Move web Dockerfile to single stage since multi-stage has been causing issues w/ github actions

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

@@ -1,109 +0,0 @@
-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-    description: 'Always attempt to pull a newer version of the image'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

@@ -1,29 +0,0 @@
-## 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

@@ -5,59 +5,40 @@ on:
     tags:
       - '*'
 
-env:
-  REGISTRY_IMAGE: danswer/danswer-backend
-  LATEST_TAG: ${{ contains(github.ref_name, 'latest') }}
-  
 jobs:
   build-and-push:
-    # TODO: investigate a matrix build like the web container 
-    # See https://runs-on.com/runners/linux/
-    runs-on: [runs-on,runner=8cpu-linux-x64,"run-id=${{ github.run_id }}"]
+    runs-on: ubuntu-latest
 
     steps:
     - name: Checkout code
-      uses: actions/checkout@v4
+      uses: actions/checkout@v2
 
     - name: Set up Docker Buildx
-      uses: docker/setup-buildx-action@v3
+      uses: docker/setup-buildx-action@v1
 
     - name: Login to Docker Hub
-      uses: docker/login-action@v3
+      uses: docker/login-action@v1
       with:
         username: ${{ secrets.DOCKER_USERNAME }}
         password: ${{ secrets.DOCKER_TOKEN }}
 
-    - name: Install build-essential
-      run: |
-        sudo apt-get update
-        sudo apt-get install -y build-essential
-          
     - name: Backend Image Docker Build and Push
-      uses: docker/build-push-action@v5
+      uses: docker/build-push-action@v2
       with:
         context: ./backend
         file: ./backend/Dockerfile
         platforms: linux/amd64,linux/arm64
         push: true
         tags: |
-          ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
-          ${{ env.LATEST_TAG == 'true' && format('{0}:latest', env.REGISTRY_IMAGE) || '' }}
+          danswer/danswer-backend:${{ github.ref_name }}
+          danswer/danswer-backend:latest
         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 }}
+        image-ref: docker.io/danswer/danswer-backend:${{ github.ref_name }}
         severity: 'CRITICAL,HIGH'
         trivyignores: ./backend/.trivyignore

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

@@ -1,136 +0,0 @@
-name: Build and Push Cloud Web Image on Tag
-# Identical to the web container build, but with correct image tag and build args
-
-on:
-  push:
-    tags:
-      - '*'
-
-env:
-  REGISTRY_IMAGE: danswer/danswer-cloud-web-server
-  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 }}
-          # 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

@@ -5,51 +5,38 @@ on:
     tags:
       - '*'
 
-env:
-  REGISTRY_IMAGE: 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 }}"]
+    runs-on: ubuntu-latest
 
     steps:
     - name: Checkout code
-      uses: actions/checkout@v4
+      uses: actions/checkout@v2
 
     - name: Set up Docker Buildx
-      uses: docker/setup-buildx-action@v3
+      uses: docker/setup-buildx-action@v1
 
     - name: Login to Docker Hub
-      uses: docker/login-action@v3
+      uses: docker/login-action@v1
       with:
         username: ${{ secrets.DOCKER_USERNAME }}
         password: ${{ secrets.DOCKER_TOKEN }}
 
     - name: Model Server Image Docker Build and Push
-      uses: docker/build-push-action@v5
+      uses: docker/build-push-action@v2
       with:
         context: ./backend
         file: ./backend/Dockerfile.model_server
         platforms: linux/amd64,linux/arm64
         push: true
         tags: |
-          ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
-          ${{ env.LATEST_TAG == 'true' && format('{0}:latest', env.REGISTRY_IMAGE) || '' }}
+          danswer/danswer-model-server:${{ github.ref_name }}
+          danswer/danswer-model-server:latest
         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

@@ -5,127 +5,38 @@ on:
     tags:
       - '*'
 
-env:
-  REGISTRY_IMAGE: danswer/danswer-web-server
-  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 }}
-          # 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:
+  build-and-push:
     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'
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v2
+
+    - name: Set up Docker Buildx
+      uses: docker/setup-buildx-action@v1
+
+    - name: Login to Docker Hub
+      uses: docker/login-action@v1
+      with:
+        username: ${{ secrets.DOCKER_USERNAME }}
+        password: ${{ secrets.DOCKER_TOKEN }}
+
+    - name: Web Image Docker Build and Push
+      uses: docker/build-push-action@v2
+      with:
+        context: ./web
+        file: ./web/Dockerfile
+        platforms: linux/amd64,linux/arm64
+        push: true
+        tags: |
+          danswer/danswer-web-server:${{ github.ref_name }}
+          danswer/danswer-web-server:latest
+        build-args: |
+          DANSWER_VERSION=${{ github.ref_name }}
+
+    - name: Run Trivy vulnerability scanner
+      uses: aquasecurity/trivy-action@master
+      with:
+        image-ref: docker.io/danswer/danswer-web-server:${{ github.ref_name }}
+        severity: 'CRITICAL,HIGH'

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

@@ -1,6 +1,3 @@
-# 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:
@@ -12,9 +9,7 @@ on:
 
 jobs:
   tag:
-    # See https://runs-on.com/runners/linux/
-    # use a lower powered instance since this just does i/o to docker hub
-    runs-on: [runs-on,runner=2cpu-linux-x64,"run-id=${{ github.run_id }}"]
+    runs-on: ubuntu-latest
     steps:
     - name: Set up Docker Buildx
       uses: docker/setup-buildx-action@v1

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

@@ -1,172 +0,0 @@
-# This workflow is intended to be manually triggered via the GitHub Action tab.
-# Given a hotfix branch, it will attempt to open a PR to all release branches and
-# by default auto merge them
-
-name: Hotfix release branches
-
-on:
-  workflow_dispatch:
-    inputs:
-      hotfix_commit:
-        description: 'Hotfix commit hash'
-        required: true
-      hotfix_suffix:
-        description: 'Hotfix branch suffix (e.g. hotfix/v0.8-{suffix})'
-        required: true
-      release_branch_pattern:
-        description: 'Release branch pattern (regex)'
-        required: true
-        default: 'release/.*'
-      auto_merge:
-        description: 'Automatically merge the hotfix PRs'
-        required: true
-        type: choice
-        default: 'true'
-        options:
-          - true
-          - false
-          
-jobs:
-  hotfix_release_branches:
-    permissions: write-all
-    # See https://runs-on.com/runners/linux/
-    # use a lower powered instance since this just does i/o to docker hub
-    runs-on: [runs-on,runner=2cpu-linux-x64,"run-id=${{ github.run_id }}"]
-    steps:
-    
-      # needs RKUO_DEPLOY_KEY for write access to merge PR's
-      - name: Checkout Repository
-        uses: actions/checkout@v4
-        with:
-          ssh-key: "${{ secrets.RKUO_DEPLOY_KEY }}"
-          fetch-depth: 0
-          
-      - name: Set up Git user
-        run: |
-          git config user.name "Richard Kuo [bot]"
-          git config user.email "rkuo[bot]@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

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

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

@@ -1,235 +0,0 @@
-name: Run Integration Tests v2
-concurrency:
-  group: Run-Integration-Tests-${{ github.workflow }}-${{ github.head_ref || github.event.workflow_run.head_branch || github.run_id }}
-  cancel-in-progress: true
-
-on:
-  merge_group:
-  pull_request:
-    branches:
-      - main
-      - 'release/**'
-
-env:
-  OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-  SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
-
-jobs:
-  integration-tests:
-    # See https://runs-on.com/runners/linux/
-    runs-on: [runs-on,runner=8cpu-linux-x64,ram=16,"run-id=${{ 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 TEST_WEB_HOSTNAME=test-runner \
-            danswer/danswer-integration:test \
-            /app/tests/integration/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
-
-      - name: Stop Docker containers
-        run: |
-          cd deployment/docker_compose
-          docker compose -f docker-compose.dev.yml -p danswer-stack down -v
-
-      - 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

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

@@ -1,124 +0,0 @@
-name: Backport on Merge
-
-# Note this workflow does not trigger the builds, be sure to manually tag the branches to trigger the builds
-
-on:
-  pull_request:
-    types: [closed]  # Later we check for merge so only PRs that go in can get backported
-
-permissions:
-  contents: write
-  actions: write
-
-jobs:
-  backport:
-    if: github.event.pull_request.merged == true
-    runs-on: ubuntu-latest
-    env:
-      GITHUB_TOKEN: ${{ secrets.YUHONG_GH_ACTIONS }}
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-        with:
-          ssh-key: "${{ secrets.RKUO_DEPLOY_KEY }}"
-          fetch-depth: 0
-
-      - name: Set up Git user
-        run: |
-          git config user.name "Richard Kuo [bot]"
-          git config user.email "rkuo[bot]@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-helm-chart-testing.yml.disabled.txt

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

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

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

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

@@ -1,61 +0,0 @@
-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: ${{ secrets.JIRA_API_TOKEN }}
-
-jobs:
-  connectors-check:
-    # See https://runs-on.com/runners/linux/
-    runs-on: [runs-on,runner=8cpu-linux-x64,"run-id=${{ 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

@@ -1,58 +0,0 @@
-name: Connector Tests
-
-on:
-  schedule:
-    # This cron expression runs the job daily at 16:00 UTC (9am PT)
-    - cron: "0 16 * * *"
-
-env:
-  # Bedrock
-  AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
-  AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
-  AWS_REGION_NAME: ${{ secrets.AWS_REGION_NAME }}
-
-  # OpenAI
-  OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-
-jobs:
-  connectors-check:
-    # See https://runs-on.com/runners/linux/
-    runs-on: [runs-on,runner=8cpu-linux-x64,"run-id=${{ 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/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

@@ -1,27 +1,22 @@
 name: Python Unit Tests
 
 on:
-  merge_group:
   pull_request:
-    branches:
-      - main
-      - 'release/**'
+    branches: [ main ]
 
 jobs:
   backend-check:
-    # See https://runs-on.com/runners/linux/
-    runs-on: [runs-on,runner=8cpu-linux-x64,"run-id=${{ github.run_id }}"]
+    runs-on: ubuntu-latest
 
     env:
       PYTHONPATH: ./backend
-      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
+      uses: actions/setup-python@v4
       with:
         python-version: '3.11'
         cache: 'pip'
@@ -32,8 +27,8 @@ jobs:
     - 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
+        pip install -r backend/requirements/default.txt
+        pip install -r backend/requirements/dev.txt
 
     - name: Run Tests
       shell: script -q -e -c "bash --noprofile --norc -eo pipefail {0}"

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

@@ -1,23 +1,21 @@
 name: Quality Checks PR
 concurrency:
-  group: Quality-Checks-PR-${{ github.workflow }}-${{ github.head_ref || github.event.workflow_run.head_branch || github.run_id }}
+  group: Quality-Checks-PR-${{ github.head_ref }}
   cancel-in-progress: true
 
 on:
-  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 }}"]
+    runs-on: ubuntu-latest
     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) || '' }}
+    - uses: actions/checkout@v4
+      with:
+        fetch-depth: 0
+    - uses: actions/setup-python@v5
+      with:
+        python-version: '3.11'
+    - uses: pre-commit/action@v3.0.0
+      with:
+        extra_args: --from-ref ${{ github.event.pull_request.base.sha }} --to-ref ${{ github.event.pull_request.head.sha }}

.github/workflows/tag-nightly.yml

@@ -1,54 +0,0 @@
-name: Nightly Tag Push
-
-on:
-  schedule:
-    - cron: '0 10 * * *' # Runs every day at 2 AM PST / 3 AM PDT / 10 AM UTC
-
-permissions:
-  contents: write  # Allows pushing tags to the repository
-
-jobs:
-  create-and-push-tag:
-    runs-on: [runs-on,runner=2cpu-linux-x64,"run-id=${{ github.run_id }}"]
-
-    steps:
-    # actions using GITHUB_TOKEN cannot trigger another workflow, but we do want this to trigger docker pushes
-    # see https://github.com/orgs/community/discussions/27028#discussioncomment-3254367 for the workaround we
-    # implement here which needs an actual user's deploy key
-    - name: Checkout code
-      uses: actions/checkout@v4
-      with:
-        ssh-key: "${{ secrets.RKUO_DEPLOY_KEY }}"
-
-    - name: Set up Git user
-      run: |
-        git config user.name "Richard Kuo [bot]"
-        git config user.email "rkuo[bot]@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

@@ -4,6 +4,4 @@
 .mypy_cache
 .idea
 /deployment/data/nginx/app.conf
-.vscode/
-*.sw?
-/backend/tests/regression/answer_quality/search_test_config.yaml
+.vscode/launch.json

.prettierignore

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

.vscode/env_template.txt

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

@@ -1,98 +1,33 @@
-/* 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": [
-		{
-	    	// 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"
             ],
-            "presentation": {
-				 "group": "2",
-			 },
-            "console": "integratedTerminal",
-            "consoleTitle": "Web Server Console"
+            "console": "integratedTerminal"
         },
         {
             "name": "Model Server",
-            "consoleName": "Model Server",
-            "type": "debugpy",
+            "type": "python",
             "request": "launch",
             "module": "uvicorn",
             "cwd": "${workspaceFolder}/backend",
-            "envFile": "${workspaceFolder}/.vscode/.env",
             "env": {
                 "LOG_LEVEL": "DEBUG",
                 "PYTHONUNBUFFERED": "1"
@@ -102,22 +37,16 @@
                 "--reload",
                 "--port",
                 "9000"
-            ],
-            "presentation": {
-				 "group": "2",
-			},
-            "consoleTitle": "Model Server Console"
+            ]
         },
         {
             "name": "API Server",
-            "consoleName": "API Server",
-            "type": "debugpy",
+            "type": "python",
             "request": "launch",
             "module": "uvicorn",
             "cwd": "${workspaceFolder}/backend",
-            "envFile": "${workspaceFolder}/.vscode/.env",
             "env": {
-                "LOG_DANSWER_MODEL_INTERACTIONS": "True",
+                "LOG_ALL_MODEL_INTERACTIONS": "True",
                 "LOG_LEVEL": "DEBUG",
                 "PYTHONUNBUFFERED": "1"
             },
@@ -126,234 +55,51 @@
                 "--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",
+            "name": "Indexing",
+            "type": "python",
             "request": "launch",
-            "program": "danswer/danswerbot/slack/listener.py",
+            "program": "danswer/background/update.py",
             "cwd": "${workspaceFolder}/backend",
-            "envFile": "${workspaceFolder}/.vscode/.env",
             "env": {
+                "ENABLE_MINI_CHUNK": "false",
                 "LOG_LEVEL": "DEBUG",
                 "PYTHONUNBUFFERED": "1",
                 "PYTHONPATH": "."
-            },
-            "presentation": {
-				 "group": "2",
-			},
-            "consoleTitle": "Slack Bot Console"
+            }
         },
+        // Celery and all async jobs, usually would include indexing as well but this is handled separately above for dev
         {
-            "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",
-            ],
-            "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",
-            ],
-            "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",
+            "type": "python",
             "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": "."
             },
+            "args": [
+                "--no-indexing"
+            ]
         },
+        // For the listner to access the Slack API,
+        // DANSWER_BOT_SLACK_APP_TOKEN & DANSWER_BOT_SLACK_BOT_TOKEN need to be set in .env file located in the root of the project
+        {
+            "name": "Slack Bot",
+            "type": "python",
+            "request": "launch",
+            "program": "danswer/danswerbot/slack/listener.py",
+            "cwd": "${workspaceFolder}/backend",
+            "envFile": "${workspaceFolder}/.env",
+            "env": {
+                "LOG_LEVEL": "DEBUG",
+                "PYTHONUNBUFFERED": "1",
+                "PYTHONPATH": "."
+            }
+        }
     ]
-}
+}

CONTRIBUTING.md

@@ -22,7 +22,7 @@ Your input is vital to making sure that Danswer moves in the right direction.
 Before starting on implementation, please raise a GitHub issue.
 
 And always feel free to message us (Chris Weaver / Yuhong Sun) on 
-[Slack](https://join.slack.com/t/danswer/shared_invite/zt-2lcmqw703-071hBuZBfNEOGUsLa5PXvQ) / 
+[Slack](https://join.slack.com/t/danswer/shared_invite/zt-2afut44lv-Rw3kSWu6_OmdAXRpCv80DQ) / 
 [Discord](https://discord.gg/TDJ59cGV2X) directly about anything at all. 
 
 
@@ -48,26 +48,23 @@ We would love to see you there!
 
 
 ## Get Started 🚀
-Danswer being a fully functional app, relies on some external software, specifically:
+Danswer being a fully functional app, relies on some external pieces of software, specifically:
 - [Postgres](https://www.postgresql.org/) (Relational DB)
 - [Vespa](https://vespa.ai/) (Vector DB/Search Engine)
-- [Redis](https://redis.io/) (Cache)
-- [Nginx](https://nginx.org/) (Not needed for development flows generally)
 
-
-> **Note:**
-> This guide provides instructions to build and run Danswer locally from source with Docker containers providing the above external software. We believe this combination is easier for
-> development purposes. If you prefer to use pre-built container images, we provide instructions on running the full Danswer stack within Docker below.
+This guide provides instructions to 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.
 
 
 ### Local Set Up
-Be sure to use Python version 3.11. For instructions on installing Python 3.11 on macOS, refer to the [CONTRIBUTING_MACOS.md](./CONTRIBUTING_MACOS.md) readme.
+It is recommended to use Python version 3.11
 
 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).
+If using a higher version, the version of Tensorflow we use may not be available for your platform.
 
 
-#### Backend: Python requirements
+#### Installing Requirements
 Currently, we use pip and recommend creating a virtual environment.
 
 For convenience here's a command for it:
@@ -75,11 +72,6 @@ For convenience here's a command for it:
 python -m venv .venv
 source .venv/bin/activate
 ```
-
-> **Note:**
-> This virtual environment MUST NOT be set up WITHIN the danswer directory if you plan on using mypy within certain IDEs.
-> For simplicity, we recommend setting up the virtual environment outside of the danswer directory.
-
 _For Windows, activate the virtual environment using Command Prompt:_
 ```bash
 .venv\Scripts\activate
@@ -93,38 +85,34 @@ 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
 ```
 
-#### Docker containers for external software
-You will need Docker installed to run these containers.
+Install Playwright (required by the Web Connector)
 
-First navigate to `danswer/deployment/docker_compose`, then start up Postgres/Vespa/Redis with:
+> Note: If you have just done the pip install, open a new terminal and source the python virtual-env again.
+This will update the path to include playwright
+
+Then install Playwright by running:
 ```bash
-docker compose -f docker-compose.dev.yml -p danswer-stack up -d index relational_db cache
+playwright install
 ```
-(index refers to Vespa, relational_db refers to Postgres, and cache refers to Redis)
 
 
-#### Running Danswer locally
+#### Dependent Docker Containers
+First navigate to `danswer/deployment/docker_compose`, then start up Vespa and Postgres with:
+```bash
+docker compose -f docker-compose.dev.yml -p danswer-stack up -d index relational_db
+```
+(index refers to Vespa and relational_db refers to Postgres)
+
+#### Running Danswer
 To start the frontend, navigate to `danswer/web` and run:
 ```bash
 npm run dev
@@ -135,10 +123,11 @@ 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"
+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.
@@ -161,7 +150,6 @@ To run the backend API server, navigate back to `danswer/backend` and run:
 ```bash
 AUTH_TYPE=disabled uvicorn danswer.main:app --reload --port 8080
 ```
-
 _For Windows (for compatibility with both PowerShell and Command Prompt):_
 ```bash
 powershell -Command "
@@ -170,58 +158,20 @@ powershell -Command "
 "
 ```
 
-> **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
-docker compose -f docker-compose.dev.yml -p danswer-stack up -d
-```
-
-After Docker pulls and starts these containers, navigate to `http://localhost:3000` to use Danswer.
-
-If you want to make changes to Danswer and run those changes in Docker, you can also build a local version of the Danswer container images that incorporates your changes like so:
-
-```bash
-docker compose -f docker-compose.dev.yml -p danswer-stack up -d --build
-```
+Note: if you need finer logging, add the additional environment variable `LOG_LEVEL=DEBUG` to the relevant services.
 
 ### Formatting and Linting
 #### Backend
 For the backend, you'll need to setup pre-commit hooks (black / reorder-python-imports).
 First, install pre-commit (if you don't have it already) following the instructions
 [here](https://pre-commit.com/#installation).
-
-With the virtual environment active, install the pre-commit library with:
-```bash
-pip install pre-commit
-```
-
 Then, from the `danswer/backend` directory, run:
 ```bash
 pre-commit install
 ```
 
 Additionally, we use `mypy` for static type checking.
-Danswer is fully type-annotated, and we want to keep it that way! 
+Danswer is fully type-annotated, and we would like to keep it that way! 
 To run the mypy checks manually, run `python -m mypy .` from the `danswer/backend` directory.
 
 
@@ -232,7 +182,6 @@ Please double check that prettier passes before creating a pull request.
 
 
 ### Release Process
-Danswer loosely follows the SemVer versioning standard.
-Major changes are released with a "minor" version bump. Currently we use patch release versions to indicate small feature changes.
+Danswer follows the semver versioning standard.
 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).

CONTRIBUTING_MACOS.md

@@ -1,31 +0,0 @@
-## 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

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

@@ -11,7 +11,7 @@
 <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-2lcmqw703-071hBuZBfNEOGUsLa5PXvQ" target="_blank">
+<a href="https://join.slack.com/t/danswer/shared_invite/zt-2afut44lv-Rw3kSWu6_OmdAXRpCv80DQ" 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">
@@ -68,13 +68,13 @@ We also have built-in support for deployment on Kubernetes. Files for that can b
 
 ## 🚧 Roadmap
 * Chat/Prompt sharing with specific teammates and user groups.
-* Multimodal model support, chat with images, video etc.
+* Multi-Model model support, chat with images, video etc.
 * Choosing between LLMs and parameters during chat session.
 * Tool calling and agent configurations options.
 * Organizational understanding and ability to locate and suggest experts from your team.
 
 
-## Other Notable Benefits of Danswer
+## Other Noteable Benefits of Danswer
 * User Authentication with document level access management.
 * Best in class Hybrid Search across all sources (BM-25 + prefix aware embedding models).
 * Admin Dashboard to configure connectors, document-sets, access, etc.
@@ -105,25 +105,5 @@ Efficiently pulls the latest changes from:
   * Websites
   * And more ...
 
-## 📚 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.

backend/.gitignore

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

backend/Dockerfile

@@ -1,20 +1,15 @@
 FROM python:3.11.7-slim-bookworm
 
 LABEL com.danswer.maintainer="founders@danswer.ai"
-LABEL com.danswer.description="This image is the web/frontend container of Danswer which \
-contains code for both the Community and Enterprise editions of Danswer. If you do not \
-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"
+LABEL com.danswer.description="This image is for the backend of Danswer. It is MIT Licensed and \
+free for all to use. You can find it at https://hub.docker.com/r/danswer/danswer-backend. For \
+more details, visit https://github.com/danswer-ai/danswer."
 
 # Default DANSWER_VERSION, typically overriden during builds by GitHub Actions.
-ARG DANSWER_VERSION=0.8-dev
-ENV DANSWER_VERSION=${DANSWER_VERSION} \
-    DANSWER_RUNNING_IN_DOCKER="true"
-
-ARG CA_CERT_CONTENT=""
-
+ARG DANSWER_VERSION=0.3-dev
+ENV DANSWER_VERSION=${DANSWER_VERSION}
 RUN echo "DANSWER_VERSION: ${DANSWER_VERSION}"
+
 # Install system dependencies
 # cmake needed for psycopg (postgres)
 # libpq-dev needed for psycopg (postgres)
@@ -22,45 +17,18 @@ RUN echo "DANSWER_VERSION: ${DANSWER_VERSION}"
 # zip for Vespa step futher down
 # ca-certificates for HTTPS
 RUN apt-get update && \
-    apt-get install -y \
-        cmake \
-        curl \
-        zip \
-        ca-certificates \
-        libgnutls30=3.7.9-2+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 && \
+    apt-get install -y cmake curl zip ca-certificates libgnutls30=3.7.9-2+deb12u2 \
+    libblkid1=2.38.1-5+deb12u1 libmount1=2.38.1-5+deb12u1 libsmartcols1=2.38.1-5+deb12u1 \
+    libuuid1=2.38.1-5+deb12u1 && \
     rm -rf /var/lib/apt/lists/* && \
     apt-get clean
 
-
-# Conditionally write the CA certificate and update certificates
-RUN if [ -n "$CA_CERT_CONTENT" ]; then \
-    echo "Adding custom CA certificate"; \
-    echo "$CA_CERT_CONTENT" > /usr/local/share/ca-certificates/my-ca.crt && \
-    chmod 644 /usr/local/share/ca-certificates/my-ca.crt && \
-    update-ca-certificates; \
-else \
-    echo "No custom CA certificate provided"; \
-fi
-
 # Install Python dependencies
 # Remove py which is pulled in by retry, py is not needed and is a CVE
 COPY ./requirements/default.txt /tmp/requirements.txt
-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 && \
+RUN pip install --no-cache-dir --upgrade -r /tmp/requirements.txt && \
     pip uninstall -y py && \
-    playwright install chromium && \
-    playwright install-deps chromium && \
+    playwright install chromium && playwright install-deps chromium && \
     ln -s /usr/local/bin/supervisord /usr/bin/supervisord
 
 # Cleanup for CVEs and size reduction
@@ -68,54 +36,30 @@ RUN pip install --no-cache-dir --upgrade \
 # 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 && \
+RUN apt-get remove -y --allow-remove-essential perl-base xserver-common xvfb cmake \
+    libldap-2.5-0 libldap-2.5-0 && \
     apt-get autoremove -y && \
     rm -rf /var/lib/apt/lists/* && \
-    rm -f /usr/local/lib/python3.11/site-packages/tornado/test/test.key
+    rm /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')"
-
+RUN python -c "from transformers import AutoTokenizer; AutoTokenizer.from_pretrained('intfloat/e5-base-v2')"
 
 # Pre-downloading NLTK for setups with limited egress
 RUN python -c "import nltk; \
 nltk.download('stopwords', quiet=True); \
+nltk.download('wordnet', quiet=True); \
 nltk.download('punkt', quiet=True);"
-# nltk.download('wordnet', quiet=True); introduce this back if lemmatization is needed
 
 # Set up application files
 WORKDIR /app
-
-# Enterprise Version Files
-COPY ./ee /app/ee
-COPY supervisord.conf /etc/supervisor/conf.d/supervisord.conf
-
-# 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
 
-# Escape hatch
-COPY ./scripts/force_delete_connector_by_id.py /app/scripts/force_delete_connector_by_id.py
-
-# Put logo in assets
-COPY ./assets /app/assets
-
-ENV PYTHONPATH=/app
+ENV PYTHONPATH /app
 
 # Default command which does nothing
 # This container is used by api server and background which specify their own CMD

backend/Dockerfile.model_server

@@ -7,39 +7,25 @@ You can find it at https://hub.docker.com/r/danswer/danswer-model-server. For mo
 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=${DANSWER_VERSION} \
-    DANSWER_RUNNING_IN_DOCKER="true"
-
-
+ARG DANSWER_VERSION=0.3-dev
+ENV DANSWER_VERSION=${DANSWER_VERSION}
 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 pip install --no-cache-dir --upgrade -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'); \
+RUN python -c "from transformers import AutoModel, AutoTokenizer, TFDistilBertForSequenceClassification; \
 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
+AutoTokenizer.from_pretrained('danswer/intent-model'); \
+AutoTokenizer.from_pretrained('intfloat/e5-base-v2'); \
+AutoTokenizer.from_pretrained('mixedbread-ai/mxbai-rerank-xsmall-v1'); \
+snapshot_download('danswer/intent-model'); \
+snapshot_download('intfloat/e5-base-v2'); \
+snapshot_download('mixedbread-ai/mxbai-rerank-xsmall-v1')"
 
 WORKDIR /app
 
@@ -55,6 +41,6 @@ COPY ./shared_configs /app/shared_configs
 # Model Server main code
 COPY ./model_server /app/model_server
 
-ENV PYTHONPATH=/app
+ENV PYTHONPATH /app
 
 CMD ["uvicorn", "model_server.main:app", "--host", "0.0.0.0", "--port", "9000"]

backend/alembic.ini

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

backend/alembic/env.py

@@ -1,203 +1,86 @@
-from sqlalchemy.engine.base import Connection
-from typing import Any
 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 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
 
-# Alembic Config object
+# this is the Alembic Config object, which provides
+# access to the values within the .ini file in use.
 config = context.config
 
 # Interpret the config file for Python logging.
-if config.config_file_name is not None and config.attributes.get(
-    "configure_logger", True
-):
+# This line sets up loggers basically.
+if config.config_file_name is not None:
     fileConfig(config.config_file_name)
 
-# Add your model's MetaData object here for 'autogenerate' support
+# add your model's MetaData object here
+# for 'autogenerate' support
+# from myapp import mymodel
+# target_metadata = mymodel.Base.metadata
 target_metadata = [Base.metadata, ResultModelBase.metadata]
 
-EXCLUDE_TABLES = {"kombu_queue", "kombu_message"}
-
-# Set up logging
-logger = logging.getLogger(__name__)
+# 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.
 
 
-def include_object(
-    object: Any, name: str, type_: str, reflected: bool, compare_to: Any
-) -> bool:
+def run_migrations_offline() -> None:
+    """Run migrations in 'offline' mode.
+
+    This configures the context with just a URL
+    and not an Engine, though an Engine is acceptable
+    here as well.  By skipping the Engine creation
+    we don't even need a DBAPI to be available.
+
+    Calls to context.execute() here emit the given string to the
+    script output.
+
     """
-    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}"'))
-
+    url = build_connection_string()
     context.configure(
-        connection=connection,
+        url=url,
         target_metadata=target_metadata,  # type: ignore
-        include_object=include_object,
-        version_table_schema=schema_name,
-        include_schemas=True,
-        compare_type=True,
-        compare_server_default=True,
-        script_location=config.get_main_option("script_location"),
+        literal_binds=True,
+        dialect_opts={"paramstyle": "named"},
     )
 
     with context.begin_transaction():
         context.run_migrations()
 
 
-async def run_async_migrations() -> None:
-    """
-    Determines whether to run migrations for a single schema or all schemas,
-    and executes migrations accordingly.
-    """
-    schema_name, create_schema, upgrade_all_tenants = get_schema_options()
+def do_run_migrations(connection: Connection) -> None:
+    context.configure(connection=connection, target_metadata=target_metadata)  # type: ignore
 
-    engine = create_async_engine(
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+async def run_async_migrations() -> None:
+    """In this scenario we need to create an Engine
+    and associate a connection with the context.
+
+    """
+
+    connectable = create_async_engine(
         build_connection_string(),
         poolclass=pool.NullPool,
     )
 
-    if upgrade_all_tenants:
-        # Run migrations for all tenant schemas sequentially
-        tenant_schemas = get_all_tenant_ids()
+    async with connectable.connect() as connection:
+        await connection.run_sync(do_run_migrations)
 
-        for schema in tenant_schemas:
-            try:
-                logger.info(f"Migrating schema: {schema}")
-                async with engine.connect() as connection:
-                    await connection.run_sync(
-                        do_run_migrations,
-                        schema_name=schema,
-                        create_schema=create_schema,
-                    )
-            except Exception as e:
-                logger.error(f"Error migrating schema {schema}: {e}")
-                raise
-    else:
-        try:
-            logger.info(f"Migrating schema: {schema_name}")
-            async with engine.connect() as connection:
-                await connection.run_sync(
-                    do_run_migrations,
-                    schema_name=schema_name,
-                    create_schema=create_schema,
-                )
-        except Exception as e:
-            logger.error(f"Error migrating schema {schema_name}: {e}")
-            raise
-
-    await engine.dispose()
-
-
-def run_migrations_offline() -> None:
-    """
-    Run migrations in 'offline' mode.
-    """
-    schema_name, _, upgrade_all_tenants = get_schema_options()
-    url = build_connection_string()
-
-    if upgrade_all_tenants:
-        # Run offline migrations for all tenant schemas
-        engine = create_async_engine(url)
-        tenant_schemas = get_all_tenant_ids()
-        engine.sync_engine.dispose()
-
-        for schema in tenant_schemas:
-            logger.info(f"Migrating schema: {schema}")
-            context.configure(
-                url=url,
-                target_metadata=target_metadata,  # type: ignore
-                literal_binds=True,
-                include_object=include_object,
-                version_table_schema=schema,
-                include_schemas=True,
-                script_location=config.get_main_option("script_location"),
-                dialect_opts={"paramstyle": "named"},
-            )
-
-            with context.begin_transaction():
-                context.run_migrations()
-    else:
-        logger.info(f"Migrating schema: {schema_name}")
-        context.configure(
-            url=url,
-            target_metadata=target_metadata,  # type: ignore
-            literal_binds=True,
-            include_object=include_object,
-            version_table_schema=schema_name,
-            include_schemas=True,
-            script_location=config.get_main_option("script_location"),
-            dialect_opts={"paramstyle": "named"},
-        )
-
-        with context.begin_transaction():
-            context.run_migrations()
+    await connectable.dispose()
 
 
 def run_migrations_online() -> None:
-    """
-    Runs migrations in 'online' mode using an asynchronous engine.
-    """
+    """Run migrations in 'online' mode."""
+
     asyncio.run(run_async_migrations())
 
 

backend/alembic/versions/0568ccf46a6b_add_thread_specific_model_selection.py

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

@@ -1,32 +0,0 @@
-"""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

@@ -1,26 +0,0 @@
-"""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/0ebb1d516877_add_ccpair_deletion_failure_message.py

@@ -1,27 +0,0 @@
-"""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/1b10e1fda030_add_additional_data_to_notifications.py

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

backend/alembic/versions/1b8206b29c5d_add_user_delete_cascades.py

@@ -1,102 +0,0 @@
-"""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

@@ -1,135 +0,0 @@
-"""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

@@ -1,44 +0,0 @@
-"""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

@@ -1,86 +0,0 @@
-"""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/27c6ecc08586_permission_framework.py

@@ -160,28 +160,12 @@ def downgrade() -> None:
             nullable=False,
         ),
     )
-
-    # 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_constraint(
+        "fk_index_attempt_credential_id", "index_attempt", type_="foreignkey"
+    )
+    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

@@ -1,32 +0,0 @@
-"""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/325975216eb3_add_icon_color_and_icon_shape_to_persona.py

@@ -1,70 +0,0 @@
-"""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/351faebd379d_add_curator_fields.py

@@ -1,90 +0,0 @@
-"""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

@@ -1,64 +0,0 @@
-"""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

@@ -11,8 +11,8 @@ import sqlalchemy as sa
 # revision identifiers, used by Alembic.
 revision = "3879338f8ba1"
 down_revision = "f1c6478c3fd8"
-branch_labels: None = None
-depends_on: None = None
+branch_labels = None
+depends_on = None
 
 
 def upgrade() -> None:

backend/alembic/versions/3a7802814195_add_alternate_assistant_to_chat_message.py

@@ -1,35 +0,0 @@
-"""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/43cbbb3f5e6a_rename_index_origin_to_index_recursively.py

@@ -1,42 +0,0 @@
-"""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

@@ -1,65 +0,0 @@
-"""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

@@ -1,23 +0,0 @@
-"""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/46b7a812670f_fix_user__external_user_group_id_fk.py

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

backend/alembic/versions/473a1a7ca408_add_display_model_names_to_llm_provider.py

@@ -1,49 +0,0 @@
-"""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/48d14957fe80_add_support_for_custom_tools.py

@@ -1,61 +0,0 @@
-"""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

@@ -1,80 +0,0 @@
-"""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

@@ -1,34 +0,0 @@
-"""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

@@ -1,72 +0,0 @@
-"""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/52a219fb5233_add_last_synced_and_last_modified_to_document_table.py

@@ -1,66 +0,0 @@
-"""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

@@ -1,79 +0,0 @@
-"""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/5c7fdadae813_match_any_keywords_flag_for_standard_.py

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

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

backend/alembic/versions/5fc1f54cc252_hybrid_enum.py

@@ -1,25 +0,0 @@
-"""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

@@ -1,162 +0,0 @@
-"""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/6756efa39ada_id_uuid_for_chat_session.py

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

backend/alembic/versions/703313b75876_add_tokenratelimit_tables.py

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

backend/alembic/versions/70f00c45c0f2_more_descriptive_filestore.py

@@ -1,68 +0,0 @@
-"""More Descriptive Filestore
-
-Revision ID: 70f00c45c0f2
-Revises: 3879338f8ba1
-Create Date: 2024-05-17 17:51:41.926893
-
-"""
-from alembic import op
-import sqlalchemy as sa
-from sqlalchemy.dialects import postgresql
-
-# revision identifiers, used by Alembic.
-revision = "70f00c45c0f2"
-down_revision = "3879338f8ba1"
-branch_labels: None = None
-depends_on: None = None
-
-
-def upgrade() -> None:
-    op.add_column("file_store", sa.Column("display_name", sa.String(), nullable=True))
-    op.add_column(
-        "file_store",
-        sa.Column(
-            "file_origin",
-            sa.String(),
-            nullable=False,
-            server_default="connector",  # Default to connector
-        ),
-    )
-    op.add_column(
-        "file_store",
-        sa.Column(
-            "file_type", sa.String(), nullable=False, server_default="text/plain"
-        ),
-    )
-    op.add_column(
-        "file_store",
-        sa.Column(
-            "file_metadata",
-            postgresql.JSONB(astext_type=sa.Text()),
-            nullable=True,
-        ),
-    )
-
-    op.execute(
-        """
-        UPDATE file_store
-        SET file_origin = CASE
-            WHEN file_name LIKE 'chat__%' THEN 'chat_upload'
-            ELSE 'connector'
-        END,
-        file_name = CASE
-            WHEN file_name LIKE 'chat__%' THEN SUBSTR(file_name, 7)
-            ELSE file_name
-        END,
-        file_type = CASE
-            WHEN file_name LIKE 'chat__%' THEN 'image/png'
-            ELSE 'text/plain'
-        END
-    """
-    )
-
-
-def downgrade() -> None:
-    op.drop_column("file_store", "file_metadata")
-    op.drop_column("file_store", "file_type")
-    op.drop_column("file_store", "file_origin")
-    op.drop_column("file_store", "display_name")

backend/alembic/versions/7477a5f5d728_added_model_defaults_for_users.py

@@ -1,24 +0,0 @@
-"""Added model defaults for users
-
-Revision ID: 7477a5f5d728
-Revises: 213fd978c6d8
-Create Date: 2024-08-04 19:00:04.512634
-
-"""
-
-from alembic import op
-import sqlalchemy as sa
-
-# revision identifiers, used by Alembic.
-revision = "7477a5f5d728"
-down_revision = "213fd978c6d8"
-branch_labels: None = None
-depends_on: None = None
-
-
-def upgrade() -> None:
-    op.add_column("user", sa.Column("default_model", sa.Text(), nullable=True))
-
-
-def downgrade() -> None:
-    op.drop_column("user", "default_model")

backend/alembic/versions/76b60d407dfb_cc_pair_name_not_unique.py

@@ -28,9 +28,5 @@ def upgrade() -> None:
 
 
 def downgrade() -> None:
-    op.create_unique_constraint(
-        "connector_credential_pair__name__key", "connector_credential_pair", ["name"]
-    )
-    op.alter_column(
-        "connector_credential_pair", "name", existing_type=sa.String(), nullable=True
-    )
+    # This wasn't really required by the code either, no good reason to make it unique again
+    pass

backend/alembic/versions/776b3bbe9092_remove_remaining_enums.py

@@ -10,7 +10,7 @@ import sqlalchemy as sa
 
 from danswer.db.models import IndexModelStatus
 from danswer.search.enums import RecencyBiasSetting
-from danswer.search.enums import SearchType
+from danswer.search.models import SearchType
 
 # revision identifiers, used by Alembic.
 revision = "776b3bbe9092"

backend/alembic/versions/795b20b85b4b_add_llm_group_permissions_control.py

@@ -1,41 +0,0 @@
-"""add_llm_group_permissions_control
-
-Revision ID: 795b20b85b4b
-Revises: 05c07bf07c00
-Create Date: 2024-07-19 11:54:35.701558
-
-"""
-from alembic import op
-import sqlalchemy as sa
-
-
-revision = "795b20b85b4b"
-down_revision = "05c07bf07c00"
-branch_labels: None = None
-depends_on: None = None
-
-
-def upgrade() -> None:
-    op.create_table(
-        "llm_provider__user_group",
-        sa.Column("llm_provider_id", sa.Integer(), nullable=False),
-        sa.Column("user_group_id", sa.Integer(), nullable=False),
-        sa.ForeignKeyConstraint(
-            ["llm_provider_id"],
-            ["llm_provider.id"],
-        ),
-        sa.ForeignKeyConstraint(
-            ["user_group_id"],
-            ["user_group.id"],
-        ),
-        sa.PrimaryKeyConstraint("llm_provider_id", "user_group_id"),
-    )
-    op.add_column(
-        "llm_provider",
-        sa.Column("is_public", sa.Boolean(), nullable=False, server_default="true"),
-    )
-
-
-def downgrade() -> None:
-    op.drop_table("llm_provider__user_group")
-    op.drop_column("llm_provider", "is_public")

backend/alembic/versions/797089dfb4d2_persona_start_date.py

@@ -1,27 +0,0 @@
-"""persona_start_date
-
-Revision ID: 797089dfb4d2
-Revises: 55546a7967ee
-Create Date: 2024-09-11 14:51:49.785835
-
-"""
-from alembic import op
-import sqlalchemy as sa
-
-
-# revision identifiers, used by Alembic.
-revision = "797089dfb4d2"
-down_revision = "55546a7967ee"
-branch_labels = None
-depends_on = None
-
-
-def upgrade() -> None:
-    op.add_column(
-        "persona",
-        sa.Column("search_start_date", sa.DateTime(timezone=True), nullable=True),
-    )
-
-
-def downgrade() -> None:
-    op.drop_column("persona", "search_start_date")

backend/alembic/versions/7aea705850d5_added_slack_auto_filter.py

@@ -1,35 +0,0 @@
-"""added slack_auto_filter
-
-Revision ID: 7aea705850d5
-Revises: 4505fd7302e1
-Create Date: 2024-07-10 11:01:23.581015
-
-"""
-from alembic import op
-import sqlalchemy as sa
-
-revision = "7aea705850d5"
-down_revision = "4505fd7302e1"
-branch_labels: None = None
-depends_on: None = None
-
-
-def upgrade() -> None:
-    op.add_column(
-        "slack_bot_config",
-        sa.Column("enable_auto_filters", sa.Boolean(), nullable=True),
-    )
-    op.execute(
-        "UPDATE slack_bot_config SET enable_auto_filters = FALSE WHERE enable_auto_filters IS NULL"
-    )
-    op.alter_column(
-        "slack_bot_config",
-        "enable_auto_filters",
-        existing_type=sa.Boolean(),
-        nullable=False,
-        server_default=sa.false(),
-    )
-
-
-def downgrade() -> None:
-    op.drop_column("slack_bot_config", "enable_auto_filters")

backend/alembic/versions/8a87bd6ec550_associate_index_attempts_with_ccpair.py

@@ -1,107 +0,0 @@
-"""associate index attempts with ccpair
-
-Revision ID: 8a87bd6ec550
-Revises: 4ea2c93919c1
-Create Date: 2024-07-22 15:15:52.558451
-
-"""
-from alembic import op
-import sqlalchemy as sa
-
-# revision identifiers, used by Alembic.
-revision = "8a87bd6ec550"
-down_revision = "4ea2c93919c1"
-branch_labels: None = None
-depends_on: None = None
-
-
-def upgrade() -> None:
-    # Add the new connector_credential_pair_id column
-    op.add_column(
-        "index_attempt",
-        sa.Column("connector_credential_pair_id", sa.Integer(), nullable=True),
-    )
-
-    # Create a foreign key constraint to the connector_credential_pair table
-    op.create_foreign_key(
-        "fk_index_attempt_connector_credential_pair_id",
-        "index_attempt",
-        "connector_credential_pair",
-        ["connector_credential_pair_id"],
-        ["id"],
-    )
-
-    # Populate the new connector_credential_pair_id column using existing connector_id and credential_id
-    op.execute(
-        """
-        UPDATE index_attempt ia
-        SET connector_credential_pair_id = (
-            SELECT id FROM connector_credential_pair ccp
-            WHERE
-                (ia.connector_id IS NULL OR ccp.connector_id = ia.connector_id)
-                AND (ia.credential_id IS NULL OR ccp.credential_id = ia.credential_id)
-            LIMIT 1
-        )
-        WHERE ia.connector_id IS NOT NULL OR ia.credential_id IS NOT NULL
-        """
-    )
-
-    # For good measure
-    op.execute(
-        """
-        DELETE FROM index_attempt
-        WHERE connector_credential_pair_id IS NULL
-        """
-    )
-
-    # Make the new connector_credential_pair_id column non-nullable
-    op.alter_column("index_attempt", "connector_credential_pair_id", nullable=False)
-
-    # Drop the old connector_id and credential_id columns
-    op.drop_column("index_attempt", "connector_id")
-    op.drop_column("index_attempt", "credential_id")
-
-    # Update the index to use connector_credential_pair_id
-    op.create_index(
-        "ix_index_attempt_latest_for_connector_credential_pair",
-        "index_attempt",
-        ["connector_credential_pair_id", "time_created"],
-    )
-
-
-def downgrade() -> None:
-    # Add back the old connector_id and credential_id columns
-    op.add_column(
-        "index_attempt", sa.Column("connector_id", sa.Integer(), nullable=True)
-    )
-    op.add_column(
-        "index_attempt", sa.Column("credential_id", sa.Integer(), nullable=True)
-    )
-
-    # Populate the old connector_id and credential_id columns using the connector_credential_pair_id
-    op.execute(
-        """
-        UPDATE index_attempt ia
-        SET connector_id = ccp.connector_id, credential_id = ccp.credential_id
-        FROM connector_credential_pair ccp
-        WHERE ia.connector_credential_pair_id = ccp.id
-        """
-    )
-
-    # Make the old connector_id and credential_id columns non-nullable
-    op.alter_column("index_attempt", "connector_id", nullable=False)
-    op.alter_column("index_attempt", "credential_id", nullable=False)
-
-    # Drop the new connector_credential_pair_id column
-    op.drop_constraint(
-        "fk_index_attempt_connector_credential_pair_id",
-        "index_attempt",
-        type_="foreignkey",
-    )
-    op.drop_column("index_attempt", "connector_credential_pair_id")
-
-    op.create_index(
-        "ix_index_attempt_latest_for_connector_credential_pair",
-        "index_attempt",
-        ["connector_id", "credential_id", "time_created"],
-    )

backend/alembic/versions/91ffac7e65b3_add_expiry_time.py

@@ -1,26 +0,0 @@
-"""add expiry time
-
-Revision ID: 91ffac7e65b3
-Revises: bc9771dccadf
-Create Date: 2024-06-24 09:39:56.462242
-
-"""
-
-from alembic import op
-import sqlalchemy as sa
-
-# revision identifiers, used by Alembic.
-revision = "91ffac7e65b3"
-down_revision = "795b20b85b4b"
-branch_labels: None = None
-depends_on: None = None
-
-
-def upgrade() -> None:
-    op.add_column(
-        "user", sa.Column("oidc_expiry", sa.DateTime(timezone=True), nullable=True)
-    )
-
-
-def downgrade() -> None:
-    op.drop_column("user", "oidc_expiry")

backend/alembic/versions/949b4a92a401_remove_rt.py

@@ -1,74 +0,0 @@
-"""remove rt
-
-Revision ID: 949b4a92a401
-Revises: 1b10e1fda030
-Create Date: 2024-10-26 13:06:06.937969
-
-"""
-from alembic import op
-from sqlalchemy.orm import Session
-
-# Import your models and constants
-from danswer.db.models import (
-    Connector,
-    ConnectorCredentialPair,
-    Credential,
-    IndexAttempt,
-)
-from danswer.configs.constants import DocumentSource
-
-
-# revision identifiers, used by Alembic.
-revision = "949b4a92a401"
-down_revision = "1b10e1fda030"
-branch_labels = None
-depends_on = None
-
-
-def upgrade() -> None:
-    # Deletes all RequestTracker connectors and associated data
-    bind = op.get_bind()
-    session = Session(bind=bind)
-
-    connectors_to_delete = (
-        session.query(Connector)
-        .filter(Connector.source == DocumentSource.REQUESTTRACKER)
-        .all()
-    )
-
-    connector_ids = [connector.id for connector in connectors_to_delete]
-
-    if connector_ids:
-        cc_pairs_to_delete = (
-            session.query(ConnectorCredentialPair)
-            .filter(ConnectorCredentialPair.connector_id.in_(connector_ids))
-            .all()
-        )
-
-        cc_pair_ids = [cc_pair.id for cc_pair in cc_pairs_to_delete]
-
-        if cc_pair_ids:
-            session.query(IndexAttempt).filter(
-                IndexAttempt.connector_credential_pair_id.in_(cc_pair_ids)
-            ).delete(synchronize_session=False)
-
-            session.query(ConnectorCredentialPair).filter(
-                ConnectorCredentialPair.id.in_(cc_pair_ids)
-            ).delete(synchronize_session=False)
-
-        credential_ids = [cc_pair.credential_id for cc_pair in cc_pairs_to_delete]
-        if credential_ids:
-            session.query(Credential).filter(Credential.id.in_(credential_ids)).delete(
-                synchronize_session=False
-            )
-
-        session.query(Connector).filter(Connector.id.in_(connector_ids)).delete(
-            synchronize_session=False
-        )
-
-    session.commit()
-
-
-def downgrade() -> None:
-    # No-op downgrade as we cannot restore deleted data
-    pass

backend/alembic/versions/a3795dce87be_migration_confluence_to_be_explicit.py

@@ -1,158 +0,0 @@
-"""migration confluence to be explicit
-
-Revision ID: a3795dce87be
-Revises: 1f60f60c3401
-Create Date: 2024-09-01 13:52:12.006740
-
-"""
-from alembic import op
-import sqlalchemy as sa
-from sqlalchemy.dialects import postgresql
-from sqlalchemy.sql import table, column
-
-revision = "a3795dce87be"
-down_revision = "1f60f60c3401"
-branch_labels: None = None
-depends_on: None = None
-
-
-def extract_confluence_keys_from_url(wiki_url: str) -> tuple[str, str, str, bool]:
-    from urllib.parse import urlparse
-
-    def _extract_confluence_keys_from_cloud_url(wiki_url: str) -> tuple[str, str, str]:
-        parsed_url = urlparse(wiki_url)
-        wiki_base = f"{parsed_url.scheme}://{parsed_url.netloc}{parsed_url.path.split('/spaces')[0]}"
-        path_parts = parsed_url.path.split("/")
-        space = path_parts[3]
-        page_id = path_parts[5] if len(path_parts) > 5 else ""
-        return wiki_base, space, page_id
-
-    def _extract_confluence_keys_from_datacenter_url(
-        wiki_url: str,
-    ) -> tuple[str, str, str]:
-        DISPLAY = "/display/"
-        PAGE = "/pages/"
-        parsed_url = urlparse(wiki_url)
-        wiki_base = f"{parsed_url.scheme}://{parsed_url.netloc}{parsed_url.path.split(DISPLAY)[0]}"
-        space = DISPLAY.join(parsed_url.path.split(DISPLAY)[1:]).split("/")[0]
-        page_id = ""
-        if (content := parsed_url.path.split(PAGE)) and len(content) > 1:
-            page_id = content[1]
-        return wiki_base, space, page_id
-
-    is_confluence_cloud = (
-        ".atlassian.net/wiki/spaces/" in wiki_url
-        or ".jira.com/wiki/spaces/" in wiki_url
-    )
-
-    if is_confluence_cloud:
-        wiki_base, space, page_id = _extract_confluence_keys_from_cloud_url(wiki_url)
-    else:
-        wiki_base, space, page_id = _extract_confluence_keys_from_datacenter_url(
-            wiki_url
-        )
-
-    return wiki_base, space, page_id, is_confluence_cloud
-
-
-def reconstruct_confluence_url(
-    wiki_base: str, space: str, page_id: str, is_cloud: bool
-) -> str:
-    if is_cloud:
-        url = f"{wiki_base}/spaces/{space}"
-        if page_id:
-            url += f"/pages/{page_id}"
-    else:
-        url = f"{wiki_base}/display/{space}"
-        if page_id:
-            url += f"/pages/{page_id}"
-    return url
-
-
-def upgrade() -> None:
-    connector = table(
-        "connector",
-        column("id", sa.Integer),
-        column("source", sa.String()),
-        column("input_type", sa.String()),
-        column("connector_specific_config", postgresql.JSONB),
-    )
-
-    # Fetch all Confluence connectors
-    connection = op.get_bind()
-    confluence_connectors = connection.execute(
-        sa.select(connector).where(
-            sa.and_(
-                connector.c.source == "CONFLUENCE", connector.c.input_type == "POLL"
-            )
-        )
-    ).fetchall()
-
-    for row in confluence_connectors:
-        config = row.connector_specific_config
-        wiki_page_url = config["wiki_page_url"]
-        wiki_base, space, page_id, is_cloud = extract_confluence_keys_from_url(
-            wiki_page_url
-        )
-
-        new_config = {
-            "wiki_base": wiki_base,
-            "space": space,
-            "page_id": page_id,
-            "is_cloud": is_cloud,
-        }
-
-        for key, value in config.items():
-            if key not in ["wiki_page_url"]:
-                new_config[key] = value
-
-        op.execute(
-            connector.update()
-            .where(connector.c.id == row.id)
-            .values(connector_specific_config=new_config)
-        )
-
-
-def downgrade() -> None:
-    connector = table(
-        "connector",
-        column("id", sa.Integer),
-        column("source", sa.String()),
-        column("input_type", sa.String()),
-        column("connector_specific_config", postgresql.JSONB),
-    )
-
-    confluence_connectors = (
-        op.get_bind()
-        .execute(
-            sa.select(connector).where(
-                connector.c.source == "CONFLUENCE", connector.c.input_type == "POLL"
-            )
-        )
-        .fetchall()
-    )
-
-    for row in confluence_connectors:
-        config = row.connector_specific_config
-        if all(key in config for key in ["wiki_base", "space", "is_cloud"]):
-            wiki_page_url = reconstruct_confluence_url(
-                config["wiki_base"],
-                config["space"],
-                config.get("page_id", ""),
-                config["is_cloud"],
-            )
-
-            new_config = {"wiki_page_url": wiki_page_url}
-            new_config.update(
-                {
-                    k: v
-                    for k, v in config.items()
-                    if k not in ["wiki_base", "space", "page_id", "is_cloud"]
-                }
-            )
-
-            op.execute(
-                connector.update()
-                .where(connector.c.id == row.id)
-                .values(connector_specific_config=new_config)
-            )

backend/alembic/versions/a3bfd0d64902_add_chosen_assistants_to_user_table.py

@@ -1,27 +0,0 @@
-"""Add chosen_assistants to User table
-
-Revision ID: a3bfd0d64902
-Revises: ec85f2b3c544
-Create Date: 2024-05-26 17:22:24.834741
-
-"""
-from alembic import op
-import sqlalchemy as sa
-from sqlalchemy.dialects import postgresql
-
-# revision identifiers, used by Alembic.
-revision = "a3bfd0d64902"
-down_revision = "ec85f2b3c544"
-branch_labels: None = None
-depends_on: None = None
-
-
-def upgrade() -> None:
-    op.add_column(
-        "user",
-        sa.Column("chosen_assistants", postgresql.ARRAY(sa.Integer()), nullable=True),
-    )
-
-
-def downgrade() -> None:
-    op.drop_column("user", "chosen_assistants")

backend/alembic/versions/ac5eaac849f9_add_last_pruned_to_connector_table.py

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

backend/alembic/versions/b082fec533f0_make_last_attempt_status_nullable.py

@@ -16,6 +16,7 @@ depends_on: None = None
 
 
 def upgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
     op.alter_column(
         "connector_credential_pair",
         "last_attempt_status",
@@ -28,15 +29,11 @@ def upgrade() -> None:
         ),
         nullable=True,
     )
+    # ### end Alembic commands ###
 
 
 def downgrade() -> None:
-    # First, update any null values to a default value
-    op.execute(
-        "UPDATE connector_credential_pair SET last_attempt_status = 'NOT_STARTED' WHERE last_attempt_status IS NULL"
-    )
-
-    # Then, make the column non-nullable
+    # ### commands auto generated by Alembic - please adjust! ###
     op.alter_column(
         "connector_credential_pair",
         "last_attempt_status",
@@ -49,3 +46,4 @@ def downgrade() -> None:
         ),
         nullable=False,
     )
+    # ### end Alembic commands ###

backend/alembic/versions/b85f02ec1308_fix_file_type_migration.py

@@ -1,28 +0,0 @@
-"""fix-file-type-migration
-
-Revision ID: b85f02ec1308
-Revises: a3bfd0d64902
-Create Date: 2024-05-31 18:09:26.658164
-
-"""
-from alembic import op
-
-# revision identifiers, used by Alembic.
-revision = "b85f02ec1308"
-down_revision = "a3bfd0d64902"
-branch_labels: None = None
-depends_on: None = None
-
-
-def upgrade() -> None:
-    op.execute(
-        """
-        UPDATE file_store
-        SET file_origin = UPPER(file_origin)
-    """
-    )
-
-
-def downgrade() -> None:
-    # Let's not break anything on purpose :)
-    pass

backend/alembic/versions/b896bbd0d5a7_backfill_is_internet_data_to_false.py

@@ -1,23 +0,0 @@
-"""backfill is_internet data to False
-
-Revision ID: b896bbd0d5a7
-Revises: 44f856ae2a4a
-Create Date: 2024-07-16 15:21:05.718571
-
-"""
-from alembic import op
-
-
-# revision identifiers, used by Alembic.
-revision = "b896bbd0d5a7"
-down_revision = "44f856ae2a4a"
-branch_labels: None = None
-depends_on: None = None
-
-
-def upgrade() -> None:
-    op.execute("UPDATE search_doc SET is_internet = FALSE WHERE is_internet IS NULL")
-
-
-def downgrade() -> None:
-    pass

backend/alembic/versions/ba98eba0f66a_add_support_for_litellm_proxy_in_.py

@@ -1,26 +0,0 @@
-"""add support for litellm proxy in reranking
-
-Revision ID: ba98eba0f66a
-Revises: bceb1e139447
-Create Date: 2024-09-06 10:36:04.507332
-
-"""
-from alembic import op
-import sqlalchemy as sa
-
-
-# revision identifiers, used by Alembic.
-revision = "ba98eba0f66a"
-down_revision = "bceb1e139447"
-branch_labels: None = None
-depends_on: None = None
-
-
-def upgrade() -> None:
-    op.add_column(
-        "search_settings", sa.Column("rerank_api_url", sa.String(), nullable=True)
-    )
-
-
-def downgrade() -> None:
-    op.drop_column("search_settings", "rerank_api_url")

backend/alembic/versions/bc9771dccadf_create_usage_reports_table.py

@@ -1,51 +0,0 @@
-"""create usage reports table
-
-Revision ID: bc9771dccadf
-Revises: 0568ccf46a6b
-Create Date: 2024-06-18 10:04:26.800282
-
-"""
-from alembic import op
-import sqlalchemy as sa
-import fastapi_users_db_sqlalchemy
-
-# revision identifiers, used by Alembic.
-revision = "bc9771dccadf"
-down_revision = "0568ccf46a6b"
-
-branch_labels: None = None
-depends_on: None = None
-
-
-def upgrade() -> None:
-    op.create_table(
-        "usage_reports",
-        sa.Column("id", sa.Integer(), nullable=False),
-        sa.Column("report_name", sa.String(), nullable=False),
-        sa.Column(
-            "requestor_user_id",
-            fastapi_users_db_sqlalchemy.generics.GUID(),
-            nullable=True,
-        ),
-        sa.Column(
-            "time_created",
-            sa.DateTime(timezone=True),
-            server_default=sa.text("now()"),
-            nullable=False,
-        ),
-        sa.Column("period_from", sa.DateTime(timezone=True), nullable=True),
-        sa.Column("period_to", sa.DateTime(timezone=True), nullable=True),
-        sa.ForeignKeyConstraint(
-            ["report_name"],
-            ["file_store.file_name"],
-        ),
-        sa.ForeignKeyConstraint(
-            ["requestor_user_id"],
-            ["user.id"],
-        ),
-        sa.PrimaryKeyConstraint("id"),
-    )
-
-
-def downgrade() -> None:
-    op.drop_table("usage_reports")

backend/alembic/versions/bceb1e139447_add_base_url_to_cloudembeddingprovider.py

@@ -1,26 +0,0 @@
-"""Add base_url to CloudEmbeddingProvider
-
-Revision ID: bceb1e139447
-Revises: a3795dce87be
-Create Date: 2024-08-28 17:00:52.554580
-
-"""
-from alembic import op
-import sqlalchemy as sa
-
-
-# revision identifiers, used by Alembic.
-revision = "bceb1e139447"
-down_revision = "a3795dce87be"
-branch_labels: None = None
-depends_on: None = None
-
-
-def upgrade() -> None:
-    op.add_column(
-        "embedding_provider", sa.Column("api_url", sa.String(), nullable=True)
-    )
-
-
-def downgrade() -> None:
-    op.drop_column("embedding_provider", "api_url")

backend/alembic/versions/bd2921608c3a_non_nullable_default_persona.py

@@ -1,43 +0,0 @@
-"""non nullable default persona
-
-Revision ID: bd2921608c3a
-Revises: 797089dfb4d2
-Create Date: 2024-09-20 10:28:37.992042
-
-"""
-from alembic import op
-import sqlalchemy as sa
-
-
-# revision identifiers, used by Alembic.
-revision = "bd2921608c3a"
-down_revision = "797089dfb4d2"
-branch_labels = None
-depends_on = None
-
-
-def upgrade() -> None:
-    # Set existing NULL values to False
-    op.execute(
-        "UPDATE persona SET is_default_persona = FALSE WHERE is_default_persona IS NULL"
-    )
-
-    # Alter the column to be not nullable with a default value of False
-    op.alter_column(
-        "persona",
-        "is_default_persona",
-        existing_type=sa.Boolean(),
-        nullable=False,
-        server_default=sa.text("false"),
-    )
-
-
-def downgrade() -> None:
-    # Revert the changes
-    op.alter_column(
-        "persona",
-        "is_default_persona",
-        existing_type=sa.Boolean(),
-        nullable=True,
-        server_default=None,
-    )

backend/alembic/versions/c18cdf4b497e_add_standard_answer_tables.py

@@ -1,75 +0,0 @@
-"""Add standard_answer tables
-
-Revision ID: c18cdf4b497e
-Revises: 3a7802814195
-Create Date: 2024-06-06 15:15:02.000648
-
-"""
-from alembic import op
-import sqlalchemy as sa
-
-# revision identifiers, used by Alembic.
-revision = "c18cdf4b497e"
-down_revision = "3a7802814195"
-branch_labels: None = None
-depends_on: None = None
-
-
-def upgrade() -> None:
-    op.create_table(
-        "standard_answer",
-        sa.Column("id", sa.Integer(), nullable=False),
-        sa.Column("keyword", sa.String(), nullable=False),
-        sa.Column("answer", sa.String(), nullable=False),
-        sa.Column("active", sa.Boolean(), nullable=False),
-        sa.PrimaryKeyConstraint("id"),
-        sa.UniqueConstraint("keyword"),
-    )
-    op.create_table(
-        "standard_answer_category",
-        sa.Column("id", sa.Integer(), nullable=False),
-        sa.Column("name", sa.String(), nullable=False),
-        sa.PrimaryKeyConstraint("id"),
-        sa.UniqueConstraint("name"),
-    )
-    op.create_table(
-        "standard_answer__standard_answer_category",
-        sa.Column("standard_answer_id", sa.Integer(), nullable=False),
-        sa.Column("standard_answer_category_id", sa.Integer(), nullable=False),
-        sa.ForeignKeyConstraint(
-            ["standard_answer_category_id"],
-            ["standard_answer_category.id"],
-        ),
-        sa.ForeignKeyConstraint(
-            ["standard_answer_id"],
-            ["standard_answer.id"],
-        ),
-        sa.PrimaryKeyConstraint("standard_answer_id", "standard_answer_category_id"),
-    )
-    op.create_table(
-        "slack_bot_config__standard_answer_category",
-        sa.Column("slack_bot_config_id", sa.Integer(), nullable=False),
-        sa.Column("standard_answer_category_id", sa.Integer(), nullable=False),
-        sa.ForeignKeyConstraint(
-            ["slack_bot_config_id"],
-            ["slack_bot_config.id"],
-        ),
-        sa.ForeignKeyConstraint(
-            ["standard_answer_category_id"],
-            ["standard_answer_category.id"],
-        ),
-        sa.PrimaryKeyConstraint("slack_bot_config_id", "standard_answer_category_id"),
-    )
-
-    op.add_column(
-        "chat_session", sa.Column("slack_thread_id", sa.String(), nullable=True)
-    )
-
-
-def downgrade() -> None:
-    op.drop_column("chat_session", "slack_thread_id")
-
-    op.drop_table("slack_bot_config__standard_answer_category")
-    op.drop_table("standard_answer__standard_answer_category")
-    op.drop_table("standard_answer_category")
-    op.drop_table("standard_answer")

backend/alembic/versions/c5b692fa265c_add_index_attempt_errors_table.py

@@ -1,57 +0,0 @@
-"""Add index_attempt_errors table
-
-Revision ID: c5b692fa265c
-Revises: 4a951134c801
-Create Date: 2024-08-08 14:06:39.581972
-
-"""
-from alembic import op
-import sqlalchemy as sa
-from sqlalchemy.dialects import postgresql
-
-# revision identifiers, used by Alembic.
-revision = "c5b692fa265c"
-down_revision = "4a951134c801"
-branch_labels: None = None
-depends_on: None = None
-
-
-def upgrade() -> None:
-    op.create_table(
-        "index_attempt_errors",
-        sa.Column("id", sa.Integer(), nullable=False),
-        sa.Column("index_attempt_id", sa.Integer(), nullable=True),
-        sa.Column("batch", sa.Integer(), nullable=True),
-        sa.Column(
-            "doc_summaries",
-            postgresql.JSONB(astext_type=sa.Text()),
-            nullable=False,
-        ),
-        sa.Column("error_msg", sa.Text(), nullable=True),
-        sa.Column("traceback", sa.Text(), nullable=True),
-        sa.Column(
-            "time_created",
-            sa.DateTime(timezone=True),
-            server_default=sa.text("now()"),
-            nullable=False,
-        ),
-        sa.ForeignKeyConstraint(
-            ["index_attempt_id"],
-            ["index_attempt.id"],
-        ),
-        sa.PrimaryKeyConstraint("id"),
-    )
-    op.create_index(
-        "index_attempt_id",
-        "index_attempt_errors",
-        ["time_created"],
-        unique=False,
-    )
-    # ### end Alembic commands ###
-
-
-def downgrade() -> None:
-    # ### commands auto generated by Alembic - please adjust! ###
-    op.drop_index("index_attempt_id", table_name="index_attempt_errors")
-    op.drop_table("index_attempt_errors")
-    # ### end Alembic commands ###

backend/alembic/versions/c99d76fcd298_add_nullable_to_persona_id_in_chat_.py

@@ -1,31 +0,0 @@
-"""add nullable to persona id in Chat Session
-
-Revision ID: c99d76fcd298
-Revises: 5c7fdadae813
-Create Date: 2024-07-09 19:27:01.579697
-
-"""
-
-from alembic import op
-import sqlalchemy as sa
-
-# revision identifiers, used by Alembic.
-revision = "c99d76fcd298"
-down_revision = "5c7fdadae813"
-branch_labels = None
-depends_on = None
-
-
-def upgrade() -> None:
-    op.alter_column(
-        "chat_session", "persona_id", existing_type=sa.INTEGER(), nullable=True
-    )
-
-
-def downgrade() -> None:
-    op.alter_column(
-        "chat_session",
-        "persona_id",
-        existing_type=sa.INTEGER(),
-        nullable=False,
-    )

backend/alembic/versions/d5645c915d0e_remove_deletion_attempt_table.py

@@ -19,9 +19,6 @@ depends_on: None = None
 def upgrade() -> None:
     op.drop_table("deletion_attempt")
 
-    # Remove the DeletionStatus enum
-    op.execute("DROP TYPE IF EXISTS deletionstatus;")
-
 
 def downgrade() -> None:
     op.create_table(

backend/alembic/versions/d716b0791ddd_combined_slack_id_fields.py

@@ -1,45 +0,0 @@
-"""combined slack id fields
-
-Revision ID: d716b0791ddd
-Revises: 7aea705850d5
-Create Date: 2024-07-10 17:57:45.630550
-
-"""
-from alembic import op
-
-# revision identifiers, used by Alembic.
-revision = "d716b0791ddd"
-down_revision = "7aea705850d5"
-branch_labels: None = None
-depends_on: None = None
-
-
-def upgrade() -> None:
-    op.execute(
-        """
-    UPDATE slack_bot_config
-    SET channel_config = jsonb_set(
-        channel_config,
-        '{respond_member_group_list}',
-        coalesce(channel_config->'respond_team_member_list', '[]'::jsonb) ||
-        coalesce(channel_config->'respond_slack_group_list', '[]'::jsonb)
-    ) - 'respond_team_member_list' - 'respond_slack_group_list'
-    """
-    )
-
-
-def downgrade() -> None:
-    op.execute(
-        """
-    UPDATE slack_bot_config
-    SET channel_config = jsonb_set(
-        jsonb_set(
-            channel_config - 'respond_member_group_list',
-            '{respond_team_member_list}',
-            '[]'::jsonb
-        ),
-        '{respond_slack_group_list}',
-        '[]'::jsonb
-    )
-    """
-    )

backend/alembic/versions/d9ec13955951_remove__dim_suffix_from_model_name.py

@@ -1,31 +0,0 @@
-"""Remove _alt suffix from model_name
-
-Revision ID: d9ec13955951
-Revises: da4c21c69164
-Create Date: 2024-08-20 16:31:32.955686
-
-"""
-
-from alembic import op
-
-
-# revision identifiers, used by Alembic.
-revision = "d9ec13955951"
-down_revision = "da4c21c69164"
-branch_labels: None = None
-depends_on: None = None
-
-
-def upgrade() -> None:
-    op.execute(
-        """
-        UPDATE embedding_model
-        SET model_name = regexp_replace(model_name, '__danswer_alt_index$', '')
-        WHERE model_name LIKE '%__danswer_alt_index'
-    """
-    )
-
-
-def downgrade() -> None:
-    # We can't reliably add the __danswer_alt_index suffix back, so we'll leave this empty
-    pass

backend/alembic/versions/da4c21c69164_chosen_assistants_changed_to_jsonb.py

@@ -1,65 +0,0 @@
-"""chosen_assistants changed to jsonb
-
-Revision ID: da4c21c69164
-Revises: c5b692fa265c
-Create Date: 2024-08-18 19:06:47.291491
-
-"""
-import json
-from alembic import op
-import sqlalchemy as sa
-from sqlalchemy.dialects import postgresql
-
-# revision identifiers, used by Alembic.
-revision = "da4c21c69164"
-down_revision = "c5b692fa265c"
-branch_labels: None = None
-depends_on: None = None
-
-
-def upgrade() -> None:
-    conn = op.get_bind()
-    existing_ids_and_chosen_assistants = conn.execute(
-        sa.text('select id, chosen_assistants from "user"')
-    )
-    op.drop_column(
-        "user",
-        "chosen_assistants",
-    )
-    op.add_column(
-        "user",
-        sa.Column(
-            "chosen_assistants",
-            postgresql.JSONB(astext_type=sa.Text()),
-            nullable=True,
-        ),
-    )
-    for id, chosen_assistants in existing_ids_and_chosen_assistants:
-        conn.execute(
-            sa.text(
-                'update "user" set chosen_assistants = :chosen_assistants where id = :id'
-            ),
-            {"chosen_assistants": json.dumps(chosen_assistants), "id": id},
-        )
-
-
-def downgrade() -> None:
-    conn = op.get_bind()
-    existing_ids_and_chosen_assistants = conn.execute(
-        sa.text('select id, chosen_assistants from "user"')
-    )
-    op.drop_column(
-        "user",
-        "chosen_assistants",
-    )
-    op.add_column(
-        "user",
-        sa.Column("chosen_assistants", postgresql.ARRAY(sa.Integer()), nullable=True),
-    )
-    for id, chosen_assistants in existing_ids_and_chosen_assistants:
-        conn.execute(
-            sa.text(
-                'update "user" set chosen_assistants = :chosen_assistants where id = :id'
-            ),
-            {"chosen_assistants": chosen_assistants, "id": id},
-        )

backend/alembic/versions/dbaa756c2ccf_embedding_models.py

@@ -9,7 +9,7 @@ from alembic import op
 import sqlalchemy as sa
 from sqlalchemy import table, column, String, Integer, Boolean
 
-from danswer.db.search_settings import (
+from danswer.db.embedding_model import (
     get_new_default_embedding_model,
     get_old_default_embedding_model,
     user_has_overridden_embedding_model,
@@ -71,14 +71,14 @@ def upgrade() -> None:
                 "query_prefix": old_embedding_model.query_prefix,
                 "passage_prefix": old_embedding_model.passage_prefix,
                 "index_name": old_embedding_model.index_name,
-                "status": IndexModelStatus.PRESENT,
+                "status": old_embedding_model.status,
             }
         ],
     )
     # if the user has not overridden the default embedding model via env variables,
     # insert the new default model into the database to auto-upgrade them
     if not user_has_overridden_embedding_model():
-        new_embedding_model = get_new_default_embedding_model()
+        new_embedding_model = get_new_default_embedding_model(is_present=False)
         op.bulk_insert(
             EmbeddingModel,
             [
@@ -136,4 +136,4 @@ def downgrade() -> None:
     )
     op.drop_column("index_attempt", "embedding_model_id")
     op.drop_table("embedding_model")
-    op.execute("DROP TYPE IF EXISTS indexmodelstatus;")
+    op.execute("DROP TYPE indexmodelstatus;")

backend/alembic/versions/e1392f05e840_added_input_prompts.py

@@ -1,58 +0,0 @@
-"""Added input prompts
-
-Revision ID: e1392f05e840
-Revises: 08a1eda20fe1
-Create Date: 2024-07-13 19:09:22.556224
-
-"""
-
-import fastapi_users_db_sqlalchemy
-
-from alembic import op
-import sqlalchemy as sa
-
-# revision identifiers, used by Alembic.
-revision = "e1392f05e840"
-down_revision = "08a1eda20fe1"
-branch_labels: None = None
-depends_on: None = None
-
-
-def upgrade() -> None:
-    op.create_table(
-        "inputprompt",
-        sa.Column("id", sa.Integer(), autoincrement=True, nullable=False),
-        sa.Column("prompt", sa.String(), nullable=False),
-        sa.Column("content", sa.String(), nullable=False),
-        sa.Column("active", sa.Boolean(), nullable=False),
-        sa.Column("is_public", sa.Boolean(), nullable=False),
-        sa.Column(
-            "user_id",
-            fastapi_users_db_sqlalchemy.generics.GUID(),
-            nullable=True,
-        ),
-        sa.ForeignKeyConstraint(
-            ["user_id"],
-            ["user.id"],
-        ),
-        sa.PrimaryKeyConstraint("id"),
-    )
-    op.create_table(
-        "inputprompt__user",
-        sa.Column("input_prompt_id", sa.Integer(), nullable=False),
-        sa.Column("user_id", sa.Integer(), nullable=False),
-        sa.ForeignKeyConstraint(
-            ["input_prompt_id"],
-            ["inputprompt.id"],
-        ),
-        sa.ForeignKeyConstraint(
-            ["user_id"],
-            ["inputprompt.id"],
-        ),
-        sa.PrimaryKeyConstraint("input_prompt_id", "user_id"),
-    )
-
-
-def downgrade() -> None:
-    op.drop_table("inputprompt__user")
-    op.drop_table("inputprompt")

backend/alembic/versions/e209dc5a8156_added_prune_frequency.py

@@ -1,22 +0,0 @@
-"""added-prune-frequency
-
-Revision ID: e209dc5a8156
-Revises: 48d14957fe80
-Create Date: 2024-06-16 16:02:35.273231
-
-"""
-from alembic import op
-import sqlalchemy as sa
-
-revision = "e209dc5a8156"
-down_revision = "48d14957fe80"
-branch_labels = None  # type: ignore
-depends_on = None  # type: ignore
-
-
-def upgrade() -> None:
-    op.add_column("connector", sa.Column("prune_freq", sa.Integer(), nullable=True))
-
-
-def downgrade() -> None:
-    op.drop_column("connector", "prune_freq")

backend/alembic/versions/e4334d5b33ba_add_deployment_name_to_llmprovider.py

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

backend/alembic/versions/ec85f2b3c544_remove_last_attempt_status_from_cc_pair.py

@@ -1,31 +0,0 @@
-"""Remove Last Attempt Status from CC Pair
-
-Revision ID: ec85f2b3c544
-Revises: 3879338f8ba1
-Create Date: 2024-05-23 21:39:46.126010
-
-"""
-from alembic import op
-import sqlalchemy as sa
-
-# revision identifiers, used by Alembic.
-revision = "ec85f2b3c544"
-down_revision = "70f00c45c0f2"
-branch_labels: None = None
-depends_on: None = None
-
-
-def upgrade() -> None:
-    op.drop_column("connector_credential_pair", "last_attempt_status")
-
-
-def downgrade() -> None:
-    op.add_column(
-        "connector_credential_pair",
-        sa.Column(
-            "last_attempt_status",
-            sa.VARCHAR(),
-            autoincrement=False,
-            nullable=True,
-        ),
-    )

backend/alembic/versions/ee3f4b47fad5_added_alternate_model_to_chat_message.py

@@ -1,28 +0,0 @@
-"""Added alternate model to chat message
-
-Revision ID: ee3f4b47fad5
-Revises: 2d2304e27d8c
-Create Date: 2024-08-12 00:11:50.915845
-
-"""
-
-from alembic import op
-import sqlalchemy as sa
-
-
-# revision identifiers, used by Alembic.
-revision = "ee3f4b47fad5"
-down_revision = "2d2304e27d8c"
-branch_labels: None = None
-depends_on: None = None
-
-
-def upgrade() -> None:
-    op.add_column(
-        "chat_message",
-        sa.Column("overridden_model", sa.String(length=255), nullable=True),
-    )
-
-
-def downgrade() -> None:
-    op.drop_column("chat_message", "overridden_model")

backend/alembic/versions/efb35676026c_standard_answer_match_regex_flag.py

@@ -1,32 +0,0 @@
-"""standard answer match_regex flag
-
-Revision ID: efb35676026c
-Revises: 0ebb1d516877
-Create Date: 2024-09-11 13:55:46.101149
-
-"""
-from alembic import op
-import sqlalchemy as sa
-
-# revision identifiers, used by Alembic.
-revision = "efb35676026c"
-down_revision = "0ebb1d516877"
-branch_labels = None
-depends_on = None
-
-
-def upgrade() -> None:
-    # ### commands auto generated by Alembic - please adjust! ###
-    op.add_column(
-        "standard_answer",
-        sa.Column(
-            "match_regex", 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_regex")
-    # ### end Alembic commands ###

backend/alembic/versions/f17bf3b0d9f1_embedding_provider_by_provider_type.py

@@ -1,172 +0,0 @@
-"""embedding provider by provider type
-
-Revision ID: f17bf3b0d9f1
-Revises: 351faebd379d
-Create Date: 2024-08-21 13:13:31.120460
-
-"""
-
-from alembic import op
-import sqlalchemy as sa
-
-
-# revision identifiers, used by Alembic.
-revision = "f17bf3b0d9f1"
-down_revision = "351faebd379d"
-branch_labels: None = None
-depends_on: None = None
-
-
-def upgrade() -> None:
-    # Add provider_type column to embedding_provider
-    op.add_column(
-        "embedding_provider",
-        sa.Column("provider_type", sa.String(50), nullable=True),
-    )
-
-    # Update provider_type with existing name values
-    op.execute("UPDATE embedding_provider SET provider_type = UPPER(name)")
-
-    # Make provider_type not nullable
-    op.alter_column("embedding_provider", "provider_type", nullable=False)
-
-    # Drop the foreign key constraint in embedding_model table
-    op.drop_constraint(
-        "fk_embedding_model_cloud_provider", "embedding_model", type_="foreignkey"
-    )
-
-    # Drop the existing primary key constraint
-    op.drop_constraint("embedding_provider_pkey", "embedding_provider", type_="primary")
-
-    # Create a new primary key constraint on provider_type
-    op.create_primary_key(
-        "embedding_provider_pkey", "embedding_provider", ["provider_type"]
-    )
-
-    # Add provider_type column to embedding_model
-    op.add_column(
-        "embedding_model",
-        sa.Column("provider_type", sa.String(50), nullable=True),
-    )
-
-    # Update provider_type for existing embedding models
-    op.execute(
-        """
-        UPDATE embedding_model
-        SET provider_type = (
-            SELECT provider_type
-            FROM embedding_provider
-            WHERE embedding_provider.id = embedding_model.cloud_provider_id
-        )
-    """
-    )
-
-    # Drop the old id column from embedding_provider
-    op.drop_column("embedding_provider", "id")
-
-    # Drop the name column from embedding_provider
-    op.drop_column("embedding_provider", "name")
-
-    # Drop the default_model_id column from embedding_provider
-    op.drop_column("embedding_provider", "default_model_id")
-
-    # Drop the old cloud_provider_id column from embedding_model
-    op.drop_column("embedding_model", "cloud_provider_id")
-
-    # Create the new foreign key constraint
-    op.create_foreign_key(
-        "fk_embedding_model_cloud_provider",
-        "embedding_model",
-        "embedding_provider",
-        ["provider_type"],
-        ["provider_type"],
-    )
-
-
-def downgrade() -> None:
-    # Drop the foreign key constraint in embedding_model table
-    op.drop_constraint(
-        "fk_embedding_model_cloud_provider", "embedding_model", type_="foreignkey"
-    )
-
-    # Add back the cloud_provider_id column to embedding_model
-    op.add_column(
-        "embedding_model", sa.Column("cloud_provider_id", sa.Integer(), nullable=True)
-    )
-    op.add_column("embedding_provider", sa.Column("id", sa.Integer(), nullable=True))
-
-    # Assign incrementing IDs to embedding providers
-    op.execute(
-        """
-        CREATE SEQUENCE IF NOT EXISTS embedding_provider_id_seq;"""
-    )
-    op.execute(
-        """
-        UPDATE embedding_provider SET id = nextval('embedding_provider_id_seq');
-    """
-    )
-
-    # Update cloud_provider_id based on provider_type
-    op.execute(
-        """
-        UPDATE embedding_model
-        SET cloud_provider_id = CASE
-            WHEN provider_type IS NULL THEN NULL
-            ELSE (
-                SELECT id
-                FROM embedding_provider
-                WHERE embedding_provider.provider_type = embedding_model.provider_type
-            )
-        END
-    """
-    )
-
-    # Drop the provider_type column from embedding_model
-    op.drop_column("embedding_model", "provider_type")
-
-    # Add back the columns to embedding_provider
-    op.add_column("embedding_provider", sa.Column("name", sa.String(50), nullable=True))
-    op.add_column(
-        "embedding_provider", sa.Column("default_model_id", sa.Integer(), nullable=True)
-    )
-
-    # Drop the existing primary key constraint on provider_type
-    op.drop_constraint("embedding_provider_pkey", "embedding_provider", type_="primary")
-
-    # Create the original primary key constraint on id
-    op.create_primary_key("embedding_provider_pkey", "embedding_provider", ["id"])
-
-    # Update name with existing provider_type values
-    op.execute(
-        """
-        UPDATE embedding_provider
-        SET name = CASE
-            WHEN provider_type = 'OPENAI' THEN 'OpenAI'
-            WHEN provider_type = 'COHERE' THEN 'Cohere'
-            WHEN provider_type = 'GOOGLE' THEN 'Google'
-            WHEN provider_type = 'VOYAGE' THEN 'Voyage'
-            ELSE provider_type
-        END
-    """
-    )
-
-    # Drop the provider_type column from embedding_provider
-    op.drop_column("embedding_provider", "provider_type")
-
-    # Recreate the foreign key constraint in embedding_model table
-    op.create_foreign_key(
-        "fk_embedding_model_cloud_provider",
-        "embedding_model",
-        "embedding_provider",
-        ["cloud_provider_id"],
-        ["id"],
-    )
-
-    # Recreate the foreign key constraint in embedding_model table
-    op.create_foreign_key(
-        "fk_embedding_provider_default_model",
-        "embedding_provider",
-        "embedding_model",
-        ["default_model_id"],
-        ["id"],
-    )

backend/alembic/versions/f32615f71aeb_add_custom_headers_to_tools.py

@@ -1,26 +0,0 @@
-"""add custom headers to tools
-
-Revision ID: f32615f71aeb
-Revises: bd2921608c3a
-Create Date: 2024-09-12 20:26:38.932377
-
-"""
-from alembic import op
-import sqlalchemy as sa
-from sqlalchemy.dialects import postgresql
-
-# revision identifiers, used by Alembic.
-revision = "f32615f71aeb"
-down_revision = "bd2921608c3a"
-branch_labels = None
-depends_on = None
-
-
-def upgrade() -> None:
-    op.add_column(
-        "tool", sa.Column("custom_headers", postgresql.JSONB(), nullable=True)
-    )
-
-
-def downgrade() -> None:
-    op.drop_column("tool", "custom_headers")