k

* Simplified slackbot response groups and fixed need more help bug

* mypy fixes

* added exceptions for the couldnt find passthrough arrays

.github/workflows/docker-build-and-push-on-tag.yml

@@ -1,41 +0,0 @@
-name: Build and Push Docker Images on Tagging
-
-on:
-  push:
-    tags:
-      - '*'
-
-jobs:
-  build-and-push:
-    runs-on: ubuntu-latest
-
-    steps:
-    - name: Checkout code
-      uses: actions/checkout@v2
-
-    - name: Set up Docker Buildx
-      uses: docker/setup-buildx-action@v1
-
-    - name: Login to Docker Hub
-      uses: docker/login-action@v1
-      with:
-        username: ${{ secrets.DOCKER_USERNAME }}
-        password: ${{ secrets.DOCKER_TOKEN }}
-
-    - name: Web Server Docker Build and Push
-      uses: docker/build-push-action@v2
-      with:
-        context: ./web
-        file: ./web/Dockerfile
-        platforms: linux/amd64,linux/arm64
-        push: true
-        tags: danswer/danswer-web-server:${{ github.ref_name }}
-
-    - name: Api Server Docker Build and Push
-      uses: docker/build-push-action@v2
-      with:
-        context: ./backend
-        file: ./backend/Dockerfile
-        platforms: linux/amd64,linux/arm64
-        push: true
-        tags: danswer/danswer-backend:${{ github.ref_name }}

.github/workflows/docker-build-backend-container-on-merge-group.yml

@@ -0,0 +1,33 @@
+name: Build Backend Image on Merge Group
+
+on:
+  merge_group:
+    types: [checks_requested]
+
+env:
+  REGISTRY_IMAGE: danswer/danswer-backend
+
+jobs:
+  build:
+    # TODO: make this a matrix build like the web containers
+    runs-on: 
+      group: amd64-image-builders
+      
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v2
+
+    - name: Set up Docker Buildx
+      uses: docker/setup-buildx-action@v3
+
+    - name: Backend Image Docker Build
+      uses: docker/build-push-action@v5
+      with:
+        context: ./backend
+        file: ./backend/Dockerfile
+        platforms: linux/amd64,linux/arm64
+        push: false
+        tags: |
+          ${{ env.REGISTRY_IMAGE }}:latest
+        build-args: |
+          DANSWER_VERSION=v0.0.1

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

@@ -0,0 +1,49 @@
+name: Build and Push Backend Image on Tag
+
+on:
+  push:
+    tags:
+      - '*'
+
+env:
+  REGISTRY_IMAGE: danswer/danswer-backend
+
+jobs:
+  build-and-push:
+    # TODO: make this a matrix build like the web containers
+    runs-on: 
+      group: amd64-image-builders
+
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v2
+
+    - 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: Backend Image Docker Build and Push
+      uses: docker/build-push-action@v5
+      with:
+        context: ./backend
+        file: ./backend/Dockerfile
+        platforms: linux/amd64,linux/arm64
+        push: true
+        tags: |
+          ${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
+          ${{ env.REGISTRY_IMAGE }}:latest
+        build-args: |
+          DANSWER_VERSION=${{ github.ref_name }}
+
+    - name: Run Trivy vulnerability scanner
+      uses: aquasecurity/trivy-action@master
+      with:
+        # To run locally: trivy image --severity HIGH,CRITICAL danswer/danswer-backend
+        image-ref: docker.io/${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
+        severity: 'CRITICAL,HIGH'
+        trivyignores: ./backend/.trivyignore

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

@@ -0,0 +1,42 @@
+name: Build and Push Model Server Image on Tag
+
+on:
+  push:
+    tags:
+      - '*'
+
+jobs:
+  build-and-push:
+    runs-on: ubuntu-latest
+
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v2
+
+    - name: Set up Docker Buildx
+      uses: docker/setup-buildx-action@v3
+
+    - name: Login to Docker Hub
+      uses: docker/login-action@v3
+      with:
+        username: ${{ secrets.DOCKER_USERNAME }}
+        password: ${{ secrets.DOCKER_TOKEN }}
+
+    - name: Model Server Image Docker Build and Push
+      uses: docker/build-push-action@v5
+      with:
+        context: ./backend
+        file: ./backend/Dockerfile.model_server
+        platforms: linux/amd64,linux/arm64
+        push: true
+        tags: |
+          danswer/danswer-model-server:${{ github.ref_name }}
+          danswer/danswer-model-server:latest
+        build-args: |
+          DANSWER_VERSION=${{ github.ref_name }}
+
+    - name: Run Trivy vulnerability scanner
+      uses: aquasecurity/trivy-action@master
+      with:
+        image-ref: docker.io/danswer/danswer-model-server:${{ github.ref_name }}
+        severity: 'CRITICAL,HIGH'

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

@@ -0,0 +1,119 @@
+name: Build and Push Web Image on Tag
+
+on:
+  push:
+    tags:
+      - '*'
+
+env:
+  REGISTRY_IMAGE: danswer/danswer-web-server
+
+jobs:
+  build:
+    runs-on: 
+      group: ${{ matrix.platform == 'linux/amd64' && 'amd64-image-builders' || 'arm64-image-builders' }}
+    strategy:
+      fail-fast: false
+      matrix:
+        platform:
+          - linux/amd64
+          - linux/arm64
+
+    steps:
+      - name: Prepare
+        run: |
+          platform=${{ 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.REGISTRY_IMAGE }}:latest
+      
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+      
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_TOKEN }}
+    
+      - name: Build and push by digest
+        id: build
+        uses: docker/build-push-action@v5
+        with:
+          context: ./web
+          file: ./web/Dockerfile
+          platforms: ${{ matrix.platform }}
+          push: true
+          build-args: |
+            DANSWER_VERSION=${{ github.ref_name }}
+          # needed due to weird interactions with the builds for different platforms  
+          no-cache: true
+          labels: ${{ steps.meta.outputs.labels }}
+          outputs: type=image,name=${{ env.REGISTRY_IMAGE }},push-by-digest=true,name-canonical=true,push=true
+      
+      - name: Export digest
+        run: |
+          mkdir -p /tmp/digests
+          digest="${{ steps.build.outputs.digest }}"
+          touch "/tmp/digests/${digest#sha256:}"          
+      
+      - name: Upload digest
+        uses: actions/upload-artifact@v4
+        with:
+          name: digests-${{ env.PLATFORM_PAIR }}
+          path: /tmp/digests/*
+          if-no-files-found: error
+          retention-days: 1
+
+  merge:
+    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: Run Trivy vulnerability scanner
+        uses: aquasecurity/trivy-action@master
+        with:
+          image-ref: docker.io/${{ env.REGISTRY_IMAGE }}:${{ github.ref_name }}
+          severity: 'CRITICAL,HIGH'

.github/workflows/docker-build-web-container-on-merge-group.yml

@@ -0,0 +1,53 @@
+name: Build Web Image on Merge Group
+
+on:
+  merge_group:
+    types: [checks_requested]
+
+env:
+  REGISTRY_IMAGE: danswer/danswer-web-server
+
+jobs:
+  build:
+    runs-on: 
+      group: ${{ matrix.platform == 'linux/amd64' && 'amd64-image-builders' || 'arm64-image-builders' }}
+    strategy:
+      fail-fast: false
+      matrix:
+        platform:
+          - linux/amd64
+          - linux/arm64
+
+    steps:
+      - name: Prepare
+        run: |
+          platform=${{ 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 }}:latest
+      
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+    
+      - name: Build by digest
+        id: build
+        uses: docker/build-push-action@v5
+        with:
+          context: ./web
+          file: ./web/Dockerfile
+          platforms: ${{ matrix.platform }}
+          push: false
+          build-args: |
+            DANSWER_VERSION=v0.0.1
+          # needed due to weird interactions with the builds for different platforms  
+          no-cache: true
+          labels: ${{ steps.meta.outputs.labels }}

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

@@ -25,16 +25,8 @@ jobs:
 
     - name: Pull, Tag and Push Web Server Image
       run: |
-        docker pull danswer/danswer-web-server:${{ github.event.inputs.version }}
-        docker tag danswer/danswer-web-server:${{ github.event.inputs.version }} danswer/danswer-web-server:latest
-        docker push danswer/danswer-web-server:latest
-        docker manifest create danswer/danswer-web-server:latest danswer/danswer-web-server:latest
-        docker manifest push danswer/danswer-web-server:latest
+        docker buildx imagetools create -t danswer/danswer-web-server:latest danswer/danswer-web-server:${{ github.event.inputs.version }}
 
     - name: Pull, Tag and Push API Server Image
       run: |
-        docker pull danswer/danswer-backend:${{ github.event.inputs.version }}
-        docker tag danswer/danswer-backend:${{ github.event.inputs.version }} danswer/danswer-backend:latest
-        docker push danswer/danswer-backend:latest
-        docker manifest create danswer/danswer-backend:latest danswer/danswer-backend:latest
-        docker manifest push danswer/danswer-backend:latest
+        docker buildx imagetools create -t danswer/danswer-backend:latest danswer/danswer-backend:${{ github.event.inputs.version }}

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

@@ -11,7 +11,7 @@ jobs:
     steps:
     - name: Checkout code
       uses: actions/checkout@v3
-    
+
     - name: Set up Python
       uses: actions/setup-python@v4
       with:
@@ -20,16 +20,23 @@ jobs:
         cache-dependency-path: |
           backend/requirements/default.txt
           backend/requirements/dev.txt
-    - run: | 
+          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
 
     - name: Run MyPy
       run: |
         cd backend
         mypy .
 
+    - name: Run ruff
+      run: |
+        cd backend
+        ruff .
+
     - name: Check import order with reorder-python-imports
       run: |
         cd backend

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

@@ -0,0 +1,35 @@
+name: Python Unit Tests
+
+on:
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  backend-check:
+    runs-on: ubuntu-latest
+
+    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 -r backend/requirements/default.txt
+        pip install -r backend/requirements/dev.txt
+
+    - name: Run Tests
+      shell: script -q -e -c "bash --noprofile --norc -eo pipefail {0}"
+      run: py.test -o junit_family=xunit2 -xv --ff backend/tests/unit

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

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

.gitignore

@@ -1 +1,9 @@
-.env
+.env
+.DS_store
+.venv
+.mypy_cache
+.idea
+/deployment/data/nginx/app.conf
+.vscode/launch.json
+*.sw?
+/backend/tests/regression/answer_quality/search_test_config.yaml

.pre-commit-config.yaml

@@ -15,10 +15,31 @@ repos:
       # in the backend directory called `alembic`
       exclude: ^backend/alembic/
 
-  # We would like to have a mypy pre-commit hook, but due to the fact that 
-  # pre-commit runs in it's own isolated environment, we would need to install 
+  # These settings will remove unused imports with side effects
+  # Note: The repo currently does not and should not have imports with side effects
+  - repo: https://github.com/PyCQA/autoflake
+    rev: v2.2.0
+    hooks:
+      - id: autoflake
+        args: [ '--remove-all-unused-imports', '--remove-unused-variables', '--in-place' , '--recursive']
+
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    # Ruff version.
+    rev: v0.0.286
+    hooks:
+      - id: ruff
+  - repo: https://github.com/pre-commit/mirrors-prettier
+    rev: v3.1.0
+    hooks:
+    - id: prettier
+      types_or: [html, css, javascript, ts, tsx]
+      additional_dependencies:
+      - prettier
+
+  # We would like to have a mypy pre-commit hook, but due to the fact that
+  # pre-commit runs in it's own isolated environment, we would need to install
   # and keep in sync all dependencies so mypy has access to the appropriate type
-  # stubs. This does not seem worth it at the moment, so for now we will stick to 
+  # stubs. This does not seem worth it at the moment, so for now we will stick to
   # having mypy run via Github Actions / manually by contributors
   # - repo: https://github.com/pre-commit/mirrors-mypy
   #   rev: v1.1.1
@@ -30,15 +51,15 @@ repos:
   #       # with requirements/dev.txt + requirements/default.txt
   #       additional_dependencies: [
   #         alembic==1.10.4,
-  #         types-beautifulsoup4==4.12.0.3, 
-  #         types-html5lib==1.1.11.13, 
-  #         types-oauthlib==3.2.0.9, 
-  #         types-psycopg2==2.9.21.10, 
-  #         types-python-dateutil==2.8.19.13, 
-  #         types-regex==2023.3.23.1, 
-  #         types-requests==2.28.11.17, 
-  #         types-retry==0.9.9.3, 
+  #         types-beautifulsoup4==4.12.0.3,
+  #         types-html5lib==1.1.11.13,
+  #         types-oauthlib==3.2.0.9,
+  #         types-psycopg2==2.9.21.10,
+  #         types-python-dateutil==2.8.19.13,
+  #         types-regex==2023.3.23.1,
+  #         types-requests==2.28.11.17,
+  #         types-retry==0.9.9.3,
   #         types-urllib3==1.26.25.11
   #       ]
   #       # TODO: add back once errors are addressed
-  #       # args: [--strict]  
+  #       # args: [--strict]

.vscode/env_template.txt

@@ -0,0 +1,52 @@
+# Copy this file to .env at the base of the repo and fill in the <REPLACE THIS> values
+# This will help with development iteration speed and reduce repeat tasks for dev
+# 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_CHUNK_FILTER=True
+
+
+# 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 3.5 turbo due to it being cheaper
+GEN_AI_MODEL_VERSION=gpt-3.5-turbo
+FAST_GEN_AI_MODEL_VERSION=gpt-3.5-turbo
+
+# 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.json

@@ -1,65 +0,0 @@
-{
-    // 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",
-    "configurations": [
-        {
-            "name": "Danswer backend",
-            "type": "python",
-            "request": "launch",
-            "module": "uvicorn",
-            "cwd": "${workspaceFolder}/backend",
-            "env": {
-                "LOG_LEVEL": "DEBUG",
-                "DISABLE_AUTH": "True",
-                "TYPESENSE_API_KEY": "typesense_api_key",
-                "DYNAMIC_CONFIG_DIR_PATH": "./dynamic_config_storage",
-            },
-            "args": [
-                "danswer.main:app",
-                "--reload",
-                "--port",
-                "8080"
-            ]
-        },
-        {
-            "name": "Danswer indexer",
-            "type": "python",
-            "request": "launch",
-            "program": "danswer/background/update.py",
-            "cwd": "${workspaceFolder}/backend",
-            "env": {
-                "LOG_LEVEL": "DEBUG",
-                "PYTHONPATH": ".",
-                "TYPESENSE_API_KEY": "typesense_api_key",
-                "DYNAMIC_CONFIG_DIR_PATH": "./dynamic_config_storage",
-            },
-        },
-        {
-            "name": "Danswer temp files deletion",
-            "type": "python",
-            "request": "launch",
-            "program": "danswer/background/file_deletion.py",
-            "cwd": "${workspaceFolder}/backend",
-            "env": {
-                "LOG_LEVEL": "DEBUG",
-                "PYTHONPATH": "${workspaceFolder}/backend",
-            },
-        },
-        // For the listner to access the Slack API,
-        // DANSWER_BOT_SLACK_APP_TOKEN & DANSWER_BOT_SLACK_BOT_TOKEN need to be set in .env file located in the root of the project
-        {
-            "name": "Danswer slack bot listener",
-            "type": "python",
-            "request": "launch",
-            "program": "danswer/listeners/slack_listener.py",
-            "cwd": "${workspaceFolder}/backend",
-            "envFile": "${workspaceFolder}/.env",
-            "env": {
-                "LOG_LEVEL": "DEBUG",
-                "PYTHONPATH": ".",
-            },
-        }
-    ]
-}

.vscode/launch.template.jsonc

@@ -0,0 +1,129 @@
+/*
+
+  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",
+    "configurations": [
+        {
+            "name": "Web Server",
+            "type": "node",
+            "request": "launch",
+            "cwd": "${workspaceRoot}/web",
+            "runtimeExecutable": "npm",
+            "envFile": "${workspaceFolder}/.env",
+            "runtimeArgs": [
+                "run", "dev"
+            ],
+            "console": "integratedTerminal"
+        },
+        {
+            "name": "Model Server",
+            "type": "python",
+            "request": "launch",
+            "module": "uvicorn",
+            "cwd": "${workspaceFolder}/backend",
+            "envFile": "${workspaceFolder}/.env",
+            "env": {
+                "LOG_LEVEL": "DEBUG",
+                "PYTHONUNBUFFERED": "1"
+            },
+            "args": [
+                "model_server.main:app",
+                "--reload",
+                "--port",
+                "9000"
+            ]
+        },
+        {
+            "name": "API Server",
+            "type": "python",
+            "request": "launch",
+            "module": "uvicorn",
+            "cwd": "${workspaceFolder}/backend",
+            "envFile": "${workspaceFolder}/.env",
+            "env": {
+                "LOG_DANSWER_MODEL_INTERACTIONS": "True",
+                "LOG_LEVEL": "DEBUG",
+                "PYTHONUNBUFFERED": "1"
+            },
+            "args": [
+                "danswer.main:app",
+                "--reload",
+                "--port",
+                "8080"
+            ]
+        },
+        {
+            "name": "Indexing",
+            "type": "python",
+            "request": "launch",
+            "program": "danswer/background/update.py",
+            "cwd": "${workspaceFolder}/backend",
+            "envFile": "${workspaceFolder}/.env",
+            "env": {
+                "ENABLE_MINI_CHUNK": "false",
+                "LOG_LEVEL": "DEBUG",
+                "PYTHONUNBUFFERED": "1",
+                "PYTHONPATH": "."
+            }
+        },
+        // Celery and all async jobs, usually would include indexing as well but this is handled separately above for dev
+        {
+            "name": "Background Jobs",
+            "type": "python",
+            "request": "launch",
+            "program": "scripts/dev_run_background_jobs.py",
+            "cwd": "${workspaceFolder}/backend",
+            "envFile": "${workspaceFolder}/.env",
+            "env": {
+                "LOG_DANSWER_MODEL_INTERACTIONS": "True",
+                "LOG_LEVEL": "DEBUG",
+                "PYTHONUNBUFFERED": "1",
+                "PYTHONPATH": "."
+            },
+            "args": [
+                "--no-indexing"
+            ]
+        },
+        // For the listner to access the Slack API,
+        // DANSWER_BOT_SLACK_APP_TOKEN & DANSWER_BOT_SLACK_BOT_TOKEN need to be set in .env file located in the root of the project
+        {
+            "name": "Slack Bot",
+            "type": "python",
+            "request": "launch",
+            "program": "danswer/danswerbot/slack/listener.py",
+            "cwd": "${workspaceFolder}/backend",
+            "envFile": "${workspaceFolder}/.env",
+            "env": {
+                "LOG_LEVEL": "DEBUG",
+                "PYTHONUNBUFFERED": "1",
+                "PYTHONPATH": "."
+            }
+        },
+        {
+            "name": "Pytest",
+            "type": "python",
+            "request": "launch",
+            "module": "pytest",
+            "cwd": "${workspaceFolder}/backend",
+            "envFile": "${workspaceFolder}/.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"
+            ]
+        }
+    ]
+}

CONTRIBUTING.md

@@ -1,3 +1,5 @@
+<!-- DANSWER_METADATA={"link": "https://github.com/danswer-ai/danswer/blob/main/CONTRIBUTING.md"} -->
+
 # Contributing to Danswer
 Hey there! We are so excited that you're interested in Danswer.
 
@@ -6,7 +8,7 @@ As an open source project in a rapidly changing space, we welcome all contributi
 
 ## 💃 Guidelines
 ### Contribution Opportunities
-The [GitHub issues](https://github.com/danswer-ai/danswer/issues) page is a great place to start for contribution ideas.
+The [GitHub Issues](https://github.com/danswer-ai/danswer/issues) page is a great place to start for contribution ideas.
 
 Issues that have been explicitly approved by the maintainers (aligned with the direction of the project)
 will be marked with the `approved by maintainers` label.
@@ -19,7 +21,9 @@ If you have a new/different contribution in mind, we'd love to hear about it!
 Your input is vital to making sure that Danswer moves in the right direction.
 Before starting on implementation, please raise a GitHub issue.
 
-And always feel free to message us (Chris Weaver / Yuhong Sun) on Slack / Discord directly about anything at all. 
+And always feel free to message us (Chris Weaver / Yuhong Sun) on 
+[Slack](https://join.slack.com/t/danswer/shared_invite/zt-2afut44lv-Rw3kSWu6_OmdAXRpCv80DQ) / 
+[Discord](https://discord.gg/TDJ59cGV2X) directly about anything at all. 
 
 
 ### Contributing Code
@@ -36,7 +40,7 @@ Our goal is to make contributing as easy as possible. If you run into any issues
 That way we can help future contributors and users can avoid the same issue.
 
 We also have support channels and generally interesting discussions on our
-[Slack](https://join.slack.com/t/danswer/shared_invite/zt-1u3h3ke3b-VGh1idW19R8oiNRiKBYv2w)
+[Slack](https://join.slack.com/t/danswer/shared_invite/zt-2afut44lv-Rw3kSWu6_OmdAXRpCv80DQ)
 and 
 [Discord](https://discord.gg/TDJ59cGV2X).
 
@@ -44,10 +48,9 @@ We would love to see you there!
 
 
 ## Get Started 🚀
-Danswer being a fully functional app, relies on several external pieces of software, specifically:
-- Postgres
-- Vector DB ([Qdrant](https://github.com/qdrant/qdrant))
-- Search Engine ([Typesense](https://github.com/typesense/typesense))
+Danswer being a fully functional app, relies on some external pieces of software, specifically:
+- [Postgres](https://www.postgresql.org/) (Relational DB)
+- [Vespa](https://vespa.ai/) (Vector DB/Search Engine)
 
 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
@@ -55,11 +58,10 @@ development purposes but also feel free to just use the containers and update wi
 
 
 ### Local Set Up
-We've tested primarily with Python versions >= 3.11 but the code should work with Python >= 3.9.
+It is recommended to use Python version 3.11
 
-This guide skips a few optional features for simplicity, reach out if you need any of these:
-- User Authentication feature
-- File Connector background job
+If using a lower version, modifications will have to be made to the code.
+If using a higher version, the version of Tensorflow we use may not be available for your platform.
 
 
 #### Installing Requirements
@@ -70,15 +72,24 @@ For convenience here's a command for it:
 python -m venv .venv
 source .venv/bin/activate
 ```
-_For Windows activate via:_
+
+--> Note that this virtual environment MUST NOT be set up WITHIN the danswer
+directory
+
+_For Windows, activate the virtual environment using Command Prompt:_
 ```bash
 .venv\Scripts\activate
 ```
+If using PowerShell, the command slightly differs:
+```powershell
+.venv\Scripts\Activate.ps1
+```
 
 Install the required python dependencies:
 ```bash
 pip install -r danswer/backend/requirements/default.txt
 pip install -r danswer/backend/requirements/dev.txt
+pip install -r danswer/backend/requirements/model_server.txt
 ```
 
 Install [Node.js and npm](https://docs.npmjs.com/downloading-and-installing-node-js-and-npm) for the frontend.
@@ -87,79 +98,68 @@ Once the above is done, navigate to `danswer/web` run:
 npm i
 ```
 
-Install Playwright (required by the Web Connector), with the python venv active, run:
+Install Playwright (required by the Web Connector)
+
+> Note: If you have just done the pip install, open a new terminal and source the python virtual-env again.
+This will update the path to include playwright
+
+Then install Playwright by running:
 ```bash
 playwright install
 ```
 
 
 #### Dependent Docker Containers
-First navigate to `danswer/deployment/docker_compose`, then start up the containers with:
-
-Postgres:
+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 relational_db
+docker compose -f docker-compose.dev.yml -p danswer-stack up -d index relational_db
 ```
-
-Qdrant:
-```bash
-docker compose -f docker-compose.dev.yml -p danswer-stack up -d vector_db
-```
-
-Typesense:
-```bash
-docker compose -f docker-compose.dev.yml -p danswer-stack up -d search_engine
-```
-
+(index refers to Vespa and relational_db refers to Postgres)
 
 #### Running Danswer
-
-Setup a folder to store config. Navigate to `danswer/backend` and run:
-```bash
-mkdir dynamic_config_storage
-```
-
 To start the frontend, navigate to `danswer/web` and run:
 ```bash
-DISABLE_AUTH=true npm run dev
+npm run dev
 ```
-_for Windows, run:_
+
+Next, start the model server which runs the local NLP models.
+Navigate to `danswer/backend` and run:
 ```bash
-(SET "DISABLE_AUTH=true" && npm run dev)
+uvicorn model_server.main:app --reload --port 9000
+```
+_For Windows (for compatibility with both PowerShell and Command Prompt):_
+```bash
+powershell -Command "
+    uvicorn model_server.main:app --reload --port 9000
+"
 ```
 
+The first time running Danswer, you will need to run the DB migrations for Postgres.
+After the first time, this is no longer required unless the DB models change.
 
-The first time running Danswer, you will need to run the DB migrations.
 Navigate to `danswer/backend` and with the venv active, run:
 ```bash
 alembic upgrade head
 ```
 
-To run the backend API server, navigate to `danswer/backend` and run:
+Next, start the task queue which orchestrates the background jobs.
+Jobs that take more time are run async from the API server.
+
+Still in `danswer/backend`, run:
 ```bash
-DISABLE_AUTH=True TYPESENSE_API_KEY=typesense_api_key DYNAMIC_CONFIG_DIR_PATH=./dynamic_config_storage uvicorn danswer.main:app --reload --port 8080
+python ./scripts/dev_run_background_jobs.py
+```
+
+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 " $env:DISABLE_AUTH='True'; $env:TYPESENSE_API_KEY='typesense_api_key'; $env:DYNAMIC_CONFIG_DIR_PATH='./dynamic_config_storage'; uvicorn danswer.main:app --reload --port 8080 "
-```
-
-To run the background job to check for connector updates and index documents, navigate to `danswer/backend` and run:
-```bash
-PYTHONPATH=. TYPESENSE_API_KEY=typesense_api_key DYNAMIC_CONFIG_DIR_PATH=./dynamic_config_storage python danswer/background/update.py
-```
-_For Windows:_
-```bash
-powershell -Command " $env:PYTHONPATH='.'; $env:TYPESENSE_API_KEY='typesense_api_key'; $env:DYNAMIC_CONFIG_DIR_PATH='./dynamic_config_storage'; python danswer/background/update.py "
-```
-
-To run the background job which handles deletion of connectors, navigate to `danswer/backend` and run:
-```bash
-PYTHONPATH=. TYPESENSE_API_KEY=typesense_api_key DYNAMIC_CONFIG_DIR_PATH=./dynamic_config_storage python danswer/background/connector_deletion.py
-```
-_For Windows:_
-```bash
-powershell -Command " $env:PYTHONPATH='.'; $env:TYPESENSE_API_KEY='typesense_api_key'; $env:DYNAMIC_CONFIG_DIR_PATH='./dynamic_config_storage'; python danswer/background/connector_deletion.py "
+powershell -Command "
+    $env:AUTH_TYPE='disabled'
+    uvicorn danswer.main:app --reload --port 8080 
+"
 ```
 
 Note: if you need finer logging, add the additional environment variable `LOG_LEVEL=DEBUG` to the relevant services.
@@ -176,20 +176,16 @@ pre-commit install
 
 Additionally, we use `mypy` for static type checking.
 Danswer is fully type-annotated, and we would like to keep it that way! 
-Right now, there is no automated type checking at the moment (coming soon), but we ask you to manually run it before
-creating a pull requests with `python -m mypy .` from the `danswer/backend` directory.
+To run the mypy checks manually, run `python -m mypy .` from the `danswer/backend` directory.
 
 
 #### Web
 We use `prettier` for formatting. The desired version (2.8.8) will be installed via a `npm i` from the `danswer/web` directory. 
 To run the formatter, use `npx prettier --write .` from the `danswer/web` directory.
-Like `mypy`, we have no automated formatting yet (coming soon), but we request that, for now,
-you run this manually before creating a pull request.
+Please double check that prettier passes before creating a pull request.
 
 
 ### Release Process
 Danswer follows the semver versioning standard.
 A set of Docker containers will be pushed automatically to DockerHub with every tag.
 You can see the containers [here](https://hub.docker.com/search?q=danswer%2F).
-
-As pre-1.0 software, even patch releases may contain breaking or non-backwards-compatible changes.

LICENSE

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

README.md

@@ -1,15 +1,17 @@
+<!-- DANSWER_METADATA={"link": "https://github.com/danswer-ai/danswer/blob/main/README.md"} -->
+
 <h2 align="center">
 <a href="https://www.danswer.ai/"> <img width="50%" src="https://github.com/danswer-owners/danswer/blob/1fabd9372d66cd54238847197c33f091a724803b/DanswerWithName.png?raw=true)" /></a>
 </h2>
 
 <p align="center">
-<p align="center">OpenSource Enterprise Question-Answering</p>
+<p align="center">Open Source Gen-AI Chat + Unified Search.</p>
 
 <p align="center">
 <a href="https://docs.danswer.dev/" target="_blank">
     <img src="https://img.shields.io/badge/docs-view-blue" alt="Documentation">
 </a>
-<a href="https://join.slack.com/t/danswer/shared_invite/zt-1u5ycen3o-6SJbWfivLWP5LPyp_jftuw" target="_blank">
+<a href="https://join.slack.com/t/danswer/shared_invite/zt-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">
@@ -20,25 +22,108 @@
 </a>
 </p>
 
-<strong>[Danswer](https://www.danswer.ai/)</strong> allows you to ask natural language questions against internal documents and get back reliable answers backed by quotes and references from the source material so that you can always trust what you get back. You can connect to a number of common tools such as Slack, GitHub, Confluence, amongst others.
+<strong>[Danswer](https://www.danswer.ai/)</strong> is the AI Assistant connected to your company's docs, apps, and people. 
+Danswer provides a Chat interface and plugs into any LLM of your choice. Danswer can be deployed anywhere and for any 
+scale - on a laptop, on-premise, or to cloud. Since you own the deployment, your user data and chats are fully in your 
+own control. Danswer is MIT licensed and designed to be modular and easily extensible. The system also comes fully ready 
+for production usage with user authentication, role management (admin/basic users), chat persistence, and a UI for 
+configuring Personas (AI Assistants) and their Prompts.
 
-Check out our <strong><a href="https://www.youtube.com/watch?v=geNzY1nbCnU">Video Demo</a></strong>!
+Danswer also serves as a Unified Search across all common workplace tools such as Slack, Google Drive, Confluence, etc.
+By combining LLMs and team specific knowledge, Danswer becomes a subject matter expert for the team. Imagine ChatGPT if
+it had access to your team's unique knowledge! It enables questions such as "A customer wants feature X, is this already
+supported?" or "Where's the pull request for feature Y?"
+
+<h3>Usage</h3>
+
+Danswer Web App:
+
+https://github.com/danswer-ai/danswer/assets/32520769/563be14c-9304-47b5-bf0a-9049c2b6f410
 
 
-## Features 💃
-* Direct QA powered by Generative AI models with answers backed by quotes and source links.
-* Intelligent Document Retrieval (Semantic Search/Reranking) using the latest LLMs.
-* An AI Helper backed by a custom Deep Learning model to interpret user intent.
-* User authentication and document level access management.
-* Connectors to Slack, GitHub, GoogleDrive, Confluence, local files, and web scraping, with more to come.
-* Option to use Opensource LLMs like Orca, Falcon etc. in place of OpenAI GPT.
-* Management Dashboard to manage connectors and set up features such as live update fetching.
-* One line Docker Compose (or Kubernetes) deployment to host Danswer anywhere.
+Or, plug Danswer into your existing Slack workflows (more integrations to come 😁):
 
-## Upcoming
-* Chat/Conversation support.
-* Templates to easily build custom connectors.
-* Personalized search
+https://github.com/danswer-ai/danswer/assets/25087905/3e19739b-d178-4371-9a38-011430bdec1b
+
+
+For more details on the Admin UI to manage connectors and users, check out our 
+<strong><a href="https://www.youtube.com/watch?v=geNzY1nbCnU">Full Video Demo</a></strong>!
+
+## Deployment
+
+Danswer can easily be run locally (even on a laptop) or deployed on a virtual machine with a single
+`docker compose` command. Checkout our [docs](https://docs.danswer.dev/quickstart) to learn more.
+
+We also have built-in support for deployment on Kubernetes. Files for that can be found [here](https://github.com/danswer-ai/danswer/tree/main/deployment/kubernetes).
+
+
+## 💃 Main Features 
+* Chat UI with the ability to select documents to chat with.
+* Create custom AI Assistants with different prompts and backing knowledge sets.
+* Connect Danswer with LLM of your choice (self-host for a fully airgapped solution).
+* Document Search + AI Answers for natural language queries.
+* Connectors to all common workplace tools like Google Drive, Confluence, Slack, etc.
+* Slack integration to get answers and search results directly in Slack.
+
+
+## 🚧 Roadmap
+* Chat/Prompt sharing with specific teammates and user groups.
+* Multi-Model model support, chat with images, video etc.
+* Choosing between LLMs and parameters during chat session.
+* Tool calling and agent configurations options.
+* Organizational understanding and ability to locate and suggest experts from your team.
+
+
+## Other Noteable Benefits of Danswer
+* User Authentication with document level access management.
+* Best in class Hybrid Search across all sources (BM-25 + prefix aware embedding models).
+* Admin Dashboard to configure connectors, document-sets, access, etc.
+* Custom deep learning models + learn from user feedback.
+* Easy deployment and ability to host Danswer anywhere of your choosing.
+
+
+## 🔌 Connectors
+Efficiently pulls the latest changes from:
+  * Slack
+  * GitHub
+  * Google Drive
+  * Confluence
+  * Jira
+  * Zendesk
+  * Gmail
+  * Notion
+  * Gong
+  * Slab
+  * Linear
+  * Productboard
+  * Guru
+  * Bookstack
+  * Document360
+  * Sharepoint
+  * Hubspot
+  * Local Files
+  * Websites
+  * And more ...
+
+## 📚 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/.dockerignore

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

backend/.gitignore

@@ -1,9 +1,11 @@
 __pycache__/
+.mypy_cache
 .idea/
 site_crawls/
 .ipynb_checkpoints/
 api_keys.py
 *ipynb
-qdrant-data/
-typesense-data/
-.env
+.env*
+vespa-app.zip
+dynamic_config_storage/
+celerybeat-schedule*

backend/.trivyignore

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

backend/Dockerfile

@@ -1,23 +1,103 @@
-FROM python:3.11-slim-bullseye
+FROM python:3.11.7-slim-bookworm
 
-RUN apt-get update \
-    && apt-get install -y git cmake pkg-config libprotobuf-c-dev protobuf-compiler \
-       libprotobuf-dev libgoogle-perftools-dev libpq-dev build-essential cron curl \
-       supervisor \
-    && rm -rf /var/lib/apt/lists/*
+LABEL com.danswer.maintainer="founders@danswer.ai"
+LABEL com.danswer.description="This image is the web/frontend container of Danswer which \
+contains code for both the Community and Enterprise editions of Danswer. If you do not \
+have a contract or agreement with DanswerAI, you are not permitted to use the Enterprise \
+Edition features outside of personal development or testing purposes. Please reach out to \
+founders@danswer.ai for more information. Please visit https://github.com/danswer-ai/danswer"
 
+# 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}"
+# Install system dependencies
+# cmake needed for psycopg (postgres)
+# libpq-dev needed for psycopg (postgres)
+# curl included just for users' convenience
+# zip for Vespa step futher down
+# ca-certificates for HTTPS
+RUN apt-get update && \
+    apt-get install -y \
+        cmake \
+        curl \
+        zip \
+        ca-certificates \
+        libgnutls30=3.7.9-2+deb12u3 \
+        libblkid1=2.38.1-5+deb12u1 \
+        libmount1=2.38.1-5+deb12u1 \
+        libsmartcols1=2.38.1-5+deb12u1 \
+        libuuid1=2.38.1-5+deb12u1 \
+        libxmlsec1-dev \
+        pkg-config \
+        gcc && \
+    rm -rf /var/lib/apt/lists/* && \
+    apt-get clean
+
+# Install Python dependencies
+# Remove py which is pulled in by retry, py is not needed and is a CVE
 COPY ./requirements/default.txt /tmp/requirements.txt
-RUN pip install --no-cache-dir --upgrade -r /tmp/requirements.txt
-RUN playwright install
-RUN playwright install-deps
+COPY ./requirements/ee.txt /tmp/ee-requirements.txt
+RUN pip install --no-cache-dir --upgrade \
+        -r /tmp/requirements.txt \
+        -r /tmp/ee-requirements.txt && \
+    pip uninstall -y py && \
+    playwright install chromium && \
+    playwright install-deps chromium && \
+    ln -s /usr/local/bin/supervisord /usr/bin/supervisord
 
+# Cleanup for CVEs and size reduction
+# https://github.com/tornadoweb/tornado/issues/3107
+# xserver-common and xvfb included by playwright installation but not needed after
+# perl-base is part of the base Python Debian image but not needed for Danswer functionality
+# perl-base could only be removed with --allow-remove-essential
+RUN apt-get update && \
+    apt-get remove -y --allow-remove-essential \
+        perl-base \
+        xserver-common \
+        xvfb \
+        cmake \
+        libldap-2.5-0 \
+        libxmlsec1-dev \
+        pkg-config \
+        gcc && \
+    apt-get install -y libxmlsec1-openssl && \
+    apt-get autoremove -y && \
+    rm -rf /var/lib/apt/lists/* && \
+    rm -f /usr/local/lib/python3.11/site-packages/tornado/test/test.key
+
+# Pre-downloading models for setups with limited egress
+RUN python -c "from transformers import AutoTokenizer; AutoTokenizer.from_pretrained('intfloat/e5-base-v2')"
+
+# Pre-downloading NLTK for setups with limited egress
+RUN python -c "import nltk; \
+nltk.download('stopwords', quiet=True); \
+nltk.download('wordnet', quiet=True); \
+nltk.download('punkt', quiet=True);"
+
+# 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 /etc/supervisor/conf.d/supervisord.conf
+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
 
-# By default this container does nothing, it is used by api server and background which specify their own CMD
+# Default command which does nothing
+# This container is used by api server and background which specify their own CMD
 CMD ["tail", "-f", "/dev/null"]

backend/Dockerfile.model_server

@@ -0,0 +1,46 @@
+FROM python:3.11.7-slim-bookworm
+
+LABEL com.danswer.maintainer="founders@danswer.ai"
+LABEL com.danswer.description="This image is for the Danswer model server which runs all of the \
+AI models for Danswer. This container and all the code is MIT Licensed and free for all to use. \
+You can find it at https://hub.docker.com/r/danswer/danswer-model-server. For more details, \
+visit https://github.com/danswer-ai/danswer."
+
+# Default DANSWER_VERSION, typically overriden during builds by GitHub Actions.
+ARG DANSWER_VERSION=0.3-dev
+ENV DANSWER_VERSION=${DANSWER_VERSION}
+RUN echo "DANSWER_VERSION: ${DANSWER_VERSION}"
+
+COPY ./requirements/model_server.txt /tmp/requirements.txt
+RUN pip install --no-cache-dir --upgrade -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'); \
+AutoTokenizer.from_pretrained('mixedbread-ai/mxbai-rerank-xsmall-v1'); \
+snapshot_download('danswer/intent-model'); \
+snapshot_download('intfloat/e5-base-v2'); \
+snapshot_download('mixedbread-ai/mxbai-rerank-xsmall-v1')"
+
+WORKDIR /app
+
+# Utils used by model server
+COPY ./danswer/utils/logger.py /app/danswer/utils/logger.py
+
+# Place to fetch version information
+COPY ./danswer/__init__.py /app/danswer/__init__.py
+
+# Shared between Danswer Backend and Model Server
+COPY ./shared_configs /app/shared_configs
+
+# Model Server main code
+COPY ./model_server /app/model_server
+
+ENV PYTHONPATH /app
+
+CMD ["uvicorn", "model_server.main:app", "--host", "0.0.0.0", "--port", "9000"]

backend/alembic/README.md

@@ -1,4 +1,8 @@
-Generic single-database configuration with an async dbapi.
+<!-- DANSWER_METADATA={"link": "https://github.com/danswer-ai/danswer/blob/main/backend/alembic/README.md"} -->
+
+# Alembic DB Migrations
+These files are for creating/updating the tables in the Relational DB (Postgres).
+Danswer migrations use a generic single-database configuration with an async dbapi.
 
 ## To generate new migrations: 
 run from danswer/backend:
@@ -7,7 +11,6 @@ run from danswer/backend:
 More info can be found here: https://alembic.sqlalchemy.org/en/latest/autogenerate.html
 
 ## Running migrations
-
 To run all un-applied migrations:
 `alembic upgrade head`
 

backend/alembic/env.py

@@ -7,6 +7,7 @@ from danswer.db.models import Base
 from sqlalchemy import pool
 from sqlalchemy.engine import Connection
 from sqlalchemy.ext.asyncio import create_async_engine
+from celery.backends.database.session import ResultModelBase  # type: ignore
 
 # this is the Alembic Config object, which provides
 # access to the values within the .ini file in use.
@@ -21,7 +22,7 @@ if config.config_file_name is not None:
 # for 'autogenerate' support
 # from myapp import mymodel
 # target_metadata = mymodel.Base.metadata
-target_metadata = Base.metadata
+target_metadata = [Base.metadata, ResultModelBase.metadata]
 
 # other values from the config, defined by the needs of env.py,
 # can be acquired:
@@ -44,7 +45,7 @@ def run_migrations_offline() -> None:
     url = build_connection_string()
     context.configure(
         url=url,
-        target_metadata=target_metadata,
+        target_metadata=target_metadata,  # type: ignore
         literal_binds=True,
         dialect_opts={"paramstyle": "named"},
     )
@@ -54,7 +55,7 @@ def run_migrations_offline() -> None:
 
 
 def do_run_migrations(connection: Connection) -> None:
-    context.configure(connection=connection, target_metadata=target_metadata)
+    context.configure(connection=connection, target_metadata=target_metadata)  # type: ignore
 
     with context.begin_transaction():
         context.run_migrations()

backend/alembic/versions/0568ccf46a6b_add_thread_specific_model_selection.py

@@ -0,0 +1,31 @@
+"""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:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.add_column(
+        "chat_session",
+        sa.Column("current_alternate_model", sa.String(), nullable=True),
+    )
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_column("chat_session", "current_alternate_model")
+    # ### end Alembic commands ###

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/0a2b51deb0b8_add_starter_prompts.py

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

backend/alembic/versions/0a98909f2757_enable_encrypted_fields.py

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

backend/alembic/versions/15326fcec57e_introduce_danswer_apis.py

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

backend/alembic/versions/173cae5bba26_port_config_store.py

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

backend/alembic/versions/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",
+        "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:

backend/alembic/versions/30c1d5744104_persona_datetime_aware.py

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

backend/alembic/versions/3879338f8ba1_add_tool_table.py

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

backend/alembic/versions/38eda64af7fe_add_chat_session_sharing.py

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

backend/alembic/versions/3a7802814195_add_alternate_assistant_to_chat_message.py

@@ -0,0 +1,38 @@
+"""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:
+    # ### commands auto generated by Alembic - please adjust! ###
+    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"],
+    )
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_constraint("fk_chat_message_persona", "chat_message", type_="foreignkey")
+    op.drop_column("chat_message", "alternate_assistant_id")

backend/alembic/versions/3b25685ff73c_move_is_public_to_cc_pair.py

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

backend/alembic/versions/3c5e35aa9af0_polling_document_count.py

@@ -12,8 +12,8 @@ from alembic import op
 # revision identifiers, used by Alembic.
 revision = "3c5e35aa9af0"
 down_revision = "27c6ecc08586"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:
@@ -35,6 +35,7 @@ def upgrade() -> None:
                 "SUCCESS",
                 "FAILED",
                 name="indexingstatus",
+                native_enum=False,
             ),
             nullable=False,
         ),

backend/alembic/versions/401c1ac29467_add_tables_for_ui_based_llm_.py

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

backend/alembic/versions/44f856ae2a4a_add_cloud_embedding_model.py

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

backend/alembic/versions/4505fd7302e1_added_is_internet_to_dbdoc.py

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

backend/alembic/versions/465f78d9b7f9_larger_access_tokens_for_oauth.py

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

backend/alembic/versions/46625e4745d4_remove_native_enum.py

@@ -0,0 +1,31 @@
+"""Remove Native Enum
+
+Revision ID: 46625e4745d4
+Revises: 9d97fecfab7f
+Create Date: 2023-10-27 11:38:33.803145
+
+"""
+from alembic import op
+from sqlalchemy import String
+
+# revision identifiers, used by Alembic.
+revision = "46625e4745d4"
+down_revision = "9d97fecfab7f"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    # At this point, we directly changed some previous migrations,
+    # https://github.com/danswer-ai/danswer/pull/637
+    # Due to using Postgres native Enums, it caused some complications for first time users.
+    # To remove those complications, all Enums are only handled application side moving forward.
+    # This migration exists to ensure that existing users don't run into upgrade issues.
+    op.alter_column("index_attempt", "status", type_=String)
+    op.alter_column("connector_credential_pair", "last_attempt_status", type_=String)
+    op.execute("DROP TYPE IF EXISTS indexingstatus")
+
+
+def downgrade() -> None:
+    # We don't want Native Enums, do nothing
+    pass

backend/alembic/versions/4738e4b3bae1_pg_file_store.py

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

backend/alembic/versions/47433d30de82_create_indexattempt_table.py

@@ -1,7 +1,7 @@
 """Create IndexAttempt table
 
 Revision ID: 47433d30de82
-Revises: 
+Revises:
 Create Date: 2023-05-04 00:55:32.971991
 
 """
@@ -11,9 +11,9 @@ from sqlalchemy.dialects import postgresql
 
 # revision identifiers, used by Alembic.
 revision = "47433d30de82"
-down_revision = None
-branch_labels = None
-depends_on = None
+down_revision: None = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:
@@ -59,6 +59,7 @@ def upgrade() -> None:
                 "SUCCESS",
                 "FAILED",
                 name="indexingstatus",
+                native_enum=False,
             ),
             nullable=False,
         ),
@@ -70,4 +71,3 @@ def upgrade() -> None:
 
 def downgrade() -> None:
     op.drop_table("index_attempt")
-    sa.Enum(name="indexingstatus").drop(op.get_bind(), checkfirst=False)

backend/alembic/versions/475fcefe8826_add_name_to_api_key.py

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

backend/alembic/versions/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/50b683a8295c_add_additional_retrieval_controls_to_.py

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

backend/alembic/versions/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

@@ -0,0 +1,59 @@
+"""Add document set tables
+
+Revision ID: 57b53544726e
+Revises: 800f48024ae9
+Create Date: 2023-09-20 16:59:39.097177
+
+"""
+from alembic import op
+import fastapi_users_db_sqlalchemy
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "57b53544726e"
+down_revision = "800f48024ae9"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "document_set",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column("name", sa.String(), nullable=False),
+        sa.Column("description", sa.String(), nullable=False),
+        sa.Column(
+            "user_id",
+            fastapi_users_db_sqlalchemy.generics.GUID(),
+            nullable=True,
+        ),
+        sa.Column("is_up_to_date", sa.Boolean(), nullable=False),
+        sa.ForeignKeyConstraint(
+            ["user_id"],
+            ["user.id"],
+        ),
+        sa.PrimaryKeyConstraint("id"),
+        sa.UniqueConstraint("name"),
+    )
+    op.create_table(
+        "document_set__connector_credential_pair",
+        sa.Column("document_set_id", sa.Integer(), nullable=False),
+        sa.Column("connector_credential_pair_id", sa.Integer(), nullable=False),
+        sa.Column("is_current", sa.Boolean(), nullable=False),
+        sa.ForeignKeyConstraint(
+            ["connector_credential_pair_id"],
+            ["connector_credential_pair.id"],
+        ),
+        sa.ForeignKeyConstraint(
+            ["document_set_id"],
+            ["document_set.id"],
+        ),
+        sa.PrimaryKeyConstraint(
+            "document_set_id", "connector_credential_pair_id", "is_current"
+        ),
+    )
+
+
+def downgrade() -> None:
+    op.drop_table("document_set__connector_credential_pair")
+    op.drop_table("document_set")

backend/alembic/versions/5809c0787398_add_chat_sessions.py

@@ -0,0 +1,85 @@
+"""Add Chat Sessions
+
+Revision ID: 5809c0787398
+Revises: d929f0c1c6af
+Create Date: 2023-09-04 15:29:44.002164
+
+"""
+import fastapi_users_db_sqlalchemy
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "5809c0787398"
+down_revision = "d929f0c1c6af"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "chat_session",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column(
+            "user_id",
+            fastapi_users_db_sqlalchemy.generics.GUID(),
+            nullable=True,
+        ),
+        sa.Column("description", sa.Text(), nullable=False),
+        sa.Column("deleted", sa.Boolean(), nullable=False),
+        sa.Column(
+            "time_updated",
+            sa.DateTime(timezone=True),
+            server_default=sa.text("now()"),
+            nullable=False,
+        ),
+        sa.Column(
+            "time_created",
+            sa.DateTime(timezone=True),
+            server_default=sa.text("now()"),
+            nullable=False,
+        ),
+        sa.ForeignKeyConstraint(
+            ["user_id"],
+            ["user.id"],
+        ),
+        sa.PrimaryKeyConstraint("id"),
+    )
+    op.create_table(
+        "chat_message",
+        sa.Column("chat_session_id", sa.Integer(), nullable=False),
+        sa.Column("message_number", sa.Integer(), nullable=False),
+        sa.Column("edit_number", sa.Integer(), nullable=False),
+        sa.Column("parent_edit_number", sa.Integer(), nullable=True),
+        sa.Column("latest", sa.Boolean(), nullable=False),
+        sa.Column("message", sa.Text(), nullable=False),
+        sa.Column(
+            "message_type",
+            sa.Enum(
+                "SYSTEM",
+                "USER",
+                "ASSISTANT",
+                "DANSWER",
+                name="messagetype",
+                native_enum=False,
+            ),
+            nullable=False,
+        ),
+        sa.Column(
+            "time_sent",
+            sa.DateTime(timezone=True),
+            server_default=sa.text("now()"),
+            nullable=False,
+        ),
+        sa.ForeignKeyConstraint(
+            ["chat_session_id"],
+            ["chat_session.id"],
+        ),
+        sa.PrimaryKeyConstraint("chat_session_id", "message_number", "edit_number"),
+    )
+
+
+def downgrade() -> None:
+    op.drop_table("chat_message")
+    op.drop_table("chat_session")

backend/alembic/versions/5e84129c8be3_add_docs_indexed_column_to_index_.py

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

backend/alembic/versions/5f4b8568a221_add_removed_documents_to_index_attempt.py

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

backend/alembic/versions/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 +1,83 @@
+"""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.dynamic_configs.factory import get_dynamic_config_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_dynamic_config_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_dynamic_config_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

@@ -0,0 +1,81 @@
+"""Permission Auto Sync Framework
+
+Revision ID: 72bdc9929a46
+Revises: 475fcefe8826
+Create Date: 2024-04-14 21:15:28.659634
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "72bdc9929a46"
+down_revision = "475fcefe8826"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    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"),
+    )
+    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(
+        "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"),
+    )
+
+
+def downgrade() -> None:
+    op.drop_table("permission_sync_run")
+    op.drop_table("external_permission")
+    op.drop_table("email_to_external_user_cache")

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

@@ -0,0 +1,26 @@
+"""Count Chat Tokens
+
+Revision ID: 767f1c2a00eb
+Revises: dba7f71618f5
+Create Date: 2023-09-21 10:03:21.509899
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "767f1c2a00eb"
+down_revision = "dba7f71618f5"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "chat_message", sa.Column("token_count", sa.Integer(), nullable=False)
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("chat_message", "token_count")

backend/alembic/versions/76b60d407dfb_cc_pair_name_not_unique.py

@@ -0,0 +1,32 @@
+"""CC-Pair Name not Unique
+
+Revision ID: 76b60d407dfb
+Revises: b156fa702355
+Create Date: 2023-12-22 21:42:10.018804
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "76b60d407dfb"
+down_revision = "b156fa702355"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.execute("DELETE FROM connector_credential_pair WHERE name IS NULL")
+    op.drop_constraint(
+        "connector_credential_pair__name__key",
+        "connector_credential_pair",
+        type_="unique",
+    )
+    op.alter_column(
+        "connector_credential_pair", "name", existing_type=sa.String(), nullable=False
+    )
+
+
+def downgrade() -> None:
+    # This wasn't really required by the code either, no good reason to make it unique again
+    pass

backend/alembic/versions/776b3bbe9092_remove_remaining_enums.py

@@ -0,0 +1,71 @@
+"""Remove Remaining Enums
+
+Revision ID: 776b3bbe9092
+Revises: 4738e4b3bae1
+Create Date: 2024-03-22 21:34:27.629444
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+from danswer.db.models import IndexModelStatus
+from danswer.search.enums import RecencyBiasSetting
+from danswer.search.models import SearchType
+
+# revision identifiers, used by Alembic.
+revision = "776b3bbe9092"
+down_revision = "4738e4b3bae1"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.alter_column(
+        "persona",
+        "search_type",
+        type_=sa.String,
+        existing_type=sa.Enum(SearchType, native_enum=False),
+        existing_nullable=False,
+    )
+    op.alter_column(
+        "persona",
+        "recency_bias",
+        type_=sa.String,
+        existing_type=sa.Enum(RecencyBiasSetting, native_enum=False),
+        existing_nullable=False,
+    )
+
+    # Because the indexmodelstatus enum does not have a mapping to a string type
+    # we need this workaround instead of directly changing the type
+    op.add_column("embedding_model", sa.Column("temp_status", sa.String))
+    op.execute("UPDATE embedding_model SET temp_status = status::text")
+    op.drop_column("embedding_model", "status")
+    op.alter_column("embedding_model", "temp_status", new_column_name="status")
+
+    op.execute("DROP TYPE IF EXISTS searchtype")
+    op.execute("DROP TYPE IF EXISTS recencybiassetting")
+    op.execute("DROP TYPE IF EXISTS indexmodelstatus")
+
+
+def downgrade() -> None:
+    op.alter_column(
+        "persona",
+        "search_type",
+        type_=sa.Enum(SearchType, native_enum=False),
+        existing_type=sa.String(length=50),
+        existing_nullable=False,
+    )
+    op.alter_column(
+        "persona",
+        "recency_bias",
+        type_=sa.Enum(RecencyBiasSetting, native_enum=False),
+        existing_type=sa.String(length=50),
+        existing_nullable=False,
+    )
+    op.alter_column(
+        "embedding_model",
+        "status",
+        type_=sa.Enum(IndexModelStatus, native_enum=False),
+        existing_type=sa.String(length=50),
+        existing_nullable=False,
+    )

backend/alembic/versions/77d07dffae64_forcibly_remove_more_enum_types_from_.py

@@ -0,0 +1,35 @@
+"""forcibly remove more enum types from postgres
+
+Revision ID: 77d07dffae64
+Revises: d61e513bef0a
+Create Date: 2023-11-01 12:33:01.999617
+
+"""
+from alembic import op
+from sqlalchemy import String
+
+
+# revision identifiers, used by Alembic.
+revision = "77d07dffae64"
+down_revision = "d61e513bef0a"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    # In a PR:
+    # https://github.com/danswer-ai/danswer/pull/397/files#diff-f05fb341f6373790b91852579631b64ca7645797a190837156a282b67e5b19c2
+    # we directly changed some previous migrations. This caused some users to have native enums
+    # while others wouldn't. This has caused some issues when adding new fields to these enums.
+    # This migration manually changes the enum types to ensure that nobody uses native enums.
+    op.alter_column("query_event", "selected_search_flow", type_=String)
+    op.alter_column("query_event", "feedback", type_=String)
+    op.alter_column("document_retrieval_feedback", "feedback", type_=String)
+    op.execute("DROP TYPE IF EXISTS searchtype")
+    op.execute("DROP TYPE IF EXISTS qafeedbacktype")
+    op.execute("DROP TYPE IF EXISTS searchfeedbacktype")
+
+
+def downgrade() -> None:
+    # We don't want Native Enums, do nothing
+    pass

backend/alembic/versions/78dbe7e38469_task_tracking.py

@@ -0,0 +1,48 @@
+"""Task Tracking
+
+Revision ID: 78dbe7e38469
+Revises: 7ccea01261f6
+Create Date: 2023-10-15 23:40:50.593262
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "78dbe7e38469"
+down_revision = "7ccea01261f6"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "task_queue_jobs",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column("task_id", sa.String(), nullable=False),
+        sa.Column("task_name", sa.String(), nullable=False),
+        sa.Column(
+            "status",
+            sa.Enum(
+                "PENDING",
+                "STARTED",
+                "SUCCESS",
+                "FAILURE",
+                name="taskstatus",
+                native_enum=False,
+            ),
+            nullable=False,
+        ),
+        sa.Column("start_time", sa.DateTime(timezone=True), nullable=True),
+        sa.Column(
+            "register_time",
+            sa.DateTime(timezone=True),
+            server_default=sa.text("now()"),
+            nullable=False,
+        ),
+        sa.PrimaryKeyConstraint("id"),
+    )
+
+
+def downgrade() -> None:
+    op.drop_table("task_queue_jobs")

backend/alembic/versions/79acd316403a_add_api_key_table.py

@@ -0,0 +1,48 @@
+"""Add api_key table
+
+Revision ID: 79acd316403a
+Revises: 904e5138fffb
+Create Date: 2024-01-11 17:56:37.934381
+
+"""
+from alembic import op
+import fastapi_users_db_sqlalchemy
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "79acd316403a"
+down_revision = "904e5138fffb"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "api_key",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column("hashed_api_key", sa.String(), nullable=False),
+        sa.Column("api_key_display", sa.String(), nullable=False),
+        sa.Column(
+            "user_id",
+            fastapi_users_db_sqlalchemy.generics.GUID(),
+            nullable=False,
+        ),
+        sa.Column(
+            "owner_id",
+            fastapi_users_db_sqlalchemy.generics.GUID(),
+            nullable=True,
+        ),
+        sa.Column(
+            "created_at",
+            sa.DateTime(timezone=True),
+            server_default=sa.text("now()"),
+            nullable=False,
+        ),
+        sa.PrimaryKeyConstraint("id"),
+        sa.UniqueConstraint("api_key_display"),
+        sa.UniqueConstraint("hashed_api_key"),
+    )
+
+
+def downgrade() -> None:
+    op.drop_table("api_key")

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

@@ -0,0 +1,31 @@
+"""Store Chat Retrieval Docs
+
+Revision ID: 7ccea01261f6
+Revises: a570b80a5f20
+Create Date: 2023-10-15 10:39:23.317453
+
+"""
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision = "7ccea01261f6"
+down_revision = "a570b80a5f20"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "chat_message",
+        sa.Column(
+            "reference_docs",
+            postgresql.JSONB(astext_type=sa.Text()),
+            nullable=True,
+        ),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("chat_message", "reference_docs")

backend/alembic/versions/7da0ae5ad583_add_description_to_persona.py

@@ -0,0 +1,23 @@
+"""Add description to persona
+
+Revision ID: 7da0ae5ad583
+Revises: e86866a9c78a
+Create Date: 2023-11-27 00:16:19.959414
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "7da0ae5ad583"
+down_revision = "e86866a9c78a"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.add_column("persona", sa.Column("description", sa.String(), nullable=True))
+
+
+def downgrade() -> None:
+    op.drop_column("persona", "description")

backend/alembic/versions/7da543f5672f_add_slackbotconfig_table.py

@@ -0,0 +1,38 @@
+"""Add SlackBotConfig table
+
+Revision ID: 7da543f5672f
+Revises: febe9eaa0644
+Create Date: 2023-09-24 16:34:17.526128
+
+"""
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision = "7da543f5672f"
+down_revision = "febe9eaa0644"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "slack_bot_config",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column("persona_id", sa.Integer(), nullable=True),
+        sa.Column(
+            "channel_config",
+            postgresql.JSONB(astext_type=sa.Text()),
+            nullable=False,
+        ),
+        sa.ForeignKeyConstraint(
+            ["persona_id"],
+            ["persona.id"],
+        ),
+        sa.PrimaryKeyConstraint("id"),
+    )
+
+
+def downgrade() -> None:
+    op.drop_table("slack_bot_config")

backend/alembic/versions/7f726bad5367_slack_followup.py

@@ -0,0 +1,26 @@
+"""Slack Followup
+
+Revision ID: 7f726bad5367
+Revises: 79acd316403a
+Create Date: 2024-01-15 00:19:55.991224
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "7f726bad5367"
+down_revision = "79acd316403a"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "chat_feedback",
+        sa.Column("required_followup", sa.Boolean(), nullable=True),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("chat_feedback", "required_followup")

backend/alembic/versions/7f99be1cb9f5_add_index_for_getting_documents_just_by_.py

@@ -0,0 +1,35 @@
+"""Add index for getting documents just by connector id / credential id
+
+Revision ID: 7f99be1cb9f5
+Revises: 78dbe7e38469
+Create Date: 2023-10-15 22:48:15.487762
+
+"""
+from alembic import op
+
+
+# revision identifiers, used by Alembic.
+revision = "7f99be1cb9f5"
+down_revision = "78dbe7e38469"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.create_index(
+        op.f(
+            "ix_document_by_connector_credential_pair_pkey__connector_id__credential_id"
+        ),
+        "document_by_connector_credential_pair",
+        ["connector_id", "credential_id"],
+        unique=False,
+    )
+
+
+def downgrade() -> None:
+    op.drop_index(
+        op.f(
+            "ix_document_by_connector_credential_pair_pkey__connector_id__credential_id"
+        ),
+        table_name="document_by_connector_credential_pair",
+    )

backend/alembic/versions/800f48024ae9_add_id_to_connectorcredentialpair.py

@@ -0,0 +1,60 @@
+"""Add ID to ConnectorCredentialPair
+
+Revision ID: 800f48024ae9
+Revises: 767f1c2a00eb
+Create Date: 2023-09-19 16:13:42.299715
+
+"""
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.schema import Sequence, CreateSequence
+
+# revision identifiers, used by Alembic.
+revision = "800f48024ae9"
+down_revision = "767f1c2a00eb"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    sequence = Sequence("connector_credential_pair_id_seq")
+    op.execute(CreateSequence(sequence))  # type: ignore
+    op.add_column(
+        "connector_credential_pair",
+        sa.Column(
+            "id", sa.Integer(), nullable=True, server_default=sequence.next_value()
+        ),
+    )
+    op.add_column(
+        "connector_credential_pair",
+        sa.Column("name", sa.String(), nullable=True),
+    )
+
+    # fill in IDs for existing rows
+    op.execute(
+        "UPDATE connector_credential_pair SET id = nextval('connector_credential_pair_id_seq') WHERE id IS NULL"
+    )
+    op.alter_column("connector_credential_pair", "id", nullable=False)
+
+    op.create_unique_constraint(
+        "connector_credential_pair__name__key", "connector_credential_pair", ["name"]
+    )
+    op.create_unique_constraint(
+        "connector_credential_pair__id__key", "connector_credential_pair", ["id"]
+    )
+
+
+def downgrade() -> None:
+    op.drop_constraint(
+        "connector_credential_pair__name__key",
+        "connector_credential_pair",
+        type_="unique",
+    )
+    op.drop_constraint(
+        "connector_credential_pair__id__key",
+        "connector_credential_pair",
+        type_="unique",
+    )
+    op.drop_column("connector_credential_pair", "name")
+    op.drop_column("connector_credential_pair", "id")
+    op.execute("DROP SEQUENCE connector_credential_pair_id_seq")

backend/alembic/versions/80696cf850ae_add_chat_session_to_query_event.py

@@ -0,0 +1,36 @@
+"""Add chat session to query_event
+
+Revision ID: 80696cf850ae
+Revises: 15326fcec57e
+Create Date: 2023-11-26 02:38:35.008070
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "80696cf850ae"
+down_revision = "15326fcec57e"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "query_event",
+        sa.Column("chat_session_id", sa.Integer(), nullable=True),
+    )
+    op.create_foreign_key(
+        "fk_query_event_chat_session_id",
+        "query_event",
+        "chat_session",
+        ["chat_session_id"],
+        ["id"],
+    )
+
+
+def downgrade() -> None:
+    op.drop_constraint(
+        "fk_query_event_chat_session_id", "query_event", type_="foreignkey"
+    )
+    op.drop_column("query_event", "chat_session_id")

backend/alembic/versions/891cd83c87a8_add_is_visible_to_persona.py

@@ -0,0 +1,34 @@
+"""Add is_visible to Persona
+
+Revision ID: 891cd83c87a8
+Revises: 76b60d407dfb
+Create Date: 2023-12-21 11:55:54.132279
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "891cd83c87a8"
+down_revision = "76b60d407dfb"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "persona",
+        sa.Column("is_visible", sa.Boolean(), nullable=True),
+    )
+    op.execute("UPDATE persona SET is_visible = true")
+    op.alter_column("persona", "is_visible", nullable=False)
+
+    op.add_column(
+        "persona",
+        sa.Column("display_priority", sa.Integer(), nullable=True),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("persona", "is_visible")
+    op.drop_column("persona", "display_priority")

backend/alembic/versions/8987770549c0_add_full_exception_stack_trace.py

@@ -0,0 +1,25 @@
+"""Add full exception stack trace
+
+Revision ID: 8987770549c0
+Revises: ec3ec2eabf7b
+Create Date: 2024-02-10 19:31:28.339135
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "8987770549c0"
+down_revision = "ec3ec2eabf7b"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "index_attempt", sa.Column("full_exception_trace", sa.Text(), nullable=True)
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("index_attempt", "full_exception_trace")

backend/alembic/versions/8aabb57f3b49_restructure_document_indices.py

@@ -0,0 +1,39 @@
+"""Restructure Document Indices
+
+Revision ID: 8aabb57f3b49
+Revises: 5e84129c8be3
+Create Date: 2023-08-18 21:15:57.629515
+
+"""
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision = "8aabb57f3b49"
+down_revision = "5e84129c8be3"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.drop_table("chunk")
+    op.execute("DROP TYPE IF EXISTS documentstoretype")
+
+
+def downgrade() -> None:
+    op.create_table(
+        "chunk",
+        sa.Column("id", sa.VARCHAR(), autoincrement=False, nullable=False),
+        sa.Column(
+            "document_store_type",
+            postgresql.ENUM("VECTOR", "KEYWORD", name="documentstoretype"),
+            autoincrement=False,
+            nullable=False,
+        ),
+        sa.Column("document_id", sa.VARCHAR(), autoincrement=False, nullable=False),
+        sa.ForeignKeyConstraint(
+            ["document_id"], ["document.id"], name="chunk_document_id_fkey"
+        ),
+        sa.PrimaryKeyConstraint("id", "document_store_type", name="chunk_pkey"),
+    )

backend/alembic/versions/8e26726b7683_chat_context_addition.py

@@ -0,0 +1,40 @@
+"""Chat Context Addition
+
+Revision ID: 8e26726b7683
+Revises: 5809c0787398
+Create Date: 2023-09-13 18:34:31.327944
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "8e26726b7683"
+down_revision = "5809c0787398"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "persona",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column("name", sa.String(), nullable=False),
+        sa.Column("system_text", sa.Text(), nullable=True),
+        sa.Column("tools_text", sa.Text(), nullable=True),
+        sa.Column("hint_text", sa.Text(), nullable=True),
+        sa.Column("default_persona", sa.Boolean(), nullable=False),
+        sa.Column("deleted", sa.Boolean(), nullable=False),
+        sa.PrimaryKeyConstraint("id"),
+    )
+    op.add_column("chat_message", sa.Column("persona_id", sa.Integer(), nullable=True))
+    op.create_foreign_key(
+        "fk_chat_message_persona_id", "chat_message", "persona", ["persona_id"], ["id"]
+    )
+
+
+def downgrade() -> None:
+    op.drop_constraint("fk_chat_message_persona_id", "chat_message", type_="foreignkey")
+    op.drop_column("chat_message", "persona_id")
+    op.drop_table("persona")

backend/alembic/versions/904451035c9b_store_tool_details.py

@@ -0,0 +1,32 @@
+"""Store Tool Details
+
+Revision ID: 904451035c9b
+Revises: 3b25685ff73c
+Create Date: 2023-10-05 12:29:26.620000
+
+"""
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision = "904451035c9b"
+down_revision = "3b25685ff73c"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "persona",
+        sa.Column("tools", postgresql.JSONB(astext_type=sa.Text()), nullable=True),
+    )
+    op.drop_column("persona", "tools_text")
+
+
+def downgrade() -> None:
+    op.add_column(
+        "persona",
+        sa.Column("tools_text", sa.TEXT(), autoincrement=False, nullable=True),
+    )
+    op.drop_column("persona", "tools")

backend/alembic/versions/904e5138fffb_tags.py

@@ -0,0 +1,61 @@
+"""Tags
+
+Revision ID: 904e5138fffb
+Revises: 891cd83c87a8
+Create Date: 2024-01-01 10:44:43.733974
+
+"""
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision = "904e5138fffb"
+down_revision = "891cd83c87a8"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "tag",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column("tag_key", sa.String(), nullable=False),
+        sa.Column("tag_value", sa.String(), nullable=False),
+        sa.Column("source", sa.String(), nullable=False),
+        sa.PrimaryKeyConstraint("id"),
+        sa.UniqueConstraint(
+            "tag_key", "tag_value", "source", name="_tag_key_value_source_uc"
+        ),
+    )
+    op.create_table(
+        "document__tag",
+        sa.Column("document_id", sa.String(), nullable=False),
+        sa.Column("tag_id", sa.Integer(), nullable=False),
+        sa.ForeignKeyConstraint(
+            ["document_id"],
+            ["document.id"],
+        ),
+        sa.ForeignKeyConstraint(
+            ["tag_id"],
+            ["tag.id"],
+        ),
+        sa.PrimaryKeyConstraint("document_id", "tag_id"),
+    )
+
+    op.add_column(
+        "search_doc",
+        sa.Column(
+            "doc_metadata",
+            postgresql.JSONB(astext_type=sa.Text()),
+            nullable=True,
+        ),
+    )
+    op.execute("UPDATE search_doc SET doc_metadata = '{}' WHERE doc_metadata IS NULL")
+    op.alter_column("search_doc", "doc_metadata", nullable=False)
+
+
+def downgrade() -> None:
+    op.drop_table("document__tag")
+    op.drop_table("tag")
+    op.drop_column("search_doc", "doc_metadata")

backend/alembic/versions/91fd3b470d1a_remove_documentsource_from_tag.py

@@ -0,0 +1,36 @@
+"""Remove DocumentSource from Tag
+
+Revision ID: 91fd3b470d1a
+Revises: 173cae5bba26
+Create Date: 2024-03-21 12:05:23.956734
+
+"""
+from alembic import op
+import sqlalchemy as sa
+from danswer.configs.constants import DocumentSource
+
+# revision identifiers, used by Alembic.
+revision = "91fd3b470d1a"
+down_revision = "173cae5bba26"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.alter_column(
+        "tag",
+        "source",
+        type_=sa.String(length=50),
+        existing_type=sa.Enum(DocumentSource, native_enum=False),
+        existing_nullable=False,
+    )
+
+
+def downgrade() -> None:
+    op.alter_column(
+        "tag",
+        "source",
+        type_=sa.Enum(DocumentSource, native_enum=False),
+        existing_type=sa.String(length=50),
+        existing_nullable=False,
+    )

backend/alembic/versions/9d97fecfab7f_added_retrieved_docs_to_query_event.py

@@ -0,0 +1,31 @@
+"""Added retrieved docs to query event
+
+Revision ID: 9d97fecfab7f
+Revises: ffc707a226b4
+Create Date: 2023-10-20 12:22:31.930449
+
+"""
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision = "9d97fecfab7f"
+down_revision = "ffc707a226b4"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "query_event",
+        sa.Column(
+            "retrieved_document_ids",
+            postgresql.ARRAY(sa.String()),
+            nullable=True,
+        ),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("query_event", "retrieved_document_ids")

backend/alembic/versions/a3bfd0d64902_add_chosen_assistants_to_user_table.py

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

backend/alembic/versions/a570b80a5f20_usergroup_tables.py

@@ -0,0 +1,67 @@
+"""UserGroup tables
+
+Revision ID: a570b80a5f20
+Revises: 904451035c9b
+Create Date: 2023-10-02 12:27:10.265725
+
+"""
+from alembic import op
+import fastapi_users_db_sqlalchemy
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "a570b80a5f20"
+down_revision = "904451035c9b"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "user_group",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column("name", sa.String(), nullable=False),
+        sa.Column("is_up_to_date", sa.Boolean(), nullable=False),
+        sa.Column("is_up_for_deletion", sa.Boolean(), nullable=False),
+        sa.PrimaryKeyConstraint("id"),
+        sa.UniqueConstraint("name"),
+    )
+    op.create_table(
+        "user__user_group",
+        sa.Column("user_group_id", sa.Integer(), nullable=False),
+        sa.Column(
+            "user_id",
+            fastapi_users_db_sqlalchemy.generics.GUID(),
+            nullable=False,
+        ),
+        sa.ForeignKeyConstraint(
+            ["user_group_id"],
+            ["user_group.id"],
+        ),
+        sa.ForeignKeyConstraint(
+            ["user_id"],
+            ["user.id"],
+        ),
+        sa.PrimaryKeyConstraint("user_group_id", "user_id"),
+    )
+    op.create_table(
+        "user_group__connector_credential_pair",
+        sa.Column("user_group_id", sa.Integer(), nullable=False),
+        sa.Column("cc_pair_id", sa.Integer(), nullable=False),
+        sa.Column("is_current", sa.Boolean(), nullable=False),
+        sa.ForeignKeyConstraint(
+            ["cc_pair_id"],
+            ["connector_credential_pair.id"],
+        ),
+        sa.ForeignKeyConstraint(
+            ["user_group_id"],
+            ["user_group.id"],
+        ),
+        sa.PrimaryKeyConstraint("user_group_id", "cc_pair_id", "is_current"),
+    )
+
+
+def downgrade() -> None:
+    op.drop_table("user_group__connector_credential_pair")
+    op.drop_table("user__user_group")
+    op.drop_table("user_group")

backend/alembic/versions/ae62505e3acc_add_saml_accounts.py

@@ -0,0 +1,47 @@
+"""Add SAML Accounts
+
+Revision ID: ae62505e3acc
+Revises: 7da543f5672f
+Create Date: 2023-09-26 16:19:30.933183
+
+"""
+import fastapi_users_db_sqlalchemy
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "ae62505e3acc"
+down_revision = "7da543f5672f"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "saml",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column(
+            "user_id",
+            fastapi_users_db_sqlalchemy.generics.GUID(),
+            nullable=False,
+        ),
+        sa.Column("encrypted_cookie", sa.Text(), nullable=False),
+        sa.Column("expires_at", sa.DateTime(timezone=True), nullable=True),
+        sa.Column(
+            "updated_at",
+            sa.DateTime(timezone=True),
+            server_default=sa.text("now()"),
+            nullable=False,
+        ),
+        sa.ForeignKeyConstraint(
+            ["user_id"],
+            ["user.id"],
+        ),
+        sa.PrimaryKeyConstraint("id"),
+        sa.UniqueConstraint("encrypted_cookie"),
+        sa.UniqueConstraint("user_id"),
+    )
+
+
+def downgrade() -> None:
+    op.drop_table("saml")

backend/alembic/versions/b082fec533f0_make_last_attempt_status_nullable.py

@@ -6,14 +6,13 @@ Create Date: 2023-08-06 12:05:47.087325
 
 """
 from alembic import op
-import sqlalchemy as sa
 from sqlalchemy.dialects import postgresql
 
 # revision identifiers, used by Alembic.
 revision = "b082fec533f0"
 down_revision = "df0c7ad8a076"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:

backend/alembic/versions/b156fa702355_chat_reworked.py

@@ -0,0 +1,520 @@
+"""Chat Reworked
+
+Revision ID: b156fa702355
+Revises: baf71f781b9e
+Create Date: 2023-12-12 00:57:41.823371
+
+"""
+import fastapi_users_db_sqlalchemy
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+from sqlalchemy.dialects.postgresql import ENUM
+from danswer.configs.constants import DocumentSource
+
+# revision identifiers, used by Alembic.
+revision = "b156fa702355"
+down_revision = "baf71f781b9e"
+branch_labels: None = None
+depends_on: None = None
+
+
+searchtype_enum = ENUM(
+    "KEYWORD", "SEMANTIC", "HYBRID", name="searchtype", create_type=True
+)
+recencybiassetting_enum = ENUM(
+    "FAVOR_RECENT",
+    "BASE_DECAY",
+    "NO_DECAY",
+    "AUTO",
+    name="recencybiassetting",
+    create_type=True,
+)
+
+
+def upgrade() -> None:
+    bind = op.get_bind()
+    searchtype_enum.create(bind)
+    recencybiassetting_enum.create(bind)
+
+    # This is irrecoverable, whatever
+    op.execute("DELETE FROM chat_feedback")
+    op.execute("DELETE FROM document_retrieval_feedback")
+
+    op.create_table(
+        "search_doc",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column("document_id", sa.String(), nullable=False),
+        sa.Column("chunk_ind", sa.Integer(), nullable=False),
+        sa.Column("semantic_id", sa.String(), nullable=False),
+        sa.Column("link", sa.String(), nullable=True),
+        sa.Column("blurb", sa.String(), nullable=False),
+        sa.Column("boost", sa.Integer(), nullable=False),
+        sa.Column(
+            "source_type",
+            sa.Enum(DocumentSource, native=False),
+            nullable=False,
+        ),
+        sa.Column("hidden", sa.Boolean(), nullable=False),
+        sa.Column("score", sa.Float(), nullable=False),
+        sa.Column("match_highlights", postgresql.ARRAY(sa.String()), nullable=False),
+        sa.Column("updated_at", sa.DateTime(timezone=True), nullable=True),
+        sa.Column("primary_owners", postgresql.ARRAY(sa.String()), nullable=True),
+        sa.Column("secondary_owners", postgresql.ARRAY(sa.String()), nullable=True),
+        sa.PrimaryKeyConstraint("id"),
+    )
+    op.create_table(
+        "prompt",
+        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=False),
+        sa.Column("description", sa.String(), nullable=False),
+        sa.Column("system_prompt", sa.Text(), nullable=False),
+        sa.Column("task_prompt", sa.Text(), nullable=False),
+        sa.Column("include_citations", sa.Boolean(), nullable=False),
+        sa.Column("datetime_aware", sa.Boolean(), nullable=False),
+        sa.Column("default_prompt", sa.Boolean(), nullable=False),
+        sa.Column("deleted", sa.Boolean(), nullable=False),
+        sa.ForeignKeyConstraint(
+            ["user_id"],
+            ["user.id"],
+        ),
+        sa.PrimaryKeyConstraint("id"),
+    )
+    op.create_table(
+        "persona__prompt",
+        sa.Column("persona_id", sa.Integer(), nullable=False),
+        sa.Column("prompt_id", sa.Integer(), nullable=False),
+        sa.ForeignKeyConstraint(
+            ["persona_id"],
+            ["persona.id"],
+        ),
+        sa.ForeignKeyConstraint(
+            ["prompt_id"],
+            ["prompt.id"],
+        ),
+        sa.PrimaryKeyConstraint("persona_id", "prompt_id"),
+    )
+
+    # Changes to persona first so chat_sessions can have the right persona
+    # The empty persona will be overwritten on server startup
+    op.add_column(
+        "persona",
+        sa.Column(
+            "user_id",
+            fastapi_users_db_sqlalchemy.generics.GUID(),
+            nullable=True,
+        ),
+    )
+    op.add_column(
+        "persona",
+        sa.Column(
+            "search_type",
+            searchtype_enum,
+            nullable=True,
+        ),
+    )
+    op.execute("UPDATE persona SET search_type = 'HYBRID'")
+    op.alter_column("persona", "search_type", nullable=False)
+    op.add_column(
+        "persona",
+        sa.Column("llm_relevance_filter", sa.Boolean(), nullable=True),
+    )
+    op.execute("UPDATE persona SET llm_relevance_filter = TRUE")
+    op.alter_column("persona", "llm_relevance_filter", nullable=False)
+    op.add_column(
+        "persona",
+        sa.Column("llm_filter_extraction", sa.Boolean(), nullable=True),
+    )
+    op.execute("UPDATE persona SET llm_filter_extraction = TRUE")
+    op.alter_column("persona", "llm_filter_extraction", nullable=False)
+    op.add_column(
+        "persona",
+        sa.Column(
+            "recency_bias",
+            recencybiassetting_enum,
+            nullable=True,
+        ),
+    )
+    op.execute("UPDATE persona SET recency_bias = 'BASE_DECAY'")
+    op.alter_column("persona", "recency_bias", nullable=False)
+    op.alter_column("persona", "description", existing_type=sa.VARCHAR(), nullable=True)
+    op.execute("UPDATE persona SET description = ''")
+    op.alter_column("persona", "description", nullable=False)
+    op.create_foreign_key("persona__user_fk", "persona", "user", ["user_id"], ["id"])
+    op.drop_column("persona", "datetime_aware")
+    op.drop_column("persona", "tools")
+    op.drop_column("persona", "hint_text")
+    op.drop_column("persona", "apply_llm_relevance_filter")
+    op.drop_column("persona", "retrieval_enabled")
+    op.drop_column("persona", "system_text")
+
+    # Need to create a persona row so fk can work
+    result = bind.execute(sa.text("SELECT 1 FROM persona WHERE id = 0"))
+    exists = result.fetchone()
+    if not exists:
+        op.execute(
+            sa.text(
+                """
+                INSERT INTO persona (
+                    id, user_id, name, description, search_type, num_chunks,
+                    llm_relevance_filter, llm_filter_extraction, recency_bias,
+                    llm_model_version_override, default_persona, deleted
+                ) VALUES (
+                    0, NULL, '', '', 'HYBRID', NULL,
+                    TRUE, TRUE, 'BASE_DECAY', NULL, TRUE, FALSE
+                )
+                """
+            )
+        )
+    delete_statement = sa.text(
+        """
+        DELETE FROM persona
+        WHERE name = 'Danswer' AND default_persona = TRUE AND id != 0
+        """
+    )
+
+    bind.execute(delete_statement)
+
+    op.add_column(
+        "chat_feedback",
+        sa.Column("chat_message_id", sa.Integer(), nullable=False),
+    )
+    op.drop_constraint(
+        "chat_feedback_chat_message_chat_session_id_chat_message_me_fkey",
+        "chat_feedback",
+        type_="foreignkey",
+    )
+    op.drop_column("chat_feedback", "chat_message_edit_number")
+    op.drop_column("chat_feedback", "chat_message_chat_session_id")
+    op.drop_column("chat_feedback", "chat_message_message_number")
+    op.add_column(
+        "chat_message",
+        sa.Column(
+            "id",
+            sa.Integer(),
+            primary_key=True,
+            autoincrement=True,
+            nullable=False,
+            unique=True,
+        ),
+    )
+    op.add_column(
+        "chat_message",
+        sa.Column("parent_message", sa.Integer(), nullable=True),
+    )
+    op.add_column(
+        "chat_message",
+        sa.Column("latest_child_message", sa.Integer(), nullable=True),
+    )
+    op.add_column(
+        "chat_message", sa.Column("rephrased_query", sa.Text(), nullable=True)
+    )
+    op.add_column("chat_message", sa.Column("prompt_id", sa.Integer(), nullable=True))
+    op.add_column(
+        "chat_message",
+        sa.Column("citations", postgresql.JSONB(astext_type=sa.Text()), nullable=True),
+    )
+    op.add_column("chat_message", sa.Column("error", sa.Text(), nullable=True))
+    op.drop_constraint("fk_chat_message_persona_id", "chat_message", type_="foreignkey")
+    op.create_foreign_key(
+        "chat_message__prompt_fk", "chat_message", "prompt", ["prompt_id"], ["id"]
+    )
+    op.drop_column("chat_message", "parent_edit_number")
+    op.drop_column("chat_message", "persona_id")
+    op.drop_column("chat_message", "reference_docs")
+    op.drop_column("chat_message", "edit_number")
+    op.drop_column("chat_message", "latest")
+    op.drop_column("chat_message", "message_number")
+    op.add_column("chat_session", sa.Column("one_shot", sa.Boolean(), nullable=True))
+    op.execute("UPDATE chat_session SET one_shot = TRUE")
+    op.alter_column("chat_session", "one_shot", nullable=False)
+    op.alter_column(
+        "chat_session",
+        "persona_id",
+        existing_type=sa.INTEGER(),
+        nullable=True,
+    )
+    op.execute("UPDATE chat_session SET persona_id = 0")
+    op.alter_column("chat_session", "persona_id", nullable=False)
+    op.add_column(
+        "document_retrieval_feedback",
+        sa.Column("chat_message_id", sa.Integer(), nullable=False),
+    )
+    op.drop_constraint(
+        "document_retrieval_feedback_qa_event_id_fkey",
+        "document_retrieval_feedback",
+        type_="foreignkey",
+    )
+    op.create_foreign_key(
+        "document_retrieval_feedback__chat_message_fk",
+        "document_retrieval_feedback",
+        "chat_message",
+        ["chat_message_id"],
+        ["id"],
+    )
+    op.drop_column("document_retrieval_feedback", "qa_event_id")
+
+    # Relation table must be created after the other tables are correct
+    op.create_table(
+        "chat_message__search_doc",
+        sa.Column("chat_message_id", sa.Integer(), nullable=False),
+        sa.Column("search_doc_id", sa.Integer(), nullable=False),
+        sa.ForeignKeyConstraint(
+            ["chat_message_id"],
+            ["chat_message.id"],
+        ),
+        sa.ForeignKeyConstraint(
+            ["search_doc_id"],
+            ["search_doc.id"],
+        ),
+        sa.PrimaryKeyConstraint("chat_message_id", "search_doc_id"),
+    )
+
+    # Needs to be created after chat_message id field is added
+    op.create_foreign_key(
+        "chat_feedback__chat_message_fk",
+        "chat_feedback",
+        "chat_message",
+        ["chat_message_id"],
+        ["id"],
+    )
+
+    op.drop_table("query_event")
+
+
+def downgrade() -> None:
+    op.drop_constraint(
+        "chat_feedback__chat_message_fk", "chat_feedback", type_="foreignkey"
+    )
+    op.drop_constraint(
+        "document_retrieval_feedback__chat_message_fk",
+        "document_retrieval_feedback",
+        type_="foreignkey",
+    )
+    op.drop_constraint("persona__user_fk", "persona", type_="foreignkey")
+    op.drop_constraint("chat_message__prompt_fk", "chat_message", type_="foreignkey")
+    op.drop_constraint(
+        "chat_message__search_doc_chat_message_id_fkey",
+        "chat_message__search_doc",
+        type_="foreignkey",
+    )
+    op.add_column(
+        "persona",
+        sa.Column("system_text", sa.TEXT(), autoincrement=False, nullable=True),
+    )
+    op.add_column(
+        "persona",
+        sa.Column(
+            "retrieval_enabled",
+            sa.BOOLEAN(),
+            autoincrement=False,
+            nullable=True,
+        ),
+    )
+    op.execute("UPDATE persona SET retrieval_enabled = TRUE")
+    op.alter_column("persona", "retrieval_enabled", nullable=False)
+    op.add_column(
+        "persona",
+        sa.Column(
+            "apply_llm_relevance_filter",
+            sa.BOOLEAN(),
+            autoincrement=False,
+            nullable=True,
+        ),
+    )
+    op.add_column(
+        "persona",
+        sa.Column("hint_text", sa.TEXT(), autoincrement=False, nullable=True),
+    )
+    op.add_column(
+        "persona",
+        sa.Column(
+            "tools",
+            postgresql.JSONB(astext_type=sa.Text()),
+            autoincrement=False,
+            nullable=True,
+        ),
+    )
+    op.add_column(
+        "persona",
+        sa.Column("datetime_aware", sa.BOOLEAN(), autoincrement=False, nullable=True),
+    )
+    op.execute("UPDATE persona SET datetime_aware = TRUE")
+    op.alter_column("persona", "datetime_aware", nullable=False)
+    op.alter_column("persona", "description", existing_type=sa.VARCHAR(), nullable=True)
+    op.drop_column("persona", "recency_bias")
+    op.drop_column("persona", "llm_filter_extraction")
+    op.drop_column("persona", "llm_relevance_filter")
+    op.drop_column("persona", "search_type")
+    op.drop_column("persona", "user_id")
+    op.add_column(
+        "document_retrieval_feedback",
+        sa.Column("qa_event_id", sa.INTEGER(), autoincrement=False, nullable=False),
+    )
+    op.drop_column("document_retrieval_feedback", "chat_message_id")
+    op.alter_column(
+        "chat_session", "persona_id", existing_type=sa.INTEGER(), nullable=True
+    )
+    op.drop_column("chat_session", "one_shot")
+    op.add_column(
+        "chat_message",
+        sa.Column(
+            "message_number",
+            sa.INTEGER(),
+            autoincrement=False,
+            nullable=False,
+            primary_key=True,
+        ),
+    )
+    op.add_column(
+        "chat_message",
+        sa.Column("latest", sa.BOOLEAN(), autoincrement=False, nullable=False),
+    )
+    op.add_column(
+        "chat_message",
+        sa.Column(
+            "edit_number",
+            sa.INTEGER(),
+            autoincrement=False,
+            nullable=False,
+            primary_key=True,
+        ),
+    )
+    op.add_column(
+        "chat_message",
+        sa.Column(
+            "reference_docs",
+            postgresql.JSONB(astext_type=sa.Text()),
+            autoincrement=False,
+            nullable=True,
+        ),
+    )
+    op.add_column(
+        "chat_message",
+        sa.Column("persona_id", sa.INTEGER(), autoincrement=False, nullable=True),
+    )
+    op.add_column(
+        "chat_message",
+        sa.Column(
+            "parent_edit_number",
+            sa.INTEGER(),
+            autoincrement=False,
+            nullable=True,
+        ),
+    )
+    op.create_foreign_key(
+        "fk_chat_message_persona_id",
+        "chat_message",
+        "persona",
+        ["persona_id"],
+        ["id"],
+    )
+    op.drop_column("chat_message", "error")
+    op.drop_column("chat_message", "citations")
+    op.drop_column("chat_message", "prompt_id")
+    op.drop_column("chat_message", "rephrased_query")
+    op.drop_column("chat_message", "latest_child_message")
+    op.drop_column("chat_message", "parent_message")
+    op.drop_column("chat_message", "id")
+    op.add_column(
+        "chat_feedback",
+        sa.Column(
+            "chat_message_message_number",
+            sa.INTEGER(),
+            autoincrement=False,
+            nullable=False,
+        ),
+    )
+    op.add_column(
+        "chat_feedback",
+        sa.Column(
+            "chat_message_chat_session_id",
+            sa.INTEGER(),
+            autoincrement=False,
+            nullable=False,
+            primary_key=True,
+        ),
+    )
+    op.add_column(
+        "chat_feedback",
+        sa.Column(
+            "chat_message_edit_number",
+            sa.INTEGER(),
+            autoincrement=False,
+            nullable=False,
+        ),
+    )
+    op.drop_column("chat_feedback", "chat_message_id")
+    op.create_table(
+        "query_event",
+        sa.Column("id", sa.INTEGER(), autoincrement=True, nullable=False),
+        sa.Column("query", sa.VARCHAR(), autoincrement=False, nullable=False),
+        sa.Column(
+            "selected_search_flow",
+            sa.VARCHAR(),
+            autoincrement=False,
+            nullable=True,
+        ),
+        sa.Column("llm_answer", sa.VARCHAR(), autoincrement=False, nullable=True),
+        sa.Column("feedback", sa.VARCHAR(), autoincrement=False, nullable=True),
+        sa.Column("user_id", sa.UUID(), autoincrement=False, nullable=True),
+        sa.Column(
+            "time_created",
+            postgresql.TIMESTAMP(timezone=True),
+            server_default=sa.text("now()"),
+            autoincrement=False,
+            nullable=False,
+        ),
+        sa.Column(
+            "retrieved_document_ids",
+            postgresql.ARRAY(sa.VARCHAR()),
+            autoincrement=False,
+            nullable=True,
+        ),
+        sa.Column("chat_session_id", sa.INTEGER(), autoincrement=False, nullable=True),
+        sa.ForeignKeyConstraint(
+            ["chat_session_id"],
+            ["chat_session.id"],
+            name="fk_query_event_chat_session_id",
+        ),
+        sa.ForeignKeyConstraint(
+            ["user_id"], ["user.id"], name="query_event_user_id_fkey"
+        ),
+        sa.PrimaryKeyConstraint("id", name="query_event_pkey"),
+    )
+    op.drop_table("chat_message__search_doc")
+    op.drop_table("persona__prompt")
+    op.drop_table("prompt")
+    op.drop_table("search_doc")
+    op.create_unique_constraint(
+        "uq_chat_message_combination",
+        "chat_message",
+        ["chat_session_id", "message_number", "edit_number"],
+    )
+    op.create_foreign_key(
+        "chat_feedback_chat_message_chat_session_id_chat_message_me_fkey",
+        "chat_feedback",
+        "chat_message",
+        [
+            "chat_message_chat_session_id",
+            "chat_message_message_number",
+            "chat_message_edit_number",
+        ],
+        ["chat_session_id", "message_number", "edit_number"],
+    )
+    op.create_foreign_key(
+        "document_retrieval_feedback_qa_event_id_fkey",
+        "document_retrieval_feedback",
+        "query_event",
+        ["qa_event_id"],
+        ["id"],
+    )
+
+    op.execute("DROP TYPE IF EXISTS searchtype")
+    op.execute("DROP TYPE IF EXISTS recencybiassetting")
+    op.execute("DROP TYPE IF EXISTS documentsource")

backend/alembic/versions/b85f02ec1308_fix_file_type_migration.py

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

backend/alembic/versions/b896bbd0d5a7_backfill_is_internet_data_to_false.py

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

backend/alembic/versions/baf71f781b9e_add_llm_model_version_override_to_.py

@@ -0,0 +1,26 @@
+"""Add llm_model_version_override to Persona
+
+Revision ID: baf71f781b9e
+Revises: 50b683a8295c
+Create Date: 2023-12-06 21:56:50.286158
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "baf71f781b9e"
+down_revision = "50b683a8295c"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "persona",
+        sa.Column("llm_model_version_override", sa.String(), nullable=True),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("persona", "llm_model_version_override")

backend/alembic/versions/bc9771dccadf_create_usage_reports_table.py

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

backend/alembic/versions/c18cdf4b497e_add_standard_answer_tables.py

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

backend/alembic/versions/d5645c915d0e_remove_deletion_attempt_table.py

@@ -0,0 +1,73 @@
+"""Remove deletion_attempt table
+
+Revision ID: d5645c915d0e
+Revises: 8e26726b7683
+Create Date: 2023-09-14 15:04:14.444909
+
+"""
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision = "d5645c915d0e"
+down_revision = "8e26726b7683"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.drop_table("deletion_attempt")
+
+
+def downgrade() -> None:
+    op.create_table(
+        "deletion_attempt",
+        sa.Column("id", sa.INTEGER(), autoincrement=True, nullable=False),
+        sa.Column("connector_id", sa.INTEGER(), autoincrement=False, nullable=False),
+        sa.Column("credential_id", sa.INTEGER(), autoincrement=False, nullable=False),
+        sa.Column(
+            "status",
+            postgresql.ENUM(
+                "NOT_STARTED",
+                "IN_PROGRESS",
+                "SUCCESS",
+                "FAILED",
+                name="deletionstatus",
+            ),
+            autoincrement=False,
+            nullable=False,
+        ),
+        sa.Column(
+            "num_docs_deleted",
+            sa.INTEGER(),
+            autoincrement=False,
+            nullable=False,
+        ),
+        sa.Column("error_msg", sa.VARCHAR(), autoincrement=False, nullable=True),
+        sa.Column(
+            "time_created",
+            postgresql.TIMESTAMP(timezone=True),
+            server_default=sa.text("now()"),
+            autoincrement=False,
+            nullable=False,
+        ),
+        sa.Column(
+            "time_updated",
+            postgresql.TIMESTAMP(timezone=True),
+            server_default=sa.text("now()"),
+            autoincrement=False,
+            nullable=False,
+        ),
+        sa.ForeignKeyConstraint(
+            ["connector_id"],
+            ["connector.id"],
+            name="deletion_attempt_connector_id_fkey",
+        ),
+        sa.ForeignKeyConstraint(
+            ["credential_id"],
+            ["credential.id"],
+            name="deletion_attempt_credential_id_fkey",
+        ),
+        sa.PrimaryKeyConstraint("id", name="deletion_attempt_pkey"),
+    )

backend/alembic/versions/d61e513bef0a_add_total_docs_for_index_attempt.py

@@ -0,0 +1,32 @@
+"""Add Total Docs for Index Attempt
+
+Revision ID: d61e513bef0a
+Revises: 46625e4745d4
+Create Date: 2023-10-27 23:02:43.369964
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "d61e513bef0a"
+down_revision = "46625e4745d4"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "index_attempt",
+        sa.Column("new_docs_indexed", sa.Integer(), nullable=True),
+    )
+    op.alter_column(
+        "index_attempt", "num_docs_indexed", new_column_name="total_docs_indexed"
+    )
+
+
+def downgrade() -> None:
+    op.alter_column(
+        "index_attempt", "total_docs_indexed", new_column_name="num_docs_indexed"
+    )
+    op.drop_column("index_attempt", "new_docs_indexed")

backend/alembic/versions/d7111c1238cd_remove_document_ids.py

@@ -12,8 +12,8 @@ from sqlalchemy.dialects import postgresql
 # revision identifiers, used by Alembic.
 revision = "d7111c1238cd"
 down_revision = "465f78d9b7f9"
-branch_labels = None
-depends_on = None
+branch_labels: None = None
+depends_on: None = None
 
 
 def upgrade() -> None:

backend/alembic/versions/d716b0791ddd_combined_slack_id_fields.py

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

backend/alembic/versions/d929f0c1c6af_feedback_feature.py

@@ -0,0 +1,94 @@
+"""Feedback Feature
+
+Revision ID: d929f0c1c6af
+Revises: 8aabb57f3b49
+Create Date: 2023-08-27 13:03:54.274987
+
+"""
+import fastapi_users_db_sqlalchemy
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "d929f0c1c6af"
+down_revision = "8aabb57f3b49"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "query_event",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column("query", sa.String(), nullable=False),
+        sa.Column(
+            "selected_search_flow",
+            sa.Enum("KEYWORD", "SEMANTIC", name="searchtype", native_enum=False),
+            nullable=True,
+        ),
+        sa.Column("llm_answer", sa.String(), nullable=True),
+        sa.Column(
+            "feedback",
+            sa.Enum("LIKE", "DISLIKE", name="qafeedbacktype", native_enum=False),
+            nullable=True,
+        ),
+        sa.Column(
+            "user_id",
+            fastapi_users_db_sqlalchemy.generics.GUID(),
+            nullable=True,
+        ),
+        sa.Column(
+            "time_created",
+            sa.DateTime(timezone=True),
+            server_default=sa.text("now()"),
+            nullable=False,
+        ),
+        sa.ForeignKeyConstraint(
+            ["user_id"],
+            ["user.id"],
+        ),
+        sa.PrimaryKeyConstraint("id"),
+    )
+    op.create_table(
+        "document_retrieval_feedback",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column("qa_event_id", sa.Integer(), nullable=False),
+        sa.Column("document_id", sa.String(), nullable=False),
+        sa.Column("document_rank", sa.Integer(), nullable=False),
+        sa.Column("clicked", sa.Boolean(), nullable=False),
+        sa.Column(
+            "feedback",
+            sa.Enum(
+                "ENDORSE",
+                "REJECT",
+                "HIDE",
+                "UNHIDE",
+                name="searchfeedbacktype",
+                native_enum=False,
+            ),
+            nullable=True,
+        ),
+        sa.ForeignKeyConstraint(
+            ["document_id"],
+            ["document.id"],
+        ),
+        sa.ForeignKeyConstraint(
+            ["qa_event_id"],
+            ["query_event.id"],
+        ),
+        sa.PrimaryKeyConstraint("id"),
+    )
+    op.add_column("document", sa.Column("boost", sa.Integer(), nullable=False))
+    op.add_column("document", sa.Column("hidden", sa.Boolean(), nullable=False))
+    op.add_column("document", sa.Column("semantic_id", sa.String(), nullable=False))
+    op.add_column("document", sa.Column("link", sa.String(), nullable=True))
+
+
+def downgrade() -> None:
+    op.drop_column("document", "link")
+    op.drop_column("document", "semantic_id")
+    op.drop_column("document", "hidden")
+    op.drop_column("document", "boost")
+    op.drop_table("document_retrieval_feedback")
+    op.drop_table("query_event")

backend/alembic/versions/dba7f71618f5_danswer_custom_tool_flow.py

@@ -0,0 +1,29 @@
+"""Danswer Custom Tool Flow
+
+Revision ID: dba7f71618f5
+Revises: d5645c915d0e
+Create Date: 2023-09-18 15:18:37.370972
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "dba7f71618f5"
+down_revision = "d5645c915d0e"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "persona",
+        sa.Column("retrieval_enabled", sa.Boolean(), nullable=True),
+    )
+    op.execute("UPDATE persona SET retrieval_enabled = true")
+    op.alter_column("persona", "retrieval_enabled", nullable=False)
+
+
+def downgrade() -> None:
+    op.drop_column("persona", "retrieval_enabled")

backend/alembic/versions/dbaa756c2ccf_embedding_models.py

@@ -0,0 +1,139 @@
+"""Embedding Models
+
+Revision ID: dbaa756c2ccf
+Revises: 7f726bad5367
+Create Date: 2024-01-25 17:12:31.813160
+
+"""
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy import table, column, String, Integer, Boolean
+
+from danswer.db.embedding_model import (
+    get_new_default_embedding_model,
+    get_old_default_embedding_model,
+    user_has_overridden_embedding_model,
+)
+from danswer.db.models import IndexModelStatus
+
+# revision identifiers, used by Alembic.
+revision = "dbaa756c2ccf"
+down_revision = "7f726bad5367"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "embedding_model",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column("model_name", sa.String(), nullable=False),
+        sa.Column("model_dim", sa.Integer(), nullable=False),
+        sa.Column("normalize", sa.Boolean(), nullable=False),
+        sa.Column("query_prefix", sa.String(), nullable=False),
+        sa.Column("passage_prefix", sa.String(), nullable=False),
+        sa.Column("index_name", sa.String(), nullable=False),
+        sa.Column(
+            "status",
+            sa.Enum(IndexModelStatus, native=False),
+            nullable=False,
+        ),
+        sa.PrimaryKeyConstraint("id"),
+    )
+    # since all index attempts must be associated with an embedding model,
+    # need to put something in here to avoid nulls. On server startup,
+    # this value will be overriden
+    EmbeddingModel = table(
+        "embedding_model",
+        column("id", Integer),
+        column("model_name", String),
+        column("model_dim", Integer),
+        column("normalize", Boolean),
+        column("query_prefix", String),
+        column("passage_prefix", String),
+        column("index_name", String),
+        column(
+            "status", sa.Enum(IndexModelStatus, name="indexmodelstatus", native=False)
+        ),
+    )
+    # insert an embedding model row that corresponds to the embedding model
+    # the user selected via env variables before this change. This is needed since
+    # all index_attempts must be associated with an embedding model, so without this
+    # we will run into violations of non-null contraints
+    old_embedding_model = get_old_default_embedding_model()
+    op.bulk_insert(
+        EmbeddingModel,
+        [
+            {
+                "model_name": old_embedding_model.model_name,
+                "model_dim": old_embedding_model.model_dim,
+                "normalize": old_embedding_model.normalize,
+                "query_prefix": old_embedding_model.query_prefix,
+                "passage_prefix": old_embedding_model.passage_prefix,
+                "index_name": old_embedding_model.index_name,
+                "status": old_embedding_model.status,
+            }
+        ],
+    )
+    # if the user has not overridden the default embedding model via env variables,
+    # insert the new default model into the database to auto-upgrade them
+    if not user_has_overridden_embedding_model():
+        new_embedding_model = get_new_default_embedding_model(is_present=False)
+        op.bulk_insert(
+            EmbeddingModel,
+            [
+                {
+                    "model_name": new_embedding_model.model_name,
+                    "model_dim": new_embedding_model.model_dim,
+                    "normalize": new_embedding_model.normalize,
+                    "query_prefix": new_embedding_model.query_prefix,
+                    "passage_prefix": new_embedding_model.passage_prefix,
+                    "index_name": new_embedding_model.index_name,
+                    "status": IndexModelStatus.FUTURE,
+                }
+            ],
+        )
+
+    op.add_column(
+        "index_attempt",
+        sa.Column("embedding_model_id", sa.Integer(), nullable=True),
+    )
+    op.execute(
+        "UPDATE index_attempt SET embedding_model_id=1 WHERE embedding_model_id IS NULL"
+    )
+    op.alter_column(
+        "index_attempt",
+        "embedding_model_id",
+        existing_type=sa.Integer(),
+        nullable=False,
+    )
+    op.create_foreign_key(
+        "index_attempt__embedding_model_fk",
+        "index_attempt",
+        "embedding_model",
+        ["embedding_model_id"],
+        ["id"],
+    )
+    op.create_index(
+        "ix_embedding_model_present_unique",
+        "embedding_model",
+        ["status"],
+        unique=True,
+        postgresql_where=sa.text("status = 'PRESENT'"),
+    )
+    op.create_index(
+        "ix_embedding_model_future_unique",
+        "embedding_model",
+        ["status"],
+        unique=True,
+        postgresql_where=sa.text("status = 'FUTURE'"),
+    )
+
+
+def downgrade() -> None:
+    op.drop_constraint(
+        "index_attempt__embedding_model_fk", "index_attempt", type_="foreignkey"
+    )
+    op.drop_column("index_attempt", "embedding_model_id")
+    op.drop_table("embedding_model")
+    op.execute("DROP TYPE indexmodelstatus;")