ]; then
+              echo "Curl encountered an error, possibly exit code 56. Continuing to retry..."
+            else
+              echo "Service not ready yet (HTTP status $response). Retrying in 5 seconds..."
+            fi
+            
+            sleep 5
+          done
+          echo "Finished waiting for service."
+          
+      - name: Run Tests
+        shell: script -q -e -c "bash --noprofile --norc -eo pipefail {0}"
+        run: |
+          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
+            
+      - name: Dump all-container logs (optional)
+        if: always()
+        run: |
+          cd deployment/docker_compose
+          docker compose -f docker-compose.model-server-test.yml -p onyx-stack logs --no-color > $GITHUB_WORKSPACE/docker-compose.log || true
+
+      - name: Upload logs
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: docker-all-logs
+          path: ${{ github.workspace }}/docker-compose.log
+          
+      - name: Stop Docker containers
+        if: always()
+        run: |
+          cd deployment/docker_compose
+          docker compose -f docker-compose.model-server-test.yml -p onyx-stack down -v
+          

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

@@ -1,22 +1,27 @@
 name: Python Unit Tests
 
 on:
+  merge_group:
   pull_request:
-    branches: [ main ]
+    branches:
+      - main
+      - 'release/**'
 
 jobs:
   backend-check:
-    runs-on: ubuntu-latest
+    # See https://runs-on.com/runners/linux/
+    runs-on: [runs-on,runner=8cpu-linux-x64,"run-id=${{ github.run_id }}"]
 
     env:
       PYTHONPATH: ./backend
-
+      REDIS_CLOUD_PYTEST_PASSWORD: ${{ secrets.REDIS_CLOUD_PYTEST_PASSWORD }}
+      
     steps:
     - name: Checkout code
       uses: actions/checkout@v4
 
     - name: Set up Python
-      uses: actions/setup-python@v4
+      uses: actions/setup-python@v5
       with:
         python-version: '3.11'
         cache: 'pip'
@@ -27,8 +32,8 @@ jobs:
     - name: Install Dependencies
       run: |
         python -m pip install --upgrade pip
-        pip install -r backend/requirements/default.txt
-        pip install -r backend/requirements/dev.txt
+        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}"

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

@@ -1,21 +1,23 @@
 name: Quality Checks PR
 concurrency:
-  group: Quality-Checks-PR-${{ github.head_ref }}
+  group: Quality-Checks-PR-${{ github.workflow }}-${{ github.head_ref || github.event.workflow_run.head_branch || github.run_id }}
   cancel-in-progress: true
 
 on:
+  merge_group:
   pull_request: null
 
 jobs:
   quality-checks:
-    runs-on: ubuntu-latest
+    # See https://runs-on.com/runners/linux/
+    runs-on: [runs-on,runner=8cpu-linux-x64,"run-id=${{ github.run_id }}"]
     steps:
-    - uses: actions/checkout@v4
-      with:
-        fetch-depth: 0
-    - uses: actions/setup-python@v5
-      with:
-        python-version: '3.11'
-    - uses: pre-commit/action@v3.0.0
-      with:
-        extra_args: --from-ref ${{ github.event.pull_request.base.sha }} --to-ref ${{ github.event.pull_request.head.sha }}
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+      - uses: pre-commit/action@v3.0.1
+        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/tag-nightly.yml

@@ -0,0 +1,53 @@
+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

@@ -4,4 +4,9 @@
 .mypy_cache
 .idea
 /deployment/data/nginx/app.conf
-.vscode/launch.json
+.vscode/
+*.sw?
+/backend/tests/regression/answer_quality/search_test_config.yaml
+/web/test-results/
+backend/onyx/agent_search/main/test_data.json
+backend/tests/regression/answer_quality/test_data.json

.prettierignore

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

.vscode/env_template.txt

@@ -0,0 +1,60 @@
+# Copy this file to .env in the .vscode folder
+# Fill in the <REPLACE THIS> values as needed, it is recommended to set the GEN_AI_API_KEY value to avoid having to set up an LLM in the UI
+# Also check out danswer/backend/scripts/restart_containers.sh for a script to restart the containers which Danswer relies on outside of VSCode/Cursor processes
+
+# For local dev, often user Authentication is not needed
+AUTH_TYPE=disabled
+
+# Skip warm up for dev
+SKIP_WARM_UP=True
+
+# Always keep these on for Dev
+# Logs all model prompts to stdout
+LOG_DANSWER_MODEL_INTERACTIONS=True
+# More verbose logging
+LOG_LEVEL=debug
+
+
+# This passes top N results to LLM an additional time for reranking prior to answer generation
+# This step is quite heavy on token usage so we disable it for dev generally
+DISABLE_LLM_DOC_RELEVANCE=False
+
+
+# Useful if you want to toggle auth on/off (google_oauth/OIDC specifically)
+OAUTH_CLIENT_ID=<REPLACE THIS>
+OAUTH_CLIENT_SECRET=<REPLACE THIS>
+# Generally not useful for dev, we don't generally want to set up an SMTP server for dev
+REQUIRE_EMAIL_VERIFICATION=False
+
+
+# Set these so if you wipe the DB, you don't end up having to go through the UI every time
+GEN_AI_API_KEY=<REPLACE THIS>
+OPENAI_API_KEY=<REPLACE THIS>
+# If answer quality isn't important for dev, use gpt-4o-mini since it's cheaper
+GEN_AI_MODEL_VERSION=gpt-4o
+FAST_GEN_AI_MODEL_VERSION=gpt-4o
+
+# For Danswer Slack Bot, overrides the UI values so no need to set this up via UI every time
+# Only needed if using DanswerBot
+#DANSWER_BOT_SLACK_APP_TOKEN=<REPLACE THIS>
+#DANSWER_BOT_SLACK_BOT_TOKEN=<REPLACE THIS>
+
+
+# Python stuff
+PYTHONPATH=../backend
+PYTHONUNBUFFERED=1
+
+
+# Internet Search 
+BING_API_KEY=<REPLACE THIS>
+
+
+# Enable the full set of Danswer Enterprise Edition features
+# NOTE: DO NOT ENABLE THIS UNLESS YOU HAVE A PAID ENTERPRISE LICENSE (or if you are using this for local testing/development)
+ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=False
+
+# Agent Search configs  # TODO: Remove give proper namings
+AGENT_RETRIEVAL_STATS=False   # Note: This setting will incur substantial re-ranking effort
+AGENT_RERANKING_STATS=True
+AGENT_MAX_QUERY_RETRIEVAL_RESULTS=20
+AGENT_RERANKING_MAX_QUERY_RETRIEVAL_RESULTS=20

.vscode/launch.template.jsonc

@@ -1,82 +1,401 @@
-/*
-
-  Copy this file into '.vscode/launch.json' or merge its
-  contents into your existing configurations.
-
-*/
+/* Copy this file into '.vscode/launch.json' or merge its contents into your existing configurations. */
 
 {
     // Use IntelliSense to learn about possible attributes.
     // Hover to view descriptions of existing attributes.
     // 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",
+            "configurations": [
+                "Web Server",
+                "Model Server",
+                "API Server",
+                "Slack Bot",
+		  		"Celery primary", 
+		  		"Celery light", 
+		  		"Celery heavy", 
+		  		"Celery indexing", 
+		  		"Celery beat",
+                "Celery monitoring",
+            ],
+			"presentation": {
+				 "group": "1",
+			 }
+        },
+		{
+			"name": "Web / Model / API",
+		  	"configurations": [
+		  		"Web Server", 
+		  		"Model Server", 
+		  		"API Server",
+		  	],
+			"presentation": {
+				 "group": "1",
+			 }
+		},
+		{
+			"name": "Celery (all)",
+		  	"configurations": [
+		  		"Celery primary", 
+		  		"Celery light", 
+		  		"Celery heavy", 
+		  		"Celery indexing", 
+		  		"Celery beat",
+                "Celery monitoring",
+		  	],
+			"presentation": {
+				 "group": "1",
+			 }
+		}
+    ],
     "configurations": [
-        {
-            "name": "API Server",
-            "type": "python",
-            "request": "launch",
-            "module": "uvicorn",
-            "cwd": "${workspaceFolder}/backend",
-            "env": {
-                "LOG_LEVEL": "DEBUG",
-                "DISABLE_AUTH": "True",
-                "TYPESENSE_API_KEY": "typesense_api_key",
-                "DYNAMIC_CONFIG_DIR_PATH": "./dynamic_config_storage"
-            },
-            "args": [
-                "danswer.main:app",
-                "--reload",
-                "--port",
-                "8080"
-            ]
-        },
-        {
-            "name": "Indexer",
-            "type": "python",
-            "request": "launch",
-            "program": "danswer/background/update.py",
-            "cwd": "${workspaceFolder}/backend",
-            "env": {
-                "LOG_LEVEL": "DEBUG",
-                "PYTHONPATH": ".",
-                "TYPESENSE_API_KEY": "typesense_api_key",
-                "DYNAMIC_CONFIG_DIR_PATH": "./dynamic_config_storage"
-            }
-        },
-        {
-            "name": "Temp File Deletion",
-            "type": "python",
-            "request": "launch",
-            "program": "danswer/background/file_deletion.py",
-            "cwd": "${workspaceFolder}/backend",
-            "env": {
-                "LOG_LEVEL": "DEBUG",
-                "PYTHONPATH": "${workspaceFolder}/backend"
-            }
-        },
-        // 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 Listener",
-            "type": "python",
-            "request": "launch",
-            "program": "danswer/listeners/slack_listener.py",
-            "cwd": "${workspaceFolder}/backend",
-            "envFile": "${workspaceFolder}/.env",
-            "env": {
-                "LOG_LEVEL": "DEBUG"
-            }
-        },
+		{
+	    	// Dummy entry used to label the group
+			"name": "--- Individual ---",
+			"type": "node",
+			"request": "launch",
+			"presentation": {
+				"group": "2",
+				"order": 0
+			}
+		},
         {
             "name": "Web Server",
             "type": "node",
             "request": "launch",
             "cwd": "${workspaceRoot}/web",
             "runtimeExecutable": "npm",
+            "envFile": "${workspaceFolder}/.vscode/.env",
             "runtimeArgs": [
                 "run", "dev"
             ],
-            "console": "integratedTerminal"
-        }
+            "presentation": {
+				 "group": "2",
+			 },
+            "console": "integratedTerminal",
+            "consoleTitle": "Web Server Console"
+        },
+        {
+            "name": "Model Server",
+            "consoleName": "Model Server",
+            "type": "debugpy",
+            "request": "launch",
+            "module": "uvicorn",
+            "cwd": "${workspaceFolder}/backend",
+            "envFile": "${workspaceFolder}/.vscode/.env",
+            "env": {
+                "LOG_LEVEL": "DEBUG",
+                "PYTHONUNBUFFERED": "1"
+            },
+            "args": [
+                "model_server.main:app",
+                "--reload",
+                "--port",
+                "9000"
+            ],
+            "presentation": {
+				 "group": "2",
+			},
+            "consoleTitle": "Model Server Console"
+        },
+        {
+            "name": "API Server",
+            "consoleName": "API Server",
+            "type": "debugpy",
+            "request": "launch",
+            "module": "uvicorn",
+            "cwd": "${workspaceFolder}/backend",
+            "envFile": "${workspaceFolder}/.vscode/.env",
+            "env": {
+                "LOG_DANSWER_MODEL_INTERACTIONS": "True",
+                "LOG_LEVEL": "DEBUG",
+                "PYTHONUNBUFFERED": "1"
+            },
+            "args": [
+                "onyx.main:app",
+                "--reload",
+                "--port",
+                "8080"
+            ],
+            "presentation": {
+				 "group": "2",
+			 },
+            "consoleTitle": "API Server Console"
+        },
+        // For the listener to access the Slack API,
+        // DANSWER_BOT_SLACK_APP_TOKEN & DANSWER_BOT_SLACK_BOT_TOKEN need to be set in .env file located in the root of the project
+        {
+            "name": "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",
+            "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,checkpoint_cleanup",
+            ],
+            "presentation": {
+				 "group": "2",
+			 },
+            "consoleTitle": "Celery light Console"
+        },
+        {
+            "name": "Celery heavy",
+            "type": "debugpy",
+            "request": "launch",
+            "module": "celery",
+            "cwd": "${workspaceFolder}/backend",
+            "envFile": "${workspaceFolder}/.vscode/.env",
+            "env": {
+                "LOG_LEVEL": "INFO",
+                "PYTHONUNBUFFERED": "1",
+                "PYTHONPATH": "."
+            },
+            "args": [
+                "-A",
+                "onyx.background.celery.versioned_apps.heavy",
+                "worker",
+                "--pool=threads",
+                "--concurrency=4",
+                "--prefetch-multiplier=1",
+                "--loglevel=INFO",
+                "--hostname=heavy@%n",
+                "-Q",
+                "connector_pruning,connector_doc_permissions_sync,connector_external_group_sync",
+            ],
+            "presentation": {
+				 "group": "2",
+			 },
+            "consoleTitle": "Celery heavy Console"
+        },
+        {
+            "name": "Celery indexing",
+            "type": "debugpy",
+            "request": "launch",
+            "module": "celery",
+            "cwd": "${workspaceFolder}/backend",
+            "envFile": "${workspaceFolder}/.vscode/.env",
+            "env": {
+                "ENABLE_MULTIPASS_INDEXING": "false",
+                "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"
+        },
+        {
+            "name": "Celery monitoring",
+            "type": "debugpy",
+            "request": "launch",
+            "module": "celery",
+            "cwd": "${workspaceFolder}/backend",
+            "envFile": "${workspaceFolder}/.vscode/.env",
+            "env": {},
+            "args": [
+                "-A",
+                "onyx.background.celery.versioned_apps.monitoring",
+                "worker",
+                "--pool=solo",
+                "--concurrency=1",
+                "--prefetch-multiplier=1",
+                "--loglevel=INFO",
+                "--hostname=monitoring@%n",
+                "-Q",
+                "monitoring",
+            ],
+            "presentation": {
+				 "group": "2",
+			 },
+            "consoleTitle": "Celery monitoring Console"
+        },
+        {
+            "name": "Celery beat",
+            "type": "debugpy",
+            "request": "launch",
+            "module": "celery",
+            "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",
+            "consoleName": "Pytest",
+            "type": "debugpy",
+            "request": "launch",
+            "module": "pytest",
+            "cwd": "${workspaceFolder}/backend",
+            "envFile": "${workspaceFolder}/.vscode/.env",
+            "env": {
+                "LOG_LEVEL": "DEBUG",
+                "PYTHONUNBUFFERED": "1",
+                "PYTHONPATH": "."
+            },
+            "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"
+        },
+		{
+	    	// 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",
+            "request": "launch",
+            "runtimeExecutable": "bash",
+            "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": "."
+            },
+        },
+        {
+            "name": "Install Python Requirements",
+            "type": "node",
+            "request": "launch",
+            "runtimeExecutable": "bash",
+            "runtimeArgs": [
+                "-c",
+                "pip install -r backend/requirements/default.txt && pip install -r backend/requirements/dev.txt && pip install -r backend/requirements/ee.txt && pip install -r backend/requirements/model_server.txt"
+            ],
+            "cwd": "${workspaceFolder}",
+            "console": "integratedTerminal",
+            "presentation": {
+                 "group": "3"
+            }
+        },
     ]
-}
+}

CONTRIBUTING.md

@@ -1,139 +1,210 @@
-<!-- DANSWER_METADATA={"link": "https://github.com/danswer-ai/danswer/blob/main/CONTRIBUTING.md"} -->
+<!-- DANSWER_METADATA={"link": "https://github.com/onyx-dot-app/onyx/blob/main/CONTRIBUTING.md"} -->
 
-# Contributing to Danswer
-Hey there! We are so excited that you're interested in Danswer.
+# Contributing to Onyx
+
+Hey there! We are so excited that you're interested in Onyx.
 
 As an open source project in a rapidly changing space, we welcome all contributions.
 
-
 ## 💃 Guidelines
+
 ### Contribution Opportunities
-The [GitHub Issues](https://github.com/danswer-ai/danswer/issues) page is a great place to start for contribution ideas.
+
+The [GitHub Issues](https://github.com/onyx-dot-app/onyx/issues) page is a great place to start for contribution ideas.
+
+To ensure that your contribution is aligned with the project's direction, please reach out to Hagen (or any other maintainer) on the Onyx team
+via [Slack](https://join.slack.com/t/onyx-dot-app/shared_invite/zt-2twesxdr6-5iQitKZQpgq~hYIZ~dv3KA) /
+[Discord](https://discord.gg/TDJ59cGV2X) or [email](mailto:founders@onyx.app).
 
 Issues that have been explicitly approved by the maintainers (aligned with the direction of the project)
 will be marked with the `approved by maintainers` label.
 Issues marked `good first issue` are an especially great place to start.
 
 **Connectors** to other tools are another great place to contribute. For details on how, refer to this
-[README.md](https://github.com/danswer-ai/danswer/blob/main/backend/danswer/connectors/README.md).
+[README.md](https://github.com/onyx-dot-app/onyx/blob/main/backend/onyx/connectors/README.md).
 
 If you have a new/different contribution in mind, we'd love to hear about it!
-Your input is vital to making sure that Danswer moves in the right direction.
+Your input is vital to making sure that Onyx moves in the right direction.
 Before starting on implementation, please raise a GitHub issue.
 
-And always feel free to message us (Chris Weaver / Yuhong Sun) on 
-[Slack](https://join.slack.com/t/danswer/shared_invite/zt-2afut44lv-Rw3kSWu6_OmdAXRpCv80DQ) / 
-[Discord](https://discord.gg/TDJ59cGV2X) directly about anything at all. 
-
+Also, always feel free to message the founders (Chris Weaver / Yuhong Sun) on
+[Slack](https://join.slack.com/t/onyx-dot-app/shared_invite/zt-2twesxdr6-5iQitKZQpgq~hYIZ~dv3KA) /
+[Discord](https://discord.gg/TDJ59cGV2X) directly about anything at all.
 
 ### Contributing Code
+
 To contribute to this project, please follow the
 ["fork and pull request"](https://docs.github.com/en/get-started/quickstart/contributing-to-projects) workflow.
 When opening a pull request, mention related issues and feel free to tag relevant maintainers.
 
 Before creating a pull request please make sure that the new changes conform to the formatting and linting requirements.
-See the [Formatting and Linting](#-formatting-and-linting) section for how to run these checks locally.
-
+See the [Formatting and Linting](#formatting-and-linting) section for how to run these checks locally.
 
 ### Getting Help 🙋
+
 Our goal is to make contributing as easy as possible. If you run into any issues please don't hesitate to reach out.
 That way we can help future contributors and users can avoid the same issue.
 
 We also have support channels and generally interesting discussions on our
-[Slack](https://join.slack.com/t/danswer/shared_invite/zt-2afut44lv-Rw3kSWu6_OmdAXRpCv80DQ)
-and 
+[Slack](https://join.slack.com/t/onyx-dot-app/shared_invite/zt-2twesxdr6-5iQitKZQpgq~hYIZ~dv3KA)
+and
 [Discord](https://discord.gg/TDJ59cGV2X).
 
 We would love to see you there!
 
-
 ## Get Started 🚀
-Danswer being a fully functional app, relies on some external pieces of software, specifically:
+
+Onyx being a fully functional app, relies on some external software, specifically:
+
 - [Postgres](https://www.postgresql.org/) (Relational DB)
 - [Vespa](https://vespa.ai/) (Vector DB/Search Engine)
+- [Redis](https://redis.io/) (Cache)
+- [Nginx](https://nginx.org/) (Not needed for development flows generally)
 
-This guide provides instructions to set up the Danswer specific services outside of Docker because it's easier for
-development purposes but also feel free to just use the containers and update with local changes by providing the
-`--build` flag.
-
+> **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.
 
 ### Local Set Up
-It is recommended to use Python version 3.11
+
+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, the version of Tensorflow we use may not be available for your platform.
+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
 
-#### Installing 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.
+
 _For Windows, activate the virtual environment using Command Prompt:_
+
 ```bash
 .venv\Scripts\activate
 ```
+
 If using PowerShell, the command slightly differs:
+
 ```powershell
 .venv\Scripts\Activate.ps1
 ```
 
 Install the required python dependencies:
+
 ```bash
-pip install -r danswer/backend/requirements/default.txt
-pip install -r danswer/backend/requirements/dev.txt
-pip install -r danswer/backend/requirements/model_server.txt
+pip install -r onyx/backend/requirements/default.txt
+pip install -r onyx/backend/requirements/dev.txt
+pip install -r onyx/backend/requirements/ee.txt
+pip install -r onyx/backend/requirements/model_server.txt
 ```
 
-Install [Node.js and npm](https://docs.npmjs.com/downloading-and-installing-node-js-and-npm) for the frontend.
-Once the above is done, navigate to `danswer/web` run:
-```bash
-npm i
-```
+Install Playwright for Python (headless browser required by the Web Connector)
 
-Install Playwright (required by the Web Connector)
+In the activated Python virtualenv, install Playwright for Python by running:
 
-> Note: If you have just done the pip install, open a new terminal and source the python virtual-env again.
-This will update the path to include playwright
-
-Then install Playwright by running:
 ```bash
 playwright install
 ```
 
+You may have to deactivate and reactivate your virtualenv for `playwright` to appear on your path.
+
+#### 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:
 
-#### Dependent Docker Containers
-First navigate to `danswer/deployment/docker_compose`, then start up Vespa and Postgres with:
 ```bash
-docker compose -f docker-compose.dev.yml -p danswer-stack up -d index relational_db
+npm i
 ```
-(index refers to Vespa and relational_db refers to Postgres)
 
-#### Running Danswer
-To start the frontend, navigate to `danswer/web` and run:
+## Formatting and Linting
+
+### Backend
+
+For the backend, you'll need to setup pre-commit hooks (black / reorder-python-imports).
+First, install pre-commit (if you don't have it already) following the instructions
+[here](https://pre-commit.com/#installation).
+
+With the virtual environment active, install the pre-commit library with:
+
+```bash
+pip install pre-commit
+```
+
+Then, from the `onyx/backend` directory, run:
+
+```bash
+pre-commit install
+```
+
+Additionally, we use `mypy` for static type checking.
+Onyx is fully type-annotated, and we want to keep it that way!
+To run the mypy checks manually, run `python -m mypy .` from the `onyx/backend` directory.
+
+### Web
+
+We use `prettier` for formatting. The desired version (2.8.8) will be installed via a `npm i` from the `onyx/web` directory.
+To run the formatter, use `npx prettier --write .` from the `onyx/web` directory.
+Please double check that prettier passes before creating a pull request.
+
+# Running the application for development
+
+## Developing using VSCode Debugger (recommended)
+
+We highly recommend using VSCode debugger for development.
+See [CONTRIBUTING_VSCODE.md](./CONTRIBUTING_VSCODE.md) for more details.
+
+Otherwise, you can follow the instructions below to run the application for development.
+
+## Manually running the application for development
+### Docker containers for external software
+
+You will need Docker installed to run these containers.
+
+First navigate to `onyx/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
+```
+
+(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:
+
 ```bash
 npm run dev
 ```
 
 Next, start the model server which runs the local NLP models.
-Navigate to `danswer/backend` and run:
+Navigate to `onyx/backend` and run:
+
 ```bash
 uvicorn model_server.main:app --reload --port 9000
 ```
+
 _For Windows (for compatibility with both PowerShell and Command Prompt):_
+
 ```bash
-powershell -Command "
-    uvicorn model_server.main:app --reload --port 9000
-"
+powershell -Command "uvicorn model_server.main:app --reload --port 9000"
 ```
 
-The first time running Danswer, you will need to run the DB migrations for Postgres.
+The first time running Onyx, you will need to run the DB migrations for Postgres.
 After the first time, this is no longer required unless the DB models change.
 
-Navigate to `danswer/backend` and with the venv active, run:
+Navigate to `onyx/backend` and with the venv active, run:
+
 ```bash
 alembic upgrade head
 ```
@@ -141,47 +212,65 @@ alembic upgrade head
 Next, start the task queue which orchestrates the background jobs.
 Jobs that take more time are run async from the API server.
 
-Still in `danswer/backend`, run:
+Still in `onyx/backend`, run:
+
 ```bash
 python ./scripts/dev_run_background_jobs.py
 ```
 
-To run the backend API server, navigate back to `danswer/backend` and run:
+To run the backend API server, navigate back to `onyx/backend` and run:
+
 ```bash
-AUTH_TYPE=disabled uvicorn danswer.main:app --reload --port 8080
+AUTH_TYPE=disabled uvicorn onyx.main:app --reload --port 8080
 ```
+
 _For Windows (for compatibility with both PowerShell and Command Prompt):_
+
 ```bash
 powershell -Command "
     $env:AUTH_TYPE='disabled'
-    uvicorn danswer.main:app --reload --port 8080 
+    uvicorn onyx.main:app --reload --port 8080
 "
 ```
 
-Note: if you need finer logging, add the additional environment variable `LOG_LEVEL=DEBUG` to the relevant services.
+> **Note:**
+> If you need finer logging, add the additional environment variable `LOG_LEVEL=DEBUG` to the relevant services.
+
+#### Wrapping up
+
+You should now have 4 servers running:
+
+- Web server
+- Backend API
+- 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.
+
+You've successfully set up a local Onyx instance! 🏁
+
+#### Running the Onyx application in a container
+
+You can run the full Onyx application stack from pre-built images including all external software dependencies.
+
+Navigate to `onyx/deployment/docker_compose` and run:
 
-### 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).
-Then, from the `danswer/backend` directory, run:
 ```bash
-pre-commit install
+docker compose -f docker-compose.dev.yml -p onyx-stack up -d
 ```
 
-Additionally, we use `mypy` for static type checking.
-Danswer is fully type-annotated, and we would like to keep it that way! 
-To run the mypy checks manually, run `python -m mypy .` from the `danswer/backend` directory.
+After Docker pulls and starts these containers, navigate to `http://localhost:3000` to use Onyx.
 
+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:
 
-#### Web
-We use `prettier` for formatting. The desired version (2.8.8) will be installed via a `npm i` from the `danswer/web` directory. 
-To run the formatter, use `npx prettier --write .` from the `danswer/web` directory.
-Please double check that prettier passes before creating a pull request.
+```bash
+docker compose -f docker-compose.dev.yml -p onyx-stack up -d --build
+```
 
 
 ### Release Process
-Danswer follows the semver versioning standard.
+
+Onyx loosely follows the SemVer versioning standard.
+Major changes are released with a "minor" version bump. Currently we use patch release versions to indicate small feature changes.
 A set of Docker containers will be pushed automatically to DockerHub with every tag.
-You can see the containers [here](https://hub.docker.com/search?q=danswer%2F).
+You can see the containers [here](https://hub.docker.com/search?q=onyx%2F).

CONTRIBUTING_MACOS.md

@@ -0,0 +1,36 @@
+## 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).
+
+### 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"
+```
+
+> **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
+ensure it is running before continuing with the docker commands.
+
+### Formatting and Linting
+
+MacOS will likely require you to remove some quarantine attributes on some of the hooks for them to execute properly.
+After installing pre-commit, run the following command:
+
+```bash
+sudo xattr -r -d com.apple.quarantine ~/.cache/pre-commit
+```

CONTRIBUTING_VSCODE.md

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

LICENSE

@@ -1,6 +1,10 @@
-MIT License
+Copyright (c) 2023-present DanswerAI, Inc.
 
-Copyright (c) 2023 Yuhong Sun, Chris Weaver
+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.
 
 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

@@ -1,109 +1,116 @@
-<!-- DANSWER_METADATA={"link": "https://github.com/danswer-ai/danswer/blob/main/README.md"} -->
+<!-- DANSWER_METADATA={"link": "https://github.com/onyx-dot-app/onyx/blob/main/README.md"} -->
+
+<a name="readme-top"></a>
 
 <h2 align="center">
-<a href="https://www.danswer.ai/"> <img width="50%" src="https://github.com/danswer-owners/danswer/blob/1fabd9372d66cd54238847197c33f091a724803b/DanswerWithName.png?raw=true)" /></a>
+<a href="https://www.onyx.app/"> <img width="50%" src="https://github.com/onyx-dot-app/onyx/blob/logo/OnyxLogoCropped.jpg?raw=true)" /></a>
 </h2>
 
 <p align="center">
-<p align="center">Open Source Gen-AI Chat + Unified Search.</p>
+<p align="center">Open Source Gen-AI + Enterprise Search.</p>
 
 <p align="center">
-<a href="https://docs.danswer.dev/" target="_blank">
+<a href="https://docs.onyx.app/" target="_blank">
     <img src="https://img.shields.io/badge/docs-view-blue" alt="Documentation">
 </a>
-<a href="https://join.slack.com/t/danswer/shared_invite/zt-2afut44lv-Rw3kSWu6_OmdAXRpCv80DQ" target="_blank">
+<a href="https://join.slack.com/t/onyx-dot-app/shared_invite/zt-2twesxdr6-5iQitKZQpgq~hYIZ~dv3KA" target="_blank">
     <img src="https://img.shields.io/badge/slack-join-blue.svg?logo=slack" alt="Slack">
 </a>
 <a href="https://discord.gg/TDJ59cGV2X" target="_blank">
     <img src="https://img.shields.io/badge/discord-join-blue.svg?logo=discord&logoColor=white" alt="Discord">
 </a>
-<a href="https://github.com/danswer-ai/danswer/blob/main/README.md" target="_blank">
+<a href="https://github.com/onyx-dot-app/onyx/blob/main/README.md" target="_blank">
     <img src="https://img.shields.io/static/v1?label=license&message=MIT&color=blue" alt="License">
 </a>
 </p>
 
-<strong>[Danswer](https://www.danswer.ai/)</strong> is the AI Assistant connected to your company's docs, apps, and people. 
-Danswer provides a Chat interface and plugs into any LLM of your choice. Danswer can be deployed anywhere and for any 
-scale - on a laptop, on-premise, or to cloud. Since you own the deployment, your user data and chats are fully in your 
-own control. Danswer is MIT licensed and designed to be modular and easily extensible. The system also comes fully ready 
-for production usage with user authentication, role management (admin/basic users), chat persistence, and a UI for 
-configuring Personas (AI Assistants) and their Prompts.
-
-Danswer also serves as a Unified Search across all common workplace tools such as Slack, Google Drive, Confluence, etc.
-By combining LLMs and team specific knowledge, Danswer becomes a subject matter expert for the team. Imagine ChatGPT if
-it had access to your team's unique knowledge! It enables questions such as "A customer wants feature X, is this already
-supported?" or "Where's the pull request for feature Y?"
-
-<h3>Usage</h3>
-
-Danswer Web App:
-
-https://github.com/danswer-ai/danswer/assets/32520769/563be14c-9304-47b5-bf0a-9049c2b6f410
+<strong>[Onyx](https://www.onyx.app/)</strong> (formerly Danswer) is the AI platform connected to your company's docs, apps, and people.
+Onyx provides a feature rich Chat interface and plugs into any LLM of your choice.
+Keep knowledge and access controls sync-ed across over 40 connectors like Google Drive, Slack, Confluence, Salesforce, etc.
+Create custom AI agents with unique prompts, knowledge, and actions that the agents can take.
+Onyx can be deployed securely anywhere and for any scale - on a laptop, on-premise, or to cloud.
 
 
-Or, plug Danswer into your existing Slack workflows (more integrations to come 😁):
+<h3>Feature Highlights</h3>
 
-https://github.com/danswer-ai/danswer/assets/25087905/3e19739b-d178-4371-9a38-011430bdec1b
+**Deep research over your team's knowledge:**
+
+https://private-user-images.githubusercontent.com/32520769/414509312-48392e83-95d0-4fb5-8650-a396e05e0a32.mp4?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.a9D8A0sgKE9AoaoE-mfFbJ6_OKYeqaf7TZ4Han2JfW8
 
 
-For more details on the Admin UI to manage connectors and users, check out our 
-<strong><a href="https://www.youtube.com/watch?v=geNzY1nbCnU">Full Video Demo</a></strong>!
+**Use Onyx as a secure AI Chat with any LLM:**
+
+![Onyx Chat Silent Demo](https://github.com/onyx-dot-app/onyx/releases/download/v0.21.1/OnyxChatSilentDemo.gif)
+
+
+**Easily set up connectors to your apps:**
+
+![Onyx Connector Silent Demo](https://github.com/onyx-dot-app/onyx/releases/download/v0.21.1/OnyxConnectorSilentDemo.gif)
+
+
+**Access Onyx where your team already works:**
+
+![Onyx Bot Demo](https://github.com/onyx-dot-app/onyx/releases/download/v0.21.1/OnyxBot.png)
+
 
 ## Deployment
+**To try it out for free and get started in seconds, check out [Onyx Cloud](https://cloud.onyx.app/signup)**.
 
-Danswer can easily be run locally (even on a laptop) or deployed on a virtual machine with a single
-`docker compose` command. Checkout our [docs](https://docs.danswer.dev/quickstart) to learn more.
+Onyx can also be run locally (even on a laptop) or deployed on a virtual machine with a single
+`docker compose` command. Checkout our [docs](https://docs.onyx.app/quickstart) to learn more.
 
-We also have built-in support for deployment on Kubernetes. Files for that can be found [here](https://github.com/danswer-ai/danswer/tree/main/deployment/kubernetes).
+We also have built-in support for high-availability/scalable deployment on Kubernetes.
+References [here](https://github.com/onyx-dot-app/onyx/tree/main/deployment).
 
 
-## 💃 Main Features 
-* Chat UI with the ability to select documents to chat with.
-* Create custom AI Assistants with different prompts and backing knowledge sets.
-* Connect Danswer with LLM of your choice (self-host for a fully airgapped solution).
-* Document Search + AI Answers for natural language queries.
-* Connectors to all common workplace tools like Google Drive, Confluence, Slack, etc.
-* Slack integration to get answers and search results directly in Slack.
+## 🔍 Other Notable Benefits of Onyx
+- Custom deep learning models for indexing and inference time, only through Onyx + learning from user feedback.
+- Flexible security features like SSO (OIDC/SAML/OAuth2), RBAC, encryption of credentials, etc.
+- Knowledge curation features like document-sets, query history, usage analytics, etc.
+- Scalable deployment options tested up to many tens of thousands users and hundreds of millions of documents.
 
 
 ## 🚧 Roadmap
-* Chat/Prompt sharing with specific teammates and user groups.
-* 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.
-
-
-## 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.
+- New methods in information retrieval (StructRAG, LightGraphRAG, etc.)
+- Personalized Search
+- Organizational understanding and ability to locate and suggest experts from your team.
+- Code Search
+- SQL and Structured Query Language
 
 
 ## 🔌 Connectors
-Efficiently pulls the latest changes from:
-  * Slack
-  * GitHub
-  * Google Drive
-  * Confluence
-  * Jira
-  * Zendesk
-  * Gmail
-  * Notion
-  * Gong
-  * Slab
-  * Linear
-  * Productboard
-  * Guru
-  * Bookstack
-  * Document360
-  * Sharepoint
-  * Hubspot
-  * Local Files
-  * Websites
-  * And more ...
+Keep knowledge and access up to sync across 40+ connectors:
+
+- Google Drive
+- Confluence
+- Slack
+- Gmail
+- Salesforce
+- Microsoft Sharepoint
+- Github
+- Jira
+- Zendesk
+- Gong
+- Microsoft Teams
+- Dropbox
+- Local Files
+- Websites
+- And more ...
+
+See the full list [here](https://docs.onyx.app/connectors).
+
+
+## 📚 Licensing
+There are two editions of Onyx:
+
+- Onyx Community Edition (CE) is available freely under the MIT Expat license. Simply follow the Deployment guide above.
+- Onyx Enterprise Edition (EE) includes extra features that are primarily useful for larger organizations.
+For feature details, check out [our website](https://www.onyx.app/pricing).
+
+To try the Onyx Enterprise Edition:
+1. Checkout [Onyx Cloud](https://cloud.onyx.app/signup).
+2. For self-hosting the Enterprise Edition, contact us at [founders@onyx.app](mailto:founders@onyx.app) or book a call with us on our [Cal](https://cal.com/team/onyx/founders).
+
 
 ## 💡 Contributing
 Looking to contribute? Please check out the [Contribution Guide](CONTRIBUTING.md) for more details.

backend/.gitignore

@@ -5,7 +5,8 @@ site_crawls/
 .ipynb_checkpoints/
 api_keys.py
 *ipynb
-.env
+.env*
 vespa-app.zip
 dynamic_config_storage/
-celerybeat-schedule
+celerybeat-schedule*
+onyx/connectors/salesforce/data/

backend/Dockerfile

@@ -1,15 +1,21 @@
 FROM python:3.11.7-slim-bookworm
 
-LABEL com.danswer.maintainer="founders@danswer.ai"
-LABEL com.danswer.description="This image is for the backend of Danswer. It is MIT Licensed and \
-free for all to use. You can find it at https://hub.docker.com/r/danswer/danswer-backend. For \
-more details, visit https://github.com/danswer-ai/danswer."
+LABEL com.danswer.maintainer="founders@onyx.app"
+LABEL com.danswer.description="This image is the web/frontend container of Onyx which \
+contains code for both the Community and Enterprise editions of Onyx. If you do not \
+have a contract or agreement with DanswerAI, you are not permitted to use the Enterprise \
+Edition features outside of personal development or testing purposes. Please reach out to \
+founders@onyx.app for more information. Please visit https://github.com/onyx-dot-app/onyx"
 
-# Default DANSWER_VERSION, typically overriden during builds by GitHub Actions.
-ARG DANSWER_VERSION=0.3-dev
-ENV DANSWER_VERSION=${DANSWER_VERSION}
-RUN echo "DANSWER_VERSION: ${DANSWER_VERSION}"
+# Default ONYX_VERSION, typically overriden during builds by GitHub Actions.
+ARG ONYX_VERSION=0.8-dev
+# DO_NOT_TRACK is used to disable telemetry for Unstructured
+ENV ONYX_VERSION=${ONYX_VERSION} \
+    DANSWER_RUNNING_IN_DOCKER="true" \
+    DO_NOT_TRACK="true"
 
+
+RUN echo "ONYX_VERSION: ${ONYX_VERSION}"
 # Install system dependencies
 # cmake needed for psycopg (postgres)
 # libpq-dev needed for psycopg (postgres)
@@ -17,49 +23,94 @@ RUN echo "DANSWER_VERSION: ${DANSWER_VERSION}"
 # zip for Vespa step futher down
 # ca-certificates for HTTPS
 RUN apt-get update && \
-    apt-get install -y cmake curl zip ca-certificates libgnutls30=3.7.9-2+deb12u2 \
-    libblkid1=2.38.1-5+deb12u1 libmount1=2.38.1-5+deb12u1 libsmartcols1=2.38.1-5+deb12u1 \
-    libuuid1=2.38.1-5+deb12u1 && \
+    apt-get install -y \
+        cmake \
+        curl \
+        zip \
+        ca-certificates \
+        libgnutls30 \
+        libblkid1 \
+        libmount1 \
+        libsmartcols1 \
+        libuuid1 \
+        libxmlsec1-dev \
+        pkg-config \
+        gcc \
+        nano \
+        vim && \
     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
-RUN pip install --no-cache-dir --upgrade -r /tmp/requirements.txt && \
+COPY ./requirements/ee.txt /tmp/ee-requirements.txt
+RUN pip install --no-cache-dir --upgrade \
+        --retries 5 \
+        --timeout 30 \
+        -r /tmp/requirements.txt \
+        -r /tmp/ee-requirements.txt && \
     pip uninstall -y py && \
-    playwright install chromium && playwright install-deps chromium && \
+    playwright install chromium && \
+    playwright install-deps chromium && \
     ln -s /usr/local/bin/supervisord /usr/bin/supervisord
 
 # Cleanup for CVEs and size reduction
 # https://github.com/tornadoweb/tornado/issues/3107
 # xserver-common and xvfb included by playwright installation but not needed after
-# perl-base is part of the base Python Debian image but not needed for Danswer functionality
+# perl-base is part of the base Python Debian image but not needed for Onyx functionality
 # perl-base could only be removed with --allow-remove-essential
-RUN apt-get remove -y --allow-remove-essential perl-base xserver-common xvfb cmake \
-    libldap-2.5-0 libldap-2.5-0 && \
+RUN apt-get update && \
+    apt-get remove -y --allow-remove-essential \
+        perl-base \
+        xserver-common \
+        xvfb \
+        cmake \
+        libldap-2.5-0 \
+        libxmlsec1-dev \
+        pkg-config \
+        gcc && \
+    apt-get install -y libxmlsec1-openssl && \
     apt-get autoremove -y && \
     rm -rf /var/lib/apt/lists/* && \
-    rm /usr/local/lib/python3.11/site-packages/tornado/test/test.key
+    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 transformers import AutoTokenizer; AutoTokenizer.from_pretrained('intfloat/e5-base-v2')"
+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); \
-nltk.download('wordnet', quiet=True); \
 nltk.download('punkt', quiet=True);"
+# nltk.download('wordnet', quiet=True); introduce this back if lemmatization is needed
 
 # Set up application files
 WORKDIR /app
-COPY ./danswer /app/danswer
+
+# Enterprise Version Files
+COPY ./ee /app/ee
+COPY supervisord.conf /etc/supervisor/conf.d/supervisord.conf
+
+# Set up application files
+COPY ./onyx /app/onyx
 COPY ./shared_configs /app/shared_configs
 COPY ./alembic /app/alembic
+COPY ./alembic_tenants /app/alembic_tenants
 COPY ./alembic.ini /app/alembic.ini
 COPY supervisord.conf /usr/etc/supervisord.conf
 
-ENV PYTHONPATH /app
+# Escape hatch scripts
+COPY ./scripts/debugging /app/scripts/debugging
+COPY ./scripts/force_delete_connector_by_id.py /app/scripts/force_delete_connector_by_id.py
+
+# Put logo in assets
+COPY ./assets /app/assets
+
+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

@@ -1,46 +1,60 @@
 FROM python:3.11.7-slim-bookworm
 
-LABEL com.danswer.maintainer="founders@danswer.ai"
-LABEL com.danswer.description="This image is for the Danswer model server which runs all of the \
-AI models for Danswer. This container and all the code is MIT Licensed and free for all to use. \
-You can find it at https://hub.docker.com/r/danswer/danswer-model-server. For more details, \
-visit https://github.com/danswer-ai/danswer."
+LABEL com.danswer.maintainer="founders@onyx.app"
+LABEL com.danswer.description="This image is for the Onyx model server which runs all of the \
+AI models for Onyx. This container and all the code is MIT Licensed and free for all to use. \
+You can find it at https://hub.docker.com/r/onyx/onyx-model-server. For more details, \
+visit https://github.com/onyx-dot-app/onyx."
 
-# Default DANSWER_VERSION, typically overriden during builds by GitHub Actions.
-ARG DANSWER_VERSION=0.3-dev
-ENV DANSWER_VERSION=${DANSWER_VERSION}
-RUN echo "DANSWER_VERSION: ${DANSWER_VERSION}"
+# Default ONYX_VERSION, typically overriden during builds by GitHub Actions.
+ARG ONYX_VERSION=0.8-dev
+ENV ONYX_VERSION=${ONYX_VERSION} \
+    DANSWER_RUNNING_IN_DOCKER="true"
+
+
+RUN echo "ONYX_VERSION: ${ONYX_VERSION}"
 
 COPY ./requirements/model_server.txt /tmp/requirements.txt
-RUN pip install --no-cache-dir --upgrade -r /tmp/requirements.txt
+RUN pip install --no-cache-dir --upgrade \
+        --retries 5 \
+        --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
-RUN python -c "from transformers import AutoModel, AutoTokenizer, TFDistilBertForSequenceClassification; \
-from huggingface_hub import snapshot_download; \
-AutoTokenizer.from_pretrained('danswer/intent-model'); \
-AutoTokenizer.from_pretrained('intfloat/e5-base-v2'); \
+# Download tokenizers, distilbert for the Onyx model
+# Download model weights
+# Run Nomic to pull in the custom architecture and have it cached locally
+RUN python -c "from transformers import AutoTokenizer; \
+AutoTokenizer.from_pretrained('distilbert-base-uncased'); \
 AutoTokenizer.from_pretrained('mixedbread-ai/mxbai-rerank-xsmall-v1'); \
-snapshot_download('danswer/intent-model'); \
-snapshot_download('intfloat/e5-base-v2'); \
-snapshot_download('mixedbread-ai/mxbai-rerank-xsmall-v1')"
+from huggingface_hub import snapshot_download; \
+snapshot_download(repo_id='danswer/hybrid-intent-token-classifier', revision='v1.0.3'); \
+snapshot_download('nomic-ai/nomic-embed-text-v1'); \
+snapshot_download('mixedbread-ai/mxbai-rerank-xsmall-v1'); \
+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
+RUN mv /root/.cache/huggingface /root/.cache/temp_huggingface
 
 WORKDIR /app
 
 # Utils used by model server
-COPY ./danswer/utils/logger.py /app/danswer/utils/logger.py
+COPY ./onyx/utils/logger.py /app/onyx/utils/logger.py
 
 # Place to fetch version information
-COPY ./danswer/__init__.py /app/danswer/__init__.py
+COPY ./onyx/__init__.py /app/onyx/__init__.py
 
-# Shared between Danswer Backend and Model Server
+# Shared between Onyx Backend and Model Server
 COPY ./shared_configs /app/shared_configs
 
 # Model Server main code
 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.
 
-[alembic]
+[DEFAULT]
 # path to migration scripts
 script_location = alembic
 
@@ -47,7 +47,8 @@ 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
@@ -106,3 +107,12 @@ 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

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

backend/alembic/env.py

@@ -1,86 +1,235 @@
+from typing import Any, Literal
+from onyx.db.engine import get_iam_auth_token
+from onyx.configs.app_configs import USE_IAM_AUTH
+from onyx.configs.app_configs import POSTGRES_HOST
+from onyx.configs.app_configs import POSTGRES_PORT
+from onyx.configs.app_configs import POSTGRES_USER
+from onyx.configs.app_configs import AWS_REGION_NAME
+from onyx.db.engine import build_connection_string
+from onyx.db.engine import get_all_tenant_ids
+from sqlalchemy import event
+from sqlalchemy import pool
+from sqlalchemy import text
+from sqlalchemy.engine.base import Connection
+import os
+import ssl
 import asyncio
+import logging
 from logging.config import fileConfig
 
 from alembic import context
-from 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.schema import SchemaItem
+from onyx.configs.constants import SSL_CERT_FILE
+from shared_configs.configs import MULTI_TENANT, POSTGRES_DEFAULT_SCHEMA
+from onyx.db.models import Base
 from celery.backends.database.session import ResultModelBase  # type: ignore
 
-# this is the Alembic Config object, which provides
-# access to the values within the .ini file in use.
+# Alembic Config object
 config = context.config
 
-# Interpret the config file for Python logging.
-# This line sets up loggers basically.
-if config.config_file_name is not None:
+if config.config_file_name is not None and config.attributes.get(
+    "configure_logger", True
+):
     fileConfig(config.config_file_name)
 
-# add your model's MetaData object here
-# for 'autogenerate' support
-# from myapp import mymodel
-# target_metadata = mymodel.Base.metadata
 target_metadata = [Base.metadata, ResultModelBase.metadata]
 
-# 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"}
+logger = logging.getLogger(__name__)
+
+ssl_context: ssl.SSLContext | None = None
+if USE_IAM_AUTH:
+    if not os.path.exists(SSL_CERT_FILE):
+        raise FileNotFoundError(f"Expected {SSL_CERT_FILE} when USE_IAM_AUTH is true.")
+    ssl_context = ssl.create_default_context(cafile=SSL_CERT_FILE)
 
 
-def run_migrations_offline() -> None:
-    """Run migrations in 'offline' mode.
+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
 
-    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.
+def get_schema_options() -> tuple[str, bool, bool]:
+    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:
+    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"))
+
+    connection.execute(text(f'SET search_path TO "{schema_name}"'))
 
-    """
-    url = build_connection_string()
     context.configure(
-        url=url,
+        connection=connection,
         target_metadata=target_metadata,  # type: ignore
-        literal_binds=True,
-        dialect_opts={"paramstyle": "named"},
+        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"),
     )
 
     with context.begin_transaction():
         context.run_migrations()
 
 
-def do_run_migrations(connection: Connection) -> None:
-    context.configure(connection=connection, target_metadata=target_metadata)  # type: ignore
+def provide_iam_token_for_alembic(
+    dialect: Any, conn_rec: Any, cargs: Any, cparams: Any
+) -> None:
+    if USE_IAM_AUTH:
+        # Database connection settings
+        region = AWS_REGION_NAME
+        host = POSTGRES_HOST
+        port = POSTGRES_PORT
+        user = POSTGRES_USER
 
-    with context.begin_transaction():
-        context.run_migrations()
+        # Get IAM authentication token
+        token = get_iam_auth_token(host, port, user, region)
+
+        # For Alembic / SQLAlchemy in this context, set SSL and password
+        cparams["password"] = token
+        cparams["ssl"] = ssl_context
 
 
 async def run_async_migrations() -> None:
-    """In this scenario we need to create an Engine
-    and associate a connection with the context.
+    schema_name, create_schema, upgrade_all_tenants = get_schema_options()
 
-    """
-
-    connectable = create_async_engine(
+    engine = create_async_engine(
         build_connection_string(),
         poolclass=pool.NullPool,
     )
 
-    async with connectable.connect() as connection:
-        await connection.run_sync(do_run_migrations)
+    if USE_IAM_AUTH:
 
-    await connectable.dispose()
+        @event.listens_for(engine.sync_engine, "do_connect")
+        def event_provide_iam_token_for_alembic(
+            dialect: Any, conn_rec: Any, cargs: Any, cparams: Any
+        ) -> None:
+            provide_iam_token_for_alembic(dialect, conn_rec, cargs, cparams)
+
+    if upgrade_all_tenants:
+        tenant_schemas = get_all_tenant_ids()
+        for schema in tenant_schemas:
+            try:
+                logger.info(f"Migrating schema: {schema}")
+                async with engine.connect() as connection:
+                    await connection.run_sync(
+                        do_run_migrations,
+                        schema_name=schema,
+                        create_schema=create_schema,
+                    )
+            except Exception as e:
+                logger.error(f"Error migrating schema {schema}: {e}")
+                raise
+    else:
+        try:
+            logger.info(f"Migrating schema: {schema_name}")
+            async with engine.connect() as connection:
+                await connection.run_sync(
+                    do_run_migrations,
+                    schema_name=schema_name,
+                    create_schema=create_schema,
+                )
+        except Exception as e:
+            logger.error(f"Error migrating schema {schema_name}: {e}")
+            raise
+
+    await engine.dispose()
+
+
+def run_migrations_offline() -> None:
+    schema_name, _, upgrade_all_tenants = get_schema_options()
+    url = build_connection_string()
+
+    if upgrade_all_tenants:
+        engine = create_async_engine(url)
+
+        if USE_IAM_AUTH:
+
+            @event.listens_for(engine.sync_engine, "do_connect")
+            def event_provide_iam_token_for_alembic_offline(
+                dialect: Any, conn_rec: Any, cargs: Any, cparams: Any
+            ) -> None:
+                provide_iam_token_for_alembic(dialect, conn_rec, cargs, cparams)
+
+        tenant_schemas = get_all_tenant_ids()
+        engine.sync_engine.dispose()
+
+        for schema in tenant_schemas:
+            logger.info(f"Migrating schema: {schema}")
+            context.configure(
+                url=url,
+                target_metadata=target_metadata,  # type: ignore
+                literal_binds=True,
+                include_object=include_object,
+                version_table_schema=schema,
+                include_schemas=True,
+                script_location=config.get_main_option("script_location"),
+                dialect_opts={"paramstyle": "named"},
+            )
+
+            with context.begin_transaction():
+                context.run_migrations()
+    else:
+        logger.info(f"Migrating schema: {schema_name}")
+        context.configure(
+            url=url,
+            target_metadata=target_metadata,  # type: ignore
+            literal_binds=True,
+            include_object=include_object,
+            version_table_schema=schema_name,
+            include_schemas=True,
+            script_location=config.get_main_option("script_location"),
+            dialect_opts={"paramstyle": "named"},
+        )
+
+        with context.begin_transaction():
+            context.run_migrations()
 
 
 def run_migrations_online() -> None:
-    """Run migrations in 'online' mode."""
-
     asyncio.run(run_async_migrations())
 
 

backend/alembic/versions/027381bce97c_add_shortcut_option_for_users.py

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

backend/alembic/versions/0568ccf46a6b_add_thread_specific_model_selection.py

@@ -0,0 +1,27 @@
+"""Add thread specific model selection
+
+Revision ID: 0568ccf46a6b
+Revises: e209dc5a8156
+Create Date: 2024-06-19 14:25:36.376046
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "0568ccf46a6b"
+down_revision = "e209dc5a8156"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "chat_session",
+        sa.Column("current_alternate_model", sa.String(), nullable=True),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("chat_session", "current_alternate_model")

backend/alembic/versions/05c07bf07c00_add_search_doc_relevance_details.py

@@ -0,0 +1,32 @@
+"""add search doc relevance details
+
+Revision ID: 05c07bf07c00
+Revises: b896bbd0d5a7
+Create Date: 2024-07-10 17:48:15.886653
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "05c07bf07c00"
+down_revision = "b896bbd0d5a7"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "search_doc",
+        sa.Column("is_relevant", sa.Boolean(), nullable=True),
+    )
+    op.add_column(
+        "search_doc",
+        sa.Column("relevance_explanation", sa.String(), nullable=True),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("search_doc", "relevance_explanation")
+    op.drop_column("search_doc", "is_relevant")

backend/alembic/versions/08a1eda20fe1_add_earliest_indexing_to_connector.py

@@ -0,0 +1,26 @@
+"""add_indexing_start_to_connector
+
+Revision ID: 08a1eda20fe1
+Revises: 8a87bd6ec550
+Create Date: 2024-07-23 11:12:39.462397
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "08a1eda20fe1"
+down_revision = "8a87bd6ec550"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "connector", sa.Column("indexing_start", sa.DateTime(), nullable=True)
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("connector", "indexing_start")

backend/alembic/versions/0a2b51deb0b8_add_starter_prompts.py

@@ -12,8 +12,8 @@ from sqlalchemy.dialects import postgresql
 # revision identifiers, used by Alembic.
 revision = "0a2b51deb0b8"
 down_revision = "5f4b8568a221"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:

backend/alembic/versions/0a98909f2757_enable_encrypted_fields.py

@@ -0,0 +1,113 @@
+"""Enable Encrypted Fields
+
+Revision ID: 0a98909f2757
+Revises: 570282d33c49
+Create Date: 2024-05-05 19:30:34.317972
+
+"""
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.sql import table
+from sqlalchemy.dialects import postgresql
+import json
+
+from onyx.utils.encryption import encrypt_string_to_bytes
+
+# revision identifiers, used by Alembic.
+revision = "0a98909f2757"
+down_revision = "570282d33c49"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    connection = op.get_bind()
+
+    op.alter_column("key_value_store", "value", nullable=True)
+    op.add_column(
+        "key_value_store",
+        sa.Column(
+            "encrypted_value",
+            sa.LargeBinary,
+            nullable=True,
+        ),
+    )
+
+    # Need a temporary column to translate the JSONB to binary
+    op.add_column("credential", sa.Column("temp_column", sa.LargeBinary()))
+
+    creds_table = table(
+        "credential",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column(
+            "credential_json",
+            postgresql.JSONB(astext_type=sa.Text()),
+            nullable=False,
+        ),
+        sa.Column(
+            "temp_column",
+            sa.LargeBinary(),
+            nullable=False,
+        ),
+    )
+
+    results = connection.execute(sa.select(creds_table))
+
+    # This uses the MIT encrypt which does not actually encrypt the credentials
+    # In other words, this upgrade does not apply the encryption. Porting existing sensitive data
+    # and key rotation currently is not supported and will come out in the future
+    for row_id, creds, _ in results:
+        creds_binary = encrypt_string_to_bytes(json.dumps(creds))
+        connection.execute(
+            creds_table.update()
+            .where(creds_table.c.id == row_id)
+            .values(temp_column=creds_binary)
+        )
+
+    op.drop_column("credential", "credential_json")
+    op.alter_column("credential", "temp_column", new_column_name="credential_json")
+
+    op.add_column("llm_provider", sa.Column("temp_column", sa.LargeBinary()))
+
+    llm_table = table(
+        "llm_provider",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column(
+            "api_key",
+            sa.String(),
+            nullable=False,
+        ),
+        sa.Column(
+            "temp_column",
+            sa.LargeBinary(),
+            nullable=False,
+        ),
+    )
+    results = connection.execute(sa.select(llm_table))
+
+    for row_id, api_key, _ in results:
+        llm_key = encrypt_string_to_bytes(api_key)
+        connection.execute(
+            llm_table.update()
+            .where(llm_table.c.id == row_id)
+            .values(temp_column=llm_key)
+        )
+
+    op.drop_column("llm_provider", "api_key")
+    op.alter_column("llm_provider", "temp_column", new_column_name="api_key")
+
+
+def downgrade() -> None:
+    # Some information loss but this is ok. Should not allow decryption via downgrade.
+    op.drop_column("credential", "credential_json")
+    op.drop_column("llm_provider", "api_key")
+
+    op.add_column("llm_provider", sa.Column("api_key", sa.String()))
+    op.add_column(
+        "credential",
+        sa.Column("credential_json", postgresql.JSONB(astext_type=sa.Text())),
+    )
+
+    op.execute("DELETE FROM key_value_store WHERE value IS NULL")
+    op.alter_column("key_value_store", "value", nullable=False)
+    op.drop_column("key_value_store", "encrypted_value")

backend/alembic/versions/0ebb1d516877_add_ccpair_deletion_failure_message.py

@@ -0,0 +1,27 @@
+"""add ccpair deletion failure message
+
+Revision ID: 0ebb1d516877
+Revises: 52a219fb5233
+Create Date: 2024-09-10 15:03:48.233926
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "0ebb1d516877"
+down_revision = "52a219fb5233"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "connector_credential_pair",
+        sa.Column("deletion_failure_message", sa.String(), nullable=True),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("connector_credential_pair", "deletion_failure_message")

backend/alembic/versions/0f7ff6d75b57_add_index_to_index_attempt_time_created.py

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

backend/alembic/versions/15326fcec57e_introduce_onyx_apis.py

@@ -1,4 +1,4 @@
-"""Introduce Danswer APIs
+"""Introduce Onyx APIs
 
 Revision ID: 15326fcec57e
 Revises: 77d07dffae64
@@ -8,13 +8,13 @@ Create Date: 2023-11-11 20:51:24.228999
 from alembic import op
 import sqlalchemy as sa
 
-from danswer.configs.constants import DocumentSource
+from onyx.configs.constants import DocumentSource
 
 # revision identifiers, used by Alembic.
 revision = "15326fcec57e"
 down_revision = "77d07dffae64"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:

backend/alembic/versions/173cae5bba26_port_config_store.py

@@ -12,8 +12,8 @@ from sqlalchemy.dialects import postgresql
 # revision identifiers, used by Alembic.
 revision = "173cae5bba26"
 down_revision = "e50154680a5c"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:

backend/alembic/versions/177de57c21c9_display_custom_llm_models.py

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

backend/alembic/versions/1a03d2c2856b_add_indexes_to_document__tag.py

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

backend/alembic/versions/1b10e1fda030_add_additional_data_to_notifications.py

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

backend/alembic/versions/1b8206b29c5d_add_user_delete_cascades.py

@@ -0,0 +1,102 @@
+"""add_user_delete_cascades
+
+Revision ID: 1b8206b29c5d
+Revises: 35e6853a51d5
+Create Date: 2024-09-18 11:48:59.418726
+
+"""
+from alembic import op
+
+
+# revision identifiers, used by Alembic.
+revision = "1b8206b29c5d"
+down_revision = "35e6853a51d5"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.drop_constraint("credential_user_id_fkey", "credential", type_="foreignkey")
+    op.create_foreign_key(
+        "credential_user_id_fkey",
+        "credential",
+        "user",
+        ["user_id"],
+        ["id"],
+        ondelete="CASCADE",
+    )
+
+    op.drop_constraint("chat_session_user_id_fkey", "chat_session", type_="foreignkey")
+    op.create_foreign_key(
+        "chat_session_user_id_fkey",
+        "chat_session",
+        "user",
+        ["user_id"],
+        ["id"],
+        ondelete="CASCADE",
+    )
+
+    op.drop_constraint("chat_folder_user_id_fkey", "chat_folder", type_="foreignkey")
+    op.create_foreign_key(
+        "chat_folder_user_id_fkey",
+        "chat_folder",
+        "user",
+        ["user_id"],
+        ["id"],
+        ondelete="CASCADE",
+    )
+
+    op.drop_constraint("prompt_user_id_fkey", "prompt", type_="foreignkey")
+    op.create_foreign_key(
+        "prompt_user_id_fkey", "prompt", "user", ["user_id"], ["id"], ondelete="CASCADE"
+    )
+
+    op.drop_constraint("notification_user_id_fkey", "notification", type_="foreignkey")
+    op.create_foreign_key(
+        "notification_user_id_fkey",
+        "notification",
+        "user",
+        ["user_id"],
+        ["id"],
+        ondelete="CASCADE",
+    )
+
+    op.drop_constraint("inputprompt_user_id_fkey", "inputprompt", type_="foreignkey")
+    op.create_foreign_key(
+        "inputprompt_user_id_fkey",
+        "inputprompt",
+        "user",
+        ["user_id"],
+        ["id"],
+        ondelete="CASCADE",
+    )
+
+
+def downgrade() -> None:
+    op.drop_constraint("credential_user_id_fkey", "credential", type_="foreignkey")
+    op.create_foreign_key(
+        "credential_user_id_fkey", "credential", "user", ["user_id"], ["id"]
+    )
+
+    op.drop_constraint("chat_session_user_id_fkey", "chat_session", type_="foreignkey")
+    op.create_foreign_key(
+        "chat_session_user_id_fkey", "chat_session", "user", ["user_id"], ["id"]
+    )
+
+    op.drop_constraint("chat_folder_user_id_fkey", "chat_folder", type_="foreignkey")
+    op.create_foreign_key(
+        "chat_folder_user_id_fkey", "chat_folder", "user", ["user_id"], ["id"]
+    )
+
+    op.drop_constraint("prompt_user_id_fkey", "prompt", type_="foreignkey")
+    op.create_foreign_key("prompt_user_id_fkey", "prompt", "user", ["user_id"], ["id"])
+
+    op.drop_constraint("notification_user_id_fkey", "notification", type_="foreignkey")
+    op.create_foreign_key(
+        "notification_user_id_fkey", "notification", "user", ["user_id"], ["id"]
+    )
+
+    op.drop_constraint("inputprompt_user_id_fkey", "inputprompt", type_="foreignkey")
+    op.create_foreign_key(
+        "inputprompt_user_id_fkey", "inputprompt", "user", ["user_id"], ["id"]
+    )

backend/alembic/versions/1f60f60c3401_embedding_model_search_settings.py

@@ -0,0 +1,135 @@
+"""embedding model -> search settings
+
+Revision ID: 1f60f60c3401
+Revises: f17bf3b0d9f1
+Create Date: 2024-08-25 12:39:51.731632
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+from onyx.configs.chat_configs import NUM_POSTPROCESSED_RESULTS
+
+# revision identifiers, used by Alembic.
+revision = "1f60f60c3401"
+down_revision = "f17bf3b0d9f1"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.drop_constraint(
+        "index_attempt__embedding_model_fk", "index_attempt", type_="foreignkey"
+    )
+    # Rename the table
+    op.rename_table("embedding_model", "search_settings")
+
+    # Add new columns
+    op.add_column(
+        "search_settings",
+        sa.Column(
+            "multipass_indexing", sa.Boolean(), nullable=False, server_default="false"
+        ),
+    )
+    op.add_column(
+        "search_settings",
+        sa.Column(
+            "multilingual_expansion",
+            postgresql.ARRAY(sa.String()),
+            nullable=False,
+            server_default="{}",
+        ),
+    )
+    op.add_column(
+        "search_settings",
+        sa.Column(
+            "disable_rerank_for_streaming",
+            sa.Boolean(),
+            nullable=False,
+            server_default="false",
+        ),
+    )
+    op.add_column(
+        "search_settings", sa.Column("rerank_model_name", sa.String(), nullable=True)
+    )
+    op.add_column(
+        "search_settings", sa.Column("rerank_provider_type", sa.String(), nullable=True)
+    )
+    op.add_column(
+        "search_settings", sa.Column("rerank_api_key", sa.String(), nullable=True)
+    )
+    op.add_column(
+        "search_settings",
+        sa.Column(
+            "num_rerank",
+            sa.Integer(),
+            nullable=False,
+            server_default=str(NUM_POSTPROCESSED_RESULTS),
+        ),
+    )
+
+    # Add the new column as nullable initially
+    op.add_column(
+        "index_attempt", sa.Column("search_settings_id", sa.Integer(), nullable=True)
+    )
+
+    # Populate the new column with data from the existing embedding_model_id
+    op.execute("UPDATE index_attempt SET search_settings_id = embedding_model_id")
+
+    # Create the foreign key constraint
+    op.create_foreign_key(
+        "fk_index_attempt_search_settings",
+        "index_attempt",
+        "search_settings",
+        ["search_settings_id"],
+        ["id"],
+    )
+
+    # Make the new column non-nullable
+    op.alter_column("index_attempt", "search_settings_id", nullable=False)
+
+    # Drop the old embedding_model_id column
+    op.drop_column("index_attempt", "embedding_model_id")
+
+
+def downgrade() -> None:
+    # Add back the embedding_model_id column
+    op.add_column(
+        "index_attempt", sa.Column("embedding_model_id", sa.Integer(), nullable=True)
+    )
+
+    # Populate the old column with data from search_settings_id
+    op.execute("UPDATE index_attempt SET embedding_model_id = search_settings_id")
+
+    # Make the old column non-nullable
+    op.alter_column("index_attempt", "embedding_model_id", nullable=False)
+
+    # Drop the foreign key constraint
+    op.drop_constraint(
+        "fk_index_attempt_search_settings", "index_attempt", type_="foreignkey"
+    )
+
+    # Drop the new search_settings_id column
+    op.drop_column("index_attempt", "search_settings_id")
+
+    # Rename the table back
+    op.rename_table("search_settings", "embedding_model")
+
+    # Remove added columns
+    op.drop_column("embedding_model", "num_rerank")
+    op.drop_column("embedding_model", "rerank_api_key")
+    op.drop_column("embedding_model", "rerank_provider_type")
+    op.drop_column("embedding_model", "rerank_model_name")
+    op.drop_column("embedding_model", "disable_rerank_for_streaming")
+    op.drop_column("embedding_model", "multilingual_expansion")
+    op.drop_column("embedding_model", "multipass_indexing")
+
+    op.create_foreign_key(
+        "index_attempt__embedding_model_fk",
+        "index_attempt",
+        "embedding_model",
+        ["embedding_model_id"],
+        ["id"],
+    )

backend/alembic/versions/213fd978c6d8_notifications.py

@@ -0,0 +1,44 @@
+"""notifications
+
+Revision ID: 213fd978c6d8
+Revises: 5fc1f54cc252
+Create Date: 2024-08-10 11:13:36.070790
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "213fd978c6d8"
+down_revision = "5fc1f54cc252"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "notification",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column(
+            "notif_type",
+            sa.String(),
+            nullable=False,
+        ),
+        sa.Column(
+            "user_id",
+            sa.UUID(),
+            nullable=True,
+        ),
+        sa.Column("dismissed", sa.Boolean(), nullable=False),
+        sa.Column("last_shown", sa.DateTime(timezone=True), nullable=False),
+        sa.Column("first_shown", sa.DateTime(timezone=True), nullable=False),
+        sa.ForeignKeyConstraint(
+            ["user_id"],
+            ["user.id"],
+        ),
+        sa.PrimaryKeyConstraint("id"),
+    )
+
+
+def downgrade() -> None:
+    op.drop_table("notification")

backend/alembic/versions/23957775e5f5_remove_feedback_foreignkey_constraint.py

@@ -0,0 +1,86 @@
+"""remove-feedback-foreignkey-constraint
+
+Revision ID: 23957775e5f5
+Revises: bc9771dccadf
+Create Date: 2024-06-27 16:04:51.480437
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "23957775e5f5"
+down_revision = "bc9771dccadf"
+branch_labels = None  # type: ignore
+depends_on = None  # type: ignore
+
+
+def upgrade() -> None:
+    op.drop_constraint(
+        "chat_feedback__chat_message_fk", "chat_feedback", type_="foreignkey"
+    )
+    op.create_foreign_key(
+        "chat_feedback__chat_message_fk",
+        "chat_feedback",
+        "chat_message",
+        ["chat_message_id"],
+        ["id"],
+        ondelete="SET NULL",
+    )
+    op.alter_column(
+        "chat_feedback", "chat_message_id", existing_type=sa.Integer(), nullable=True
+    )
+    op.drop_constraint(
+        "document_retrieval_feedback__chat_message_fk",
+        "document_retrieval_feedback",
+        type_="foreignkey",
+    )
+    op.create_foreign_key(
+        "document_retrieval_feedback__chat_message_fk",
+        "document_retrieval_feedback",
+        "chat_message",
+        ["chat_message_id"],
+        ["id"],
+        ondelete="SET NULL",
+    )
+    op.alter_column(
+        "document_retrieval_feedback",
+        "chat_message_id",
+        existing_type=sa.Integer(),
+        nullable=True,
+    )
+
+
+def downgrade() -> None:
+    op.alter_column(
+        "chat_feedback", "chat_message_id", existing_type=sa.Integer(), nullable=False
+    )
+    op.drop_constraint(
+        "chat_feedback__chat_message_fk", "chat_feedback", type_="foreignkey"
+    )
+    op.create_foreign_key(
+        "chat_feedback__chat_message_fk",
+        "chat_feedback",
+        "chat_message",
+        ["chat_message_id"],
+        ["id"],
+    )
+
+    op.alter_column(
+        "document_retrieval_feedback",
+        "chat_message_id",
+        existing_type=sa.Integer(),
+        nullable=False,
+    )
+    op.drop_constraint(
+        "document_retrieval_feedback__chat_message_fk",
+        "document_retrieval_feedback",
+        type_="foreignkey",
+    )
+    op.create_foreign_key(
+        "document_retrieval_feedback__chat_message_fk",
+        "document_retrieval_feedback",
+        "chat_message",
+        ["chat_message_id"],
+        ["id"],
+    )

backend/alembic/versions/2666d766cb9b_google_oauth2.py

@@ -13,8 +13,8 @@ from alembic import op
 # revision identifiers, used by Alembic.
 revision = "2666d766cb9b"
 down_revision = "6d387b3196c2"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:

backend/alembic/versions/26b931506ecb_default_chosen_assistants_to_none.py

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

backend/alembic/versions/27c6ecc08586_permission_framework.py

@@ -13,8 +13,8 @@ from sqlalchemy.dialects import postgresql
 # revision identifiers, used by Alembic.
 revision = "27c6ecc08586"
 down_revision = "2666d766cb9b"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:
@@ -160,12 +160,28 @@ def downgrade() -> None:
             nullable=False,
         ),
     )
-    op.drop_constraint(
-        "fk_index_attempt_credential_id", "index_attempt", type_="foreignkey"
-    )
-    op.drop_constraint(
-        "fk_index_attempt_connector_id", "index_attempt", type_="foreignkey"
-    )
+
+    # Check if the constraint exists before dropping
+    conn = op.get_bind()
+    inspector = sa.inspect(conn)
+    constraints = inspector.get_foreign_keys("index_attempt")
+
+    if any(
+        constraint["name"] == "fk_index_attempt_credential_id"
+        for constraint in constraints
+    ):
+        op.drop_constraint(
+            "fk_index_attempt_credential_id", "index_attempt", type_="foreignkey"
+        )
+
+    if any(
+        constraint["name"] == "fk_index_attempt_connector_id"
+        for constraint in constraints
+    ):
+        op.drop_constraint(
+            "fk_index_attempt_connector_id", "index_attempt", type_="foreignkey"
+        )
+
     op.drop_column("index_attempt", "credential_id")
     op.drop_column("index_attempt", "connector_id")
     op.drop_table("connector_credential_pair")

backend/alembic/versions/2955778aa44c_add_chunk_count_to_document.py

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

backend/alembic/versions/2cdeff6d8c93_set_built_in_to_default.py

@@ -0,0 +1,32 @@
+"""set built in to default
+
+Revision ID: 2cdeff6d8c93
+Revises: f5437cc136c5
+Create Date: 2025-02-11 14:57:51.308775
+
+"""
+from alembic import op
+
+
+# revision identifiers, used by Alembic.
+revision = "2cdeff6d8c93"
+down_revision = "f5437cc136c5"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # Prior to this migration / point in the codebase history,
+    # built in personas were implicitly treated as default personas (with no option to change this)
+    # This migration makes that explicit
+    op.execute(
+        """
+        UPDATE persona
+        SET is_default_persona = TRUE
+        WHERE builtin_persona = TRUE
+    """
+    )
+
+
+def downgrade() -> None:
+    pass

backend/alembic/versions/2d2304e27d8c_add_above_below_to_persona.py

@@ -0,0 +1,32 @@
+"""Add Above Below to Persona
+
+Revision ID: 2d2304e27d8c
+Revises: 4b08d97e175a
+Create Date: 2024-08-21 19:15:15.762948
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "2d2304e27d8c"
+down_revision = "4b08d97e175a"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.add_column("persona", sa.Column("chunks_above", sa.Integer(), nullable=True))
+    op.add_column("persona", sa.Column("chunks_below", sa.Integer(), nullable=True))
+
+    op.execute(
+        "UPDATE persona SET chunks_above = 1, chunks_below = 1 WHERE chunks_above IS NULL AND chunks_below IS NULL"
+    )
+
+    op.alter_column("persona", "chunks_above", nullable=False)
+    op.alter_column("persona", "chunks_below", nullable=False)
+
+
+def downgrade() -> None:
+    op.drop_column("persona", "chunks_below")
+    op.drop_column("persona", "chunks_above")

backend/alembic/versions/2daa494a0851_add_group_sync_time.py

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

backend/alembic/versions/2f80c6a2550f_add_chat_session_specific_temperature_.py

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

backend/alembic/versions/30c1d5744104_persona_datetime_aware.py

@@ -11,8 +11,8 @@ import sqlalchemy as sa
 # revision identifiers, used by Alembic.
 revision = "30c1d5744104"
 down_revision = "7f99be1cb9f5"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:

backend/alembic/versions/325975216eb3_add_icon_color_and_icon_shape_to_persona.py

@@ -0,0 +1,70 @@
+"""Add icon_color and icon_shape to Persona
+
+Revision ID: 325975216eb3
+Revises: 91ffac7e65b3
+Create Date: 2024-07-24 21:29:31.784562
+
+"""
+import random
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.sql import table, column, select
+
+# revision identifiers, used by Alembic.
+revision = "325975216eb3"
+down_revision = "91ffac7e65b3"
+branch_labels: None = None
+depends_on: None = None
+
+
+colorOptions = [
+    "#FF6FBF",
+    "#6FB1FF",
+    "#B76FFF",
+    "#FFB56F",
+    "#6FFF8D",
+    "#FF6F6F",
+    "#6FFFFF",
+]
+
+
+# Function to generate a random shape ensuring at least 3 of the middle 4 squares are filled
+def generate_random_shape() -> int:
+    center_squares = [12, 10, 6, 14, 13, 11, 7, 15]
+    center_fill = random.choice(center_squares)
+    remaining_squares = [i for i in range(16) if not (center_fill & (1 << i))]
+    random.shuffle(remaining_squares)
+    for i in range(10 - bin(center_fill).count("1")):
+        center_fill |= 1 << remaining_squares[i]
+    return center_fill
+
+
+def upgrade() -> None:
+    op.add_column("persona", sa.Column("icon_color", sa.String(), nullable=True))
+    op.add_column("persona", sa.Column("icon_shape", sa.Integer(), nullable=True))
+    op.add_column("persona", sa.Column("uploaded_image_id", sa.String(), nullable=True))
+
+    persona = table(
+        "persona",
+        column("id", sa.Integer),
+        column("icon_color", sa.String),
+        column("icon_shape", sa.Integer),
+    )
+
+    conn = op.get_bind()
+    personas = conn.execute(select(persona.c.id))
+
+    for persona_id in personas:
+        random_color = random.choice(colorOptions)
+        random_shape = generate_random_shape()
+        conn.execute(
+            persona.update()
+            .where(persona.c.id == persona_id[0])
+            .values(icon_color=random_color, icon_shape=random_shape)
+        )
+
+
+def downgrade() -> None:
+    op.drop_column("persona", "icon_shape")
+    op.drop_column("persona", "uploaded_image_id")
+    op.drop_column("persona", "icon_color")

backend/alembic/versions/33cb72ea4d80_single_tool_call_per_message.py

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

backend/alembic/versions/33ea50e88f24_foreign_key_input_prompts.py

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

backend/alembic/versions/351faebd379d_add_curator_fields.py

@@ -0,0 +1,90 @@
+"""Add curator fields
+
+Revision ID: 351faebd379d
+Revises: ee3f4b47fad5
+Create Date: 2024-08-15 22:37:08.397052
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "351faebd379d"
+down_revision = "ee3f4b47fad5"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    # Add is_curator column to User__UserGroup table
+    op.add_column(
+        "user__user_group",
+        sa.Column("is_curator", sa.Boolean(), nullable=False, server_default="false"),
+    )
+
+    # Use batch mode to modify the enum type
+    with op.batch_alter_table("user", schema=None) as batch_op:
+        batch_op.alter_column(  # type: ignore[attr-defined]
+            "role",
+            type_=sa.Enum(
+                "BASIC",
+                "ADMIN",
+                "CURATOR",
+                "GLOBAL_CURATOR",
+                name="userrole",
+                native_enum=False,
+            ),
+            existing_type=sa.Enum("BASIC", "ADMIN", name="userrole", native_enum=False),
+            existing_nullable=False,
+        )
+    # Create the association table
+    op.create_table(
+        "credential__user_group",
+        sa.Column("credential_id", sa.Integer(), nullable=False),
+        sa.Column("user_group_id", sa.Integer(), nullable=False),
+        sa.ForeignKeyConstraint(
+            ["credential_id"],
+            ["credential.id"],
+        ),
+        sa.ForeignKeyConstraint(
+            ["user_group_id"],
+            ["user_group.id"],
+        ),
+        sa.PrimaryKeyConstraint("credential_id", "user_group_id"),
+    )
+    op.add_column(
+        "credential",
+        sa.Column(
+            "curator_public", sa.Boolean(), nullable=False, server_default="false"
+        ),
+    )
+
+
+def downgrade() -> None:
+    # Update existing records to ensure they fit within the BASIC/ADMIN roles
+    op.execute(
+        "UPDATE \"user\" SET role = 'ADMIN' WHERE role IN ('CURATOR', 'GLOBAL_CURATOR')"
+    )
+
+    # Remove is_curator column from User__UserGroup table
+    op.drop_column("user__user_group", "is_curator")
+
+    with op.batch_alter_table("user", schema=None) as batch_op:
+        batch_op.alter_column(  # type: ignore[attr-defined]
+            "role",
+            type_=sa.Enum(
+                "BASIC", "ADMIN", name="userrole", native_enum=False, length=20
+            ),
+            existing_type=sa.Enum(
+                "BASIC",
+                "ADMIN",
+                "CURATOR",
+                "GLOBAL_CURATOR",
+                name="userrole",
+                native_enum=False,
+            ),
+            existing_nullable=False,
+        )
+    # Drop the association table
+    op.drop_table("credential__user_group")
+    op.drop_column("credential", "curator_public")

backend/alembic/versions/35e518e0ddf4_properly_cascade.py

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

backend/alembic/versions/35e6853a51d5_server_default_chosen_assistants.py

@@ -0,0 +1,64 @@
+"""server default chosen assistants
+
+Revision ID: 35e6853a51d5
+Revises: c99d76fcd298
+Create Date: 2024-09-13 13:20:32.885317
+
+"""
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision = "35e6853a51d5"
+down_revision = "c99d76fcd298"
+branch_labels = None
+depends_on = None
+
+DEFAULT_ASSISTANTS = [-2, -1, 0]
+
+
+def upgrade() -> None:
+    # Step 1: Update any NULL values to the default value
+    # This upgrades existing users without ordered assistant
+    # to have default assistants set to visible assistants which are
+    # accessible by them.
+    op.execute(
+        """
+        UPDATE "user" u
+        SET chosen_assistants = (
+            SELECT jsonb_agg(
+                p.id ORDER BY
+                    COALESCE(p.display_priority, 2147483647) ASC,
+                    p.id ASC
+            )
+            FROM persona p
+            LEFT JOIN persona__user pu ON p.id = pu.persona_id AND pu.user_id = u.id
+            WHERE p.is_visible = true
+            AND (p.is_public = true OR pu.user_id IS NOT NULL)
+        )
+        WHERE chosen_assistants IS NULL
+        OR chosen_assistants = 'null'
+        OR jsonb_typeof(chosen_assistants) = 'null'
+        OR (jsonb_typeof(chosen_assistants) = 'string' AND chosen_assistants = '"null"')
+    """
+    )
+
+    # Step 2: Alter the column to make it non-nullable
+    op.alter_column(
+        "user",
+        "chosen_assistants",
+        type_=postgresql.JSONB(astext_type=sa.Text()),
+        nullable=False,
+        server_default=sa.text(f"'{DEFAULT_ASSISTANTS}'::jsonb"),
+    )
+
+
+def downgrade() -> None:
+    op.alter_column(
+        "user",
+        "chosen_assistants",
+        type_=postgresql.JSONB(astext_type=sa.Text()),
+        nullable=True,
+        server_default=None,
+    )

backend/alembic/versions/369644546676_add_composite_index_for_index_attempt_.py

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

backend/alembic/versions/3879338f8ba1_add_tool_table.py

@@ -0,0 +1,45 @@
+"""Add tool table
+
+Revision ID: 3879338f8ba1
+Revises: f1c6478c3fd8
+Create Date: 2024-05-11 16:11:23.718084
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "3879338f8ba1"
+down_revision = "f1c6478c3fd8"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "tool",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column("name", sa.String(), nullable=False),
+        sa.Column("description", sa.Text(), nullable=True),
+        sa.Column("in_code_tool_id", sa.String(), nullable=True),
+        sa.PrimaryKeyConstraint("id"),
+    )
+    op.create_table(
+        "persona__tool",
+        sa.Column("persona_id", sa.Integer(), nullable=False),
+        sa.Column("tool_id", sa.Integer(), nullable=False),
+        sa.ForeignKeyConstraint(
+            ["persona_id"],
+            ["persona.id"],
+        ),
+        sa.ForeignKeyConstraint(
+            ["tool_id"],
+            ["tool.id"],
+        ),
+        sa.PrimaryKeyConstraint("persona_id", "tool_id"),
+    )
+
+
+def downgrade() -> None:
+    op.drop_table("persona__tool")
+    op.drop_table("tool")

backend/alembic/versions/38eda64af7fe_add_chat_session_sharing.py

@@ -11,8 +11,8 @@ import sqlalchemy as sa
 # revision identifiers, used by Alembic.
 revision = "38eda64af7fe"
 down_revision = "776b3bbe9092"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:

backend/alembic/versions/3a7802814195_add_alternate_assistant_to_chat_message.py

@@ -0,0 +1,35 @@
+"""add alternate assistant to chat message
+
+Revision ID: 3a7802814195
+Revises: 23957775e5f5
+Create Date: 2024-06-05 11:18:49.966333
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "3a7802814195"
+down_revision = "23957775e5f5"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "chat_message", sa.Column("alternate_assistant_id", sa.Integer(), nullable=True)
+    )
+    op.create_foreign_key(
+        "fk_chat_message_persona",
+        "chat_message",
+        "persona",
+        ["alternate_assistant_id"],
+        ["id"],
+    )
+
+
+def downgrade() -> None:
+    op.drop_constraint("fk_chat_message_persona", "chat_message", type_="foreignkey")
+    op.drop_column("chat_message", "alternate_assistant_id")

backend/alembic/versions/3b25685ff73c_move_is_public_to_cc_pair.py

@@ -11,8 +11,8 @@ import sqlalchemy as sa
 # revision identifiers, used by Alembic.
 revision = "3b25685ff73c"
 down_revision = "e0a68a81d434"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:

backend/alembic/versions/3bd4c84fe72f_improved_index.py

@@ -0,0 +1,397 @@
+"""improved index
+
+Revision ID: 3bd4c84fe72f
+Revises: 8f43500ee275
+Create Date: 2025-02-26 13:07:56.217791
+
+"""
+from alembic import op
+import time
+from sqlalchemy import text
+
+# revision identifiers, used by Alembic.
+revision = "3bd4c84fe72f"
+down_revision = "8f43500ee275"
+branch_labels = None
+depends_on = None
+
+
+# NOTE:
+# This migration addresses issues with the previous migration (8f43500ee275) which caused
+# an outage by creating an index without using CONCURRENTLY. This migration:
+#
+# 1. Creates more efficient full-text search capabilities using tsvector columns and GIN indexes
+# 2. Uses CONCURRENTLY for all index creation to prevent table locking
+# 3. Explicitly manages transactions with COMMIT statements to allow CONCURRENTLY to work
+# (see: https://www.postgresql.org/docs/9.4/sql-createindex.html#SQL-CREATEINDEX-CONCURRENTLY)
+# (see: https://github.com/sqlalchemy/alembic/issues/277)
+# 4. Adds indexes to both chat_message and chat_session tables for comprehensive search
+
+
+def upgrade():
+    # --- PART 1: chat_message table ---
+    # Step 1: Add nullable column (quick, minimal locking)
+    # op.execute("ALTER TABLE chat_message DROP COLUMN IF EXISTS message_tsv")
+    # op.execute("DROP TRIGGER IF EXISTS chat_message_tsv_trigger ON chat_message")
+    # op.execute("DROP FUNCTION IF EXISTS update_chat_message_tsv()")
+    # op.execute("ALTER TABLE chat_message DROP COLUMN IF EXISTS message_tsv")
+    # # Drop chat_session tsv trigger if it exists
+    # op.execute("DROP TRIGGER IF EXISTS chat_session_tsv_trigger ON chat_session")
+    # op.execute("DROP FUNCTION IF EXISTS update_chat_session_tsv()")
+    # op.execute("ALTER TABLE chat_session DROP COLUMN IF EXISTS title_tsv")
+    # raise Exception("Stop here")
+    time.time()
+    op.execute("ALTER TABLE chat_message ADD COLUMN IF NOT EXISTS message_tsv tsvector")
+
+    # Step 2: Create function and trigger for new/updated rows
+    op.execute(
+        """
+    CREATE OR REPLACE FUNCTION update_chat_message_tsv()
+    RETURNS TRIGGER AS $$
+    BEGIN
+      NEW.message_tsv = to_tsvector('english', NEW.message);
+      RETURN NEW;
+    END;
+    $$ LANGUAGE plpgsql
+    """
+    )
+
+    # Create trigger in a separate execute call
+    op.execute(
+        """
+    CREATE TRIGGER chat_message_tsv_trigger
+    BEFORE INSERT OR UPDATE ON chat_message
+    FOR EACH ROW EXECUTE FUNCTION update_chat_message_tsv()
+    """
+    )
+
+    # Step 3: Update existing rows in batches using Python
+    time.time()
+
+    # Get connection and count total rows
+    connection = op.get_bind()
+    total_count_result = connection.execute(
+        text("SELECT COUNT(*) FROM chat_message")
+    ).scalar()
+    total_count = total_count_result if total_count_result is not None else 0
+    batch_size = 5000
+    batches = 0
+
+    # Calculate total batches needed
+    total_batches = (
+        (total_count + batch_size - 1) // batch_size if total_count > 0 else 0
+    )
+
+    # Process in batches - properly handling UUIDs by using OFFSET/LIMIT approach
+    for batch_num in range(total_batches):
+        offset = batch_num * batch_size
+
+        # Execute update for this batch using OFFSET/LIMIT which works with UUIDs
+        connection.execute(
+            text(
+                """
+            UPDATE chat_message
+            SET message_tsv = to_tsvector('english', message)
+            WHERE id IN (
+                SELECT id FROM chat_message
+                WHERE message_tsv IS NULL
+                ORDER BY id
+                LIMIT :batch_size OFFSET :offset
+            )
+            """
+            ).bindparams(batch_size=batch_size, offset=offset)
+        )
+
+        # Commit each batch
+        connection.execute(text("COMMIT"))
+        # Start a new transaction
+        connection.execute(text("BEGIN"))
+
+        batches += 1
+
+    # Final check for any remaining NULL values
+    connection.execute(
+        text(
+            """
+    UPDATE chat_message SET message_tsv = to_tsvector('english', message)
+    WHERE message_tsv IS NULL
+    """
+        )
+    )
+
+    # Create GIN index concurrently
+    connection.execute(text("COMMIT"))
+
+    time.time()
+
+    connection.execute(
+        text(
+            """
+    CREATE INDEX CONCURRENTLY IF NOT EXISTS idx_chat_message_tsv
+    ON chat_message USING GIN (message_tsv)
+    """
+        )
+    )
+
+    # First drop the trigger as it won't be needed anymore
+    connection.execute(
+        text(
+            """
+    DROP TRIGGER IF EXISTS chat_message_tsv_trigger ON chat_message;
+    """
+        )
+    )
+
+    connection.execute(
+        text(
+            """
+    DROP FUNCTION IF EXISTS update_chat_message_tsv();
+    """
+        )
+    )
+
+    # Add new generated column
+    time.time()
+    connection.execute(
+        text(
+            """
+    ALTER TABLE chat_message
+    ADD COLUMN message_tsv_gen tsvector
+    GENERATED ALWAYS AS (to_tsvector('english', message)) STORED;
+    """
+        )
+    )
+
+    connection.execute(text("COMMIT"))
+
+    time.time()
+
+    connection.execute(
+        text(
+            """
+    CREATE INDEX CONCURRENTLY IF NOT EXISTS idx_chat_message_tsv_gen
+    ON chat_message USING GIN (message_tsv_gen)
+    """
+        )
+    )
+
+    # Drop old index and column
+    connection.execute(text("COMMIT"))
+
+    connection.execute(
+        text(
+            """
+    DROP INDEX CONCURRENTLY IF EXISTS idx_chat_message_tsv;
+    """
+        )
+    )
+    connection.execute(text("COMMIT"))
+    connection.execute(
+        text(
+            """
+    ALTER TABLE chat_message DROP COLUMN message_tsv;
+    """
+        )
+    )
+
+    # Rename new column to old name
+    connection.execute(
+        text(
+            """
+    ALTER TABLE chat_message RENAME COLUMN message_tsv_gen TO message_tsv;
+    """
+        )
+    )
+
+    # --- PART 2: chat_session table ---
+
+    # Step 1: Add nullable column (quick, minimal locking)
+    time.time()
+    connection.execute(
+        text(
+            "ALTER TABLE chat_session ADD COLUMN IF NOT EXISTS description_tsv tsvector"
+        )
+    )
+
+    # Step 2: Create function and trigger for new/updated rows - SPLIT INTO SEPARATE CALLS
+    connection.execute(
+        text(
+            """
+    CREATE OR REPLACE FUNCTION update_chat_session_tsv()
+    RETURNS TRIGGER AS $$
+    BEGIN
+      NEW.description_tsv = to_tsvector('english', COALESCE(NEW.description, ''));
+      RETURN NEW;
+    END;
+    $$ LANGUAGE plpgsql
+    """
+        )
+    )
+
+    # Create trigger in a separate execute call
+    connection.execute(
+        text(
+            """
+    CREATE TRIGGER chat_session_tsv_trigger
+    BEFORE INSERT OR UPDATE ON chat_session
+    FOR EACH ROW EXECUTE FUNCTION update_chat_session_tsv()
+    """
+        )
+    )
+
+    # Step 3: Update existing rows in batches using Python
+    time.time()
+
+    # Get the maximum ID to determine batch count
+    # Cast id to text for MAX function since it's a UUID
+    max_id_result = connection.execute(
+        text("SELECT COALESCE(MAX(id::text), '0') FROM chat_session")
+    ).scalar()
+    max_id_result if max_id_result is not None else "0"
+    batch_size = 5000
+    batches = 0
+
+    # Get all IDs ordered to process in batches
+    rows = connection.execute(
+        text("SELECT id FROM chat_session ORDER BY id")
+    ).fetchall()
+    total_rows = len(rows)
+
+    # Process in batches
+    for batch_num, batch_start in enumerate(range(0, total_rows, batch_size)):
+        batch_end = min(batch_start + batch_size, total_rows)
+        batch_ids = [row[0] for row in rows[batch_start:batch_end]]
+
+        if not batch_ids:
+            continue
+
+        # Use IN clause instead of BETWEEN for UUIDs
+        placeholders = ", ".join([f":id{i}" for i in range(len(batch_ids))])
+        params = {f"id{i}": id_val for i, id_val in enumerate(batch_ids)}
+
+        # Execute update for this batch
+        connection.execute(
+            text(
+                f"""
+            UPDATE chat_session
+            SET description_tsv = to_tsvector('english', COALESCE(description, ''))
+            WHERE id IN ({placeholders})
+            AND description_tsv IS NULL
+            """
+            ).bindparams(**params)
+        )
+
+        # Commit each batch
+        connection.execute(text("COMMIT"))
+        # Start a new transaction
+        connection.execute(text("BEGIN"))
+
+        batches += 1
+
+    # Final check for any remaining NULL values
+    connection.execute(
+        text(
+            """
+    UPDATE chat_session SET description_tsv = to_tsvector('english', COALESCE(description, ''))
+    WHERE description_tsv IS NULL
+    """
+        )
+    )
+
+    # Create GIN index concurrently
+    connection.execute(text("COMMIT"))
+
+    time.time()
+    connection.execute(
+        text(
+            """
+    CREATE INDEX CONCURRENTLY IF NOT EXISTS idx_chat_session_desc_tsv
+    ON chat_session USING GIN (description_tsv)
+    """
+        )
+    )
+
+    # After Final check for chat_session
+    # First drop the trigger as it won't be needed anymore
+    connection.execute(
+        text(
+            """
+    DROP TRIGGER IF EXISTS chat_session_tsv_trigger ON chat_session;
+    """
+        )
+    )
+
+    connection.execute(
+        text(
+            """
+    DROP FUNCTION IF EXISTS update_chat_session_tsv();
+    """
+        )
+    )
+    # Add new generated column
+    time.time()
+    connection.execute(
+        text(
+            """
+    ALTER TABLE chat_session
+    ADD COLUMN description_tsv_gen tsvector
+    GENERATED ALWAYS AS (to_tsvector('english', COALESCE(description, ''))) STORED;
+    """
+        )
+    )
+
+    # Create new index on generated column
+    connection.execute(text("COMMIT"))
+
+    time.time()
+    connection.execute(
+        text(
+            """
+    CREATE INDEX CONCURRENTLY IF NOT EXISTS idx_chat_session_desc_tsv_gen
+    ON chat_session USING GIN (description_tsv_gen)
+    """
+        )
+    )
+
+    # Drop old index and column
+    connection.execute(text("COMMIT"))
+
+    connection.execute(
+        text(
+            """
+    DROP INDEX CONCURRENTLY IF EXISTS idx_chat_session_desc_tsv;
+    """
+        )
+    )
+    connection.execute(text("COMMIT"))
+    connection.execute(
+        text(
+            """
+    ALTER TABLE chat_session DROP COLUMN description_tsv;
+    """
+        )
+    )
+
+    # Rename new column to old name
+    connection.execute(
+        text(
+            """
+    ALTER TABLE chat_session RENAME COLUMN description_tsv_gen TO description_tsv;
+    """
+        )
+    )
+
+
+def downgrade() -> None:
+    # Drop the indexes first (use CONCURRENTLY for dropping too)
+    op.execute("COMMIT")
+    op.execute("DROP INDEX CONCURRENTLY IF EXISTS idx_chat_message_tsv;")
+
+    op.execute("COMMIT")
+    op.execute("DROP INDEX CONCURRENTLY IF EXISTS idx_chat_session_desc_tsv;")
+
+    # Then drop the columns
+    op.execute("ALTER TABLE chat_message DROP COLUMN IF EXISTS message_tsv;")
+    op.execute("ALTER TABLE chat_session DROP COLUMN IF EXISTS description_tsv;")
+
+    op.execute("DROP INDEX IF EXISTS idx_chat_message_message_lower;")

backend/alembic/versions/3c5e35aa9af0_polling_document_count.py

@@ -12,8 +12,8 @@ from alembic import op
 # revision identifiers, used by Alembic.
 revision = "3c5e35aa9af0"
 down_revision = "27c6ecc08586"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:

backend/alembic/versions/3c6531f32351_add_back_input_prompts.py

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

backend/alembic/versions/401c1ac29467_add_tables_for_ui_based_llm_.py

@@ -0,0 +1,49 @@
+"""Add tables for UI-based LLM configuration
+
+Revision ID: 401c1ac29467
+Revises: 703313b75876
+Create Date: 2024-04-13 18:07:29.153817
+
+"""
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision = "401c1ac29467"
+down_revision = "703313b75876"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "llm_provider",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column("name", sa.String(), nullable=False),
+        sa.Column("api_key", sa.String(), nullable=True),
+        sa.Column("api_base", sa.String(), nullable=True),
+        sa.Column("api_version", sa.String(), nullable=True),
+        sa.Column(
+            "custom_config",
+            postgresql.JSONB(astext_type=sa.Text()),
+            nullable=True,
+        ),
+        sa.Column("default_model_name", sa.String(), nullable=False),
+        sa.Column("fast_default_model_name", sa.String(), nullable=True),
+        sa.Column("is_default_provider", sa.Boolean(), unique=True, nullable=True),
+        sa.Column("model_names", postgresql.ARRAY(sa.String()), nullable=True),
+        sa.PrimaryKeyConstraint("id"),
+        sa.UniqueConstraint("name"),
+    )
+
+    op.add_column(
+        "persona",
+        sa.Column("llm_model_provider_override", sa.String(), nullable=True),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("persona", "llm_model_provider_override")
+
+    op.drop_table("llm_provider")

backend/alembic/versions/43cbbb3f5e6a_rename_index_origin_to_index_recursively.py

@@ -0,0 +1,42 @@
+"""Rename index_origin to index_recursively
+
+Revision ID: 1d6ad76d1f37
+Revises: e1392f05e840
+Create Date: 2024-08-01 12:38:54.466081
+
+"""
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision = "1d6ad76d1f37"
+down_revision = "e1392f05e840"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.execute(
+        """
+        UPDATE connector
+        SET connector_specific_config = jsonb_set(
+            connector_specific_config,
+            '{index_recursively}',
+            'true'::jsonb
+        ) - 'index_origin'
+        WHERE connector_specific_config ? 'index_origin'
+    """
+    )
+
+
+def downgrade() -> None:
+    op.execute(
+        """
+        UPDATE connector
+        SET connector_specific_config = jsonb_set(
+            connector_specific_config,
+            '{index_origin}',
+            connector_specific_config->'index_recursively'
+        ) - 'index_recursively'
+        WHERE connector_specific_config ? 'index_recursively'
+    """
+    )

backend/alembic/versions/44f856ae2a4a_add_cloud_embedding_model.py

@@ -0,0 +1,65 @@
+"""add cloud embedding model and update embedding_model
+
+Revision ID: 44f856ae2a4a
+Revises: d716b0791ddd
+Create Date: 2024-06-28 20:01:05.927647
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "44f856ae2a4a"
+down_revision = "d716b0791ddd"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    # Create embedding_provider table
+    op.create_table(
+        "embedding_provider",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column("name", sa.String(), nullable=False),
+        sa.Column("api_key", sa.LargeBinary(), nullable=True),
+        sa.Column("default_model_id", sa.Integer(), nullable=True),
+        sa.PrimaryKeyConstraint("id"),
+        sa.UniqueConstraint("name"),
+    )
+
+    # Add cloud_provider_id to embedding_model table
+    op.add_column(
+        "embedding_model", sa.Column("cloud_provider_id", sa.Integer(), nullable=True)
+    )
+
+    # Add foreign key constraints
+    op.create_foreign_key(
+        "fk_embedding_model_cloud_provider",
+        "embedding_model",
+        "embedding_provider",
+        ["cloud_provider_id"],
+        ["id"],
+    )
+    op.create_foreign_key(
+        "fk_embedding_provider_default_model",
+        "embedding_provider",
+        "embedding_model",
+        ["default_model_id"],
+        ["id"],
+    )
+
+
+def downgrade() -> None:
+    # Remove foreign key constraints
+    op.drop_constraint(
+        "fk_embedding_model_cloud_provider", "embedding_model", type_="foreignkey"
+    )
+    op.drop_constraint(
+        "fk_embedding_provider_default_model", "embedding_provider", type_="foreignkey"
+    )
+
+    # Remove cloud_provider_id column
+    op.drop_column("embedding_model", "cloud_provider_id")
+
+    # Drop embedding_provider table
+    op.drop_table("embedding_provider")

backend/alembic/versions/4505fd7302e1_added_is_internet_to_dbdoc.py

@@ -0,0 +1,23 @@
+"""added is_internet to DBDoc
+
+Revision ID: 4505fd7302e1
+Revises: c18cdf4b497e
+Create Date: 2024-06-18 20:46:09.095034
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "4505fd7302e1"
+down_revision = "c18cdf4b497e"
+
+
+def upgrade() -> None:
+    op.add_column("search_doc", sa.Column("is_internet", sa.Boolean(), nullable=True))
+    op.add_column("tool", sa.Column("display_name", sa.String(), nullable=True))
+
+
+def downgrade() -> None:
+    op.drop_column("tool", "display_name")
+    op.drop_column("search_doc", "is_internet")

backend/alembic/versions/465f78d9b7f9_larger_access_tokens_for_oauth.py

@@ -12,8 +12,8 @@ import sqlalchemy as sa
 # revision identifiers, used by Alembic.
 revision = "465f78d9b7f9"
 down_revision = "3c5e35aa9af0"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:

backend/alembic/versions/46625e4745d4_remove_native_enum.py

@@ -11,13 +11,13 @@ from sqlalchemy import String
 # revision identifiers, used by Alembic.
 revision = "46625e4745d4"
 down_revision = "9d97fecfab7f"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:
     # At this point, we directly changed some previous migrations,
-    # https://github.com/danswer-ai/danswer/pull/637
+    # https://github.com/onyx-dot-app/onyx/pull/637
     # Due to using Postgres native Enums, it caused some complications for first time users.
     # To remove those complications, all Enums are only handled application side moving forward.
     # This migration exists to ensure that existing users don't run into upgrade issues.

backend/alembic/versions/46b7a812670f_fix_user__external_user_group_id_fk.py

@@ -0,0 +1,46 @@
+"""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/4738e4b3bae1_pg_file_store.py

@@ -11,8 +11,8 @@ import sqlalchemy as sa
 # revision identifiers, used by Alembic.
 revision = "4738e4b3bae1"
 down_revision = "e91df4e935ef"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:

backend/alembic/versions/473a1a7ca408_add_display_model_names_to_llm_provider.py

@@ -0,0 +1,49 @@
+"""Add display_model_names to llm_provider
+
+Revision ID: 473a1a7ca408
+Revises: 325975216eb3
+Create Date: 2024-07-25 14:31:02.002917
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision = "473a1a7ca408"
+down_revision = "325975216eb3"
+branch_labels: None = None
+depends_on: None = None
+
+default_models_by_provider = {
+    "openai": ["gpt-4", "gpt-4o", "gpt-4o-mini"],
+    "bedrock": [
+        "meta.llama3-1-70b-instruct-v1:0",
+        "meta.llama3-1-8b-instruct-v1:0",
+        "anthropic.claude-3-opus-20240229-v1:0",
+        "mistral.mistral-large-2402-v1:0",
+        "anthropic.claude-3-5-sonnet-20240620-v1:0",
+    ],
+    "anthropic": ["claude-3-opus-20240229", "claude-3-5-sonnet-20240620"],
+}
+
+
+def upgrade() -> None:
+    op.add_column(
+        "llm_provider",
+        sa.Column("display_model_names", postgresql.ARRAY(sa.String()), nullable=True),
+    )
+
+    connection = op.get_bind()
+    for provider, models in default_models_by_provider.items():
+        connection.execute(
+            sa.text(
+                "UPDATE llm_provider SET display_model_names = :models WHERE provider = :provider"
+            ),
+            {"models": models, "provider": provider},
+        )
+
+
+def downgrade() -> None:
+    op.drop_column("llm_provider", "display_model_names")

backend/alembic/versions/47433d30de82_create_indexattempt_table.py

@@ -11,9 +11,9 @@ from sqlalchemy.dialects import postgresql
 
 # revision identifiers, used by Alembic.
 revision = "47433d30de82"
-down_revision = None
-branch_labels = None
-depends_on = None
+down_revision: None = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:

backend/alembic/versions/475fcefe8826_add_name_to_api_key.py

@@ -11,8 +11,8 @@ import sqlalchemy as sa
 # revision identifiers, used by Alembic.
 revision = "475fcefe8826"
 down_revision = "ecab2b3f1a3b"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:

backend/alembic/versions/47e5bef3a1d7_add_persona_categories.py

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

backend/alembic/versions/48d14957fe80_add_support_for_custom_tools.py

@@ -0,0 +1,61 @@
+"""Add support for custom tools
+
+Revision ID: 48d14957fe80
+Revises: b85f02ec1308
+Create Date: 2024-06-09 14:58:19.946509
+
+"""
+from alembic import op
+import fastapi_users_db_sqlalchemy
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision = "48d14957fe80"
+down_revision = "b85f02ec1308"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "tool",
+        sa.Column(
+            "openapi_schema",
+            postgresql.JSONB(astext_type=sa.Text()),
+            nullable=True,
+        ),
+    )
+    op.add_column(
+        "tool",
+        sa.Column(
+            "user_id",
+            fastapi_users_db_sqlalchemy.generics.GUID(),
+            nullable=True,
+        ),
+    )
+    op.create_foreign_key("tool_user_fk", "tool", "user", ["user_id"], ["id"])
+
+    op.create_table(
+        "tool_call",
+        sa.Column("id", sa.Integer(), primary_key=True),
+        sa.Column("tool_id", sa.Integer(), nullable=False),
+        sa.Column("tool_name", sa.String(), nullable=False),
+        sa.Column(
+            "tool_arguments", postgresql.JSONB(astext_type=sa.Text()), nullable=False
+        ),
+        sa.Column(
+            "tool_result", postgresql.JSONB(astext_type=sa.Text()), nullable=False
+        ),
+        sa.Column(
+            "message_id", sa.Integer(), sa.ForeignKey("chat_message.id"), nullable=False
+        ),
+    )
+
+
+def downgrade() -> None:
+    op.drop_table("tool_call")
+
+    op.drop_constraint("tool_user_fk", "tool", type_="foreignkey")
+    op.drop_column("tool", "user_id")
+    op.drop_column("tool", "openapi_schema")

backend/alembic/versions/4a951134c801_moved_status_to_connector_credential_.py

@@ -0,0 +1,80 @@
+"""Moved status to connector credential pair
+
+Revision ID: 4a951134c801
+Revises: 7477a5f5d728
+Create Date: 2024-08-10 19:20:34.527559
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "4a951134c801"
+down_revision = "7477a5f5d728"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "connector_credential_pair",
+        sa.Column(
+            "status",
+            sa.Enum(
+                "ACTIVE",
+                "PAUSED",
+                "DELETING",
+                name="connectorcredentialpairstatus",
+                native_enum=False,
+            ),
+            nullable=True,
+        ),
+    )
+
+    # Update status of connector_credential_pair based on connector's disabled status
+    op.execute(
+        """
+        UPDATE connector_credential_pair
+        SET status = CASE
+            WHEN (
+                SELECT disabled
+                FROM connector
+                WHERE connector.id = connector_credential_pair.connector_id
+            ) = FALSE THEN 'ACTIVE'
+            ELSE 'PAUSED'
+        END
+        """
+    )
+
+    # Make the status column not nullable after setting values
+    op.alter_column("connector_credential_pair", "status", nullable=False)
+
+    op.drop_column("connector", "disabled")
+
+
+def downgrade() -> None:
+    op.add_column(
+        "connector",
+        sa.Column("disabled", sa.BOOLEAN(), autoincrement=False, nullable=True),
+    )
+
+    # Update disabled status of connector based on connector_credential_pair's status
+    op.execute(
+        """
+        UPDATE connector
+        SET disabled = CASE
+            WHEN EXISTS (
+                SELECT 1
+                FROM connector_credential_pair
+                WHERE connector_credential_pair.connector_id = connector.id
+                AND connector_credential_pair.status = 'ACTIVE'
+            ) THEN FALSE
+            ELSE TRUE
+        END
+        """
+    )
+
+    # Make the disabled column not nullable after setting values
+    op.alter_column("connector", "disabled", nullable=False)
+
+    op.drop_column("connector_credential_pair", "status")

backend/alembic/versions/4b08d97e175a_change_default_prune_freq.py

@@ -0,0 +1,34 @@
+"""change default prune_freq
+
+Revision ID: 4b08d97e175a
+Revises: d9ec13955951
+Create Date: 2024-08-20 15:28:52.993827
+
+"""
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision = "4b08d97e175a"
+down_revision = "d9ec13955951"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.execute(
+        """
+        UPDATE connector
+        SET prune_freq = 2592000
+        WHERE prune_freq = 86400
+        """
+    )
+
+
+def downgrade() -> None:
+    op.execute(
+        """
+        UPDATE connector
+        SET prune_freq = 86400
+        WHERE prune_freq = 2592000
+        """
+    )

backend/alembic/versions/4d58345da04a_lowercase_user_emails.py

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

backend/alembic/versions/4ea2c93919c1_add_type_to_credentials.py

@@ -0,0 +1,72 @@
+"""Add type to credentials
+
+Revision ID: 4ea2c93919c1
+Revises: 473a1a7ca408
+Create Date: 2024-07-18 13:07:13.655895
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "4ea2c93919c1"
+down_revision = "473a1a7ca408"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    # Add the new 'source' column to the 'credential' table
+    op.add_column(
+        "credential",
+        sa.Column(
+            "source",
+            sa.String(length=100),  # Use String instead of Enum
+            nullable=True,  # Initially allow NULL values
+        ),
+    )
+    op.add_column(
+        "credential",
+        sa.Column(
+            "name",
+            sa.String(),
+            nullable=True,
+        ),
+    )
+
+    # Create a temporary table that maps each credential to a single connector source.
+    # This is needed because a credential can be associated with multiple connectors,
+    # but we want to assign a single source to each credential.
+    # We use DISTINCT ON to ensure we only get one row per credential_id.
+    op.execute(
+        """
+    CREATE TEMPORARY TABLE temp_connector_credential AS
+    SELECT DISTINCT ON (cc.credential_id)
+        cc.credential_id,
+        c.source AS connector_source
+    FROM connector_credential_pair cc
+    JOIN connector c ON cc.connector_id = c.id
+    """
+    )
+
+    # Update the 'source' column in the 'credential' table
+    op.execute(
+        """
+    UPDATE credential cred
+    SET source = COALESCE(
+        (SELECT connector_source
+         FROM temp_connector_credential temp
+         WHERE cred.id = temp.credential_id),
+        'NOT_APPLICABLE'
+    )
+    """
+    )
+    # If no exception was raised, alter the column
+    op.alter_column("credential", "source", nullable=True)  # TODO modify
+    # # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    op.drop_column("credential", "source")
+    op.drop_column("credential", "name")

backend/alembic/versions/4ee1287bd26a_add_multiple_slack_bot_support.py

@@ -0,0 +1,267 @@
+"""add_multiple_slack_bot_support
+
+Revision ID: 4ee1287bd26a
+Revises: 47e5bef3a1d7
+Create Date: 2024-11-06 13:15:53.302644
+
+"""
+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
+
+
+def upgrade() -> None:
+    # 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
+    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:
+        tokens = {}
+
+    bot_token = tokens.get("bot_token")
+    app_token = tokens.get("app_token")
+
+    if bot_token and app_token:
+        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:
+            get_kv_store().delete("slack_bot_tokens_config_key")
+    except Exception:
+        pass
+    # 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")
+
+
+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:
+        pass
+
+    # Drop the new tables in reverse order
+    op.drop_table("slack_channel_config")
+    op.drop_table("slack_bot")

backend/alembic/versions/50b683a8295c_add_additional_retrieval_controls_to_.py

@@ -11,8 +11,8 @@ import sqlalchemy as sa
 # revision identifiers, used by Alembic.
 revision = "50b683a8295c"
 down_revision = "7da0ae5ad583"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:

backend/alembic/versions/52a219fb5233_add_last_synced_and_last_modified_to_document_table.py

@@ -0,0 +1,66 @@
+"""Add last synced and last modified to document table
+
+Revision ID: 52a219fb5233
+Revises: f7e58d357687
+Create Date: 2024-08-28 17:40:46.077470
+
+"""
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.sql import func
+
+# revision identifiers, used by Alembic.
+revision = "52a219fb5233"
+down_revision = "f7e58d357687"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # last modified represents the last time anything needing syncing to vespa changed
+    # including row metadata and the document itself. This obviously does not include
+    # the last_synced column.
+    op.add_column(
+        "document",
+        sa.Column(
+            "last_modified",
+            sa.DateTime(timezone=True),
+            nullable=False,
+            server_default=func.now(),
+        ),
+    )
+
+    # last synced represents the last time this document was synced to Vespa
+    op.add_column(
+        "document",
+        sa.Column("last_synced", sa.DateTime(timezone=True), nullable=True),
+    )
+
+    # Set last_synced to the same value as last_modified for existing rows
+    op.execute(
+        """
+        UPDATE document
+        SET last_synced = last_modified
+        """
+    )
+
+    op.create_index(
+        op.f("ix_document_last_modified"),
+        "document",
+        ["last_modified"],
+        unique=False,
+    )
+
+    op.create_index(
+        op.f("ix_document_last_synced"),
+        "document",
+        ["last_synced"],
+        unique=False,
+    )
+
+
+def downgrade() -> None:
+    op.drop_index(op.f("ix_document_last_synced"), table_name="document")
+    op.drop_index(op.f("ix_document_last_modified"), table_name="document")
+    op.drop_column("document", "last_synced")
+    op.drop_column("document", "last_modified")

backend/alembic/versions/54a74a0417fc_danswerbot_onyxbot.py

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

backend/alembic/versions/55546a7967ee_assistant_rework.py

@@ -0,0 +1,79 @@
+"""assistant_rework
+
+Revision ID: 55546a7967ee
+Revises: 61ff3651add4
+Create Date: 2024-09-18 17:00:23.755399
+
+"""
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+
+# revision identifiers, used by Alembic.
+revision = "55546a7967ee"
+down_revision = "61ff3651add4"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # Reworking persona and user tables for new assistant features
+    # keep track of user's chosen assistants separate from their `ordering`
+    op.add_column("persona", sa.Column("builtin_persona", sa.Boolean(), nullable=True))
+    op.execute("UPDATE persona SET builtin_persona = default_persona")
+    op.alter_column("persona", "builtin_persona", nullable=False)
+    op.drop_index("_default_persona_name_idx", table_name="persona")
+    op.create_index(
+        "_builtin_persona_name_idx",
+        "persona",
+        ["name"],
+        unique=True,
+        postgresql_where=sa.text("builtin_persona = true"),
+    )
+
+    op.add_column(
+        "user", sa.Column("visible_assistants", postgresql.JSONB(), nullable=True)
+    )
+    op.add_column(
+        "user", sa.Column("hidden_assistants", postgresql.JSONB(), nullable=True)
+    )
+    op.execute(
+        "UPDATE \"user\" SET visible_assistants = '[]'::jsonb, hidden_assistants = '[]'::jsonb"
+    )
+    op.alter_column(
+        "user",
+        "visible_assistants",
+        nullable=False,
+        server_default=sa.text("'[]'::jsonb"),
+    )
+    op.alter_column(
+        "user",
+        "hidden_assistants",
+        nullable=False,
+        server_default=sa.text("'[]'::jsonb"),
+    )
+    op.drop_column("persona", "default_persona")
+    op.add_column(
+        "persona", sa.Column("is_default_persona", sa.Boolean(), nullable=True)
+    )
+
+
+def downgrade() -> None:
+    # Reverting changes made in upgrade
+    op.drop_column("user", "hidden_assistants")
+    op.drop_column("user", "visible_assistants")
+    op.drop_index("_builtin_persona_name_idx", table_name="persona")
+
+    op.drop_column("persona", "is_default_persona")
+    op.add_column("persona", sa.Column("default_persona", sa.Boolean(), nullable=True))
+    op.execute("UPDATE persona SET default_persona = builtin_persona")
+    op.alter_column("persona", "default_persona", nullable=False)
+    op.drop_column("persona", "builtin_persona")
+    op.create_index(
+        "_default_persona_name_idx",
+        "persona",
+        ["name"],
+        unique=True,
+        postgresql_where=sa.text("default_persona = true"),
+    )

backend/alembic/versions/570282d33c49_track_onyxbot_explicitly.py

@@ -0,0 +1,27 @@
+"""Track Onyxbot Explicitly
+
+Revision ID: 570282d33c49
+Revises: 7547d982db8f
+Create Date: 2024-05-04 17:49:28.568109
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "570282d33c49"
+down_revision = "7547d982db8f"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "chat_session", sa.Column("danswerbot_flow", sa.Boolean(), nullable=True)
+    )
+    op.execute("UPDATE chat_session SET danswerbot_flow = one_shot")
+    op.alter_column("chat_session", "danswerbot_flow", nullable=False)
+
+
+def downgrade() -> None:
+    op.drop_column("chat_session", "danswerbot_flow")