error -> warning + clean

* first cut at redis

* some new helper functions for the db

* ignore kombu tables in alembic migrations (used by celery)

* multiline commands for readability, add vespa_metadata_sync queue to worker

* typo fix

* fix returning tuple fields

* add constants

* fix _get_access_for_document

* docstrings!

* fix double function declaration and typing

* fix type hinting

* add a global redis pool

* Add get_document function

* use task_logger in various celery tasks

* add celeryconfig.py to simplify configuration. Will be used in a subsequent commit

* Add celery redis helper. used in a subsequent PR

* kombu warning getting spammy since celery is not self managing its queue in Postgres any more

* add last_modified and last_synced to documents

* fix task naming convention

* use celeryconfig.py

* the big one. adds queues and tasks, updates functions to use the queues with priorities, etc

* change vespa index log line to debug

* mypy fixes

* update alembic migration

* fix fence ordering, rename to "monitor", fix fetch_versioned_implementation call

* mypy

* switch to monotonic time

* fix startup dependencies on redis

* rebase alembic migration

* kombu cleanup - fail silently

* mypy

* add redis_host environment override

* update REDIS_HOST env var in docker-compose.dev.yml

* update the rest of the docker files

* in flight

* harden indexing-status endpoint against db changes happening in the background.  Needs further improvement but OK for now.

* allow no task syncs to run because we create certain objects with no entries but initially marked as out of date

* add back writing to vespa on indexing

* actually working connector deletion

* update contributing guide

* backporting fixes from background_deletion

* renaming cache to cache_volume

* add redis password to various deployments

* try setting up pr testing for helm

* fix indent

* hopefully this release version actually exists

* fix command line option to --chart-dirs

* fetch-depth 0

* edit values.yaml

* try setting ct working directory

* bypass testing only on change for now

* move files and lint them

* update helm testing

* some issues suggest using --config works

* add vespa repo

* add postgresql repo

* increase timeout

* try amd64 runner

* fix redis password reference

* add comment to helm chart testing workflow

* rename helm testing workflow to disable it

* adding clarifying comments

* address code review

* missed a file

* remove commented warning ... just not needed

* fix imports

* refactor to use update_single

* mypy fixes

* add vespa test

* multiple celery workers

* update logs as well and set prefetch multipliers appropriate to the worker intent

* add db refresh to connector deletion

* add some preliminary locking

* organize tasks into separate files

* celery auto associates tasks created inside another task, which bloats the result metadata considerably. trail=False prevents this.

* code review fixes

* move monitor_usergroup_taskset to ee, improve logging

* add multi workers to dev_run_background_jobs.py

* update supervisord with some recommended settings for celery

* name celery workers and shorten dev script prefixing

* add configurable sql alchemy engine settings on startup (needed for various intents like API server, different celery workers and tasks, etc)

* fix comments

* autoscale sqlalchemy pool size to celery concurrency (allow override later?)

* supervisord needs the percent symbols escaped

* use name as primary check, some minor refactoring and type hinting too.

* stash merge (may not function yet)

* remove dead code

* more cleanup

* remove dead file

* we shouldn't be checking for deletion attempts in the db any more

* print cc_pair_id

* print status on status mismatch again

* add logging when cc_pair isn't present

* don't indexing any ingestion type connectors, and don't pause any connectors that aren't active

* add more specific check for deletion completion

* remove flaky mediawiki test site

* move is_pruning

* remove unused code

* remove old function

---------

Co-authored-by: Richard Kuo <rkuo@rkuo.com>

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

@@ -0,0 +1,76 @@
+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 retry in seconds'
+    required: false
+    default: '5'
+
+runs:
+  using: "composite"
+  steps:
+    - name: Build and push Docker image (First Attempt)
+      id: buildx1
+      uses: docker/build-push-action@v5
+      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 to retry
+      if: steps.buildx1.outcome != 'success'
+      run: |
+        echo "First attempt failed. Waiting ${{ inputs.retry-wait-time }} seconds before retry..."
+        sleep ${{ inputs.retry-wait-time }}
+      shell: bash
+
+    - name: Build and push Docker image (Retry Attempt)
+      if: steps.buildx1.outcome != 'success'
+      uses: docker/build-push-action@v5
+      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 }}

.github/pull_request_template.md

@@ -0,0 +1,25 @@
+## 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
+[Any know risks or failure modes to point out to reviewers]
+
+
+## Related Issue(s)
+[If applicable, link to the issue(s) this PR addresses]
+
+
+## Checklist:
+- [ ] All of the automated tests pass
+- [ ] All PR comments are addressed and marked resolved
+- [ ] If there are migrations, they have been rebased to latest main
+- [ ] If there are new dependencies, they are added to the requirements
+- [ ] If there are new environment variables, they are added to all of the deployment methods
+- [ ] If there are new APIs that don't require auth, they are added to PUBLIC_ENDPOINT_SPECS
+- [ ] Docker images build and basic functionalities work
+- [ ] Author has done a final read through of the PR right before merge

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

@@ -5,40 +5,59 @@ on:
     tags:
       - '*'
 
+env:
+  REGISTRY_IMAGE: danswer/danswer-backend
+  LATEST_TAG: ${{ contains(github.ref_name, 'latest') }}
+  
 jobs:
   build-and-push:
-    runs-on: ubuntu-latest
+    # TODO: investigate a matrix build like the web container 
+    # See https://runs-on.com/runners/linux/
+    runs-on: [runs-on,runner=8cpu-linux-x64,"run-id=${{ github.run_id }}"]
 
     steps:
     - name: Checkout code
-      uses: actions/checkout@v2
+      uses: actions/checkout@v4
 
     - name: Set up Docker Buildx
-      uses: docker/setup-buildx-action@v1
+      uses: docker/setup-buildx-action@v3
 
     - name: Login to Docker Hub
-      uses: docker/login-action@v1
+      uses: docker/login-action@v3
       with:
         username: ${{ secrets.DOCKER_USERNAME }}
         password: ${{ secrets.DOCKER_TOKEN }}
 
+    - name: Install build-essential
+      run: |
+        sudo apt-get update
+        sudo apt-get install -y build-essential
+          
     - name: Backend Image Docker Build and Push
-      uses: docker/build-push-action@v2
+      uses: docker/build-push-action@v5
       with:
         context: ./backend
         file: ./backend/Dockerfile
         platforms: linux/amd64,linux/arm64
         push: true
         tags: |
-          danswer/danswer-backend:${{ github.ref_name }}
-          danswer/danswer-backend:latest
+          ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
+          ${{ env.LATEST_TAG == 'true' && format('{0}:latest', env.REGISTRY_IMAGE) || '' }}
         build-args: |
           DANSWER_VERSION=${{ github.ref_name }}
 
+    # trivy has their own rate limiting issues causing this action to flake
+    # we worked around it by hardcoding to different db repos in env
+    # can re-enable when they figure it out
+    # https://github.com/aquasecurity/trivy/discussions/7538
+    # https://github.com/aquasecurity/trivy-action/issues/389
     - name: Run Trivy vulnerability scanner
       uses: aquasecurity/trivy-action@master
+      env:
+        TRIVY_DB_REPOSITORY: 'public.ecr.aws/aquasecurity/trivy-db:2'
+        TRIVY_JAVA_DB_REPOSITORY: 'public.ecr.aws/aquasecurity/trivy-java-db:1'
       with:
         # To run locally: trivy image --severity HIGH,CRITICAL danswer/danswer-backend
-        image-ref: docker.io/danswer/danswer-backend:${{ github.ref_name }}
+        image-ref: docker.io/${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
         severity: 'CRITICAL,HIGH'
         trivyignores: ./backend/.trivyignore

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

@@ -5,38 +5,51 @@ on:
     tags:
       - '*'
 
+env:
+  REGISTRY_IMAGE: danswer/danswer-model-server
+  LATEST_TAG: ${{ contains(github.ref_name, 'latest') }}
+  
 jobs:
   build-and-push:
-    runs-on: ubuntu-latest
+    # See https://runs-on.com/runners/linux/
+    runs-on: [runs-on,runner=8cpu-linux-x64,"run-id=${{ github.run_id }}"]
 
     steps:
     - name: Checkout code
-      uses: actions/checkout@v2
+      uses: actions/checkout@v4
 
     - name: Set up Docker Buildx
-      uses: docker/setup-buildx-action@v1
+      uses: docker/setup-buildx-action@v3
 
     - name: Login to Docker Hub
-      uses: docker/login-action@v1
+      uses: docker/login-action@v3
       with:
         username: ${{ secrets.DOCKER_USERNAME }}
         password: ${{ secrets.DOCKER_TOKEN }}
 
     - name: Model Server Image Docker Build and Push
-      uses: docker/build-push-action@v2
+      uses: docker/build-push-action@v5
       with:
         context: ./backend
         file: ./backend/Dockerfile.model_server
         platforms: linux/amd64,linux/arm64
         push: true
         tags: |
-          danswer/danswer-model-server:${{ github.ref_name }}
-          danswer/danswer-model-server:latest
+          ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
+          ${{ env.LATEST_TAG == 'true' && format('{0}:latest', env.REGISTRY_IMAGE) || '' }}
         build-args: |
           DANSWER_VERSION=${{ github.ref_name }}
 
+    # trivy has their own rate limiting issues causing this action to flake
+    # we worked around it by hardcoding to different db repos in env
+    # can re-enable when they figure it out
+    # https://github.com/aquasecurity/trivy/discussions/7538
+    # https://github.com/aquasecurity/trivy-action/issues/389
     - name: Run Trivy vulnerability scanner
       uses: aquasecurity/trivy-action@master
+      env:
+        TRIVY_DB_REPOSITORY: 'public.ecr.aws/aquasecurity/trivy-db:2'
+        TRIVY_JAVA_DB_REPOSITORY: 'public.ecr.aws/aquasecurity/trivy-java-db:1'
       with:
         image-ref: docker.io/danswer/danswer-model-server:${{ github.ref_name }}
         severity: 'CRITICAL,HIGH'

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

@@ -5,38 +5,124 @@ on:
     tags:
       - '*'
 
+env:
+  REGISTRY_IMAGE: danswer/danswer-web-server
+  LATEST_TAG: ${{ contains(github.ref_name, 'latest') }}
+  
 jobs:
-  build-and-push:
-    runs-on: ubuntu-latest
+  build:
+    runs-on: 
+      group: ${{ matrix.platform == 'linux/amd64' && 'amd64-image-builders' || 'arm64-image-builders' }}
+    strategy:
+      fail-fast: false
+      matrix:
+        platform:
+          - linux/amd64
+          - linux/arm64
 
     steps:
-    - name: Checkout code
-      uses: actions/checkout@v2
+      - name: Prepare
+        run: |
+          platform=${{ matrix.platform }}
+          echo "PLATFORM_PAIR=${platform//\//-}" >> $GITHUB_ENV          
+      
+      - name: Checkout
+        uses: actions/checkout@v4
+      
+      - name: Docker meta
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.REGISTRY_IMAGE }}
+          tags: |
+            type=raw,value=${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
+            type=raw,value=${{ env.LATEST_TAG == 'true' && format('{0}:latest', env.REGISTRY_IMAGE) || '' }}
+      
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+      
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_TOKEN }}
+    
+      - name: Build and push by digest
+        id: build
+        uses: docker/build-push-action@v5
+        with:
+          context: ./web
+          file: ./web/Dockerfile
+          platforms: ${{ matrix.platform }}
+          push: true
+          build-args: |
+            DANSWER_VERSION=${{ github.ref_name }}
+          # needed due to weird interactions with the builds for different platforms  
+          no-cache: true
+          labels: ${{ steps.meta.outputs.labels }}
+          outputs: type=image,name=${{ env.REGISTRY_IMAGE }},push-by-digest=true,name-canonical=true,push=true
+      
+      - name: Export digest
+        run: |
+          mkdir -p /tmp/digests
+          digest="${{ steps.build.outputs.digest }}"
+          touch "/tmp/digests/${digest#sha256:}"          
+      
+      - name: Upload digest
+        uses: actions/upload-artifact@v4
+        with:
+          name: digests-${{ env.PLATFORM_PAIR }}
+          path: /tmp/digests/*
+          if-no-files-found: error
+          retention-days: 1
 
-    - name: Set up Docker Buildx
-      uses: docker/setup-buildx-action@v1
+  merge:
+    runs-on: ubuntu-latest
+    needs:
+      - build
+    steps:
+      - name: Download digests
+        uses: actions/download-artifact@v4
+        with:
+          path: /tmp/digests
+          pattern: digests-*
+          merge-multiple: true
+      
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+      
+      - name: Docker meta
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.REGISTRY_IMAGE }}
+      
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_TOKEN }}
+      
+      - name: Create manifest list and push
+        working-directory: /tmp/digests
+        run: |
+          docker buildx imagetools create $(jq -cr '.tags | map("-t " + .) | join(" ")' <<< "$DOCKER_METADATA_OUTPUT_JSON") \
+            $(printf '${{ env.REGISTRY_IMAGE }}@sha256:%s ' *)          
+      
+      - name: Inspect image
+        run: |
+          docker buildx imagetools inspect ${{ env.REGISTRY_IMAGE }}:${{ steps.meta.outputs.version }}
 
-    - name: Login to Docker Hub
-      uses: docker/login-action@v1
-      with:
-        username: ${{ secrets.DOCKER_USERNAME }}
-        password: ${{ secrets.DOCKER_TOKEN }}
-
-    - name: Web Image Docker Build and Push
-      uses: docker/build-push-action@v2
-      with:
-        context: ./web
-        file: ./web/Dockerfile
-        platforms: linux/amd64,linux/arm64
-        push: true
-        tags: |
-          danswer/danswer-web-server:${{ github.ref_name }}
-          danswer/danswer-web-server:latest
-        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'
+    # trivy has their own rate limiting issues causing this action to flake
+    # we worked around it by hardcoding to different db repos in env
+    # can re-enable when they figure it out
+    # https://github.com/aquasecurity/trivy/discussions/7538
+    # https://github.com/aquasecurity/trivy-action/issues/389
+      - name: Run Trivy vulnerability scanner
+        uses: aquasecurity/trivy-action@master
+        env:
+          TRIVY_DB_REPOSITORY: 'public.ecr.aws/aquasecurity/trivy-db:2'
+          TRIVY_JAVA_DB_REPOSITORY: 'public.ecr.aws/aquasecurity/trivy-java-db:1'
+        with:
+          image-ref: docker.io/${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
+          severity: 'CRITICAL,HIGH'

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

@@ -1,3 +1,6 @@
+# This workflow is set up to be manually triggered via the GitHub Action tab.
+# Given a version, it will tag those backend and webserver images as "latest".
+
 name: Tag Latest Version
 
 on:
@@ -9,7 +12,9 @@ on:
 
 jobs:
   tag:
-    runs-on: ubuntu-latest
+    # See https://runs-on.com/runners/linux/
+    # use a lower powered instance since this just does i/o to docker hub
+    runs-on: [runs-on,runner=2cpu-linux-x64,"run-id=${{ github.run_id }}"]
     steps:
     - name: Set up Docker Buildx
       uses: docker/setup-buildx-action@v1

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

@@ -0,0 +1,178 @@
+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=${{ env.RUNS_ON_S3_BUCKET_CACHE }},mode=max
+
+      - name: Start Docker containers
+        run: |
+          cd deployment/docker_compose
+          ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true \
+          AUTH_TYPE=basic \
+          REQUIRE_EMAIL_VERIFICATION=false \
+          DISABLE_TELEMETRY=true \
+          IMAGE_TAG=test \
+          docker compose -f docker-compose.dev.yml -p danswer-stack up -d
+        id: start_docker
+
+      - name: Wait for service to be ready
+        run: |
+          echo "Starting wait-for-service script..."
+          
+          docker logs -f danswer-stack-api_server-1 &
+
+          start_time=$(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 $response). Retrying in 5 seconds..."
+            fi
+            
+            sleep 5
+          done
+          echo "Finished waiting for service."
+
+      - name: Run integration tests
+        run: |
+          echo "Running integration tests..."
+          docker run --rm --network danswer-stack_default \
+            --name test-runner \
+            -e POSTGRES_HOST=relational_db \
+            -e POSTGRES_USER=postgres \
+            -e POSTGRES_PASSWORD=password \
+            -e POSTGRES_DB=postgres \
+            -e VESPA_HOST=index \
+            -e REDIS_HOST=cache \
+            -e API_SERVER_HOST=api_server \
+            -e OPENAI_API_KEY=${OPENAI_API_KEY} \
+            -e SLACK_BOT_TOKEN=${SLACK_BOT_TOKEN} \
+            -e TEST_WEB_HOSTNAME=test-runner \
+            danswer/danswer-integration:test
+        continue-on-error: true
+        id: run_tests
+
+      - name: Check test results
+        run: |
+          if [ ${{ steps.run_tests.outcome }} == 'failure' ]; then
+            echo "Integration tests failed. Exiting with error."
+            exit 1
+          else
+            echo "All integration tests passed successfully."
+          fi
+
+      - name: Save Docker logs
+        if: success() || failure()
+        run: |
+          cd deployment/docker_compose
+          docker compose -f docker-compose.dev.yml -p danswer-stack logs > docker-compose.log
+          mv docker-compose.log ${{ github.workspace }}/docker-compose.log
+      
+      - name: Upload logs
+        if: success() || failure()
+        uses: actions/upload-artifact@v3
+        with:
+          name: docker-logs
+          path: ${{ github.workspace }}/docker-compose.log
+
+      - name: Stop Docker containers
+        run: |
+          cd deployment/docker_compose
+          docker compose -f docker-compose.dev.yml -p danswer-stack down -v

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

@@ -0,0 +1,68 @@
+# 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

@@ -1,12 +1,16 @@
 name: Python Checks
 
 on:
+  merge_group:
   pull_request:
-    branches: [ main ]
+    branches:
+      - main
+      - 'release/**'
 
 jobs:
   mypy-check:
-    runs-on: ubuntu-latest
+    # See https://runs-on.com/runners/linux/
+    runs-on: [runs-on,runner=8cpu-linux-x64,"run-id=${{ github.run_id }}"]
 
     steps:
     - name: Checkout code
@@ -23,9 +27,9 @@ jobs:
           backend/requirements/model_server.txt
     - run: |
         python -m pip install --upgrade pip
-        pip install -r backend/requirements/default.txt
-        pip install -r backend/requirements/dev.txt
-        pip install -r backend/requirements/model_server.txt
+        pip install --retries 5 --timeout 30 -r backend/requirements/default.txt
+        pip install --retries 5 --timeout 30 -r backend/requirements/dev.txt
+        pip install --retries 5 --timeout 30 -r backend/requirements/model_server.txt
 
     - name: Run MyPy
       run: |

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

@@ -0,0 +1,61 @@
+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@v4
+        with:
+          python-version: "3.11"
+          cache: "pip"
+          cache-dependency-path: |
+            backend/requirements/default.txt
+            backend/requirements/dev.txt
+
+      - name: Install Dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install --retries 5 --timeout 30 -r backend/requirements/default.txt
+          pip install --retries 5 --timeout 30 -r backend/requirements/dev.txt
+
+      - name: Run Tests
+        shell: script -q -e -c "bash --noprofile --norc -eo pipefail {0}"
+        run: py.test -o junit_family=xunit2 -xv --ff backend/tests/daily/connectors
+
+      - name: Alert on Failure
+        if: failure() && github.event_name == 'schedule'
+        env:
+          SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
+        run: |
+          curl -X POST \
+            -H 'Content-type: application/json' \
+            --data '{"text":"Scheduled Connector Tests failed! Check the run at: https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}"}' \
+            $SLACK_WEBHOOK

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

@@ -0,0 +1,58 @@
+name: Connector Tests
+
+on:
+  schedule:
+    # This cron expression runs the job daily at 16:00 UTC (9am PT)
+    - cron: "0 16 * * *"
+
+env:
+  # Bedrock
+  AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
+  AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+  AWS_REGION_NAME: ${{ secrets.AWS_REGION_NAME }}
+
+  # OpenAI
+  OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+
+jobs:
+  connectors-check:
+    # See https://runs-on.com/runners/linux/
+    runs-on: [runs-on,runner=8cpu-linux-x64,"run-id=${{ github.run_id }}"]
+
+    env:
+      PYTHONPATH: ./backend
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        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

@@ -1,16 +1,21 @@
 name: Python Unit Tests
 
 on:
+  merge_group:
   pull_request:
-    branches: [ main ]
+    branches:
+      - main
+      - 'release/**'
 
 jobs:
   backend-check:
-    runs-on: ubuntu-latest
+    # See https://runs-on.com/runners/linux/
+    runs-on: [runs-on,runner=8cpu-linux-x64,"run-id=${{ github.run_id }}"]
 
     env:
       PYTHONPATH: ./backend
-
+      REDIS_CLOUD_PYTEST_PASSWORD: ${{ secrets.REDIS_CLOUD_PYTEST_PASSWORD }}
+      
     steps:
     - name: Checkout code
       uses: actions/checkout@v4
@@ -27,8 +32,8 @@ jobs:
     - name: Install Dependencies
       run: |
         python -m pip install --upgrade pip
-        pip install -r backend/requirements/default.txt
-        pip install -r backend/requirements/dev.txt
+        pip install --retries 5 --timeout 30 -r backend/requirements/default.txt
+        pip install --retries 5 --timeout 30 -r backend/requirements/dev.txt
 
     - name: Run Tests
       shell: script -q -e -c "bash --noprofile --norc -eo pipefail {0}"

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

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

.github/workflows/tag-nightly.yml

@@ -0,0 +1,54 @@
+name: Nightly Tag Push
+
+on:
+  schedule:
+    - cron: '0 10 * * *' # Runs every day at 2 AM PST / 3 AM PDT / 10 AM UTC
+
+permissions:
+  contents: write  # Allows pushing tags to the repository
+
+jobs:
+  create-and-push-tag:
+    runs-on: [runs-on,runner=2cpu-linux-x64,"run-id=${{ github.run_id }}"]
+
+    steps:
+    # actions using GITHUB_TOKEN cannot trigger another workflow, but we do want this to trigger docker pushes
+    # see https://github.com/orgs/community/discussions/27028#discussioncomment-3254367 for the workaround we
+    # implement here which needs an actual user's deploy key
+    - name: Checkout code
+      uses: actions/checkout@v4
+      with:
+        ssh-key: "${{ secrets.RKUO_DEPLOY_KEY }}"
+
+    - name: Set up Git user
+      run: |
+        git config user.name "Richard Kuo [bot]"
+        git config user.email "rkuo[bot]@danswer.ai"
+
+    - name: Check for existing nightly tag
+      id: check_tag
+      run: |
+        if git tag --points-at HEAD --list "nightly-latest*" | grep -q .; then
+          echo "A tag starting with 'nightly-latest' already exists on HEAD."
+          echo "tag_exists=true" >> $GITHUB_OUTPUT
+        else
+          echo "No tag starting with 'nightly-latest' exists on HEAD."
+          echo "tag_exists=false" >> $GITHUB_OUTPUT
+        fi
+        
+    # don't tag again if HEAD already has a nightly-latest tag on it
+    - name: Create Nightly Tag
+      if: steps.check_tag.outputs.tag_exists == 'false'
+      env:
+        DATE: ${{ github.run_id }}
+      run: |
+        TAG_NAME="nightly-latest-$(date +'%Y%m%d')"
+        echo "Creating tag: $TAG_NAME"
+        git tag $TAG_NAME
+
+    - name: Push Tag
+      if: steps.check_tag.outputs.tag_exists == 'false'
+      run: |
+        TAG_NAME="nightly-latest-$(date +'%Y%m%d')"
+        git push origin $TAG_NAME
+        

.gitignore

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

.prettierignore

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

.vscode/env_template.txt

@@ -0,0 +1,51 @@
+# Copy this file to .env in the .vscode folder
+# Fill in the <REPLACE THIS> values as needed, it is recommended to set the GEN_AI_API_KEY value to avoid having to set up an LLM in the UI
+# Also check out danswer/backend/scripts/restart_containers.sh for a script to restart the containers which Danswer relies on outside of VSCode/Cursor processes
+
+# For local dev, often user Authentication is not needed
+AUTH_TYPE=disabled
+
+
+# Always keep these on for Dev
+# Logs all model prompts to stdout
+LOG_DANSWER_MODEL_INTERACTIONS=True
+# More verbose logging
+LOG_LEVEL=debug
+
+
+# This passes top N results to LLM an additional time for reranking prior to answer generation
+# This step is quite heavy on token usage so we disable it for dev generally
+DISABLE_LLM_DOC_RELEVANCE=False
+
+
+# Useful if you want to toggle auth on/off (google_oauth/OIDC specifically)
+OAUTH_CLIENT_ID=<REPLACE THIS>
+OAUTH_CLIENT_SECRET=<REPLACE THIS>
+# Generally not useful for dev, we don't generally want to set up an SMTP server for dev
+REQUIRE_EMAIL_VERIFICATION=False
+
+
+# Set these so if you wipe the DB, you don't end up having to go through the UI every time
+GEN_AI_API_KEY=<REPLACE THIS>
+# If answer quality isn't important for dev, use gpt-4o-mini since it's cheaper
+GEN_AI_MODEL_VERSION=gpt-4o
+FAST_GEN_AI_MODEL_VERSION=gpt-4o
+
+# For Danswer Slack Bot, overrides the UI values so no need to set this up via UI every time
+# Only needed if using DanswerBot
+#DANSWER_BOT_SLACK_APP_TOKEN=<REPLACE THIS>
+#DANSWER_BOT_SLACK_BOT_TOKEN=<REPLACE THIS>
+
+
+# Python stuff
+PYTHONPATH=../backend
+PYTHONUNBUFFERED=1
+
+
+# Internet Search 
+BING_API_KEY=<REPLACE THIS>
+
+
+# Enable the full set of Danswer Enterprise Edition features
+# NOTE: DO NOT ENABLE THIS UNLESS YOU HAVE A PAID ENTERPRISE LICENSE (or if you are using this for local testing/development)
+ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=False

.vscode/launch.template.jsonc

@@ -1,27 +1,67 @@
-/*
-
-  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": [
+        {
+            "name": "Run All Danswer Services",
+            "configurations": [
+                "Web Server",
+                "Model Server",
+                "API Server",
+                "Indexing",
+                "Background Jobs",
+                "Slack Bot"
+            ]
+        }
+    ],
     "configurations": [
         {
-            "name": "API Server",
-            "type": "python",
+            "name": "Web Server",
+            "type": "node",
+            "request": "launch",
+            "cwd": "${workspaceRoot}/web",
+            "runtimeExecutable": "npm",
+            "envFile": "${workspaceFolder}/.vscode/.env",
+            "runtimeArgs": [
+                "run", "dev"
+            ],
+            "console": "integratedTerminal"
+        },
+        {
+            "name": "Model Server",
+            "consoleName": "Model Server",
+            "type": "debugpy",
             "request": "launch",
             "module": "uvicorn",
             "cwd": "${workspaceFolder}/backend",
+            "envFile": "${workspaceFolder}/.vscode/.env",
             "env": {
                 "LOG_LEVEL": "DEBUG",
-                "DISABLE_AUTH": "True",
-                "TYPESENSE_API_KEY": "typesense_api_key",
-                "DYNAMIC_CONFIG_DIR_PATH": "./dynamic_config_storage"
+                "PYTHONUNBUFFERED": "1"
+            },
+            "args": [
+                "model_server.main:app",
+                "--reload",
+                "--port",
+                "9000"
+            ]
+        },
+        {
+            "name": "API Server",
+            "consoleName": "API Server",
+            "type": "debugpy",
+            "request": "launch",
+            "module": "uvicorn",
+            "cwd": "${workspaceFolder}/backend",
+            "envFile": "${workspaceFolder}/.vscode/.env",
+            "env": {
+                "LOG_DANSWER_MODEL_INTERACTIONS": "True",
+                "LOG_LEVEL": "DEBUG",
+                "PYTHONUNBUFFERED": "1"
             },
             "args": [
                 "danswer.main:app",
@@ -31,52 +71,83 @@
             ]
         },
         {
-            "name": "Indexer",
-            "type": "python",
+            "name": "Indexing",
+            "consoleName": "Indexing",
+            "type": "debugpy",
             "request": "launch",
             "program": "danswer/background/update.py",
             "cwd": "${workspaceFolder}/backend",
+            "envFile": "${workspaceFolder}/.vscode/.env",
             "env": {
+                "ENABLE_MULTIPASS_INDEXING": "false",
                 "LOG_LEVEL": "DEBUG",
-                "PYTHONPATH": ".",
-                "TYPESENSE_API_KEY": "typesense_api_key",
-                "DYNAMIC_CONFIG_DIR_PATH": "./dynamic_config_storage"
+                "PYTHONUNBUFFERED": "1",
+                "PYTHONPATH": "."
             }
         },
+        // Celery and all async jobs, usually would include indexing as well but this is handled separately above for dev
         {
-            "name": "Temp File Deletion",
-            "type": "python",
+            "name": "Background Jobs",
+            "consoleName": "Background Jobs",
+            "type": "debugpy",
             "request": "launch",
-            "program": "danswer/background/file_deletion.py",
+            "program": "scripts/dev_run_background_jobs.py",
             "cwd": "${workspaceFolder}/backend",
+            "envFile": "${workspaceFolder}/.vscode/.env",
             "env": {
+                "LOG_DANSWER_MODEL_INTERACTIONS": "True",
                 "LOG_LEVEL": "DEBUG",
-                "PYTHONPATH": "${workspaceFolder}/backend"
-            }
+                "PYTHONUNBUFFERED": "1",
+                "PYTHONPATH": "."
+            },
+            "args": [
+                "--no-indexing"
+            ]
         },
         // For the listner to access the Slack API,
         // DANSWER_BOT_SLACK_APP_TOKEN & DANSWER_BOT_SLACK_BOT_TOKEN need to be set in .env file located in the root of the project
         {
-            "name": "Slack Bot Listener",
-            "type": "python",
+            "name": "Slack Bot",
+            "consoleName": "Slack Bot",
+            "type": "debugpy",
             "request": "launch",
-            "program": "danswer/listeners/slack_listener.py",
+            "program": "danswer/danswerbot/slack/listener.py",
             "cwd": "${workspaceFolder}/backend",
-            "envFile": "${workspaceFolder}/.env",
+            "envFile": "${workspaceFolder}/.vscode/.env",
             "env": {
-                "LOG_LEVEL": "DEBUG"
+                "LOG_LEVEL": "DEBUG",
+                "PYTHONUNBUFFERED": "1",
+                "PYTHONPATH": "."
             }
         },
         {
-            "name": "Web Server",
+            "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"
+            ]
+        },
+        {
+            "name": "Clear and Restart External Volumes and Containers",
             "type": "node",
             "request": "launch",
-            "cwd": "${workspaceRoot}/web",
-            "runtimeExecutable": "npm",
-            "runtimeArgs": [
-                "run", "dev"
-            ],
-            "console": "integratedTerminal"
+            "runtimeExecutable": "bash",
+            "runtimeArgs": ["${workspaceFolder}/backend/scripts/restart_containers.sh"],
+            "cwd": "${workspaceFolder}",
+            "console": "integratedTerminal",
+            "stopOnEntry": true
         }
     ]
-}
+}

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-2afut44lv-Rw3kSWu6_OmdAXRpCv80DQ) / 
+[Slack](https://join.slack.com/t/danswer/shared_invite/zt-2lcmqw703-071hBuZBfNEOGUsLa5PXvQ) / 
 [Discord](https://discord.gg/TDJ59cGV2X) directly about anything at all. 
 
 
@@ -48,23 +48,26 @@ We would love to see you there!
 
 
 ## Get Started 🚀
-Danswer being a fully functional app, relies on some external pieces of software, specifically:
+Danswer being a fully functional app, relies on some external software, specifically:
 - [Postgres](https://www.postgresql.org/) (Relational DB)
 - [Vespa](https://vespa.ai/) (Vector DB/Search Engine)
+- [Redis](https://redis.io/) (Cache)
+- [Nginx](https://nginx.org/) (Not needed for development flows generally)
 
-This guide provides instructions to set up the Danswer specific services outside of Docker because it's easier for
-development purposes but also feel free to just use the containers and update with local changes by providing the
-`--build` flag.
+
+> **Note:**
+> This guide provides instructions to build and run Danswer locally from source with Docker containers providing the above external software. We believe this combination is easier for
+> development purposes. If you prefer to use pre-built container images, we provide instructions on running the full Danswer stack within Docker below.
 
 
 ### Local Set Up
-It is recommended to use Python version 3.11
+Be sure to use Python version 3.11. For instructions on installing Python 3.11 on macOS, refer to the [CONTRIBUTING_MACOS.md](./CONTRIBUTING_MACOS.md) readme.
 
 If using a lower version, modifications will have to be made to the code.
-If using a higher version, the version of Tensorflow we use may not be available for your platform.
+If using a higher version, sometimes some libraries will not be available (i.e. we had problems with Tensorflow in the past with higher versions of python).
 
 
-#### Installing Requirements
+#### Backend: Python requirements
 Currently, we use pip and recommend creating a virtual environment.
 
 For convenience here's a command for it:
@@ -72,6 +75,11 @@ 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
@@ -85,34 +93,38 @@ Install the required python dependencies:
 ```bash
 pip install -r danswer/backend/requirements/default.txt
 pip install -r danswer/backend/requirements/dev.txt
+pip install -r danswer/backend/requirements/ee.txt
 pip install -r danswer/backend/requirements/model_server.txt
 ```
 
+Install Playwright for Python (headless browser required by the Web Connector)
+
+In the activated Python virtualenv, install Playwright for Python by running:
+```bash
+playwright install
+```
+
+You may have to deactivate and reactivate your virtualenv for `playwright` to appear on your path.
+
+#### Frontend: Node dependencies
+
 Install [Node.js and npm](https://docs.npmjs.com/downloading-and-installing-node-js-and-npm) for the frontend.
 Once the above is done, navigate to `danswer/web` run:
 ```bash
 npm i
 ```
 
-Install Playwright (required by the Web Connector)
+#### Docker containers for external software
+You will need Docker installed to run these containers.
 
-> 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:
+First navigate to `danswer/deployment/docker_compose`, then start up Postgres/Vespa/Redis with:
 ```bash
-playwright install
+docker compose -f docker-compose.dev.yml -p danswer-stack up -d index relational_db cache
 ```
+(index refers to Vespa, relational_db refers to Postgres, and cache refers to Redis)
 
 
-#### Dependent Docker Containers
-First navigate to `danswer/deployment/docker_compose`, then start up 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
+#### Running Danswer locally
 To start the frontend, navigate to `danswer/web` and run:
 ```bash
 npm run dev
@@ -123,11 +135,10 @@ 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.
@@ -150,6 +161,7 @@ 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 "
@@ -158,20 +170,58 @@ powershell -Command "
 "
 ```
 
-Note: if you need finer logging, add the additional environment variable `LOG_LEVEL=DEBUG` to the relevant services.
+> **Note:**
+> If you need finer logging, add the additional environment variable `LOG_LEVEL=DEBUG` to the relevant services.
+
+#### Wrapping up
+
+You should now have 4 servers running:
+
+- Web server
+- Backend API
+- Model server
+- Background jobs
+
+Now, visit `http://localhost:3000` in your browser. You should see the 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
+```
 
 ### Formatting and Linting
 #### Backend
 For the backend, you'll need to setup pre-commit hooks (black / reorder-python-imports).
 First, install pre-commit (if you don't have it already) following the instructions
 [here](https://pre-commit.com/#installation).
+
+With the virtual environment active, install the pre-commit library with:
+```bash
+pip install pre-commit
+```
+
 Then, from the `danswer/backend` directory, run:
 ```bash
 pre-commit install
 ```
 
 Additionally, we use `mypy` for static type checking.
-Danswer is fully type-annotated, and we would like to keep it that way! 
+Danswer is fully type-annotated, and we want to keep it that way! 
 To run the mypy checks manually, run `python -m mypy .` from the `danswer/backend` directory.
 
 
@@ -182,6 +232,7 @@ Please double check that prettier passes before creating a pull request.
 
 
 ### Release Process
-Danswer follows the semver versioning standard.
+Danswer loosely follows the SemVer versioning standard.
+Major changes are released with a "minor" version bump. Currently we use patch release versions to indicate small feature changes.
 A set of Docker containers will be pushed automatically to DockerHub with every tag.
 You can see the containers [here](https://hub.docker.com/search?q=danswer%2F).

CONTRIBUTING_MACOS.md

@@ -0,0 +1,31 @@
+## Some additional notes for Mac Users
+The base instructions to set up the development environment are located in [CONTRIBUTING.md](https://github.com/danswer-ai/danswer/blob/main/CONTRIBUTING.md).
+
+### Setting up Python
+Ensure [Homebrew](https://brew.sh/) is already set up.
+
+Then install python 3.11.
+```bash
+brew install python@3.11
+```
+
+Add python 3.11 to your path: add the following line to ~/.zshrc
+```
+export PATH="$(brew --prefix)/opt/python@3.11/libexec/bin:$PATH"
+```
+
+> **Note:**
+> You will need to open a new terminal for the path change above to take effect.
+
+
+### Setting up Docker
+On macOS, you will need to install [Docker Desktop](https://www.docker.com/products/docker-desktop/) and 
+ensure it is running before continuing with the docker commands.
+
+
+### Formatting and Linting
+MacOS will likely require you to remove some quarantine attributes on some of the hooks for them to execute properly.
+After installing pre-commit, run the following command:
+```bash
+sudo xattr -r -d com.apple.quarantine ~/.cache/pre-commit
+```

LICENSE

@@ -1,6 +1,10 @@
-MIT License
+Copyright (c) 2023-present DanswerAI, Inc.
 
-Copyright (c) 2023 Yuhong Sun, Chris Weaver
+Portions of this software are licensed as follows:
+
+* All content that resides under "ee" directories of this repository, if that directory exists, is licensed under the license defined in "backend/ee/LICENSE". Specifically all content under "backend/ee" and "web/src/app/ee" is licensed under the license defined in "backend/ee/LICENSE".
+* All third party components incorporated into the Danswer Software are licensed under the original license provided by the owner of the applicable component.
+* Content outside of the above mentioned directories or restrictions above is available under the "MIT Expat" license as defined below.
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

README.md

@@ -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-2afut44lv-Rw3kSWu6_OmdAXRpCv80DQ" target="_blank">
+<a href="https://join.slack.com/t/danswer/shared_invite/zt-2lcmqw703-071hBuZBfNEOGUsLa5PXvQ" target="_blank">
     <img src="https://img.shields.io/badge/slack-join-blue.svg?logo=slack" alt="Slack">
 </a>
 <a href="https://discord.gg/TDJ59cGV2X" target="_blank">
@@ -105,5 +105,25 @@ 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
+celerybeat-schedule*

backend/Dockerfile

@@ -1,15 +1,18 @@
 FROM python:3.11.7-slim-bookworm
 
 LABEL com.danswer.maintainer="founders@danswer.ai"
-LABEL com.danswer.description="This image is for the backend of Danswer. It is MIT Licensed and \
-free for all to use. You can find it at https://hub.docker.com/r/danswer/danswer-backend. For \
-more details, visit https://github.com/danswer-ai/danswer."
+LABEL com.danswer.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"
 
 # Default DANSWER_VERSION, typically overriden during builds by GitHub Actions.
 ARG DANSWER_VERSION=0.3-dev
-ENV DANSWER_VERSION=${DANSWER_VERSION}
-RUN echo "DANSWER_VERSION: ${DANSWER_VERSION}"
+ENV DANSWER_VERSION=${DANSWER_VERSION} \
+    DANSWER_RUNNING_IN_DOCKER="true"
 
+RUN echo "DANSWER_VERSION: ${DANSWER_VERSION}"
 # Install system dependencies
 # cmake needed for psycopg (postgres)
 # libpq-dev needed for psycopg (postgres)
@@ -17,18 +20,34 @@ RUN echo "DANSWER_VERSION: ${DANSWER_VERSION}"
 # zip for Vespa step futher down
 # ca-certificates for HTTPS
 RUN apt-get update && \
-    apt-get install -y cmake curl zip ca-certificates libgnutls30=3.7.9-2+deb12u2 \
-    libblkid1=2.38.1-5+deb12u1 libmount1=2.38.1-5+deb12u1 libsmartcols1=2.38.1-5+deb12u1 \
-    libuuid1=2.38.1-5+deb12u1 && \
+    apt-get install -y \
+        cmake \
+        curl \
+        zip \
+        ca-certificates \
+        libgnutls30=3.7.9-2+deb12u3 \
+        libblkid1=2.38.1-5+deb12u1 \
+        libmount1=2.38.1-5+deb12u1 \
+        libsmartcols1=2.38.1-5+deb12u1 \
+        libuuid1=2.38.1-5+deb12u1 \
+        libxmlsec1-dev \
+        pkg-config \
+        gcc && \
     rm -rf /var/lib/apt/lists/* && \
     apt-get clean
 
 # Install Python dependencies
 # Remove py which is pulled in by retry, py is not needed and is a CVE
 COPY ./requirements/default.txt /tmp/requirements.txt
-RUN pip install --no-cache-dir --upgrade -r /tmp/requirements.txt && \
+COPY ./requirements/ee.txt /tmp/ee-requirements.txt
+RUN pip install --no-cache-dir --upgrade \
+        --retries 5 \
+        --timeout 30 \
+        -r /tmp/requirements.txt \
+        -r /tmp/ee-requirements.txt && \
     pip uninstall -y py && \
-    playwright install chromium && playwright install-deps chromium && \
+    playwright install chromium && \
+    playwright install-deps chromium && \
     ln -s /usr/local/bin/supervisord /usr/bin/supervisord
 
 # Cleanup for CVEs and size reduction
@@ -36,29 +55,52 @@ RUN pip install --no-cache-dir --upgrade -r /tmp/requirements.txt && \
 # 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 remove -y --allow-remove-essential perl-base xserver-common xvfb cmake \
-    libldap-2.5-0 libldap-2.5-0 && \
+RUN apt-get update && \
+    apt-get remove -y --allow-remove-essential \
+        perl-base \
+        xserver-common \
+        xvfb \
+        cmake \
+        libldap-2.5-0 \
+        libxmlsec1-dev \
+        pkg-config \
+        gcc && \
+    apt-get install -y libxmlsec1-openssl && \
     apt-get autoremove -y && \
     rm -rf /var/lib/apt/lists/* && \
-    rm /usr/local/lib/python3.11/site-packages/tornado/test/test.key
+    rm -f /usr/local/lib/python3.11/site-packages/tornado/test/test.key
 
 # Pre-downloading models for setups with limited egress
-RUN python -c "from transformers import AutoTokenizer; AutoTokenizer.from_pretrained('intfloat/e5-base-v2')"
+RUN python -c "from tokenizers import Tokenizer; \
+Tokenizer.from_pretrained('nomic-ai/nomic-embed-text-v1')"
+
 
 # Pre-downloading NLTK for setups with limited egress
 RUN python -c "import nltk; \
 nltk.download('stopwords', quiet=True); \
-nltk.download('wordnet', quiet=True); \
 nltk.download('punkt', quiet=True);"
+# nltk.download('wordnet', quiet=True); introduce this back if lemmatization is needed
 
 # Set up application files
 WORKDIR /app
+
+# 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.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
 
 # Default command which does nothing

backend/Dockerfile.model_server

@@ -8,24 +8,38 @@ visit https://github.com/danswer-ai/danswer."
 
 # Default DANSWER_VERSION, typically overriden during builds by GitHub Actions.
 ARG DANSWER_VERSION=0.3-dev
-ENV DANSWER_VERSION=${DANSWER_VERSION}
+ENV DANSWER_VERSION=${DANSWER_VERSION} \
+    DANSWER_RUNNING_IN_DOCKER="true"
+
+
 RUN echo "DANSWER_VERSION: ${DANSWER_VERSION}"
 
 COPY ./requirements/model_server.txt /tmp/requirements.txt
-RUN pip install --no-cache-dir --upgrade -r /tmp/requirements.txt
+RUN pip install --no-cache-dir --upgrade \
+        --retries 5 \
+        --timeout 30 \
+        -r /tmp/requirements.txt
 
 RUN apt-get remove -y --allow-remove-essential perl-base && \
     apt-get autoremove -y
 
 # Pre-downloading models for setups with limited egress
-RUN python -c "from transformers import AutoModel, AutoTokenizer, TFDistilBertForSequenceClassification; \
-from huggingface_hub import snapshot_download; \
-AutoTokenizer.from_pretrained('danswer/intent-model'); \
-AutoTokenizer.from_pretrained('intfloat/e5-base-v2'); \
+# Download tokenizers, distilbert for the 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'); \
-snapshot_download('danswer/intent-model'); \
-snapshot_download('intfloat/e5-base-v2'); \
-snapshot_download('mixedbread-ai/mxbai-rerank-xsmall-v1')"
+from huggingface_hub import snapshot_download; \
+snapshot_download(repo_id='danswer/hybrid-intent-token-classifier', revision='v1.0.3'); \
+snapshot_download('nomic-ai/nomic-embed-text-v1'); \
+snapshot_download('mixedbread-ai/mxbai-rerank-xsmall-v1'); \
+from sentence_transformers import SentenceTransformer; \
+SentenceTransformer(model_name_or_path='nomic-ai/nomic-embed-text-v1', trust_remote_code=True);"
+
+# In case the user has volumes mounted to /root/.cache/huggingface that they've downloaded while
+# running Danswer, don't overwrite it with the built in cache folder
+RUN mv /root/.cache/huggingface /root/.cache/temp_huggingface
 
 WORKDIR /app
 

backend/alembic/env.py

@@ -8,26 +8,53 @@ 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 sqlalchemy.schema import SchemaItem
+from sqlalchemy.sql import text
 
-# this is the Alembic Config object, which provides
-# access to the values within the .ini file in use.
+# Alembic Config object
 config = context.config
 
 # Interpret the config file for Python logging.
 # This line sets up loggers basically.
-if config.config_file_name is not None:
+if config.config_file_name is not None and config.attributes.get(
+    "configure_logger", True
+):
     fileConfig(config.config_file_name)
 
-# add your model's MetaData object here
+# Add your model's MetaData object here
 # for 'autogenerate' support
 # from myapp import mymodel
 # target_metadata = mymodel.Base.metadata
 target_metadata = [Base.metadata, ResultModelBase.metadata]
 
-# other values from the config, defined by the needs of env.py,
-# can be acquired:
-# my_important_option = config.get_main_option("my_important_option")
-# ... etc.
+
+def get_schema_options() -> tuple[str, bool]:
+    x_args_raw = context.get_x_argument()
+    x_args = {}
+    for arg in x_args_raw:
+        for pair in arg.split(","):
+            if "=" in pair:
+                key, value = pair.split("=", 1)
+                x_args[key] = value
+
+    schema_name = x_args.get("schema", "public")
+    create_schema = x_args.get("create_schema", "true").lower() == "true"
+    return schema_name, create_schema
+
+
+EXCLUDE_TABLES = {"kombu_queue", "kombu_message"}
+
+
+def include_object(
+    object: SchemaItem,
+    name: str,
+    type_: str,
+    reflected: bool,
+    compare_to: SchemaItem | None,
+) -> bool:
+    if type_ == "table" and name in EXCLUDE_TABLES:
+        return False
+    return True
 
 
 def run_migrations_offline() -> None:
@@ -37,17 +64,20 @@ def run_migrations_offline() -> None:
     and not an Engine, though an Engine is acceptable
     here as well.  By skipping the Engine creation
     we don't even need a DBAPI to be available.
-
     Calls to context.execute() here emit the given string to the
     script output.
-
     """
     url = build_connection_string()
+    schema, _ = get_schema_options()
+
     context.configure(
         url=url,
         target_metadata=target_metadata,  # type: ignore
         literal_binds=True,
+        include_object=include_object,
         dialect_opts={"paramstyle": "named"},
+        version_table_schema=schema,
+        include_schemas=True,
     )
 
     with context.begin_transaction():
@@ -55,18 +85,28 @@ def run_migrations_offline() -> None:
 
 
 def do_run_migrations(connection: Connection) -> None:
-    context.configure(connection=connection, target_metadata=target_metadata)  # type: ignore
+    schema, create_schema = get_schema_options()
+    if create_schema:
+        connection.execute(text(f'CREATE SCHEMA IF NOT EXISTS "{schema}"'))
+        connection.execute(text("COMMIT"))
+
+    connection.execute(text(f'SET search_path TO "{schema}"'))
+
+    context.configure(
+        connection=connection,
+        target_metadata=target_metadata,  # type: ignore
+        version_table_schema=schema,
+        include_schemas=True,
+        compare_type=True,
+        compare_server_default=True,
+    )
 
     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.
-
-    """
-
+    """Run migrations in 'online' mode."""
     connectable = create_async_engine(
         build_connection_string(),
         poolclass=pool.NullPool,
@@ -80,7 +120,6 @@ async def run_async_migrations() -> None:
 
 def run_migrations_online() -> None:
     """Run migrations in 'online' mode."""
-
     asyncio.run(run_async_migrations())
 
 

backend/alembic/versions/0568ccf46a6b_add_thread_specific_model_selection.py

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

backend/alembic/versions/05c07bf07c00_add_search_doc_relevance_details.py

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

backend/alembic/versions/08a1eda20fe1_add_earliest_indexing_to_connector.py

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

backend/alembic/versions/0a2b51deb0b8_add_starter_prompts.py

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

backend/alembic/versions/0a98909f2757_enable_encrypted_fields.py

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

backend/alembic/versions/0ebb1d516877_add_ccpair_deletion_failure_message.py

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

backend/alembic/versions/15326fcec57e_introduce_danswer_apis.py

@@ -13,8 +13,8 @@ from danswer.configs.constants import DocumentSource
 # revision identifiers, used by Alembic.
 revision = "15326fcec57e"
 down_revision = "77d07dffae64"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:

backend/alembic/versions/173cae5bba26_port_config_store.py

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

backend/alembic/versions/1b8206b29c5d_add_user_delete_cascades.py

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

backend/alembic/versions/1f60f60c3401_embedding_model_search_settings.py

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

backend/alembic/versions/213fd978c6d8_notifications.py

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

backend/alembic/versions/23957775e5f5_remove_feedback_foreignkey_constraint.py

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

backend/alembic/versions/2666d766cb9b_google_oauth2.py

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

backend/alembic/versions/27c6ecc08586_permission_framework.py

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

backend/alembic/versions/2d2304e27d8c_add_above_below_to_persona.py

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

backend/alembic/versions/30c1d5744104_persona_datetime_aware.py

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

backend/alembic/versions/325975216eb3_add_icon_color_and_icon_shape_to_persona.py

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

backend/alembic/versions/351faebd379d_add_curator_fields.py

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

backend/alembic/versions/35e6853a51d5_server_default_chosen_assistants.py

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

backend/alembic/versions/3879338f8ba1_add_tool_table.py

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

backend/alembic/versions/38eda64af7fe_add_chat_session_sharing.py

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

backend/alembic/versions/3a7802814195_add_alternate_assistant_to_chat_message.py

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

backend/alembic/versions/3b25685ff73c_move_is_public_to_cc_pair.py

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

backend/alembic/versions/3c5e35aa9af0_polling_document_count.py

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

backend/alembic/versions/401c1ac29467_add_tables_for_ui_based_llm_.py

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

backend/alembic/versions/43cbbb3f5e6a_rename_index_origin_to_index_recursively.py

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

backend/alembic/versions/44f856ae2a4a_add_cloud_embedding_model.py

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

backend/alembic/versions/4505fd7302e1_added_is_internet_to_dbdoc.py

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

backend/alembic/versions/465f78d9b7f9_larger_access_tokens_for_oauth.py

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

backend/alembic/versions/46625e4745d4_remove_native_enum.py

@@ -11,8 +11,8 @@ from sqlalchemy import String
 # revision identifiers, used by Alembic.
 revision = "46625e4745d4"
 down_revision = "9d97fecfab7f"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:

backend/alembic/versions/46b7a812670f_fix_user__external_user_group_id_fk.py

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

backend/alembic/versions/4738e4b3bae1_pg_file_store.py

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

backend/alembic/versions/473a1a7ca408_add_display_model_names_to_llm_provider.py

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

backend/alembic/versions/47433d30de82_create_indexattempt_table.py

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

backend/alembic/versions/475fcefe8826_add_name_to_api_key.py

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

backend/alembic/versions/48d14957fe80_add_support_for_custom_tools.py

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

backend/alembic/versions/4a951134c801_moved_status_to_connector_credential_.py

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

backend/alembic/versions/4b08d97e175a_change_default_prune_freq.py

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

backend/alembic/versions/4ea2c93919c1_add_type_to_credentials.py

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

backend/alembic/versions/50b683a8295c_add_additional_retrieval_controls_to_.py

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

backend/alembic/versions/52a219fb5233_add_last_synced_and_last_modified_to_document_table.py

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

backend/alembic/versions/55546a7967ee_assistant_rework.py

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

backend/alembic/versions/570282d33c49_track_danswerbot_explicitly.py

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

backend/alembic/versions/57b53544726e_add_document_set_tables.py

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

backend/alembic/versions/5809c0787398_add_chat_sessions.py

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

backend/alembic/versions/5c7fdadae813_match_any_keywords_flag_for_standard_.py

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

backend/alembic/versions/5e84129c8be3_add_docs_indexed_column_to_index_.py

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

backend/alembic/versions/5f4b8568a221_add_removed_documents_to_index_attempt.py

@@ -11,8 +11,8 @@ import sqlalchemy as sa
 # revision identifiers, used by Alembic.
 revision = "5f4b8568a221"
 down_revision = "8987770549c0"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:

backend/alembic/versions/5fc1f54cc252_hybrid_enum.py

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

backend/alembic/versions/61ff3651add4_add_permission_syncing.py

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

backend/alembic/versions/643a84a42a33_add_user_configured_names_to_llmprovider.py

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

backend/alembic/versions/6d387b3196c2_basic_auth.py

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

backend/alembic/versions/703313b75876_add_tokenratelimit_tables.py

@@ -0,0 +1,81 @@
+"""Add TokenRateLimit Tables
+
+Revision ID: 703313b75876
+Revises: fad14119fb92
+Create Date: 2024-04-15 01:36:02.952809
+
+"""
+import json
+from typing import cast
+from alembic import op
+import sqlalchemy as sa
+from danswer.key_value_store.factory import get_kv_store
+
+# revision identifiers, used by Alembic.
+revision = "703313b75876"
+down_revision = "fad14119fb92"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "token_rate_limit",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column("enabled", sa.Boolean(), nullable=False),
+        sa.Column("token_budget", sa.Integer(), nullable=False),
+        sa.Column("period_hours", sa.Integer(), nullable=False),
+        sa.Column(
+            "scope",
+            sa.String(length=10),
+            nullable=False,
+        ),
+        sa.Column(
+            "created_at",
+            sa.DateTime(timezone=True),
+            server_default=sa.text("now()"),
+            nullable=False,
+        ),
+        sa.PrimaryKeyConstraint("id"),
+    )
+    op.create_table(
+        "token_rate_limit__user_group",
+        sa.Column("rate_limit_id", sa.Integer(), nullable=False),
+        sa.Column("user_group_id", sa.Integer(), nullable=False),
+        sa.ForeignKeyConstraint(
+            ["rate_limit_id"],
+            ["token_rate_limit.id"],
+        ),
+        sa.ForeignKeyConstraint(
+            ["user_group_id"],
+            ["user_group.id"],
+        ),
+        sa.PrimaryKeyConstraint("rate_limit_id", "user_group_id"),
+    )
+
+    try:
+        settings_json = cast(str, get_kv_store().load("token_budget_settings"))
+        settings = json.loads(settings_json)
+
+        is_enabled = settings.get("enable_token_budget", False)
+        token_budget = settings.get("token_budget", -1)
+        period_hours = settings.get("period_hours", -1)
+
+        if is_enabled and token_budget > 0 and period_hours > 0:
+            op.execute(
+                f"INSERT INTO token_rate_limit \
+                    (enabled, token_budget, period_hours, scope) VALUES \
+                        ({is_enabled}, {token_budget}, {period_hours}, 'GLOBAL')"
+            )
+
+        # Delete the dynamic config
+        get_kv_store().delete("token_budget_settings")
+
+    except Exception:
+        # Ignore if the dynamic config is not found
+        pass
+
+
+def downgrade() -> None:
+    op.drop_table("token_rate_limit__user_group")
+    op.drop_table("token_rate_limit")

backend/alembic/versions/70f00c45c0f2_more_descriptive_filestore.py

@@ -0,0 +1,68 @@
+"""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/72bdc9929a46_permission_auto_sync_framework.py

@@ -11,8 +11,8 @@ import sqlalchemy as sa
 # revision identifiers, used by Alembic.
 revision = "72bdc9929a46"
 down_revision = "475fcefe8826"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:

backend/alembic/versions/7477a5f5d728_added_model_defaults_for_users.py

@@ -0,0 +1,24 @@
+"""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/7547d982db8f_chat_folders.py

@@ -0,0 +1,51 @@
+"""Chat Folders
+
+Revision ID: 7547d982db8f
+Revises: ef7da92f7213
+Create Date: 2024-05-02 15:18:56.573347
+
+"""
+from alembic import op
+import sqlalchemy as sa
+import fastapi_users_db_sqlalchemy
+
+# revision identifiers, used by Alembic.
+revision = "7547d982db8f"
+down_revision = "ef7da92f7213"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "chat_folder",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column(
+            "user_id",
+            fastapi_users_db_sqlalchemy.generics.GUID(),
+            nullable=True,
+        ),
+        sa.Column("name", sa.String(), nullable=True),
+        sa.Column("display_priority", sa.Integer(), nullable=False),
+        sa.ForeignKeyConstraint(
+            ["user_id"],
+            ["user.id"],
+        ),
+        sa.PrimaryKeyConstraint("id"),
+    )
+    op.add_column("chat_session", sa.Column("folder_id", sa.Integer(), nullable=True))
+    op.create_foreign_key(
+        "chat_session_chat_folder_fk",
+        "chat_session",
+        "chat_folder",
+        ["folder_id"],
+        ["id"],
+    )
+
+
+def downgrade() -> None:
+    op.drop_constraint(
+        "chat_session_chat_folder_fk", "chat_session", type_="foreignkey"
+    )
+    op.drop_column("chat_session", "folder_id")
+    op.drop_table("chat_folder")

backend/alembic/versions/767f1c2a00eb_count_chat_tokens.py

@@ -12,8 +12,8 @@ import sqlalchemy as sa
 # revision identifiers, used by Alembic.
 revision = "767f1c2a00eb"
 down_revision = "dba7f71618f5"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:

backend/alembic/versions/76b60d407dfb_cc_pair_name_not_unique.py

@@ -11,8 +11,8 @@ import sqlalchemy as sa
 # revision identifiers, used by Alembic.
 revision = "76b60d407dfb"
 down_revision = "b156fa702355"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:
@@ -28,5 +28,9 @@ def upgrade() -> None:
 
 
 def downgrade() -> None:
-    # This wasn't really required by the code either, no good reason to make it unique again
-    pass
+    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
+    )

backend/alembic/versions/776b3bbe9092_remove_remaining_enums.py

@@ -10,13 +10,13 @@ import sqlalchemy as sa
 
 from danswer.db.models import IndexModelStatus
 from danswer.search.enums import RecencyBiasSetting
-from danswer.search.models import SearchType
+from danswer.search.enums import SearchType
 
 # revision identifiers, used by Alembic.
 revision = "776b3bbe9092"
 down_revision = "4738e4b3bae1"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:

backend/alembic/versions/77d07dffae64_forcibly_remove_more_enum_types_from_.py

@@ -12,8 +12,8 @@ from sqlalchemy import String
 # revision identifiers, used by Alembic.
 revision = "77d07dffae64"
 down_revision = "d61e513bef0a"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:

backend/alembic/versions/78dbe7e38469_task_tracking.py

@@ -11,8 +11,8 @@ import sqlalchemy as sa
 # revision identifiers, used by Alembic.
 revision = "78dbe7e38469"
 down_revision = "7ccea01261f6"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:

backend/alembic/versions/795b20b85b4b_add_llm_group_permissions_control.py

@@ -0,0 +1,41 @@
+"""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

@@ -0,0 +1,27 @@
+"""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/79acd316403a_add_api_key_table.py

@@ -12,8 +12,8 @@ import sqlalchemy as sa
 # revision identifiers, used by Alembic.
 revision = "79acd316403a"
 down_revision = "904e5138fffb"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:

backend/alembic/versions/7aea705850d5_added_slack_auto_filter.py

@@ -0,0 +1,35 @@
+"""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/7ccea01261f6_store_chat_retrieval_docs.py

@@ -12,8 +12,8 @@ from sqlalchemy.dialects import postgresql
 # revision identifiers, used by Alembic.
 revision = "7ccea01261f6"
 down_revision = "a570b80a5f20"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:

backend/alembic/versions/7da0ae5ad583_add_description_to_persona.py

@@ -11,8 +11,8 @@ import sqlalchemy as sa
 # revision identifiers, used by Alembic.
 revision = "7da0ae5ad583"
 down_revision = "e86866a9c78a"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:

backend/alembic/versions/7da543f5672f_add_slackbotconfig_table.py

@@ -12,8 +12,8 @@ from sqlalchemy.dialects import postgresql
 # revision identifiers, used by Alembic.
 revision = "7da543f5672f"
 down_revision = "febe9eaa0644"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:

backend/alembic/versions/7f726bad5367_slack_followup.py

@@ -11,8 +11,8 @@ import sqlalchemy as sa
 # revision identifiers, used by Alembic.
 revision = "7f726bad5367"
 down_revision = "79acd316403a"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:

backend/alembic/versions/7f99be1cb9f5_add_index_for_getting_documents_just_by_.py

@@ -11,8 +11,8 @@ from alembic import op
 # revision identifiers, used by Alembic.
 revision = "7f99be1cb9f5"
 down_revision = "78dbe7e38469"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:

backend/alembic/versions/800f48024ae9_add_id_to_connectorcredentialpair.py

@@ -12,8 +12,8 @@ from sqlalchemy.schema import Sequence, CreateSequence
 # revision identifiers, used by Alembic.
 revision = "800f48024ae9"
 down_revision = "767f1c2a00eb"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:

backend/alembic/versions/80696cf850ae_add_chat_session_to_query_event.py

@@ -11,8 +11,8 @@ import sqlalchemy as sa
 # revision identifiers, used by Alembic.
 revision = "80696cf850ae"
 down_revision = "15326fcec57e"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:

backend/alembic/versions/891cd83c87a8_add_is_visible_to_persona.py

@@ -11,8 +11,8 @@ import sqlalchemy as sa
 # revision identifiers, used by Alembic.
 revision = "891cd83c87a8"
 down_revision = "76b60d407dfb"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None: