add logs

* shared filter util

* clearer comment

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+    description: 'Always attempt to pull a newer version of the image'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

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

@@ -1,34 +1,63 @@
-name: Build and Push Backend Images on Tagging
+name: Build and Push Backend Image on Tag
 
 on:
   push:
     tags:
-      - '*'
+      - "*"
+
+env:
+  REGISTRY_IMAGE: ${{ contains(github.ref_name, 'cloud') && 'danswer/danswer-backend-cloud' || 'danswer/danswer-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
+      - name: Install build-essential
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y build-essential
+
+      - name: Backend Image Docker Build and Push
+        uses: docker/build-push-action@v5
+        with:
+          context: ./backend
+          file: ./backend/Dockerfile
+          platforms: linux/amd64,linux/arm64
+          push: true
+          tags: |
+            ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
+            ${{ env.LATEST_TAG == 'true' && format('{0}:latest', env.REGISTRY_IMAGE) || '' }}
+          build-args: |
+            DANSWER_VERSION=${{ github.ref_name }}
+
+      # trivy has their own rate limiting issues causing this action to flake
+      # we worked around it by hardcoding to different db repos in env
+      # can re-enable when they figure it out
+      # https://github.com/aquasecurity/trivy/discussions/7538
+      # https://github.com/aquasecurity/trivy-action/issues/389
+      - name: Run Trivy vulnerability scanner
+        uses: aquasecurity/trivy-action@master
+        env:
+          TRIVY_DB_REPOSITORY: "public.ecr.aws/aquasecurity/trivy-db:2"
+          TRIVY_JAVA_DB_REPOSITORY: "public.ecr.aws/aquasecurity/trivy-java-db:1"
+        with:
+          # To run locally: trivy image --severity HIGH,CRITICAL danswer/danswer-backend
+          image-ref: docker.io/${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
+          severity: "CRITICAL,HIGH"
+          trivyignores: ./backend/.trivyignore

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

@@ -0,0 +1,137 @@
+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: danswer/danswer-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: ${{ matrix.platform }}
+          push: true
+          build-args: |
+            DANSWER_VERSION=${{ github.ref_name }}
+            NEXT_PUBLIC_CLOUD_ENABLED=true
+            NEXT_PUBLIC_POSTHOG_KEY=${{ secrets.POSTHOG_KEY }}
+            NEXT_PUBLIC_POSTHOG_HOST=${{ secrets.POSTHOG_HOST }}
+            NEXT_PUBLIC_SENTRY_DSN=${{ secrets.SENTRY_DSN }}
+            NEXT_PUBLIC_GTM_ENABLED=true
+          # needed due to weird interactions with the builds for different platforms
+          no-cache: true
+          labels: ${{ steps.meta.outputs.labels }}
+          outputs: type=image,name=${{ env.REGISTRY_IMAGE }},push-by-digest=true,name-canonical=true,push=true
+
+      - name: Export digest
+        run: |
+          mkdir -p /tmp/digests
+          digest="${{ steps.build.outputs.digest }}"
+          touch "/tmp/digests/${digest#sha256:}"
+
+      - name: Upload digest
+        uses: actions/upload-artifact@v4
+        with:
+          name: digests-${{ env.PLATFORM_PAIR }}
+          path: /tmp/digests/*
+          if-no-files-found: error
+          retention-days: 1
+
+  merge:
+    runs-on: ubuntu-latest
+    needs:
+      - build
+    steps:
+      - name: Download digests
+        uses: actions/download-artifact@v4
+        with:
+          path: /tmp/digests
+          pattern: digests-*
+          merge-multiple: true
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Docker meta
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.REGISTRY_IMAGE }}
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_TOKEN }}
+
+      - name: Create manifest list and push
+        working-directory: /tmp/digests
+        run: |
+          docker buildx imagetools create $(jq -cr '.tags | map("-t " + .) | join(" ")' <<< "$DOCKER_METADATA_OUTPUT_JSON") \
+            $(printf '${{ env.REGISTRY_IMAGE }}@sha256:%s ' *)
+
+      - name: Inspect image
+        run: |
+          docker buildx imagetools inspect ${{ env.REGISTRY_IMAGE }}:${{ steps.meta.outputs.version }}
+
+      # trivy has their own rate limiting issues causing this action to flake
+      # we worked around it by hardcoding to different db repos in env
+      # can re-enable when they figure it out
+      # https://github.com/aquasecurity/trivy/discussions/7538
+      # https://github.com/aquasecurity/trivy-action/issues/389
+      - name: Run Trivy vulnerability scanner
+        uses: aquasecurity/trivy-action@master
+        env:
+          TRIVY_DB_REPOSITORY: "public.ecr.aws/aquasecurity/trivy-db:2"
+          TRIVY_JAVA_DB_REPOSITORY: "public.ecr.aws/aquasecurity/trivy-java-db:1"
+        with:
+          image-ref: docker.io/${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
+          severity: "CRITICAL,HIGH"

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

@@ -0,0 +1,55 @@
+name: Build and Push Model Server Image on Tag
+
+on:
+  push:
+    tags:
+      - "*"
+
+env:
+  REGISTRY_IMAGE: ${{ contains(github.ref_name, 'cloud') && 'danswer/danswer-model-server-cloud' || 'danswer/danswer-model-server' }}
+  LATEST_TAG: ${{ contains(github.ref_name, 'latest') }}
+
+jobs:
+  build-and-push:
+    # See https://runs-on.com/runners/linux/
+    runs-on: [runs-on, runner=8cpu-linux-x64, "run-id=${{ github.run_id }}"]
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: 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: Model Server Image Docker Build and Push
+        uses: docker/build-push-action@v5
+        with:
+          context: ./backend
+          file: ./backend/Dockerfile.model_server
+          platforms: linux/amd64,linux/arm64
+          push: true
+          tags: |
+            ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
+            ${{ env.LATEST_TAG == 'true' && format('{0}:latest', env.REGISTRY_IMAGE) || '' }}
+          build-args: |
+            DANSWER_VERSION=${{ github.ref_name }}
+
+      # trivy has their own rate limiting issues causing this action to flake
+      # we worked around it by hardcoding to different db repos in env
+      # can re-enable when they figure it out
+      # https://github.com/aquasecurity/trivy/discussions/7538
+      # https://github.com/aquasecurity/trivy-action/issues/389
+      - name: Run Trivy vulnerability scanner
+        uses: aquasecurity/trivy-action@master
+        env:
+          TRIVY_DB_REPOSITORY: "public.ecr.aws/aquasecurity/trivy-db:2"
+          TRIVY_JAVA_DB_REPOSITORY: "public.ecr.aws/aquasecurity/trivy-java-db:1"
+        with:
+          image-ref: docker.io/danswer/danswer-model-server:${{ github.ref_name }}
+          severity: "CRITICAL,HIGH"

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

@@ -1,34 +1,131 @@
-name: Build and Push Web Images on Tagging
+name: Build and Push Web Image on Tag
 
 on:
   push:
     tags:
       - '*'
 
+env:
+  REGISTRY_IMAGE: danswer/danswer-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: 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: ${{ matrix.platform }}
+          push: true
+          build-args: |
+            DANSWER_VERSION=${{ github.ref_name }}
+          # needed due to weird interactions with the builds for different platforms  
+          no-cache: true
+          labels: ${{ steps.meta.outputs.labels }}
+          outputs: type=image,name=${{ env.REGISTRY_IMAGE }},push-by-digest=true,name-canonical=true,push=true
+      
+      - name: Export digest
+        run: |
+          mkdir -p /tmp/digests
+          digest="${{ steps.build.outputs.digest }}"
+          touch "/tmp/digests/${digest#sha256:}"          
+      
+      - 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
 
-    - name: Set up Docker Buildx
-      uses: docker/setup-buildx-action@v1
+  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 }}
 
-    - name: Login to Docker Hub
-      uses: docker/login-action@v1
-      with:
-        username: ${{ secrets.DOCKER_USERNAME }}
-        password: ${{ secrets.DOCKER_TOKEN }}
-
-    - name: Web Image Docker Build and Push
-      uses: docker/build-push-action@v2
-      with:
-        context: ./web
-        file: ./web/Dockerfile
-        platforms: linux/amd64,linux/arm64
-        push: true
-        tags: |
-          danswer/danswer-web-server:${{ github.ref_name }}
-          danswer/danswer-web-server:latest
+    # 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

@@ -1,3 +1,6 @@
+# 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:
@@ -9,7 +12,9 @@ on:
 
 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

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

@@ -0,0 +1,172 @@
+# 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]@danswer.ai"
+
+      - 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 +1,76 @@
+# Scan for problematic software licenses
+
+# trivy has their own rate limiting issues causing this action to flake
+# we worked around it by hardcoding to different db repos in env
+# can re-enable when they figure it out
+# https://github.com/aquasecurity/trivy/discussions/7538
+# https://github.com/aquasecurity/trivy-action/issues/389
+
+name: 'Nightly - Scan licenses'
+on:
+#   schedule:
+#     - cron: '0 14 * * *'  # Runs every day at 6 AM PST / 7 AM PDT / 2 PM UTC
+  workflow_dispatch:  # Allows manual triggering
+
+permissions:
+  actions: read
+  contents: read
+  security-events: write
+  
+jobs:
+  scan-licenses:
+    # See https://runs-on.com/runners/linux/
+    runs-on: [runs-on,runner=2cpu-linux-x64,"run-id=${{ github.run_id }}"]
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+          cache: 'pip'
+          cache-dependency-path: |
+            backend/requirements/default.txt
+            backend/requirements/dev.txt
+            backend/requirements/model_server.txt
+      
+      - name: Get explicit and transitive dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install --retries 5 --timeout 30 -r backend/requirements/default.txt
+          pip install --retries 5 --timeout 30 -r backend/requirements/dev.txt
+          pip install --retries 5 --timeout 30 -r backend/requirements/model_server.txt
+          pip freeze > requirements-all.txt
+                    
+      - name: Check python
+        id: license_check_report
+        uses: pilosus/action-pip-license-checker@v2
+        with:
+          requirements: 'requirements-all.txt'
+          fail: 'Copyleft'
+          exclude: '(?i)^(pylint|aio[-_]*).*'
+          
+      - name: Print report
+        if: ${{ always() }}
+        run: echo "${{ steps.license_check_report.outputs.report }}"
+      
+      - name: Install npm dependencies
+        working-directory: ./web
+        run: npm ci
+        
+      - name: Run Trivy vulnerability scanner in repo mode
+        uses: aquasecurity/trivy-action@0.28.0
+        with:
+          scan-type: fs
+          scanners: license
+          format: table
+#           format: sarif
+#           output: trivy-results.sarif
+          severity: HIGH,CRITICAL
+
+#       - name: Upload Trivy scan results to GitHub Security tab
+#         uses: github/codeql-action/upload-sarif@v3
+#         with:
+#           sarif_file: trivy-results.sarif

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

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

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

@@ -0,0 +1,225 @@
+name: Run Chromatic Tests
+concurrency:
+  group: Run-Chromatic-Tests-${{ github.workflow }}-${{ github.head_ref || github.event.workflow_run.head_branch || github.run_id }}
+  cancel-in-progress: true
+
+on: push
+
+env:
+  OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+  SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
+
+jobs:
+  playwright-tests:
+    name: Playwright Tests
+
+    # See https://runs-on.com/runners/linux/
+    runs-on: [runs-on,runner=8cpu-linux-x64,ram=16,"run-id=${{ github.run_id }}"]
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+          cache: 'pip'
+          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: ${{ secrets.DOCKER_TOKEN }}
+
+      # tag every docker image with "test" so that we can spin up the correct set
+      # of images during testing
+      
+      # we use the runs-on cache for docker builds
+      # in conjunction with runs-on runners, it has better speed and unlimited caching
+      # https://runs-on.com/caching/s3-cache-for-github-actions/
+      # https://runs-on.com/caching/docker/
+      # https://github.com/moby/buildkit#s3-cache-experimental
+      
+      # images are built and run locally for testing purposes. Not pushed.
+
+      - name: Build Web Docker image
+        uses: ./.github/actions/custom-build-and-push
+        with:
+          context: ./web
+          file: ./web/Dockerfile
+          platforms: linux/amd64
+          tags: danswer/danswer-web-server:test
+          push: false
+          load: true
+          cache-from: type=s3,prefix=cache/${{ github.repository }}/integration-tests/web-server/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }}
+          cache-to: type=s3,prefix=cache/${{ github.repository }}/integration-tests/web-server/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }},mode=max
+
+      - name: Build Backend Docker image
+        uses: ./.github/actions/custom-build-and-push
+        with:
+          context: ./backend
+          file: ./backend/Dockerfile
+          platforms: linux/amd64
+          tags: danswer/danswer-backend:test
+          push: false
+          load: true
+          cache-from: type=s3,prefix=cache/${{ github.repository }}/integration-tests/backend/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }}
+          cache-to: type=s3,prefix=cache/${{ github.repository }}/integration-tests/backend/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }},mode=max
+
+      - name: Build Model Server Docker image
+        uses: ./.github/actions/custom-build-and-push
+        with:
+          context: ./backend
+          file: ./backend/Dockerfile.model_server
+          platforms: linux/amd64
+          tags: danswer/danswer-model-server:test
+          push: false
+          load: true
+          cache-from: type=s3,prefix=cache/${{ github.repository }}/integration-tests/model-server/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }}
+          cache-to: type=s3,prefix=cache/${{ github.repository }}/integration-tests/model-server/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }},mode=max
+
+      - name: Start Docker containers
+        run: |
+          cd deployment/docker_compose
+          ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true \
+          AUTH_TYPE=basic \
+          REQUIRE_EMAIL_VERIFICATION=false \
+          DISABLE_TELEMETRY=true \
+          IMAGE_TAG=test \
+          docker compose -f docker-compose.dev.yml -p danswer-stack up -d
+        id: start_docker
+
+      - name: Wait for service to be ready
+        run: |
+          echo "Starting wait-for-service script..."
+          
+          docker logs -f danswer-stack-api_server-1 &
+
+          start_time=$(date +%s)
+          timeout=300  # 5 minutes in seconds
+          
+          while true; do
+            current_time=$(date +%s)
+            elapsed_time=$((current_time - start_time))
+            
+            if [ $elapsed_time -ge $timeout ]; then
+              echo "Timeout reached. Service did not become ready in 5 minutes."
+              exit 1
+            fi
+            
+            # Use curl with error handling to ignore specific exit code 56
+            response=$(curl -s -o /dev/null -w "%{http_code}" http://localhost:8080/health || echo "curl_error")
+            
+            if [ "$response" = "200" ]; then
+              echo "Service is ready!"
+              break
+            elif [ "$response" = "curl_error" ]; then
+              echo "Curl encountered an error, possibly exit code 56. Continuing to retry..."
+            else
+              echo "Service not ready yet (HTTP status $response). Retrying in 5 seconds..."
+            fi
+            
+            sleep 5
+          done
+          echo "Finished waiting for service."
+
+      - name: Run pytest playwright test init
+        working-directory: ./backend
+        env: 
+          PYTEST_IGNORE_SKIP: true
+        run: pytest -s tests/integration/tests/playwright/test_playwright.py
+
+      - name: Run Playwright tests
+        working-directory: ./web
+        run: npx playwright test
+
+      - uses: actions/upload-artifact@v4
+        if: always()
+        with:
+          # Chromatic automatically defaults to the test-results directory.
+          # Replace with the path to your custom directory and adjust the CHROMATIC_ARCHIVE_LOCATION environment variable accordingly.
+          name: test-results
+          path: ./web/test-results
+          retention-days: 30
+                    
+      # save before stopping the containers so the logs can be captured
+      - name: Save Docker logs
+        if: success() || failure()
+        run: |
+          cd deployment/docker_compose
+          docker compose -f docker-compose.dev.yml -p danswer-stack logs > docker-compose.log
+          mv docker-compose.log ${{ github.workspace }}/docker-compose.log
+      
+      - name: Upload logs
+        if: success() || failure()
+        uses: actions/upload-artifact@v4
+        with:
+          name: docker-logs
+          path: ${{ github.workspace }}/docker-compose.log
+
+      - name: Stop Docker containers
+        run: |
+          cd deployment/docker_compose
+          docker compose -f docker-compose.dev.yml -p danswer-stack down -v
+
+  chromatic-tests:
+    name: Chromatic Tests
+    
+    needs: playwright-tests
+    runs-on: [runs-on,runner=8cpu-linux-x64,ram=16,"run-id=${{ github.run_id }}"]
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          
+      - name: Setup node
+        uses: actions/setup-node@v4
+        with:
+          node-version: 22
+          
+      - name: Install node dependencies
+        working-directory: ./web
+        run: npm ci
+        
+      - name: Download Playwright test results
+        uses: actions/download-artifact@v4
+        with:
+          name: test-results
+          path: ./web/test-results
+          
+      - name: Run Chromatic
+        uses: chromaui/action@latest
+        with:
+          playwright: true
+          projectToken: ${{ secrets.CHROMATIC_PROJECT_TOKEN }}
+          workingDir: ./web
+        env: 
+          CHROMATIC_ARCHIVE_LOCATION: ./test-results

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

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

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

@@ -0,0 +1,243 @@
+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: ${{ secrets.CONFLUENCE_ACCESS_TOKEN }}
+  
+jobs:
+  integration-tests:
+    # See https://runs-on.com/runners/linux/
+    runs-on: [runs-on,runner=8cpu-linux-x64,ram=16,"run-id=${{ 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: ${{ secrets.DOCKER_TOKEN }}
+
+      # tag every docker image with "test" so that we can spin up the correct set
+      # of images during testing
+      
+      # We don't need to build the Web Docker image since it's not yet used
+      # in the integration tests. We have a separate action to verify that it builds 
+      # successfully.
+      - name: Pull Web Docker image
+        run: |
+          docker pull danswer/danswer-web-server:latest
+          docker tag danswer/danswer-web-server:latest danswer/danswer-web-server:test
+
+      # we use the runs-on cache for docker builds
+      # in conjunction with runs-on runners, it has better speed and unlimited caching
+      # https://runs-on.com/caching/s3-cache-for-github-actions/
+      # https://runs-on.com/caching/docker/
+      # https://github.com/moby/buildkit#s3-cache-experimental
+      
+      # images are built and run locally for testing purposes. Not pushed.
+      - name: Build Backend Docker image
+        uses: ./.github/actions/custom-build-and-push
+        with:
+          context: ./backend
+          file: ./backend/Dockerfile
+          platforms: linux/amd64
+          tags: danswer/danswer-backend:test
+          push: false
+          load: true
+          cache-from: type=s3,prefix=cache/${{ github.repository }}/integration-tests/backend/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }}
+          cache-to: type=s3,prefix=cache/${{ github.repository }}/integration-tests/backend/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }},mode=max
+
+      - name: Build Model Server Docker image
+        uses: ./.github/actions/custom-build-and-push
+        with:
+          context: ./backend
+          file: ./backend/Dockerfile.model_server
+          platforms: linux/amd64
+          tags: danswer/danswer-model-server:test
+          push: false
+          load: true
+          cache-from: type=s3,prefix=cache/${{ github.repository }}/integration-tests/model-server/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }}
+          cache-to: type=s3,prefix=cache/${{ github.repository }}/integration-tests/model-server/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }},mode=max
+      
+      - name: Build integration test Docker image
+        uses: ./.github/actions/custom-build-and-push
+        with:
+          context: ./backend
+          file: ./backend/tests/integration/Dockerfile
+          platforms: linux/amd64
+          tags: danswer/danswer-integration:test
+          push: false
+          load: true
+          cache-from: type=s3,prefix=cache/${{ github.repository }}/integration-tests/integration/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }}
+          cache-to: type=s3,prefix=cache/${{ github.repository }}/integration-tests/integration/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }},mode=max
+
+      # Start containers for multi-tenant tests
+      - name: Start Docker containers for multi-tenant tests
+        run: |
+          cd deployment/docker_compose
+          ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true \
+          MULTI_TENANT=true \
+          AUTH_TYPE=basic \
+          REQUIRE_EMAIL_VERIFICATION=false \
+          DISABLE_TELEMETRY=true \
+          IMAGE_TAG=test \
+          docker compose -f docker-compose.dev.yml -p danswer-stack up -d
+        id: start_docker_multi_tenant
+
+      # In practice, `cloud` Auth type would require OAUTH credentials to be set.
+      - name: Run Multi-Tenant Integration Tests
+        run: |
+          echo "Running integration tests..."
+          docker run --rm --network danswer-stack_default \
+            --name test-runner \
+            -e POSTGRES_HOST=relational_db \
+            -e POSTGRES_USER=postgres \
+            -e POSTGRES_PASSWORD=password \
+            -e POSTGRES_DB=postgres \
+            -e VESPA_HOST=index \
+            -e REDIS_HOST=cache \
+            -e API_SERVER_HOST=api_server \
+            -e OPENAI_API_KEY=${OPENAI_API_KEY} \
+            -e SLACK_BOT_TOKEN=${SLACK_BOT_TOKEN} \
+            -e TEST_WEB_HOSTNAME=test-runner \
+            -e AUTH_TYPE=cloud \
+            -e MULTI_TENANT=true \
+            danswer/danswer-integration:test \
+            /app/tests/integration/multitenant_tests
+        continue-on-error: true
+        id: run_multitenant_tests
+
+      - name: Check multi-tenant test results
+        run: |
+          if [ ${{ steps.run_tests.outcome }} == 'failure' ]; then
+            echo "Integration tests failed. Exiting with error."
+            exit 1
+          else
+            echo "All integration tests passed successfully."
+          fi 
+
+      - name: Stop multi-tenant Docker containers
+        run: |
+          cd deployment/docker_compose
+          docker compose -f docker-compose.dev.yml -p danswer-stack down -v
+
+
+      - name: Start Docker containers 
+        run: |
+          cd deployment/docker_compose
+          ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true \
+          AUTH_TYPE=basic \
+          REQUIRE_EMAIL_VERIFICATION=false \
+          DISABLE_TELEMETRY=true \
+          IMAGE_TAG=test \
+          docker compose -f docker-compose.dev.yml -p danswer-stack up -d
+        id: start_docker
+
+      - name: Wait for service to be ready
+        run: |
+          echo "Starting wait-for-service script..."
+          
+          docker logs -f danswer-stack-api_server-1 &
+
+          start_time=$(date +%s)
+          timeout=300  # 5 minutes in seconds
+          
+          while true; do
+            current_time=$(date +%s)
+            elapsed_time=$((current_time - start_time))
+            
+            if [ $elapsed_time -ge $timeout ]; then
+              echo "Timeout reached. Service did not become ready in 5 minutes."
+              exit 1
+            fi
+            
+            # Use curl with error handling to ignore specific exit code 56
+            response=$(curl -s -o /dev/null -w "%{http_code}" http://localhost:8080/health || echo "curl_error")
+            
+            if [ "$response" = "200" ]; then
+              echo "Service is ready!"
+              break
+            elif [ "$response" = "curl_error" ]; then
+              echo "Curl encountered an error, possibly exit code 56. Continuing to retry..."
+            else
+              echo "Service not ready yet (HTTP status $response). Retrying in 5 seconds..."
+            fi
+            
+            sleep 5
+          done
+          echo "Finished waiting for service."
+
+      - name: Run Standard Integration Tests
+        run: |
+          echo "Running integration tests..."
+          docker run --rm --network danswer-stack_default \
+            --name test-runner \
+            -e POSTGRES_HOST=relational_db \
+            -e POSTGRES_USER=postgres \
+            -e POSTGRES_PASSWORD=password \
+            -e POSTGRES_DB=postgres \
+            -e VESPA_HOST=index \
+            -e REDIS_HOST=cache \
+            -e API_SERVER_HOST=api_server \
+            -e OPENAI_API_KEY=${OPENAI_API_KEY} \
+            -e SLACK_BOT_TOKEN=${SLACK_BOT_TOKEN} \
+            -e CONFLUENCE_TEST_SPACE_URL=${CONFLUENCE_TEST_SPACE_URL} \
+            -e CONFLUENCE_USER_NAME=${CONFLUENCE_USER_NAME} \
+            -e CONFLUENCE_ACCESS_TOKEN=${CONFLUENCE_ACCESS_TOKEN} \
+            -e TEST_WEB_HOSTNAME=test-runner \
+            danswer/danswer-integration:test \
+            /app/tests/integration/tests \
+            /app/tests/integration/connector_job_tests
+        continue-on-error: true
+        id: run_tests
+
+      - name: Check test results
+        run: |
+          if [ ${{ steps.run_tests.outcome }} == 'failure' ]; then
+            echo "Integration tests failed. Exiting with error."
+            exit 1
+          else
+            echo "All integration tests passed successfully."
+          fi
+
+      # save before stopping the containers so the logs can be captured
+      - name: Save Docker logs
+        if: success() || failure()
+        run: |
+          cd deployment/docker_compose
+          docker compose -f docker-compose.dev.yml -p danswer-stack logs > docker-compose.log
+          mv docker-compose.log ${{ github.workspace }}/docker-compose.log
+
+      - name: Stop Docker containers
+        run: |
+          cd deployment/docker_compose
+          docker compose -f docker-compose.dev.yml -p danswer-stack down -v
+      
+      - name: Upload logs
+        if: success() || failure()
+        uses: actions/upload-artifact@v4
+        with:
+          name: docker-logs
+          path: ${{ github.workspace }}/docker-compose.log
+
+      - name: Stop Docker containers
+        run: |
+          cd deployment/docker_compose
+          docker compose -f docker-compose.dev.yml -p danswer-stack down -v

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

@@ -1,29 +1,35 @@
 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'
         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 -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
+        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 +1,69 @@
+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: ${{ secrets.SLAB_BOT_TOKEN }}
+
+jobs:
+  connectors-check:
+    # See https://runs-on.com/runners/linux/
+    runs-on: [runs-on,runner=8cpu-linux-x64,"run-id=${{ 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
+
+      - 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 +1,58 @@
+name: Connector Tests
+
+on:
+  schedule:
+    # This cron expression runs the job daily at 16:00 UTC (9am PT)
+    - cron: "0 16 * * *"
+
+env:
+  # Bedrock
+  AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
+  AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+  AWS_REGION_NAME: ${{ secrets.AWS_REGION_NAME }}
+
+  # OpenAI
+  OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+
+jobs:
+  model-check:
+    # See https://runs-on.com/runners/linux/
+    runs-on: [runs-on,runner=8cpu-linux-x64,"run-id=${{ github.run_id }}"]
+
+    env:
+      PYTHONPATH: ./backend
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+          cache: "pip"
+          cache-dependency-path: |
+            backend/requirements/default.txt
+            backend/requirements/dev.txt
+
+      - name: Install Dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install --retries 5 --timeout 30 -r backend/requirements/default.txt
+          pip install --retries 5 --timeout 30 -r backend/requirements/dev.txt
+
+      - name: Run Tests
+        shell: script -q -e -c "bash --noprofile --norc -eo pipefail {0}"
+        run: |
+          py.test -o junit_family=xunit2 -xv --ff backend/tests/daily/llm
+          py.test -o junit_family=xunit2 -xv --ff backend/tests/daily/embedding
+
+      - name: Alert on Failure
+        if: failure() && github.event_name == 'schedule'
+        env:
+          SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+        run: |
+          curl -X POST \
+            -H 'Content-type: application/json' \
+            --data '{"text":"Scheduled Model Tests failed! Check the run at: https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}"}' \
+            $SLACK_WEBHOOK

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

@@ -0,0 +1,40 @@
+name: Python Unit Tests
+
+on:
+  merge_group:
+  pull_request:
+    branches:
+      - main
+      - 'release/**'
+
+jobs:
+  backend-check:
+    # 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@v5
+      with:
+        python-version: '3.11'
+        cache: 'pip'
+        cache-dependency-path: |
+          backend/requirements/default.txt
+          backend/requirements/dev.txt
+
+    - name: Install Dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install --retries 5 --timeout 30 -r backend/requirements/default.txt
+        pip install --retries 5 --timeout 30 -r backend/requirements/dev.txt
+
+    - name: Run Tests
+      shell: script -q -e -c "bash --noprofile --norc -eo pipefail {0}"
+      run: py.test -o junit_family=xunit2 -xv --ff backend/tests/unit

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

@@ -0,0 +1,23 @@
+name: Quality Checks PR
+concurrency:
+  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:
+    # 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@v3.0.1
+        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 +1,54 @@
+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]@danswer.ai"
+
+    - name: Check for existing nightly tag
+      id: check_tag
+      run: |
+        if git tag --points-at HEAD --list "nightly-latest*" | grep -q .; then
+          echo "A tag starting with 'nightly-latest' already exists on HEAD."
+          echo "tag_exists=true" >> $GITHUB_OUTPUT
+        else
+          echo "No tag starting with 'nightly-latest' exists on HEAD."
+          echo "tag_exists=false" >> $GITHUB_OUTPUT
+        fi
+        
+    # 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

@@ -1,2 +1,10 @@
 .env
 .DS_store
+.venv
+.mypy_cache
+.idea
+/deployment/data/nginx/app.conf
+.vscode/
+*.sw?
+/backend/tests/regression/answer_quality/search_test_config.yaml
+/web/test-results/

.pre-commit-config.yaml

@@ -28,6 +28,13 @@ repos:
     rev: v0.0.286
     hooks:
       - id: ruff
+  - repo: https://github.com/pre-commit/mirrors-prettier
+    rev: v3.1.0
+    hooks:
+    - id: prettier
+      types_or: [html, css, javascript, ts, tsx]
+      additional_dependencies:
+      - prettier
 
   # We would like to have a mypy pre-commit hook, but due to the fact that
   # pre-commit runs in it's own isolated environment, we would need to install

.prettierignore

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

.vscode/env_template.txt

@@ -0,0 +1,51 @@
+# 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
+
+
+# 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>
+# 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

.vscode/launch.template.jsonc

@@ -1,82 +1,359 @@
-/*
-
-  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 Danswer Services",
+            "configurations": [
+                "Web Server",
+                "Model Server",
+                "API Server",
+                "Slack Bot",
+		  		"Celery primary", 
+		  		"Celery light", 
+		  		"Celery heavy", 
+		  		"Celery indexing", 
+		  		"Celery beat",
+            ],
+			"presentation": {
+				 "group": "1",
+			 }
+        },
+		{
+			"name": "Web / Model / API",
+		  	"configurations": [
+		  		"Web Server", 
+		  		"Model Server", 
+		  		"API Server",
+		  	],
+			"presentation": {
+				 "group": "1",
+			 }
+		},
+		{
+			"name": "Celery (all)",
+		  	"configurations": [
+		  		"Celery primary", 
+		  		"Celery light", 
+		  		"Celery heavy", 
+		  		"Celery indexing", 
+		  		"Celery beat"
+		  	],
+			"presentation": {
+				 "group": "1",
+			 }
+		}
+    ],
     "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": [
+                "danswer.main:app",
+                "--reload",
+                "--port",
+                "8080"
+            ],
+            "presentation": {
+				 "group": "2",
+			 },
+            "consoleTitle": "API Server Console"
+        },
+        // For the listener to access the Slack API,
+        // DANSWER_BOT_SLACK_APP_TOKEN & DANSWER_BOT_SLACK_BOT_TOKEN need to be set in .env file located in the root of the project
+        {
+            "name": "Slack Bot",
+            "consoleName": "Slack Bot",
+            "type": "debugpy",
+            "request": "launch",
+            "program": "danswer/danswerbot/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",
+                "danswer.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",
+                "danswer.background.celery.versioned_apps.light",
+                "worker",
+                "--pool=threads",
+                "--concurrency=64",
+                "--prefetch-multiplier=8",
+                "--loglevel=INFO",
+                "--hostname=light@%n",
+                "-Q",
+                "vespa_metadata_sync,connector_deletion,doc_permissions_upsert",
+            ],
+            "presentation": {
+				 "group": "2",
+			 },
+            "consoleTitle": "Celery light Console"
+        },
+        {
+            "name": "Celery heavy",
+            "type": "debugpy",
+            "request": "launch",
+            "module": "celery",
+            "cwd": "${workspaceFolder}/backend",
+            "envFile": "${workspaceFolder}/.vscode/.env",
+            "env": {
+                "LOG_LEVEL": "INFO",
+                "PYTHONUNBUFFERED": "1",
+                "PYTHONPATH": "."
+            },
+            "args": [
+                "-A",
+                "danswer.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",
+                "danswer.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 beat",
+            "type": "debugpy",
+            "request": "launch",
+            "module": "celery",
+            "cwd": "${workspaceFolder}/backend",
+            "envFile": "${workspaceFolder}/.vscode/.env",
+            "env": {
+                "LOG_LEVEL": "DEBUG",
+                "PYTHONUNBUFFERED": "1",
+                "PYTHONPATH": "."
+            },
+            "args": [
+                "-A",
+                "danswer.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/danswer/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": "."
+            },
+        },
     ]
-}
+}

CONTRIBUTING.md

@@ -1,3 +1,5 @@
+<!-- DANSWER_METADATA={"link": "https://github.com/danswer-ai/danswer/blob/main/CONTRIBUTING.md"} -->
+
 # Contributing to Danswer
 Hey there! We are so excited that you're interested in Danswer.
 
@@ -6,7 +8,7 @@ As an open source project in a rapidly changing space, we welcome all contributi
 
 ## 💃 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/danswer-ai/danswer/issues) page is a great place to start for contribution ideas.
 
 Issues that have been explicitly approved by the maintainers (aligned with the direction of the project)
 will be marked with the `approved by maintainers` label.
@@ -19,7 +21,9 @@ 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.
 Before starting on implementation, please raise a GitHub issue.
 
-And always feel free to message us (Chris Weaver / Yuhong Sun) on Slack / Discord directly about anything at all. 
+And always feel free to message us (Chris Weaver / Yuhong Sun) on 
+[Slack](https://join.slack.com/t/danswer/shared_invite/zt-2lcmqw703-071hBuZBfNEOGUsLa5PXvQ) / 
+[Discord](https://discord.gg/TDJ59cGV2X) directly about anything at all. 
 
 
 ### Contributing Code
@@ -28,7 +32,7 @@ To contribute to this project, please follow the
 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 🙋
@@ -36,7 +40,7 @@ Our goal is to make contributing as easy as possible. If you run into any issues
 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-1u3h3ke3b-VGh1idW19R8oiNRiKBYv2w)
+[Slack](https://join.slack.com/t/danswer/shared_invite/zt-2afut44lv-Rw3kSWu6_OmdAXRpCv80DQ)
 and 
 [Discord](https://discord.gg/TDJ59cGV2X).
 
@@ -44,24 +48,26 @@ We would love to see you there!
 
 
 ## Get Started 🚀
-Danswer being a fully functional app, relies on several external pieces of software, specifically:
-- Postgres (Relational DB)
+Danswer being a fully functional app, relies on some external software, specifically:
+- [Postgres](https://www.postgresql.org/) (Relational DB)
 - [Vespa](https://vespa.ai/) (Vector DB/Search Engine)
+- [Redis](https://redis.io/) (Cache)
+- [Nginx](https://nginx.org/) (Not needed for development flows generally)
 
-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 Danswer locally from source with Docker containers providing the above external software. We believe this combination is easier for
+> development purposes. If you prefer to use pre-built container images, we provide instructions on running the full Danswer stack within Docker below.
 
 
 ### Local Set Up
-We've tested primarily with Python versions >= 3.11 but the code should work with Python >= 3.9.
+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.
 
-This guide skips a few optional features for simplicity, reach out if you need any of these:
-- User Authentication feature
-- File Connector background job
+If using a lower version, modifications will have to be made to the code.
+If using a higher version, sometimes some libraries will not be available (i.e. we had problems with Tensorflow in the past with higher versions of python).
 
 
-#### Installing Requirements
+#### Backend: Python requirements
 Currently, we use pip and recommend creating a virtual environment.
 
 For convenience here's a command for it:
@@ -69,145 +75,164 @@ For convenience here's a command for it:
 python -m venv .venv
 source .venv/bin/activate
 ```
-_For Windows activate via:_
+
+> **Note:**
+> This virtual environment MUST NOT be set up WITHIN the danswer directory if you plan on using mypy within certain IDEs.
+> For simplicity, we recommend setting up the virtual environment outside of the danswer directory.
+
+_For Windows, activate the virtual environment using Command Prompt:_
 ```bash
 .venv\Scripts\activate
 ```
+If using PowerShell, the command slightly differs:
+```powershell
+.venv\Scripts\Activate.ps1
+```
 
 Install the required python dependencies:
 ```bash
 pip install -r danswer/backend/requirements/default.txt
 pip install -r danswer/backend/requirements/dev.txt
+pip install -r danswer/backend/requirements/ee.txt
+pip install -r danswer/backend/requirements/model_server.txt
 ```
 
+Install Playwright for Python (headless browser required by the Web Connector)
+
+In the activated Python virtualenv, install Playwright for Python by running:
+```bash
+playwright install
+```
+
+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 `danswer/web` run:
 ```bash
 npm i
 ```
 
-Install Playwright (required by the Web Connector), with the python venv active, run:
+#### Docker containers for external software
+You will need Docker installed to run these containers.
+
+First navigate to `danswer/deployment/docker_compose`, then start up Postgres/Vespa/Redis with:
 ```bash
-playwright install
+docker compose -f docker-compose.dev.yml -p danswer-stack up -d index relational_db cache
 ```
+(index refers to Vespa, relational_db refers to Postgres, and cache refers to Redis)
 
 
-#### Dependent Docker Containers
-First navigate to `danswer/deployment/docker_compose`, then start up the containers with:
-
-Postgres:
-```bash
-docker compose -f docker-compose.dev.yml -p danswer-stack up -d relational_db
-```
-
-Vespa:
-```bash
-docker compose -f docker-compose.dev.yml -p danswer-stack up -d index
-```
-
-
-#### Running Danswer
-
-Setup a folder to store config. Navigate to `danswer/backend` and run:
-```bash
-mkdir dynamic_config_storage
-```
-
+#### Running Danswer locally
 To start the frontend, navigate to `danswer/web` and run:
 ```bash
-AUTH_TYPE=disabled npm run dev
-```
-_for Windows, run:_
-```bash
-(SET "AUTH_TYPE=disabled" && npm run dev)
+npm run dev
 ```
 
+Next, start the model server which runs the local NLP models.
+Navigate to `danswer/backend` and run:
+```bash
+uvicorn model_server.main:app --reload --port 9000
+```
+
+_For Windows (for compatibility with both PowerShell and Command Prompt):_
+```bash
+powershell -Command "uvicorn model_server.main:app --reload --port 9000"
+```
 
 The first time running Danswer, you will need to run the DB migrations for Postgres.
+After the first time, this is no longer required unless the DB models change.
+
 Navigate to `danswer/backend` and with the venv active, run:
 ```bash
 alembic upgrade head
 ```
 
-Additionally, we have to package the Vespa schema deployment:
-Nagivate to `danswer/backend/danswer/datastores/vespa/app_config` and run:
+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:
 ```bash
-zip -r ../vespa-app.zip .
+python ./scripts/dev_run_background_jobs.py
 ```
-- Note: If you don't have the `zip` utility, you will need to install it prior to running the above
 
 To run the backend API server, navigate back to `danswer/backend` and run:
 ```bash
-AUTH_TYPE=disabled \
-DYNAMIC_CONFIG_DIR_PATH=./dynamic_config_storage \
-VESPA_DEPLOYMENT_ZIP=./danswer/datastores/vespa/vespa-app.zip \
-uvicorn danswer.main:app --reload --port 8080
+AUTH_TYPE=disabled uvicorn danswer.main:app --reload --port 8080
 ```
+
 _For Windows (for compatibility with both PowerShell and Command Prompt):_
 ```bash
 powershell -Command "
     $env:AUTH_TYPE='disabled'
-    $env:DYNAMIC_CONFIG_DIR_PATH='./dynamic_config_storage'
-    $env:VESPA_DEPLOYMENT_ZIP='./danswer/datastores/vespa/vespa-app.zip'
     uvicorn danswer.main:app --reload --port 8080 
 "
 ```
 
-To run the background job to check for connector updates and index documents, navigate to `danswer/backend` and run:
+> **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 Danswer onboarding wizard where you can connect your external LLM provider to Danswer.
+
+You've successfully set up a local Danswer instance! 🏁
+
+#### Running the Danswer application in a container
+
+You can run the full Danswer application stack from pre-built images including all external software dependencies.
+
+Navigate to `danswer/deployment/docker_compose` and run:
+
 ```bash
-PYTHONPATH=. DYNAMIC_CONFIG_DIR_PATH=./dynamic_config_storage python danswer/background/update.py
-```
-_For Windows:_
-```bash
-powershell -Command " $env:PYTHONPATH='.'; $env:DYNAMIC_CONFIG_DIR_PATH='./dynamic_config_storage'; python danswer/background/update.py "
+docker compose -f docker-compose.dev.yml -p danswer-stack up -d
 ```
 
-To run the background job to check for periodically check for document set updates, navigate to `danswer/backend` and run:
-```bash
-PYTHONPATH=. DYNAMIC_CONFIG_DIR_PATH=./dynamic_config_storage python danswer/background/document_set_sync_script.py
-```
-_For Windows:_
-```bash
-powershell -Command " $env:PYTHONPATH='.'; $env:DYNAMIC_CONFIG_DIR_PATH='./dynamic_config_storage'; python danswer/background/document_set_sync_script.py "
-```
+After Docker pulls and starts these containers, navigate to `http://localhost:3000` to use Danswer.
 
-To run Celery, which handles deletion of connectors + syncing of document sets, navigate to `danswer/backend` and run:
-```bash
-PYTHONPATH=. DYNAMIC_CONFIG_DIR_PATH=./dynamic_config_storage celery -A  danswer.background.celery worker --loglevel=info --concurrency=1
-```
-_For Windows:_
-```bash
-powershell -Command " $env:PYTHONPATH='.'; $env:DYNAMIC_CONFIG_DIR_PATH='./dynamic_config_storage'; celery -A  danswer.background.celery worker --loglevel=info --concurrency=1 "
-```
+If you want to make changes to Danswer and run those changes in Docker, you can also build a local version of the Danswer container images that incorporates your changes like so:
 
-Note: if you need finer logging, add the additional environment variable `LOG_LEVEL=DEBUG` to the relevant services.
+```bash
+docker compose -f docker-compose.dev.yml -p danswer-stack up -d --build
+```
 
 ### Formatting and Linting
 #### Backend
 For the backend, you'll need to setup pre-commit hooks (black / reorder-python-imports).
 First, install pre-commit (if you don't have it already) following the instructions
 [here](https://pre-commit.com/#installation).
+
+With the virtual environment active, install the pre-commit library with:
+```bash
+pip install pre-commit
+```
+
 Then, from the `danswer/backend` directory, run:
 ```bash
 pre-commit install
 ```
 
 Additionally, we use `mypy` for static type checking.
-Danswer is fully type-annotated, and we would like to keep it that way! 
-Right now, there is no automated type checking at the moment (coming soon), but we ask you to manually run it before
-creating a pull requests with `python -m mypy .` from the `danswer/backend` directory.
+Danswer is fully type-annotated, and we want to keep it that way! 
+To run the mypy checks manually, run `python -m mypy .` from the `danswer/backend` directory.
 
 
 #### Web
 We use `prettier` for formatting. The desired version (2.8.8) will be installed via a `npm i` from the `danswer/web` directory. 
 To run the formatter, use `npx prettier --write .` from the `danswer/web` directory.
-Like `mypy`, we have no automated formatting yet (coming soon), but we request that, for now,
-you run this manually before creating a pull request.
+Please double check that prettier passes before creating a pull request.
 
 
 ### Release Process
-Danswer follows the semver versioning standard.
+Danswer loosely follows the SemVer versioning standard.
+Major changes are released with a "minor" version bump. Currently we use patch release versions to indicate small feature changes.
 A set of Docker containers will be pushed automatically to DockerHub with every tag.
 You can see the containers [here](https://hub.docker.com/search?q=danswer%2F).
-
-As pre-1.0 software, even patch releases may contain breaking or non-backwards-compatible changes.

CONTRIBUTING_MACOS.md

@@ -0,0 +1,31 @@
+## Some additional notes for Mac Users
+The base instructions to set up the development environment are located in [CONTRIBUTING.md](https://github.com/danswer-ai/danswer/blob/main/CONTRIBUTING.md).
+
+### 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
+```

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 Danswer Software are licensed under the original license provided by the owner of the applicable component.
+* Content outside of the above mentioned directories or restrictions above is available under the "MIT Expat" license as defined below.
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

README.md

@@ -1,15 +1,18 @@
+<!-- DANSWER_METADATA={"link": "https://github.com/danswer-ai/danswer/blob/main/README.md"} -->
+<a name="readme-top"></a>
+
 <h2 align="center">
 <a href="https://www.danswer.ai/"> <img width="50%" src="https://github.com/danswer-owners/danswer/blob/1fabd9372d66cd54238847197c33f091a724803b/DanswerWithName.png?raw=true)" /></a>
 </h2>
 
 <p align="center">
-<p align="center">OpenSource Enterprise Question-Answering</p>
+<p align="center">Open Source Gen-AI Chat + Unified Search.</p>
 
 <p align="center">
 <a href="https://docs.danswer.dev/" target="_blank">
     <img src="https://img.shields.io/badge/docs-view-blue" alt="Documentation">
 </a>
-<a href="https://join.slack.com/t/danswer/shared_invite/zt-1u5ycen3o-6SJbWfivLWP5LPyp_jftuw" target="_blank">
+<a href="https://join.slack.com/t/danswer/shared_invite/zt-2twesxdr6-5iQitKZQpgq~hYIZ~dv3KA" target="_blank">
     <img src="https://img.shields.io/badge/slack-join-blue.svg?logo=slack" alt="Slack">
 </a>
 <a href="https://discord.gg/TDJ59cGV2X" target="_blank">
@@ -20,62 +23,124 @@
 </a>
 </p>
 
-<strong>[Danswer](https://www.danswer.ai/)</strong> allows you to ask natural language questions against internal documents and get back reliable answers backed by quotes and references from the source material so that you can always trust what you get back. You can connect to a number of common tools such as Slack, GitHub, Confluence, amongst others.
+<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 provides a fully-featured web UI:
+Danswer Web App:
+
+https://github.com/danswer-ai/danswer/assets/32520769/563be14c-9304-47b5-bf0a-9049c2b6f410
 
 
-https://github.com/danswer-ai/danswer/assets/25087905/619607a1-4ad2-41a0-9728-351752acc26e
-
-
-Or, if you prefer, you can plug Danswer into your existing Slack workflows (more integrations to come 😁):
-
+Or, plug Danswer into your existing Slack workflows (more integrations to come 😁):
 
 https://github.com/danswer-ai/danswer/assets/25087905/3e19739b-d178-4371-9a38-011430bdec1b
 
 
-For more details on the admin controls, check out our <strong><a href="https://www.youtube.com/watch?v=geNzY1nbCnU">Full Video Demo</a></strong>!
+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>!
 
-<h3>Deployment</h3>
+## Deployment
 
-Danswer can easily be tested locally or deployed on a virtual machine with a single `docker compose` command. Checkout our [docs](https://docs.danswer.dev/quickstart) to learn more.
+Danswer can easily be run locally (even on a laptop) or deployed on a virtual machine with a single
+`docker compose` command. Checkout our [docs](https://docs.danswer.dev/quickstart) to learn more.
 
 We also have built-in support for deployment on Kubernetes. Files for that can be found [here](https://github.com/danswer-ai/danswer/tree/main/deployment/kubernetes).
 
-## 💃 Features 
-* Direct QA powered by Generative AI models with answers backed by quotes and source links.
-* Intelligent Document Retrieval (Semantic Search/Reranking) using the latest LLMs.
-* An AI Helper backed by a custom Deep Learning model to interpret user intent.
-* User authentication and document level access management.
-* Support for an LLM of your choice (GPT-4, Llama2, Orca, etc.)
-* Management Dashboard to manage connectors and set up features such as live update fetching.
-* One line Docker Compose (or Kubernetes) deployment to host Danswer anywhere.
 
-## 🔌 Connectors 
+## 💃 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.
 
-Danswer currently syncs documents (every 10 minutes) from:
+
+## 🚧 Roadmap
+* Chat/Prompt sharing with specific teammates and user groups.
+* Multimodal model support, chat with images, video etc.
+* Choosing between LLMs and parameters during chat session.
+* Tool calling and agent configurations options.
+* Organizational understanding and ability to locate and suggest experts from your team.
+
+
+## Other Notable Benefits of Danswer
+* User Authentication with document level access management.
+* Best in class Hybrid Search across all sources (BM-25 + prefix aware embedding models).
+* Admin Dashboard to configure connectors, document-sets, access, etc.
+* Custom deep learning models + learn from user feedback.
+* Easy deployment and ability to host Danswer anywhere of your choosing.
+
+
+## 🔌 Connectors
+Efficiently pulls the latest changes from:
   * Slack
   * GitHub
   * Google Drive
   * Confluence
   * Jira
+  * Zendesk
+  * Gmail
   * Notion
+  * Gong
   * Slab
   * Linear
   * Productboard
   * Guru
-  * Zulip
   * Bookstack
+  * Document360
+  * Sharepoint
+  * Hubspot
   * Local Files
   * Websites
-  * With more to come...
+  * And more ...
 
-## 🚧 Roadmap
-* Chat/Conversation support.
-* Organizational understanding.
-* Ability to locate and suggest experts.
+## 📚 Editions
+
+There are two editions of Danswer:
+
+  * Danswer Community Edition (CE) is available freely under the MIT Expat license. This version has ALL the core features discussed above. This is the version of Danswer you will get if you follow the Deployment guide above.
+  * Danswer Enterprise Edition (EE) includes extra features that are primarily useful for larger organizations. Specifically, this includes:
+    * Single Sign-On (SSO), with support for both SAML and OIDC
+    * Role-based access control
+    * Document permission inheritance from connected sources
+    * Usage analytics and query history accessible to admins
+    * Whitelabeling
+    * API key authentication
+    * Encryption of secrets
+    * Any many more! Checkout [our website](https://www.danswer.ai/) for the latest.
+
+To try the Danswer Enterprise Edition: 
+
+  1. Checkout our [Cloud product](https://app.danswer.ai/signup).
+  2. For self-hosting, contact us at [founders@danswer.ai](mailto:founders@danswer.ai) or book a call with us on our [Cal](https://cal.com/team/danswer/founders).
 
 ## 💡 Contributing
 Looking to contribute? Please check out the [Contribution Guide](CONTRIBUTING.md) for more details.
+
+## ⭐Star History
+
+[![Star History Chart](https://api.star-history.com/svg?repos=danswer-ai/danswer&type=Date)](https://star-history.com/#danswer-ai/danswer&Date)
+
+## ✨Contributors
+
+<a href="https://github.com/danswer-ai/danswer/graphs/contributors">
+  <img alt="contributors" src="https://contrib.rocks/image?repo=danswer-ai/danswer"/>
+</a>
+
+<p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
+    <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
+        ↑ Back to Top ↑
+    </a>
+</p>

backend/.dockerignore

@@ -0,0 +1,17 @@
+**/__pycache__
+venv/
+env/
+*.egg-info
+.cache
+.git/
+.svn/
+.vscode/
+.idea/
+*.log
+log/
+.env
+secrets.yaml
+build/
+dist/
+.coverage
+htmlcov/

backend/.gitignore

@@ -1,11 +1,11 @@
 __pycache__/
+.mypy_cache
 .idea/
 site_crawls/
 .ipynb_checkpoints/
 api_keys.py
 *ipynb
-qdrant-data/
-typesense-data/
-.env
+.env*
 vespa-app.zip
 dynamic_config_storage/
+celerybeat-schedule*

backend/.trivyignore

@@ -0,0 +1,46 @@
+# https://github.com/madler/zlib/issues/868
+# Pulled in with base Debian image, it's part of the contrib folder but unused
+# zlib1g is fine
+# Will be gone with Debian image upgrade
+# No impact in our settings
+CVE-2023-45853
+
+# krb5 related, worst case is denial of service by resource exhaustion
+# Accept the risk
+CVE-2024-26458
+CVE-2024-26461
+CVE-2024-26462
+CVE-2024-26458
+CVE-2024-26461
+CVE-2024-26462
+CVE-2024-26458
+CVE-2024-26461
+CVE-2024-26462
+CVE-2024-26458
+CVE-2024-26461
+CVE-2024-26462
+
+# Specific to Firefox which we do not use
+# No impact in our settings
+CVE-2024-0743
+
+# bind9 related, worst case is denial of service by CPU resource exhaustion
+# Accept the risk
+CVE-2023-50387
+CVE-2023-50868
+CVE-2023-50387
+CVE-2023-50868
+
+# libexpat1, XML parsing resource exhaustion
+# We don't parse any user provided XMLs
+# No impact in our settings
+CVE-2023-52425
+CVE-2024-28757
+
+# sqlite, only used by NLTK library to grab word lemmatizer and stopwords
+# No impact in our settings
+CVE-2023-7104
+
+# libharfbuzz0b, O(n^2) growth, worst case is denial of service
+# Accept the risk
+CVE-2023-25193

backend/Dockerfile

@@ -1,61 +1,112 @@
-FROM python:3.11.4-slim-bookworm
+FROM python:3.11.7-slim-bookworm
 
-RUN apt-get update \
-    && apt-get install -y git cmake pkg-config libprotobuf-c-dev protobuf-compiler \
-       libprotobuf-dev libgoogle-perftools-dev libpq-dev build-essential cron curl \
-       supervisor zip \
-    && rm -rf /var/lib/apt/lists/*
+LABEL com.danswer.maintainer="founders@danswer.ai"
+LABEL com.danswer.description="This image is the web/frontend container of Danswer which \
+contains code for both the Community and Enterprise editions of Danswer. If you do not \
+have a contract or agreement with DanswerAI, you are not permitted to use the Enterprise \
+Edition features outside of personal development or testing purposes. Please reach out to \
+founders@danswer.ai for more information. Please visit https://github.com/danswer-ai/danswer"
 
-COPY ./requirements/default.txt /tmp/requirements.txt
-RUN pip install --no-cache-dir --upgrade -r /tmp/requirements.txt
+# Default DANSWER_VERSION, typically overriden during builds by GitHub Actions.
+ARG DANSWER_VERSION=0.8-dev
+ENV DANSWER_VERSION=${DANSWER_VERSION} \
+    DANSWER_RUNNING_IN_DOCKER="true"
 
+
+RUN echo "DANSWER_VERSION: ${DANSWER_VERSION}"
+# Install system dependencies
+# cmake needed for psycopg (postgres)
+# libpq-dev needed for psycopg (postgres)
+# curl included just for users' convenience
+# 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+deb12u3 \
+        libblkid1=2.38.1-5+deb12u1 \
+        libmount1=2.38.1-5+deb12u1 \
+        libsmartcols1=2.38.1-5+deb12u1 \
+        libuuid1=2.38.1-5+deb12u1 \
+        libxmlsec1-dev \
+        pkg-config \
+        gcc && \
+    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
-RUN pip uninstall -y py
-
-RUN playwright install chromium
-RUN playwright install-deps chromium
-
-# install nodejs and replace nodejs packaged with playwright (18.17.0) with the one installed below 
-# based on the instructions found here:
-# https://nodejs.org/en/download/package-manager#debian-and-ubuntu-based-linux-distributions
-# this is temporarily needed until playwright updates their packaged node version to
-# 20.5.1+
-RUN apt-get update
-RUN apt-get install -y ca-certificates curl gnupg
-RUN mkdir -p /etc/apt/keyrings
-RUN curl -fsSL https://deb.nodesource.com/gpgkey/nodesource-repo.gpg.key | gpg --dearmor -o /etc/apt/keyrings/nodesource.gpg
-RUN echo "deb [signed-by=/etc/apt/keyrings/nodesource.gpg] https://deb.nodesource.com/node_20.x nodistro main" | tee /etc/apt/sources.list.d/nodesource.list
-RUN apt-get update
-RUN apt-get install nodejs -y
-# replace nodejs packaged with playwright (18.17.0) with the one installed above
-RUN cp /usr/bin/node /usr/local/lib/python3.11/site-packages/playwright/driver/node
-# remove nodejs (except for the binary we moved into playwright)
-RUN apt-get remove -y nodejs
+COPY ./requirements/default.txt /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 && \
+    ln -s /usr/local/bin/supervisord /usr/bin/supervisord
 
 # Cleanup for CVEs and size reduction
-RUN apt-get remove -y linux-libc-dev \
-    && apt-get autoremove -y \
-    && rm -rf /var/lib/apt/lists/*
-
-# Remove tornado test key to placate vulnerability scanners
-# More details can be found here:
 # https://github.com/tornadoweb/tornado/issues/3107
-RUN rm /usr/local/lib/python3.11/site-packages/tornado/test/test.key
+# 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 could only be removed with --allow-remove-essential
+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 -f /usr/local/lib/python3.11/site-packages/tornado/test/test.key
 
+
+# Pre-downloading models for setups with limited egress
+RUN python -c "from tokenizers import Tokenizer; \
+Tokenizer.from_pretrained('nomic-ai/nomic-embed-text-v1')"
+
+# Pre-downloading NLTK for setups with limited egress
+RUN python -c "import nltk; \
+nltk.download('stopwords', quiet=True); \
+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
-COPY ./alembic /app/alembic
-COPY ./alembic.ini /app/alembic.ini
+
+# Enterprise Version Files
+COPY ./ee /app/ee
 COPY supervisord.conf /etc/supervisor/conf.d/supervisord.conf
 
-WORKDIR /app/danswer/datastores/vespa/app_config
-RUN zip -r /app/danswer/vespa-app.zip .
-WORKDIR /app
+# Set up application files
+COPY ./danswer /app/danswer
+COPY ./shared_configs /app/shared_configs
+COPY ./alembic /app/alembic
+COPY ./alembic_tenants /app/alembic_tenants
+COPY ./alembic.ini /app/alembic.ini
+COPY supervisord.conf /usr/etc/supervisord.conf
 
-# TODO: remove this once all users have migrated
-COPY ./scripts/migrate_vespa_to_acl.py /app/migrate_vespa_to_acl.py
+# Escape hatch
+COPY ./scripts/force_delete_connector_by_id.py /app/scripts/force_delete_connector_by_id.py
 
-ENV PYTHONPATH /app
+# Put logo in assets
+COPY ./assets /app/assets
 
-# By default this container does nothing, it is used by api server and background which specify their own CMD
+ENV PYTHONPATH=/app
+
+# Default command which does nothing
+# This container is used by api server and background which specify their own CMD
 CMD ["tail", "-f", "/dev/null"]

backend/Dockerfile.model_server

@@ -0,0 +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."
+
+# Default DANSWER_VERSION, typically overriden during builds by GitHub Actions.
+ARG DANSWER_VERSION=0.8-dev
+ENV DANSWER_VERSION=${DANSWER_VERSION} \
+    DANSWER_RUNNING_IN_DOCKER="true"
+
+
+RUN echo "DANSWER_VERSION: ${DANSWER_VERSION}"
+
+COPY ./requirements/model_server.txt /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 && \
+    apt-get autoremove -y
+
+# Pre-downloading models for setups with limited egress
+# Download tokenizers, distilbert for the Danswer model
+# Download model weights
+# Run Nomic to pull in the custom architecture and have it cached locally
+RUN python -c "from transformers import AutoTokenizer; \
+AutoTokenizer.from_pretrained('distilbert-base-uncased'); \
+AutoTokenizer.from_pretrained('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 Danswer, don't overwrite it with the built in cache folder
+RUN mv /root/.cache/huggingface /root/.cache/temp_huggingface
+
+WORKDIR /app
+
+# Utils used by model server
+COPY ./danswer/utils/logger.py /app/danswer/utils/logger.py
+
+# Place to fetch version information
+COPY ./danswer/__init__.py /app/danswer/__init__.py
+
+# Shared between Danswer Backend and Model Server
+COPY ./shared_configs /app/shared_configs
+
+# Model Server main code
+COPY ./model_server /app/model_server
+
+ENV PYTHONPATH=/app
+
+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

@@ -1,4 +1,8 @@
-Generic single-database configuration with an async dbapi.
+<!-- DANSWER_METADATA={"link": "https://github.com/danswer-ai/danswer/blob/main/backend/alembic/README.md"} -->
+
+# Alembic DB Migrations
+These files are for creating/updating the tables in the Relational DB (Postgres).
+Danswer migrations use a generic single-database configuration with an async dbapi.
 
 ## To generate new migrations: 
 run from danswer/backend:
@@ -7,7 +11,6 @@ run from danswer/backend:
 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`
 

backend/alembic/env.py

@@ -1,85 +1,215 @@
+from sqlalchemy.engine.base import Connection
+from typing import Literal
 import asyncio
 from logging.config import fileConfig
+import logging
 
 from alembic import context
+from sqlalchemy import pool
+from sqlalchemy.ext.asyncio import create_async_engine
+from sqlalchemy.sql import text
+from sqlalchemy.sql.schema import SchemaItem
+
+from shared_configs.configs import MULTI_TENANT
 from danswer.db.engine import build_connection_string
 from danswer.db.models import Base
-from sqlalchemy import pool
-from sqlalchemy.engine import Connection
-from sqlalchemy.ext.asyncio import create_async_engine
+from celery.backends.database.session import ResultModelBase  # type: ignore
+from danswer.db.engine import get_all_tenant_ids
+from shared_configs.configs import POSTGRES_DEFAULT_SCHEMA
 
-# 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
+# Add your model's MetaData object here for 'autogenerate' support
+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"}
+
+# Set up logging
+logger = logging.getLogger(__name__)
 
 
-def run_migrations_offline() -> None:
-    """Run migrations in 'offline' mode.
-
-    This configures the context with just a URL
-    and not an Engine, though an Engine is acceptable
-    here as well.  By skipping the Engine creation
-    we don't even need a DBAPI to be available.
-
-    Calls to context.execute() here emit the given string to the
-    script output.
-
+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:
     """
-    url = build_connection_string()
+    Determines whether a database object should be included in migrations.
+    Excludes specified tables from migrations.
+    """
+    if type_ == "table" and name in EXCLUDE_TABLES:
+        return False
+    return True
+
+
+def get_schema_options() -> tuple[str, bool, bool]:
+    """
+    Parses command-line options passed via '-x' in Alembic commands.
+    Recognizes 'schema', 'create_schema', and 'upgrade_all_tenants' options.
+    """
+    x_args_raw = context.get_x_argument()
+    x_args = {}
+    for arg in x_args_raw:
+        for pair in arg.split(","):
+            if "=" in pair:
+                key, value = pair.split("=", 1)
+                x_args[key.strip()] = value.strip()
+    schema_name = x_args.get("schema", POSTGRES_DEFAULT_SCHEMA)
+    create_schema = x_args.get("create_schema", "true").lower() == "true"
+    upgrade_all_tenants = x_args.get("upgrade_all_tenants", "false").lower() == "true"
+
+    if (
+        MULTI_TENANT
+        and schema_name == POSTGRES_DEFAULT_SCHEMA
+        and not upgrade_all_tenants
+    ):
+        raise ValueError(
+            "Cannot run default migrations in public schema when multi-tenancy is enabled. "
+            "Please specify a tenant-specific schema."
+        )
+
+    return schema_name, create_schema, upgrade_all_tenants
+
+
+def do_run_migrations(
+    connection: Connection, schema_name: str, create_schema: bool
+) -> None:
+    """
+    Executes migrations in the specified schema.
+    """
+    logger.info(f"About to migrate schema: {schema_name}")
+
+    if create_schema:
+        connection.execute(text(f'CREATE SCHEMA IF NOT EXISTS "{schema_name}"'))
+        connection.execute(text("COMMIT"))
+
+    # Set search_path to the target schema
+    connection.execute(text(f'SET search_path TO "{schema_name}"'))
+
     context.configure(
-        url=url,
-        target_metadata=target_metadata,
-        literal_binds=True,
-        dialect_opts={"paramstyle": "named"},
+        connection=connection,
+        target_metadata=target_metadata,  # type: ignore
+        include_object=include_object,
+        version_table_schema=schema_name,
+        include_schemas=True,
+        compare_type=True,
+        compare_server_default=True,
+        script_location=config.get_main_option("script_location"),
     )
 
     with context.begin_transaction():
         context.run_migrations()
 
 
-def do_run_migrations(connection: Connection) -> None:
-    context.configure(connection=connection, target_metadata=target_metadata)
-
-    with context.begin_transaction():
-        context.run_migrations()
-
-
 async def run_async_migrations() -> None:
-    """In this scenario we need to create an Engine
-    and associate a connection with the context.
-
     """
+    Determines whether to run migrations for a single schema or all schemas,
+    and executes migrations accordingly.
+    """
+    schema_name, create_schema, upgrade_all_tenants = get_schema_options()
 
-    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 upgrade_all_tenants:
+        # Run migrations for all tenant schemas sequentially
+        tenant_schemas = get_all_tenant_ids()
 
-    await connectable.dispose()
+        for schema in tenant_schemas:
+            try:
+                logger.info(f"Migrating schema: {schema}")
+                async with engine.connect() as connection:
+                    await connection.run_sync(
+                        do_run_migrations,
+                        schema_name=schema,
+                        create_schema=create_schema,
+                    )
+            except Exception as e:
+                logger.error(f"Error migrating schema {schema}: {e}")
+                raise
+    else:
+        try:
+            logger.info(f"Migrating schema: {schema_name}")
+            async with engine.connect() as connection:
+                await connection.run_sync(
+                    do_run_migrations,
+                    schema_name=schema_name,
+                    create_schema=create_schema,
+                )
+        except Exception as e:
+            logger.error(f"Error migrating schema {schema_name}: {e}")
+            raise
+
+    await engine.dispose()
+
+
+def run_migrations_offline() -> None:
+    """
+    Run migrations in 'offline' mode.
+    """
+    schema_name, _, upgrade_all_tenants = get_schema_options()
+    url = build_connection_string()
+
+    if upgrade_all_tenants:
+        # Run offline migrations for all tenant schemas
+        engine = create_async_engine(url)
+        tenant_schemas = get_all_tenant_ids()
+        engine.sync_engine.dispose()
+
+        for schema in tenant_schemas:
+            logger.info(f"Migrating schema: {schema}")
+            context.configure(
+                url=url,
+                target_metadata=target_metadata,  # type: ignore
+                literal_binds=True,
+                include_object=include_object,
+                version_table_schema=schema,
+                include_schemas=True,
+                script_location=config.get_main_option("script_location"),
+                dialect_opts={"paramstyle": "named"},
+            )
+
+            with context.begin_transaction():
+                context.run_migrations()
+    else:
+        logger.info(f"Migrating schema: {schema_name}")
+        context.configure(
+            url=url,
+            target_metadata=target_metadata,  # type: ignore
+            literal_binds=True,
+            include_object=include_object,
+            version_table_schema=schema_name,
+            include_schemas=True,
+            script_location=config.get_main_option("script_location"),
+            dialect_opts={"paramstyle": "named"},
+        )
+
+        with context.begin_transaction():
+            context.run_migrations()
 
 
 def run_migrations_online() -> None:
-    """Run migrations in 'online' mode."""
-
+    """
+    Runs migrations in 'online' mode using an asynchronous engine.
+    """
     asyncio.run(run_async_migrations())
 
 

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

@@ -0,0 +1,31 @@
+"""Add starter prompts
+
+Revision ID: 0a2b51deb0b8
+Revises: 5f4b8568a221
+Create Date: 2024-03-02 23:23:49.960309
+
+"""
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision = "0a2b51deb0b8"
+down_revision = "5f4b8568a221"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "persona",
+        sa.Column(
+            "starter_messages",
+            postgresql.JSONB(astext_type=sa.Text()),
+            nullable=True,
+        ),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("persona", "starter_messages")

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 danswer.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/15326fcec57e_introduce_danswer_apis.py

@@ -0,0 +1,37 @@
+"""Introduce Danswer APIs
+
+Revision ID: 15326fcec57e
+Revises: 77d07dffae64
+Create Date: 2023-11-11 20:51:24.228999
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+from danswer.configs.constants import DocumentSource
+
+# revision identifiers, used by Alembic.
+revision = "15326fcec57e"
+down_revision = "77d07dffae64"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.alter_column("credential", "is_admin", new_column_name="admin_public")
+    op.add_column(
+        "document",
+        sa.Column("from_ingestion_api", sa.Boolean(), nullable=True),
+    )
+    op.alter_column(
+        "connector",
+        "source",
+        type_=sa.String(length=50),
+        existing_type=sa.Enum(DocumentSource, native_enum=False),
+        existing_nullable=False,
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("document", "from_ingestion_api")
+    op.alter_column("credential", "admin_public", new_column_name="is_admin")

backend/alembic/versions/173cae5bba26_port_config_store.py

@@ -0,0 +1,29 @@
+"""Port Config Store
+
+Revision ID: 173cae5bba26
+Revises: e50154680a5c
+Create Date: 2024-03-19 15:30:44.425436
+
+"""
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision = "173cae5bba26"
+down_revision = "e50154680a5c"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "key_value_store",
+        sa.Column("key", sa.String(), nullable=False),
+        sa.Column("value", postgresql.JSONB(astext_type=sa.Text()), nullable=False),
+        sa.PrimaryKeyConstraint("key"),
+    )
+
+
+def downgrade() -> None:
+    op.drop_table("key_value_store")

backend/alembic/versions/177de57c21c9_display_custom_llm_models.py

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

backend/alembic/versions/1b10e1fda030_add_additional_data_to_notifications.py

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

backend/alembic/versions/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 danswer.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/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/30c1d5744104_persona_datetime_aware.py

@@ -0,0 +1,37 @@
+"""Persona Datetime Aware
+
+Revision ID: 30c1d5744104
+Revises: 7f99be1cb9f5
+Create Date: 2023-10-16 23:21:01.283424
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "30c1d5744104"
+down_revision = "7f99be1cb9f5"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.add_column("persona", sa.Column("datetime_aware", sa.Boolean(), nullable=True))
+    op.execute("UPDATE persona SET datetime_aware = TRUE")
+    op.alter_column("persona", "datetime_aware", nullable=False)
+    op.create_index(
+        "_default_persona_name_idx",
+        "persona",
+        ["name"],
+        unique=True,
+        postgresql_where=sa.text("default_persona = true"),
+    )
+
+
+def downgrade() -> None:
+    op.drop_index(
+        "_default_persona_name_idx",
+        table_name="persona",
+        postgresql_where=sa.text("default_persona = true"),
+    )
+    op.drop_column("persona", "datetime_aware")

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/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/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/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

@@ -0,0 +1,41 @@
+"""Add chat session sharing
+
+Revision ID: 38eda64af7fe
+Revises: 776b3bbe9092
+Create Date: 2024-03-27 19:41:29.073594
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "38eda64af7fe"
+down_revision = "776b3bbe9092"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "chat_session",
+        sa.Column(
+            "shared_status",
+            sa.Enum(
+                "PUBLIC",
+                "PRIVATE",
+                name="chatsessionsharedstatus",
+                native_enum=False,
+            ),
+            nullable=True,
+        ),
+    )
+    op.execute("UPDATE chat_session SET shared_status='PRIVATE'")
+    op.alter_column(
+        "chat_session",
+        "shared_status",
+        nullable=False,
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("chat_session", "shared_status")

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

@@ -0,0 +1,49 @@
+"""Move is_public to cc_pair
+
+Revision ID: 3b25685ff73c
+Revises: e0a68a81d434
+Create Date: 2023-10-05 18:47:09.582849
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "3b25685ff73c"
+down_revision = "e0a68a81d434"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "connector_credential_pair",
+        sa.Column("is_public", sa.Boolean(), nullable=True),
+    )
+    # fill in is_public for existing rows
+    op.execute(
+        "UPDATE connector_credential_pair SET is_public = true WHERE is_public IS NULL"
+    )
+    op.alter_column("connector_credential_pair", "is_public", nullable=False)
+
+    op.add_column(
+        "credential",
+        sa.Column("is_admin", sa.Boolean(), nullable=True),
+    )
+    op.execute("UPDATE credential SET is_admin = true WHERE is_admin IS NULL")
+    op.alter_column("credential", "is_admin", nullable=False)
+
+    op.drop_column("credential", "public_doc")
+
+
+def downgrade() -> None:
+    op.add_column(
+        "credential",
+        sa.Column("public_doc", sa.Boolean(), nullable=True),
+    )
+    # setting public_doc to false for all existing rows to be safe
+    # NOTE: this is likely not the correct state of the world but it's the best we can do
+    op.execute("UPDATE credential SET public_doc = false WHERE public_doc IS NULL")
+    op.alter_column("credential", "public_doc", nullable=False)
+    op.drop_column("connector_credential_pair", "is_public")
+    op.drop_column("credential", "is_admin")

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:
@@ -35,6 +35,7 @@ def upgrade() -> None:
                 "SUCCESS",
                 "FAILED",
                 name="indexingstatus",
+                native_enum=False,
             ),
             nullable=False,
         ),

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

@@ -0,0 +1,31 @@
+"""Remove Native Enum
+
+Revision ID: 46625e4745d4
+Revises: 9d97fecfab7f
+Create Date: 2023-10-27 11:38:33.803145
+
+"""
+from alembic import op
+from sqlalchemy import String
+
+# revision identifiers, used by Alembic.
+revision = "46625e4745d4"
+down_revision = "9d97fecfab7f"
+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
+    # 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.
+    op.alter_column("index_attempt", "status", type_=String)
+    op.alter_column("connector_credential_pair", "last_attempt_status", type_=String)
+    op.execute("DROP TYPE IF EXISTS indexingstatus")
+
+
+def downgrade() -> None:
+    # We don't want Native Enums, do nothing
+    pass

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

@@ -0,0 +1,28 @@
+"""PG File Store
+
+Revision ID: 4738e4b3bae1
+Revises: e91df4e935ef
+Create Date: 2024-03-20 18:53:32.461518
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "4738e4b3bae1"
+down_revision = "e91df4e935ef"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "file_store",
+        sa.Column("file_name", sa.String(), nullable=False),
+        sa.Column("lobj_oid", sa.Integer(), nullable=False),
+        sa.PrimaryKeyConstraint("file_name"),
+    )
+
+
+def downgrade() -> None:
+    op.drop_table("file_store")

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:
@@ -59,6 +59,7 @@ def upgrade() -> None:
                 "SUCCESS",
                 "FAILED",
                 name="indexingstatus",
+                native_enum=False,
             ),
             nullable=False,
         ),
@@ -70,4 +71,3 @@ def upgrade() -> None:
 
 def downgrade() -> None:
     op.drop_table("index_attempt")
-    sa.Enum(name="indexingstatus").drop(op.get_bind(), checkfirst=False)

backend/alembic/versions/475fcefe8826_add_name_to_api_key.py

@@ -0,0 +1,23 @@
+"""Add name to api_key
+
+Revision ID: 475fcefe8826
+Revises: ecab2b3f1a3b
+Create Date: 2024-04-11 11:05:18.414438
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "475fcefe8826"
+down_revision = "ecab2b3f1a3b"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.add_column("api_key", sa.Column("name", sa.String(), nullable=True))
+
+
+def downgrade() -> None:
+    op.drop_column("api_key", "name")

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

backend/alembic/versions/50b683a8295c_add_additional_retrieval_controls_to_.py

@@ -0,0 +1,28 @@
+"""Add additional retrieval controls to Persona
+
+Revision ID: 50b683a8295c
+Revises: 7da0ae5ad583
+Create Date: 2023-11-27 17:23:29.668422
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "50b683a8295c"
+down_revision = "7da0ae5ad583"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.add_column("persona", sa.Column("num_chunks", sa.Integer(), nullable=True))
+    op.add_column(
+        "persona",
+        sa.Column("apply_llm_relevance_filter", sa.Boolean(), nullable=True),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("persona", "apply_llm_relevance_filter")
+    op.drop_column("persona", "num_chunks")

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/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_danswerbot_explicitly.py

@@ -0,0 +1,27 @@
+"""Track Danswerbot 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")

backend/alembic/versions/57b53544726e_add_document_set_tables.py

@@ -12,8 +12,8 @@ import sqlalchemy as sa
 # revision identifiers, used by Alembic.
 revision = "57b53544726e"
 down_revision = "800f48024ae9"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:

backend/alembic/versions/5809c0787398_add_chat_sessions.py

@@ -13,8 +13,8 @@ import sqlalchemy as sa
 # revision identifiers, used by Alembic.
 revision = "5809c0787398"
 down_revision = "d929f0c1c6af"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:

backend/alembic/versions/5b29123cd710_nullable_search_settings_for_historic_.py

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

backend/alembic/versions/5c7fdadae813_match_any_keywords_flag_for_standard_.py

@@ -0,0 +1,35 @@
+"""match_any_keywords flag for standard answers
+
+Revision ID: 5c7fdadae813
+Revises: efb35676026c
+Create Date: 2024-09-13 18:52:59.256478
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "5c7fdadae813"
+down_revision = "efb35676026c"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.add_column(
+        "standard_answer",
+        sa.Column(
+            "match_any_keywords",
+            sa.Boolean(),
+            nullable=False,
+            server_default=sa.false(),
+        ),
+    )
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_column("standard_answer", "match_any_keywords")
+    # ### end Alembic commands ###

backend/alembic/versions/5d12a446f5c0_add_api_version_and_deployment_name_to_.py

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

backend/alembic/versions/5e84129c8be3_add_docs_indexed_column_to_index_.py

@@ -12,8 +12,8 @@ import sqlalchemy as sa
 # revision identifiers, used by Alembic.
 revision = "5e84129c8be3"
 down_revision = "e6a4bbc13fe4"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:

backend/alembic/versions/5f4b8568a221_add_removed_documents_to_index_attempt.py

@@ -0,0 +1,27 @@
+"""add removed documents to index_attempt
+
+Revision ID: 5f4b8568a221
+Revises: dbaa756c2ccf
+Create Date: 2024-02-16 15:02:03.319907
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "5f4b8568a221"
+down_revision = "8987770549c0"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "index_attempt",
+        sa.Column("docs_removed_from_index", sa.Integer()),
+    )
+    op.execute("UPDATE index_attempt SET docs_removed_from_index = 0")
+
+
+def downgrade() -> None:
+    op.drop_column("index_attempt", "docs_removed_from_index")

backend/alembic/versions/5fc1f54cc252_hybrid_enum.py

@@ -0,0 +1,25 @@
+"""hybrid-enum
+
+Revision ID: 5fc1f54cc252
+Revises: 1d6ad76d1f37
+Create Date: 2024-08-06 15:35:40.278485
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "5fc1f54cc252"
+down_revision = "1d6ad76d1f37"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.drop_column("persona", "search_type")
+
+
+def downgrade() -> None:
+    op.add_column("persona", sa.Column("search_type", sa.String(), nullable=True))
+    op.execute("UPDATE persona SET search_type = 'SEMANTIC'")
+    op.alter_column("persona", "search_type", nullable=False)

backend/alembic/versions/61ff3651add4_add_permission_syncing.py

@@ -0,0 +1,162 @@
+"""Add Permission Syncing
+
+Revision ID: 61ff3651add4
+Revises: 1b8206b29c5d
+Create Date: 2024-09-05 13:57:11.770413
+
+"""
+import fastapi_users_db_sqlalchemy
+
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision = "61ff3651add4"
+down_revision = "1b8206b29c5d"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # Admin user who set up connectors will lose access to the docs temporarily
+    # only way currently to give back access is to rerun from beginning
+    op.add_column(
+        "connector_credential_pair",
+        sa.Column(
+            "access_type",
+            sa.String(),
+            nullable=True,
+        ),
+    )
+    op.execute(
+        "UPDATE connector_credential_pair SET access_type = 'PUBLIC' WHERE is_public = true"
+    )
+    op.execute(
+        "UPDATE connector_credential_pair SET access_type = 'PRIVATE' WHERE is_public = false"
+    )
+    op.alter_column("connector_credential_pair", "access_type", nullable=False)
+
+    op.add_column(
+        "connector_credential_pair",
+        sa.Column(
+            "auto_sync_options",
+            postgresql.JSONB(astext_type=sa.Text()),
+            nullable=True,
+        ),
+    )
+    op.add_column(
+        "connector_credential_pair",
+        sa.Column("last_time_perm_sync", sa.DateTime(timezone=True), nullable=True),
+    )
+    op.drop_column("connector_credential_pair", "is_public")
+
+    op.add_column(
+        "document",
+        sa.Column("external_user_emails", postgresql.ARRAY(sa.String()), nullable=True),
+    )
+    op.add_column(
+        "document",
+        sa.Column(
+            "external_user_group_ids", postgresql.ARRAY(sa.String()), nullable=True
+        ),
+    )
+    op.add_column(
+        "document",
+        sa.Column("is_public", sa.Boolean(), nullable=True),
+    )
+
+    op.create_table(
+        "user__external_user_group_id",
+        sa.Column(
+            "user_id", fastapi_users_db_sqlalchemy.generics.GUID(), nullable=False
+        ),
+        sa.Column("external_user_group_id", sa.String(), nullable=False),
+        sa.Column("cc_pair_id", sa.Integer(), nullable=False),
+        sa.PrimaryKeyConstraint("user_id"),
+    )
+
+    op.drop_column("external_permission", "user_id")
+    op.drop_column("email_to_external_user_cache", "user_id")
+    op.drop_table("permission_sync_run")
+    op.drop_table("external_permission")
+    op.drop_table("email_to_external_user_cache")
+
+
+def downgrade() -> None:
+    op.add_column(
+        "connector_credential_pair",
+        sa.Column("is_public", sa.BOOLEAN(), nullable=True),
+    )
+    op.execute(
+        "UPDATE connector_credential_pair SET is_public = (access_type = 'PUBLIC')"
+    )
+    op.alter_column("connector_credential_pair", "is_public", nullable=False)
+
+    op.drop_column("connector_credential_pair", "auto_sync_options")
+    op.drop_column("connector_credential_pair", "access_type")
+    op.drop_column("connector_credential_pair", "last_time_perm_sync")
+    op.drop_column("document", "external_user_emails")
+    op.drop_column("document", "external_user_group_ids")
+    op.drop_column("document", "is_public")
+
+    op.drop_table("user__external_user_group_id")
+
+    # Drop the enum type at the end of the downgrade
+    op.create_table(
+        "permission_sync_run",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column(
+            "source_type",
+            sa.String(),
+            nullable=False,
+        ),
+        sa.Column("update_type", sa.String(), nullable=False),
+        sa.Column("cc_pair_id", sa.Integer(), nullable=True),
+        sa.Column(
+            "status",
+            sa.String(),
+            nullable=False,
+        ),
+        sa.Column("error_msg", sa.Text(), nullable=True),
+        sa.Column(
+            "updated_at",
+            sa.DateTime(timezone=True),
+            server_default=sa.text("now()"),
+            nullable=False,
+        ),
+        sa.ForeignKeyConstraint(
+            ["cc_pair_id"],
+            ["connector_credential_pair.id"],
+        ),
+        sa.PrimaryKeyConstraint("id"),
+    )
+    op.create_table(
+        "external_permission",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column("user_id", sa.UUID(), nullable=True),
+        sa.Column("user_email", sa.String(), nullable=False),
+        sa.Column(
+            "source_type",
+            sa.String(),
+            nullable=False,
+        ),
+        sa.Column("external_permission_group", sa.String(), nullable=False),
+        sa.ForeignKeyConstraint(
+            ["user_id"],
+            ["user.id"],
+        ),
+        sa.PrimaryKeyConstraint("id"),
+    )
+    op.create_table(
+        "email_to_external_user_cache",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column("external_user_id", sa.String(), nullable=False),
+        sa.Column("user_id", sa.UUID(), nullable=True),
+        sa.Column("user_email", sa.String(), nullable=False),
+        sa.ForeignKeyConstraint(
+            ["user_id"],
+            ["user.id"],
+        ),
+        sa.PrimaryKeyConstraint("id"),
+    )

backend/alembic/versions/643a84a42a33_add_user_configured_names_to_llmprovider.py

@@ -0,0 +1,45 @@
+"""Add user-configured names to LLMProvider
+
+Revision ID: 643a84a42a33
+Revises: 0a98909f2757
+Create Date: 2024-05-07 14:54:55.493100
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "643a84a42a33"
+down_revision = "0a98909f2757"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.add_column("llm_provider", sa.Column("provider", sa.String(), nullable=True))
+    # move "name" -> "provider" to match the new schema
+    op.execute("UPDATE llm_provider SET provider = name")
+    # pretty up display name
+    op.execute("UPDATE llm_provider SET name = 'OpenAI' WHERE name = 'openai'")
+    op.execute("UPDATE llm_provider SET name = 'Anthropic' WHERE name = 'anthropic'")
+    op.execute("UPDATE llm_provider SET name = 'Azure OpenAI' WHERE name = 'azure'")
+    op.execute("UPDATE llm_provider SET name = 'AWS Bedrock' WHERE name = 'bedrock'")
+
+    # update personas to use the new provider names
+    op.execute(
+        "UPDATE persona SET llm_model_provider_override = 'OpenAI' WHERE llm_model_provider_override = 'openai'"
+    )
+    op.execute(
+        "UPDATE persona SET llm_model_provider_override = 'Anthropic' WHERE llm_model_provider_override = 'anthropic'"
+    )
+    op.execute(
+        "UPDATE persona SET llm_model_provider_override = 'Azure OpenAI' WHERE llm_model_provider_override = 'azure'"
+    )
+    op.execute(
+        "UPDATE persona SET llm_model_provider_override = 'AWS Bedrock' WHERE llm_model_provider_override = 'bedrock'"
+    )
+
+
+def downgrade() -> None:
+    op.execute("UPDATE llm_provider SET name = provider")
+    op.drop_column("llm_provider", "provider")

backend/alembic/versions/6756efa39ada_id_uuid_for_chat_session.py

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

backend/alembic/versions/6d387b3196c2_basic_auth.py

@@ -13,8 +13,8 @@ from sqlalchemy.dialects import postgresql
 # revision identifiers, used by Alembic.
 revision = "6d387b3196c2"
 down_revision = "47433d30de82"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:

backend/alembic/versions/6d562f86c78b_remove_default_bot.py

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