rebase needs fixing

* enable seeding of analytics via file path

* remove log

.github/pull_request_template.md

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

.github/workflows/docker-build-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 +1,43 @@
+name: Build and Push Model Server Image on Tag
+
+on:
+  push:
+    tags:
+      - '*'
+
+jobs:
+  build-and-push:
+    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: ${{ secrets.DOCKER_TOKEN }}
+
+    - name: Model Server Image Docker Build and Push
+      uses: docker/build-push-action@v5
+      with:
+        context: ./backend
+        file: ./backend/Dockerfile.model_server
+        platforms: linux/amd64,linux/arm64
+        push: true
+        tags: |
+          danswer/danswer-model-server:${{ 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

@@ -0,0 +1,32 @@
+name: Tag Latest Version
+
+on:
+  workflow_dispatch:
+    inputs:
+      version:
+        description: 'The version (ie v0.0.1) to tag as latest'
+        required: true
+
+jobs:
+  tag:
+    runs-on: ubuntu-latest
+    steps:
+    - 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: Enable Docker CLI experimental features
+      run: echo "DOCKER_CLI_EXPERIMENTAL=enabled" >> $GITHUB_ENV
+
+    - name: Pull, Tag and Push Web Server Image
+      run: |
+        docker buildx imagetools create -t danswer/danswer-web-server:latest danswer/danswer-web-server:${{ github.event.inputs.version }}
+
+    - name: Pull, Tag and Push API Server Image
+      run: |
+        docker buildx imagetools create -t danswer/danswer-backend:latest danswer/danswer-backend:${{ github.event.inputs.version }}

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

@@ -0,0 +1,48 @@
+name: Python Checks
+
+on:
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  mypy-check:
+    runs-on: ubuntu-latest
+
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v3
+
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.11'
+        cache: 'pip'
+        cache-dependency-path: |
+          backend/requirements/default.txt
+          backend/requirements/dev.txt
+          backend/requirements/model_server.txt
+    - run: |
+        python -m pip install --upgrade pip
+        pip install -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
+        find ./danswer -name "*.py" | xargs reorder-python-imports --py311-plus
+
+    - name: Check code formatting with Black
+      run: |
+        cd backend
+        black --check .

.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

@@ -0,0 +1,9 @@
+.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

@@ -0,0 +1,65 @@
+repos:
+  - repo: https://github.com/psf/black
+    rev: 23.3.0
+    hooks:
+    - id: black
+      language_version: python3.11
+
+  - repo: https://github.com/asottile/reorder_python_imports
+    rev: v3.9.0
+    hooks:
+    - id: reorder-python-imports
+      args: ['--py311-plus', '--application-directories=backend/']
+      # need to ignore alembic files, since reorder-python-imports gets confused
+      # and thinks that alembic is a local package since there is a folder
+      # in the backend directory called `alembic`
+      exclude: ^backend/alembic/
+
+  # 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
+  # having mypy run via Github Actions / manually by contributors
+  # - repo: https://github.com/pre-commit/mirrors-mypy
+  #   rev: v1.1.1
+  #   hooks:
+  #     - id: mypy
+  #       exclude: ^tests/
+  #       # below are needed for type stubs since pre-commit runs in it's own
+  #       # isolated environment. Unfortunately, this needs to be kept in sync
+  #       # 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-urllib3==1.26.25.11
+  #       ]
+  #       # TODO: add back once errors are addressed
+  #       # 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_DOC_RELEVANCE=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.template.jsonc

@@ -0,0 +1,145 @@
+/*
+
+  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"
+            ],
+            "consoleTitle": "Model Server"
+        },
+        {
+            "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"
+            ],
+            "consoleTitle": "API Server"
+        },
+        {
+            "name": "Indexing",
+            "type": "python",
+            "request": "launch",
+            "program": "danswer/background/update.py",
+            "cwd": "${workspaceFolder}/backend",
+            "envFile": "${workspaceFolder}/.env",
+            "env": {
+                "ENABLE_MULTIPASS_INDEXING": "false",
+                "LOG_LEVEL": "DEBUG",
+                "PYTHONUNBUFFERED": "1",
+                "PYTHONPATH": "."
+            },
+            "consoleTitle": "Indexing"
+        },
+        // 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"
+            ],
+            "consoleTitle": "Background Jobs"
+        },
+        // 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"
+            ]
+        }
+    ],
+    "compounds": [
+        {
+            "name": "Run Danswer",
+            "configurations": [
+                "Web Server",
+                "Model Server",
+                "API Server",
+                "Indexing",
+                "Background Jobs",
+            ]
+        }
+    ]
+}

CONTRIBUTING.md

@@ -0,0 +1,191 @@
+<!-- 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.
+
+As an open source project in a rapidly changing space, we welcome all contributions.
+
+
+## 💃 Guidelines
+### Contribution Opportunities
+The [GitHub Issues](https://github.com/danswer-ai/danswer/issues) page is a great place to start for contribution ideas.
+
+Issues that have been explicitly approved by the maintainers (aligned with the direction of the project)
+will be marked with the `approved by maintainers` label.
+Issues marked `good first issue` are an especially great place to start.
+
+**Connectors** to other tools are another great place to contribute. For details on how, refer to this
+[README.md](https://github.com/danswer-ai/danswer/blob/main/backend/danswer/connectors/README.md).
+
+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](https://join.slack.com/t/danswer/shared_invite/zt-2afut44lv-Rw3kSWu6_OmdAXRpCv80DQ) / 
+[Discord](https://discord.gg/TDJ59cGV2X) directly about anything at all. 
+
+
+### Contributing Code
+To contribute to this project, please follow the
+["fork and pull request"](https://docs.github.com/en/get-started/quickstart/contributing-to-projects) workflow.
+When opening a pull request, mention related issues and feel free to tag relevant maintainers.
+
+Before creating a pull request please make sure that the new changes conform to the formatting and linting requirements.
+See the [Formatting and Linting](#-formatting-and-linting) section for how to run these checks locally.
+
+
+### Getting Help 🙋
+Our goal is to make contributing as easy as possible. If you run into any issues please don't hesitate to reach out.
+That way we can help future contributors and users can avoid the same issue.
+
+We also have support channels and generally interesting discussions on our
+[Slack](https://join.slack.com/t/danswer/shared_invite/zt-2afut44lv-Rw3kSWu6_OmdAXRpCv80DQ)
+and 
+[Discord](https://discord.gg/TDJ59cGV2X).
+
+We would love to see you there!
+
+
+## Get Started 🚀
+Danswer being a fully functional app, relies on some external pieces of software, specifically:
+- [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
+`--build` flag.
+
+
+### Local Set Up
+It is recommended to use Python version 3.11
+
+If using a lower version, modifications will have to be made to the code.
+If using a higher version, the version of Tensorflow we use may not be available for your platform.
+
+
+#### Installing Requirements
+Currently, we use pip and recommend creating a virtual environment.
+
+For convenience here's a command for it:
+```bash
+python -m venv .venv
+source .venv/bin/activate
+```
+
+--> Note 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.
+Once the above is done, navigate to `danswer/web` run:
+```bash
+npm i
+```
+
+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 Vespa and Postgres with:
+```bash
+docker compose -f docker-compose.dev.yml -p danswer-stack up -d index relational_db
+```
+(index refers to Vespa and relational_db refers to Postgres)
+
+#### Running Danswer
+To start the frontend, navigate to `danswer/web` and run:
+```bash
+npm run dev
+```
+
+Next, start the model server which runs the local NLP models.
+Navigate to `danswer/backend` and run:
+```bash
+uvicorn model_server.main:app --reload --port 9000
+```
+_For Windows (for compatibility with both PowerShell and Command Prompt):_
+```bash
+powershell -Command "
+    uvicorn model_server.main:app --reload --port 9000
+"
+```
+
+The first time running Danswer, you will need to run the DB migrations for Postgres.
+After the first time, this is no longer required unless the DB models change.
+
+Navigate to `danswer/backend` and with the venv active, run:
+```bash
+alembic upgrade head
+```
+
+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
+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: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.
+
+### Formatting and Linting
+#### Backend
+For the backend, you'll need to setup pre-commit hooks (black / reorder-python-imports).
+First, install pre-commit (if you don't have it already) following the instructions
+[here](https://pre-commit.com/#installation).
+Then, from the `danswer/backend` directory, run:
+```bash
+pre-commit install
+```
+
+Additionally, we use `mypy` for static type checking.
+Danswer is fully type-annotated, and we would like to keep it that way! 
+To run the mypy checks manually, run `python -m mypy .` from the `danswer/backend` directory.
+
+
+#### Web
+We use `prettier` for formatting. The desired version (2.8.8) will be installed via a `npm i` from the `danswer/web` directory. 
+To run the formatter, use `npx prettier --write .` from the `danswer/web` directory.
+Please double check that prettier passes before creating a pull request.
+
+
+### 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).

LICENSE

@@ -1,661 +1,25 @@
-                    GNU AFFERO GENERAL PUBLIC LICENSE
-                       Version 3, 19 November 2007
-
- Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/>
- Everyone is permitted to copy and distribute verbatim copies
- of this license document, but changing it is not allowed.
-
-                            Preamble
-
-  The GNU Affero General Public License is a free, copyleft license for
-software and other kinds of works, specifically designed to ensure
-cooperation with the community in the case of network server software.
-
-  The licenses for most software and other practical works are designed
-to take away your freedom to share and change the works.  By contrast,
-our General Public Licenses are intended to guarantee your freedom to
-share and change all versions of a program--to make sure it remains free
-software for all its users.
-
-  When we speak of free software, we are referring to freedom, not
-price.  Our General Public Licenses are designed to make sure that you
-have the freedom to distribute copies of free software (and charge for
-them if you wish), that you receive source code or can get it if you
-want it, that you can change the software or use pieces of it in new
-free programs, and that you know you can do these things.
-
-  Developers that use our General Public Licenses protect your rights
-with two steps: (1) assert copyright on the software, and (2) offer
-you this License which gives you legal permission to copy, distribute
-and/or modify the software.
-
-  A secondary benefit of defending all users' freedom is that
-improvements made in alternate versions of the program, if they
-receive widespread use, become available for other developers to
-incorporate.  Many developers of free software are heartened and
-encouraged by the resulting cooperation.  However, in the case of
-software used on network servers, this result may fail to come about.
-The GNU General Public License permits making a modified version and
-letting the public access it on a server without ever releasing its
-source code to the public.
-
-  The GNU Affero General Public License is designed specifically to
-ensure that, in such cases, the modified source code becomes available
-to the community.  It requires the operator of a network server to
-provide the source code of the modified version running there to the
-users of that server.  Therefore, public use of a modified version, on
-a publicly accessible server, gives the public access to the source
-code of the modified version.
-
-  An older license, called the Affero General Public License and
-published by Affero, was designed to accomplish similar goals.  This is
-a different license, not a version of the Affero GPL, but Affero has
-released a new version of the Affero GPL which permits relicensing under
-this license.
-
-  The precise terms and conditions for copying, distribution and
-modification follow.
-
-                       TERMS AND CONDITIONS
-
-  0. Definitions.
-
-  "This License" refers to version 3 of the GNU Affero General Public License.
-
-  "Copyright" also means copyright-like laws that apply to other kinds of
-works, such as semiconductor masks.
-
-  "The Program" refers to any copyrightable work licensed under this
-License.  Each licensee is addressed as "you".  "Licensees" and
-"recipients" may be individuals or organizations.
-
-  To "modify" a work means to copy from or adapt all or part of the work
-in a fashion requiring copyright permission, other than the making of an
-exact copy.  The resulting work is called a "modified version" of the
-earlier work or a work "based on" the earlier work.
-
-  A "covered work" means either the unmodified Program or a work based
-on the Program.
-
-  To "propagate" a work means to do anything with it that, without
-permission, would make you directly or secondarily liable for
-infringement under applicable copyright law, except executing it on a
-computer or modifying a private copy.  Propagation includes copying,
-distribution (with or without modification), making available to the
-public, and in some countries other activities as well.
-
-  To "convey" a work means any kind of propagation that enables other
-parties to make or receive copies.  Mere interaction with a user through
-a computer network, with no transfer of a copy, is not conveying.
-
-  An interactive user interface displays "Appropriate Legal Notices"
-to the extent that it includes a convenient and prominently visible
-feature that (1) displays an appropriate copyright notice, and (2)
-tells the user that there is no warranty for the work (except to the
-extent that warranties are provided), that licensees may convey the
-work under this License, and how to view a copy of this License.  If
-the interface presents a list of user commands or options, such as a
-menu, a prominent item in the list meets this criterion.
-
-  1. Source Code.
-
-  The "source code" for a work means the preferred form of the work
-for making modifications to it.  "Object code" means any non-source
-form of a work.
-
-  A "Standard Interface" means an interface that either is an official
-standard defined by a recognized standards body, or, in the case of
-interfaces specified for a particular programming language, one that
-is widely used among developers working in that language.
-
-  The "System Libraries" of an executable work include anything, other
-than the work as a whole, that (a) is included in the normal form of
-packaging a Major Component, but which is not part of that Major
-Component, and (b) serves only to enable use of the work with that
-Major Component, or to implement a Standard Interface for which an
-implementation is available to the public in source code form.  A
-"Major Component", in this context, means a major essential component
-(kernel, window system, and so on) of the specific operating system
-(if any) on which the executable work runs, or a compiler used to
-produce the work, or an object code interpreter used to run it.
-
-  The "Corresponding Source" for a work in object code form means all
-the source code needed to generate, install, and (for an executable
-work) run the object code and to modify the work, including scripts to
-control those activities.  However, it does not include the work's
-System Libraries, or general-purpose tools or generally available free
-programs which are used unmodified in performing those activities but
-which are not part of the work.  For example, Corresponding Source
-includes interface definition files associated with source files for
-the work, and the source code for shared libraries and dynamically
-linked subprograms that the work is specifically designed to require,
-such as by intimate data communication or control flow between those
-subprograms and other parts of the work.
-
-  The Corresponding Source need not include anything that users
-can regenerate automatically from other parts of the Corresponding
-Source.
-
-  The Corresponding Source for a work in source code form is that
-same work.
-
-  2. Basic Permissions.
-
-  All rights granted under this License are granted for the term of
-copyright on the Program, and are irrevocable provided the stated
-conditions are met.  This License explicitly affirms your unlimited
-permission to run the unmodified Program.  The output from running a
-covered work is covered by this License only if the output, given its
-content, constitutes a covered work.  This License acknowledges your
-rights of fair use or other equivalent, as provided by copyright law.
-
-  You may make, run and propagate covered works that you do not
-convey, without conditions so long as your license otherwise remains
-in force.  You may convey covered works to others for the sole purpose
-of having them make modifications exclusively for you, or provide you
-with facilities for running those works, provided that you comply with
-the terms of this License in conveying all material for which you do
-not control copyright.  Those thus making or running the covered works
-for you must do so exclusively on your behalf, under your direction
-and control, on terms that prohibit them from making any copies of
-your copyrighted material outside their relationship with you.
-
-  Conveying under any other circumstances is permitted solely under
-the conditions stated below.  Sublicensing is not allowed; section 10
-makes it unnecessary.
-
-  3. Protecting Users' Legal Rights From Anti-Circumvention Law.
-
-  No covered work shall be deemed part of an effective technological
-measure under any applicable law fulfilling obligations under article
-11 of the WIPO copyright treaty adopted on 20 December 1996, or
-similar laws prohibiting or restricting circumvention of such
-measures.
-
-  When you convey a covered work, you waive any legal power to forbid
-circumvention of technological measures to the extent such circumvention
-is effected by exercising rights under this License with respect to
-the covered work, and you disclaim any intention to limit operation or
-modification of the work as a means of enforcing, against the work's
-users, your or third parties' legal rights to forbid circumvention of
-technological measures.
-
-  4. Conveying Verbatim Copies.
-
-  You may convey verbatim copies of the Program's source code as you
-receive it, in any medium, provided that you conspicuously and
-appropriately publish on each copy an appropriate copyright notice;
-keep intact all notices stating that this License and any
-non-permissive terms added in accord with section 7 apply to the code;
-keep intact all notices of the absence of any warranty; and give all
-recipients a copy of this License along with the Program.
-
-  You may charge any price or no price for each copy that you convey,
-and you may offer support or warranty protection for a fee.
-
-  5. Conveying Modified Source Versions.
-
-  You may convey a work based on the Program, or the modifications to
-produce it from the Program, in the form of source code under the
-terms of section 4, provided that you also meet all of these conditions:
-
-    a) The work must carry prominent notices stating that you modified
-    it, and giving a relevant date.
-
-    b) The work must carry prominent notices stating that it is
-    released under this License and any conditions added under section
-    7.  This requirement modifies the requirement in section 4 to
-    "keep intact all notices".
-
-    c) You must license the entire work, as a whole, under this
-    License to anyone who comes into possession of a copy.  This
-    License will therefore apply, along with any applicable section 7
-    additional terms, to the whole of the work, and all its parts,
-    regardless of how they are packaged.  This License gives no
-    permission to license the work in any other way, but it does not
-    invalidate such permission if you have separately received it.
-
-    d) If the work has interactive user interfaces, each must display
-    Appropriate Legal Notices; however, if the Program has interactive
-    interfaces that do not display Appropriate Legal Notices, your
-    work need not make them do so.
-
-  A compilation of a covered work with other separate and independent
-works, which are not by their nature extensions of the covered work,
-and which are not combined with it such as to form a larger program,
-in or on a volume of a storage or distribution medium, is called an
-"aggregate" if the compilation and its resulting copyright are not
-used to limit the access or legal rights of the compilation's users
-beyond what the individual works permit.  Inclusion of a covered work
-in an aggregate does not cause this License to apply to the other
-parts of the aggregate.
-
-  6. Conveying Non-Source Forms.
-
-  You may convey a covered work in object code form under the terms
-of sections 4 and 5, provided that you also convey the
-machine-readable Corresponding Source under the terms of this License,
-in one of these ways:
-
-    a) Convey the object code in, or embodied in, a physical product
-    (including a physical distribution medium), accompanied by the
-    Corresponding Source fixed on a durable physical medium
-    customarily used for software interchange.
-
-    b) Convey the object code in, or embodied in, a physical product
-    (including a physical distribution medium), accompanied by a
-    written offer, valid for at least three years and valid for as
-    long as you offer spare parts or customer support for that product
-    model, to give anyone who possesses the object code either (1) a
-    copy of the Corresponding Source for all the software in the
-    product that is covered by this License, on a durable physical
-    medium customarily used for software interchange, for a price no
-    more than your reasonable cost of physically performing this
-    conveying of source, or (2) access to copy the
-    Corresponding Source from a network server at no charge.
-
-    c) Convey individual copies of the object code with a copy of the
-    written offer to provide the Corresponding Source.  This
-    alternative is allowed only occasionally and noncommercially, and
-    only if you received the object code with such an offer, in accord
-    with subsection 6b.
-
-    d) Convey the object code by offering access from a designated
-    place (gratis or for a charge), and offer equivalent access to the
-    Corresponding Source in the same way through the same place at no
-    further charge.  You need not require recipients to copy the
-    Corresponding Source along with the object code.  If the place to
-    copy the object code is a network server, the Corresponding Source
-    may be on a different server (operated by you or a third party)
-    that supports equivalent copying facilities, provided you maintain
-    clear directions next to the object code saying where to find the
-    Corresponding Source.  Regardless of what server hosts the
-    Corresponding Source, you remain obligated to ensure that it is
-    available for as long as needed to satisfy these requirements.
-
-    e) Convey the object code using peer-to-peer transmission, provided
-    you inform other peers where the object code and Corresponding
-    Source of the work are being offered to the general public at no
-    charge under subsection 6d.
-
-  A separable portion of the object code, whose source code is excluded
-from the Corresponding Source as a System Library, need not be
-included in conveying the object code work.
-
-  A "User Product" is either (1) a "consumer product", which means any
-tangible personal property which is normally used for personal, family,
-or household purposes, or (2) anything designed or sold for incorporation
-into a dwelling.  In determining whether a product is a consumer product,
-doubtful cases shall be resolved in favor of coverage.  For a particular
-product received by a particular user, "normally used" refers to a
-typical or common use of that class of product, regardless of the status
-of the particular user or of the way in which the particular user
-actually uses, or expects or is expected to use, the product.  A product
-is a consumer product regardless of whether the product has substantial
-commercial, industrial or non-consumer uses, unless such uses represent
-the only significant mode of use of the product.
-
-  "Installation Information" for a User Product means any methods,
-procedures, authorization keys, or other information required to install
-and execute modified versions of a covered work in that User Product from
-a modified version of its Corresponding Source.  The information must
-suffice to ensure that the continued functioning of the modified object
-code is in no case prevented or interfered with solely because
-modification has been made.
-
-  If you convey an object code work under this section in, or with, or
-specifically for use in, a User Product, and the conveying occurs as
-part of a transaction in which the right of possession and use of the
-User Product is transferred to the recipient in perpetuity or for a
-fixed term (regardless of how the transaction is characterized), the
-Corresponding Source conveyed under this section must be accompanied
-by the Installation Information.  But this requirement does not apply
-if neither you nor any third party retains the ability to install
-modified object code on the User Product (for example, the work has
-been installed in ROM).
-
-  The requirement to provide Installation Information does not include a
-requirement to continue to provide support service, warranty, or updates
-for a work that has been modified or installed by the recipient, or for
-the User Product in which it has been modified or installed.  Access to a
-network may be denied when the modification itself materially and
-adversely affects the operation of the network or violates the rules and
-protocols for communication across the network.
-
-  Corresponding Source conveyed, and Installation Information provided,
-in accord with this section must be in a format that is publicly
-documented (and with an implementation available to the public in
-source code form), and must require no special password or key for
-unpacking, reading or copying.
-
-  7. Additional Terms.
-
-  "Additional permissions" are terms that supplement the terms of this
-License by making exceptions from one or more of its conditions.
-Additional permissions that are applicable to the entire Program shall
-be treated as though they were included in this License, to the extent
-that they are valid under applicable law.  If additional permissions
-apply only to part of the Program, that part may be used separately
-under those permissions, but the entire Program remains governed by
-this License without regard to the additional permissions.
-
-  When you convey a copy of a covered work, you may at your option
-remove any additional permissions from that copy, or from any part of
-it.  (Additional permissions may be written to require their own
-removal in certain cases when you modify the work.)  You may place
-additional permissions on material, added by you to a covered work,
-for which you have or can give appropriate copyright permission.
-
-  Notwithstanding any other provision of this License, for material you
-add to a covered work, you may (if authorized by the copyright holders of
-that material) supplement the terms of this License with terms:
-
-    a) Disclaiming warranty or limiting liability differently from the
-    terms of sections 15 and 16 of this License; or
-
-    b) Requiring preservation of specified reasonable legal notices or
-    author attributions in that material or in the Appropriate Legal
-    Notices displayed by works containing it; or
-
-    c) Prohibiting misrepresentation of the origin of that material, or
-    requiring that modified versions of such material be marked in
-    reasonable ways as different from the original version; or
-
-    d) Limiting the use for publicity purposes of names of licensors or
-    authors of the material; or
-
-    e) Declining to grant rights under trademark law for use of some
-    trade names, trademarks, or service marks; or
-
-    f) Requiring indemnification of licensors and authors of that
-    material by anyone who conveys the material (or modified versions of
-    it) with contractual assumptions of liability to the recipient, for
-    any liability that these contractual assumptions directly impose on
-    those licensors and authors.
-
-  All other non-permissive additional terms are considered "further
-restrictions" within the meaning of section 10.  If the Program as you
-received it, or any part of it, contains a notice stating that it is
-governed by this License along with a term that is a further
-restriction, you may remove that term.  If a license document contains
-a further restriction but permits relicensing or conveying under this
-License, you may add to a covered work material governed by the terms
-of that license document, provided that the further restriction does
-not survive such relicensing or conveying.
-
-  If you add terms to a covered work in accord with this section, you
-must place, in the relevant source files, a statement of the
-additional terms that apply to those files, or a notice indicating
-where to find the applicable terms.
-
-  Additional terms, permissive or non-permissive, may be stated in the
-form of a separately written license, or stated as exceptions;
-the above requirements apply either way.
-
-  8. Termination.
-
-  You may not propagate or modify a covered work except as expressly
-provided under this License.  Any attempt otherwise to propagate or
-modify it is void, and will automatically terminate your rights under
-this License (including any patent licenses granted under the third
-paragraph of section 11).
-
-  However, if you cease all violation of this License, then your
-license from a particular copyright holder is reinstated (a)
-provisionally, unless and until the copyright holder explicitly and
-finally terminates your license, and (b) permanently, if the copyright
-holder fails to notify you of the violation by some reasonable means
-prior to 60 days after the cessation.
-
-  Moreover, your license from a particular copyright holder is
-reinstated permanently if the copyright holder notifies you of the
-violation by some reasonable means, this is the first time you have
-received notice of violation of this License (for any work) from that
-copyright holder, and you cure the violation prior to 30 days after
-your receipt of the notice.
-
-  Termination of your rights under this section does not terminate the
-licenses of parties who have received copies or rights from you under
-this License.  If your rights have been terminated and not permanently
-reinstated, you do not qualify to receive new licenses for the same
-material under section 10.
-
-  9. Acceptance Not Required for Having Copies.
-
-  You are not required to accept this License in order to receive or
-run a copy of the Program.  Ancillary propagation of a covered work
-occurring solely as a consequence of using peer-to-peer transmission
-to receive a copy likewise does not require acceptance.  However,
-nothing other than this License grants you permission to propagate or
-modify any covered work.  These actions infringe copyright if you do
-not accept this License.  Therefore, by modifying or propagating a
-covered work, you indicate your acceptance of this License to do so.
-
-  10. Automatic Licensing of Downstream Recipients.
-
-  Each time you convey a covered work, the recipient automatically
-receives a license from the original licensors, to run, modify and
-propagate that work, subject to this License.  You are not responsible
-for enforcing compliance by third parties with this License.
-
-  An "entity transaction" is a transaction transferring control of an
-organization, or substantially all assets of one, or subdividing an
-organization, or merging organizations.  If propagation of a covered
-work results from an entity transaction, each party to that
-transaction who receives a copy of the work also receives whatever
-licenses to the work the party's predecessor in interest had or could
-give under the previous paragraph, plus a right to possession of the
-Corresponding Source of the work from the predecessor in interest, if
-the predecessor has it or can get it with reasonable efforts.
-
-  You may not impose any further restrictions on the exercise of the
-rights granted or affirmed under this License.  For example, you may
-not impose a license fee, royalty, or other charge for exercise of
-rights granted under this License, and you may not initiate litigation
-(including a cross-claim or counterclaim in a lawsuit) alleging that
-any patent claim is infringed by making, using, selling, offering for
-sale, or importing the Program or any portion of it.
-
-  11. Patents.
-
-  A "contributor" is a copyright holder who authorizes use under this
-License of the Program or a work on which the Program is based.  The
-work thus licensed is called the contributor's "contributor version".
-
-  A contributor's "essential patent claims" are all patent claims
-owned or controlled by the contributor, whether already acquired or
-hereafter acquired, that would be infringed by some manner, permitted
-by this License, of making, using, or selling its contributor version,
-but do not include claims that would be infringed only as a
-consequence of further modification of the contributor version.  For
-purposes of this definition, "control" includes the right to grant
-patent sublicenses in a manner consistent with the requirements of
-this License.
-
-  Each contributor grants you a non-exclusive, worldwide, royalty-free
-patent license under the contributor's essential patent claims, to
-make, use, sell, offer for sale, import and otherwise run, modify and
-propagate the contents of its contributor version.
-
-  In the following three paragraphs, a "patent license" is any express
-agreement or commitment, however denominated, not to enforce a patent
-(such as an express permission to practice a patent or covenant not to
-sue for patent infringement).  To "grant" such a patent license to a
-party means to make such an agreement or commitment not to enforce a
-patent against the party.
-
-  If you convey a covered work, knowingly relying on a patent license,
-and the Corresponding Source of the work is not available for anyone
-to copy, free of charge and under the terms of this License, through a
-publicly available network server or other readily accessible means,
-then you must either (1) cause the Corresponding Source to be so
-available, or (2) arrange to deprive yourself of the benefit of the
-patent license for this particular work, or (3) arrange, in a manner
-consistent with the requirements of this License, to extend the patent
-license to downstream recipients.  "Knowingly relying" means you have
-actual knowledge that, but for the patent license, your conveying the
-covered work in a country, or your recipient's use of the covered work
-in a country, would infringe one or more identifiable patents in that
-country that you have reason to believe are valid.
-
-  If, pursuant to or in connection with a single transaction or
-arrangement, you convey, or propagate by procuring conveyance of, a
-covered work, and grant a patent license to some of the parties
-receiving the covered work authorizing them to use, propagate, modify
-or convey a specific copy of the covered work, then the patent license
-you grant is automatically extended to all recipients of the covered
-work and works based on it.
-
-  A patent license is "discriminatory" if it does not include within
-the scope of its coverage, prohibits the exercise of, or is
-conditioned on the non-exercise of one or more of the rights that are
-specifically granted under this License.  You may not convey a covered
-work if you are a party to an arrangement with a third party that is
-in the business of distributing software, under which you make payment
-to the third party based on the extent of your activity of conveying
-the work, and under which the third party grants, to any of the
-parties who would receive the covered work from you, a discriminatory
-patent license (a) in connection with copies of the covered work
-conveyed by you (or copies made from those copies), or (b) primarily
-for and in connection with specific products or compilations that
-contain the covered work, unless you entered into that arrangement,
-or that patent license was granted, prior to 28 March 2007.
-
-  Nothing in this License shall be construed as excluding or limiting
-any implied license or other defenses to infringement that may
-otherwise be available to you under applicable patent law.
-
-  12. No Surrender of Others' Freedom.
-
-  If conditions are imposed on you (whether by court order, agreement or
-otherwise) that contradict the conditions of this License, they do not
-excuse you from the conditions of this License.  If you cannot convey a
-covered work so as to satisfy simultaneously your obligations under this
-License and any other pertinent obligations, then as a consequence you may
-not convey it at all.  For example, if you agree to terms that obligate you
-to collect a royalty for further conveying from those to whom you convey
-the Program, the only way you could satisfy both those terms and this
-License would be to refrain entirely from conveying the Program.
-
-  13. Remote Network Interaction; Use with the GNU General Public License.
-
-  Notwithstanding any other provision of this License, if you modify the
-Program, your modified version must prominently offer all users
-interacting with it remotely through a computer network (if your version
-supports such interaction) an opportunity to receive the Corresponding
-Source of your version by providing access to the Corresponding Source
-from a network server at no charge, through some standard or customary
-means of facilitating copying of software.  This Corresponding Source
-shall include the Corresponding Source for any work covered by version 3
-of the GNU General Public License that is incorporated pursuant to the
-following paragraph.
-
-  Notwithstanding any other provision of this License, you have
-permission to link or combine any covered work with a work licensed
-under version 3 of the GNU General Public License into a single
-combined work, and to convey the resulting work.  The terms of this
-License will continue to apply to the part which is the covered work,
-but the work with which it is combined will remain governed by version
-3 of the GNU General Public License.
-
-  14. Revised Versions of this License.
-
-  The Free Software Foundation may publish revised and/or new versions of
-the GNU Affero General Public License from time to time.  Such new versions
-will be similar in spirit to the present version, but may differ in detail to
-address new problems or concerns.
-
-  Each version is given a distinguishing version number.  If the
-Program specifies that a certain numbered version of the GNU Affero General
-Public License "or any later version" applies to it, you have the
-option of following the terms and conditions either of that numbered
-version or of any later version published by the Free Software
-Foundation.  If the Program does not specify a version number of the
-GNU Affero General Public License, you may choose any version ever published
-by the Free Software Foundation.
-
-  If the Program specifies that a proxy can decide which future
-versions of the GNU Affero General Public License can be used, that proxy's
-public statement of acceptance of a version permanently authorizes you
-to choose that version for the Program.
-
-  Later license versions may give you additional or different
-permissions.  However, no additional obligations are imposed on any
-author or copyright holder as a result of your choosing to follow a
-later version.
-
-  15. Disclaimer of Warranty.
-
-  THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
-APPLICABLE LAW.  EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
-HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
-OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
-THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
-PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
-IS WITH YOU.  SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
-ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
-
-  16. Limitation of Liability.
-
-  IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
-WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
-THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
-GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
-USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
-DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
-PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
-EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
-SUCH DAMAGES.
-
-  17. Interpretation of Sections 15 and 16.
-
-  If the disclaimer of warranty and limitation of liability provided
-above cannot be given local legal effect according to their terms,
-reviewing courts shall apply local law that most closely approximates
-an absolute waiver of all civil liability in connection with the
-Program, unless a warranty or assumption of liability accompanies a
-copy of the Program in return for a fee.
-
-                     END OF TERMS AND CONDITIONS
-
-            How to Apply These Terms to Your New Programs
-
-  If you develop a new program, and you want it to be of the greatest
-possible use to the public, the best way to achieve this is to make it
-free software which everyone can redistribute and change under these terms.
-
-  To do so, attach the following notices to the program.  It is safest
-to attach them to the start of each source file to most effectively
-state the exclusion of warranty; and each file should have at least
-the "copyright" line and a pointer to where the full notice is found.
-
-    <one line to give the program's name and a brief idea of what it does.>
-    Copyright (C) <year>  <name of author>
-
-    This program is free software: you can redistribute it and/or modify
-    it under the terms of the GNU Affero General Public License as published
-    by the Free Software Foundation, either version 3 of the License, or
-    (at your option) any later version.
-
-    This program is distributed in the hope that it will be useful,
-    but WITHOUT ANY WARRANTY; without even the implied warranty of
-    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-    GNU Affero General Public License for more details.
-
-    You should have received a copy of the GNU Affero General Public License
-    along with this program.  If not, see <https://www.gnu.org/licenses/>.
-
-Also add information on how to contact you by electronic and paper mail.
-
-  If your software can interact with users remotely through a computer
-network, you should also make sure that it provides a way for users to
-get its source.  For example, if your program is a web application, its
-interface could display a "Source" link that leads users to an archive
-of the code.  There are many ways you could offer source, and different
-solutions will be better for different programs; see section 13 for the
-specific requirements.
-
-  You should also get your employer (if you work as a programmer) or school,
-if any, to sign a "copyright disclaimer" for the program, if necessary.
-For more information on this, and how to apply and follow the GNU AGPL, see
-<https://www.gnu.org/licenses/>.
+Copyright (c) 2023-present DanswerAI, Inc.
+
+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
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -0,0 +1,129 @@
+<!-- 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">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-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">
+    <img src="https://img.shields.io/badge/discord-join-blue.svg?logo=discord&logoColor=white" alt="Discord">
+</a>
+<a href="https://github.com/danswer-ai/danswer/blob/main/README.md" target="_blank">
+    <img src="https://img.shields.io/static/v1?label=license&message=MIT&color=blue" alt="License">
+</a>
+</p>
+
+<strong>[Danswer](https://www.danswer.ai/)</strong> is the AI Assistant connected to your company's docs, apps, and people. 
+Danswer provides a Chat interface and plugs into any LLM of your choice. Danswer can be deployed anywhere and for any 
+scale - on a laptop, on-premise, or to cloud. Since you own the deployment, your user data and chats are fully in your 
+own control. Danswer is MIT licensed and designed to be modular and easily extensible. The system also comes fully ready 
+for production usage with user authentication, role management (admin/basic users), chat persistence, and a UI for 
+configuring Personas (AI Assistants) and their Prompts.
+
+Danswer also serves as a Unified Search across all common workplace tools such as Slack, Google Drive, Confluence, etc.
+By combining LLMs and team specific knowledge, Danswer becomes a subject matter expert for the team. Imagine ChatGPT if
+it had access to your team's unique knowledge! It enables questions such as "A customer wants feature X, is this already
+supported?" or "Where's the pull request for feature Y?"
+
+<h3>Usage</h3>
+
+Danswer Web App:
+
+https://github.com/danswer-ai/danswer/assets/32520769/563be14c-9304-47b5-bf0a-9049c2b6f410
+
+
+Or, plug Danswer into your existing Slack workflows (more integrations to come 😁):
+
+https://github.com/danswer-ai/danswer/assets/25087905/3e19739b-d178-4371-9a38-011430bdec1b
+
+
+For more details on the Admin 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

@@ -0,0 +1,11 @@
+__pycache__/
+.mypy_cache
+.idea/
+site_crawls/
+.ipynb_checkpoints/
+api_keys.py
+*ipynb
+.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

@@ -0,0 +1,105 @@
+FROM python:3.11.7-slim-bookworm
+
+LABEL com.danswer.maintainer="founders@danswer.ai"
+LABEL com.danswer.description="This image is the web/frontend container of Danswer which \
+contains code for both the Community and Enterprise editions of Danswer. If you do not \
+have a contract or agreement with DanswerAI, you are not permitted to use the Enterprise \
+Edition features outside of personal development or testing purposes. Please reach out to \
+founders@danswer.ai for more information. Please visit https://github.com/danswer-ai/danswer"
+
+# 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
+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 tokenizers import Tokenizer; \
+Tokenizer.from_pretrained('nomic-ai/nomic-embed-text-v1')"
+
+
+# Pre-downloading NLTK for setups with limited egress
+RUN python -c "import nltk; \
+nltk.download('stopwords', quiet=True); \
+nltk.download('wordnet', quiet=True); \
+nltk.download('punkt', quiet=True);"
+
+# Set up application files
+WORKDIR /app
+
+# Enterprise Version Files
+COPY ./ee /app/ee
+COPY supervisord.conf /etc/supervisor/conf.d/supervisord.conf
+
+# Set up application files
+COPY ./danswer /app/danswer
+COPY ./shared_configs /app/shared_configs
+COPY ./alembic /app/alembic
+COPY ./alembic.ini /app/alembic.ini
+COPY supervisord.conf /usr/etc/supervisord.conf
+
+# Escape hatch
+COPY ./scripts/force_delete_connector_by_id.py /app/scripts/force_delete_connector_by_id.py
+
+# Put logo in assets
+COPY ./assets /app/assets
+
+ENV PYTHONPATH /app
+
+# Default command which does nothing
+# 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 +1,50 @@
+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
+# Download tokenizers, distilbert for the Danswer model
+# Download model weights
+# Run Nomic to pull in the custom architecture and have it cached locally
+RUN python -c "from transformers import AutoTokenizer; \
+AutoTokenizer.from_pretrained('distilbert-base-uncased', cache_folder='/root/.cache/temp_huggingface/hub/'); \
+AutoTokenizer.from_pretrained('mixedbread-ai/mxbai-rerank-xsmall-v1', cache_folder='/root/.cache/temp_huggingface/hub/'); \
+from huggingface_hub import snapshot_download; \
+snapshot_download(repo_id='danswer/hybrid-intent-token-classifier', revision='v1.0.3', cache_dir='/root/.cache/temp_huggingface/hub/'); \
+snapshot_download('nomic-ai/nomic-embed-text-v1', cache_dir='/root/.cache/temp_huggingface/hub/'); \
+snapshot_download('mixedbread-ai/mxbai-rerank-xsmall-v1', cache_dir='/root/.cache/temp_huggingface/hub/'); \
+from sentence_transformers import SentenceTransformer; \
+SentenceTransformer(model_name_or_path='nomic-ai/nomic-embed-text-v1', trust_remote_code=True, cache_folder='/root/.cache/temp_huggingface/hub/');"
+
+WORKDIR /app
+
+# Utils used by model server
+COPY ./danswer/utils/logger.py /app/danswer/utils/logger.py
+
+# Place to fetch version information
+COPY ./danswer/__init__.py /app/danswer/__init__.py
+
+# Shared between Danswer Backend and Model Server
+COPY ./shared_configs /app/shared_configs
+
+# Model Server main code
+COPY ./model_server /app/model_server
+
+ENV PYTHONPATH /app
+
+CMD ["uvicorn", "model_server.main:app", "--host", "0.0.0.0", "--port", "9000"]

backend/alembic.ini

@@ -0,0 +1,108 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+script_location = alembic
+
+# template used to generate migration file names; The default value is %%(rev)s_%%(slug)s
+# Uncomment the line below if you want the files to be prepended with date and time
+# file_template = %%(year)d_%%(month).2d_%%(day).2d_%%(hour).2d%%(minute).2d-%%(rev)s_%%(slug)s
+
+# sys.path path, will be prepended to sys.path if present.
+# defaults to the current working directory.
+prepend_sys_path = .
+
+# timezone to use when rendering the date within the migration file
+# as well as the filename.
+# If specified, requires the python-dateutil library that can be
+# installed by adding `alembic[tz]` to the pip requirements
+# string value is passed to dateutil.tz.gettz()
+# leave blank for localtime
+# timezone =
+
+# max length of characters to apply to the
+# "slug" field
+# truncate_slug_length = 40
+
+# set to 'true' to run the environment during
+# the 'revision' command, regardless of autogenerate
+# revision_environment = false
+
+# set to 'true' to allow .pyc and .pyo files without
+# a source .py file to be detected as revisions in the
+# versions/ directory
+# sourceless = false
+
+# version location specification; This defaults
+# to alembic/versions.  When using multiple version
+# directories, initial revisions must be specified with --version-path.
+# The path separator used here should be the separator specified by "version_path_separator" below.
+# version_locations = %(here)s/bar:%(here)s/bat:alembic/versions
+
+# version path separator; As mentioned above, this is the character used to split
+# version_locations. The default within new alembic.ini files is "os", which uses os.pathsep.
+# If this key is omitted entirely, it falls back to the legacy behavior of splitting on spaces and/or commas.
+# Valid values for version_path_separator are:
+#
+# version_path_separator = :
+# version_path_separator = ;
+# version_path_separator = space
+version_path_separator = os  # Use os.pathsep. Default configuration used for new projects.
+
+# set to 'true' to search source files recursively
+# in each "version_locations" directory
+# new in Alembic version 1.10
+# recursive_version_locations = false
+
+# the output encoding used when revision files
+# are written from script.py.mako
+# output_encoding = utf-8
+
+# sqlalchemy.url = driver://user:pass@localhost/dbname
+
+
+[post_write_hooks]
+# post_write_hooks defines scripts or Python functions that are run
+# on newly generated revision scripts.  See the documentation for further
+# detail and examples
+
+# format using "black" - use the console_scripts runner, against the "black" entrypoint
+hooks = black
+black.type = console_scripts
+black.entrypoint = black
+black.options = -l 79 REVISION_SCRIPT_FILENAME
+
+# Logging configuration
+[loggers]
+keys = root,sqlalchemy,alembic
+
+[handlers]
+keys = console
+
+[formatters]
+keys = generic
+
+[logger_root]
+level = WARN
+handlers = console
+qualname =
+
+[logger_sqlalchemy]
+level = WARN
+handlers =
+qualname = sqlalchemy.engine
+
+[logger_alembic]
+level = INFO
+handlers =
+qualname = alembic
+
+[handler_console]
+class = StreamHandler
+args = (sys.stderr,)
+level = NOTSET
+formatter = generic
+
+[formatter_generic]
+format = %(levelname)-5.5s [%(name)s] %(message)s
+datefmt = %H:%M:%S

backend/alembic/README.md

@@ -0,0 +1,19 @@
+<!-- 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:
+`alembic revision --autogenerate -m <DESCRIPTION_OF_MIGRATION>`
+
+More info can be found here: https://alembic.sqlalchemy.org/en/latest/autogenerate.html
+
+## Running migrations
+To run all un-applied migrations:
+`alembic upgrade head`
+
+To undo migrations:
+`alembic downgrade -X` 
+where X is the number of migrations you want to undo from the current state

backend/alembic/env.py

@@ -0,0 +1,90 @@
+import asyncio
+from logging.config import fileConfig
+
+from alembic import context
+from danswer.db.engine import build_connection_string
+from danswer.db.models import Base
+from sqlalchemy import pool
+from sqlalchemy.engine import Connection
+from sqlalchemy.ext.asyncio import create_async_engine
+from 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.
+config = context.config
+
+# Interpret the config file for Python logging.
+# This line sets up loggers basically.
+if config.config_file_name is not None:
+    fileConfig(config.config_file_name)
+
+# add your model's MetaData object here
+# for 'autogenerate' support
+# from myapp import mymodel
+# target_metadata = mymodel.Base.metadata
+target_metadata = [Base.metadata, ResultModelBase.metadata]
+
+# other values from the config, defined by the needs of env.py,
+# can be acquired:
+# my_important_option = config.get_main_option("my_important_option")
+# ... etc.
+
+
+def run_migrations_offline() -> None:
+    """Run migrations in 'offline' mode.
+
+    This configures the context with just a URL
+    and not an Engine, though an Engine is acceptable
+    here as well.  By skipping the Engine creation
+    we don't even need a DBAPI to be available.
+
+    Calls to context.execute() here emit the given string to the
+    script output.
+
+    """
+    url = build_connection_string()
+    context.configure(
+        url=url,
+        target_metadata=target_metadata,  # type: ignore
+        literal_binds=True,
+        dialect_opts={"paramstyle": "named"},
+    )
+
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+def do_run_migrations(connection: Connection) -> None:
+    context.configure(connection=connection, target_metadata=target_metadata)  # type: ignore
+
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+async def run_async_migrations() -> None:
+    """In this scenario we need to create an Engine
+    and associate a connection with the context.
+
+    """
+
+    connectable = create_async_engine(
+        build_connection_string(),
+        poolclass=pool.NullPool,
+    )
+
+    async with connectable.connect() as connection:
+        await connection.run_sync(do_run_migrations)
+
+    await connectable.dispose()
+
+
+def run_migrations_online() -> None:
+    """Run migrations in 'online' mode."""
+
+    asyncio.run(run_async_migrations())
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

backend/alembic/script.py.mako

@@ -0,0 +1,24 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+
+"""
+from alembic import op
+import sqlalchemy as sa
+${imports if imports else ""}
+
+# revision identifiers, used by Alembic.
+revision = ${repr(up_revision)}
+down_revision = ${repr(down_revision)}
+branch_labels = ${repr(branch_labels)}
+depends_on = ${repr(depends_on)}
+
+
+def upgrade() -> None:
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    ${downgrades if downgrades else "pass"}

backend/alembic/versions/0568ccf46a6b_add_thread_specific_model_selection.py

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

backend/alembic/versions/05c07bf07c00_add_search_doc_relevance_details.py

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

backend/alembic/versions/08a1eda20fe1_add_earliest_indexing_to_connector.py

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

backend/alembic/versions/0a2b51deb0b8_add_starter_prompts.py

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

backend/alembic/versions/0a98909f2757_enable_encrypted_fields.py

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

backend/alembic/versions/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/213fd978c6d8_notifications.py

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

backend/alembic/versions/23957775e5f5_remove_feedback_foreignkey_constraint.py

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

backend/alembic/versions/2666d766cb9b_google_oauth2.py

@@ -0,0 +1,55 @@
+"""Google OAuth2
+
+Revision ID: 2666d766cb9b
+Revises: 6d387b3196c2
+Create Date: 2023-05-05 15:49:35.716016
+
+"""
+import fastapi_users_db_sqlalchemy
+import sqlalchemy as sa
+from alembic import op
+
+
+# revision identifiers, used by Alembic.
+revision = "2666d766cb9b"
+down_revision = "6d387b3196c2"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "oauth_account",
+        sa.Column("id", fastapi_users_db_sqlalchemy.generics.GUID(), nullable=False),
+        sa.Column(
+            "user_id",
+            fastapi_users_db_sqlalchemy.generics.GUID(),
+            nullable=False,
+        ),
+        sa.Column("oauth_name", sa.String(length=100), nullable=False),
+        sa.Column("access_token", sa.String(length=1024), nullable=False),
+        sa.Column("expires_at", sa.Integer(), nullable=True),
+        sa.Column("refresh_token", sa.String(length=1024), nullable=True),
+        sa.Column("account_id", sa.String(length=320), nullable=False),
+        sa.Column("account_email", sa.String(length=320), nullable=False),
+        sa.ForeignKeyConstraint(["user_id"], ["user.id"], ondelete="cascade"),
+        sa.PrimaryKeyConstraint("id"),
+    )
+    op.create_index(
+        op.f("ix_oauth_account_account_id"),
+        "oauth_account",
+        ["account_id"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("ix_oauth_account_oauth_name"),
+        "oauth_account",
+        ["oauth_name"],
+        unique=False,
+    )
+
+
+def downgrade() -> None:
+    op.drop_index(op.f("ix_oauth_account_oauth_name"), table_name="oauth_account")
+    op.drop_index(op.f("ix_oauth_account_account_id"), table_name="oauth_account")
+    op.drop_table("oauth_account")

backend/alembic/versions/27c6ecc08586_permission_framework.py

@@ -0,0 +1,189 @@
+"""Permission Framework
+
+Revision ID: 27c6ecc08586
+Revises: 2666d766cb9b
+Create Date: 2023-05-24 18:45:17.244495
+
+"""
+import fastapi_users_db_sqlalchemy
+import sqlalchemy as sa
+from alembic import op
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision = "27c6ecc08586"
+down_revision = "2666d766cb9b"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.execute("TRUNCATE TABLE index_attempt")
+    op.create_table(
+        "connector",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column("name", sa.String(), nullable=False),
+        sa.Column(
+            "source",
+            sa.Enum(
+                "SLACK",
+                "WEB",
+                "GOOGLE_DRIVE",
+                "GITHUB",
+                "CONFLUENCE",
+                name="documentsource",
+                native_enum=False,
+            ),
+            nullable=False,
+        ),
+        sa.Column(
+            "input_type",
+            sa.Enum(
+                "LOAD_STATE",
+                "POLL",
+                "EVENT",
+                name="inputtype",
+                native_enum=False,
+            ),
+            nullable=True,
+        ),
+        sa.Column(
+            "connector_specific_config",
+            postgresql.JSONB(astext_type=sa.Text()),
+            nullable=False,
+        ),
+        sa.Column("refresh_freq", sa.Integer(), nullable=True),
+        sa.Column(
+            "time_created",
+            sa.DateTime(timezone=True),
+            server_default=sa.text("now()"),
+            nullable=False,
+        ),
+        sa.Column(
+            "time_updated",
+            sa.DateTime(timezone=True),
+            server_default=sa.text("now()"),
+            nullable=False,
+        ),
+        sa.Column("disabled", sa.Boolean(), nullable=False),
+        sa.PrimaryKeyConstraint("id"),
+    )
+    op.create_table(
+        "credential",
+        sa.Column("id", sa.Integer(), nullable=False),
+        sa.Column(
+            "credential_json",
+            postgresql.JSONB(astext_type=sa.Text()),
+            nullable=False,
+        ),
+        sa.Column(
+            "user_id",
+            fastapi_users_db_sqlalchemy.generics.GUID(),
+            nullable=True,
+        ),
+        sa.Column("public_doc", sa.Boolean(), nullable=False),
+        sa.Column(
+            "time_created",
+            sa.DateTime(timezone=True),
+            server_default=sa.text("now()"),
+            nullable=False,
+        ),
+        sa.Column(
+            "time_updated",
+            sa.DateTime(timezone=True),
+            server_default=sa.text("now()"),
+            nullable=False,
+        ),
+        sa.ForeignKeyConstraint(
+            ["user_id"],
+            ["user.id"],
+        ),
+        sa.PrimaryKeyConstraint("id"),
+    )
+    op.create_table(
+        "connector_credential_pair",
+        sa.Column("connector_id", sa.Integer(), nullable=False),
+        sa.Column("credential_id", sa.Integer(), nullable=False),
+        sa.ForeignKeyConstraint(
+            ["connector_id"],
+            ["connector.id"],
+        ),
+        sa.ForeignKeyConstraint(
+            ["credential_id"],
+            ["credential.id"],
+        ),
+        sa.PrimaryKeyConstraint("connector_id", "credential_id"),
+    )
+    op.add_column(
+        "index_attempt",
+        sa.Column("connector_id", sa.Integer(), nullable=True),
+    )
+    op.add_column(
+        "index_attempt",
+        sa.Column("credential_id", sa.Integer(), nullable=True),
+    )
+    op.create_foreign_key(
+        "fk_index_attempt_credential_id",
+        "index_attempt",
+        "credential",
+        ["credential_id"],
+        ["id"],
+    )
+    op.create_foreign_key(
+        "fk_index_attempt_connector_id",
+        "index_attempt",
+        "connector",
+        ["connector_id"],
+        ["id"],
+    )
+    op.drop_column("index_attempt", "connector_specific_config")
+    op.drop_column("index_attempt", "source")
+    op.drop_column("index_attempt", "input_type")
+
+
+def downgrade() -> None:
+    op.execute("TRUNCATE TABLE index_attempt")
+    op.add_column(
+        "index_attempt",
+        sa.Column("input_type", sa.VARCHAR(), autoincrement=False, nullable=False),
+    )
+    op.add_column(
+        "index_attempt",
+        sa.Column("source", sa.VARCHAR(), autoincrement=False, nullable=False),
+    )
+    op.add_column(
+        "index_attempt",
+        sa.Column(
+            "connector_specific_config",
+            postgresql.JSONB(astext_type=sa.Text()),
+            autoincrement=False,
+            nullable=False,
+        ),
+    )
+
+    # Check if the constraint exists before dropping
+    conn = op.get_bind()
+    inspector = sa.inspect(conn)
+    constraints = inspector.get_foreign_keys("index_attempt")
+
+    if any(
+        constraint["name"] == "fk_index_attempt_credential_id"
+        for constraint in constraints
+    ):
+        op.drop_constraint(
+            "fk_index_attempt_credential_id", "index_attempt", type_="foreignkey"
+        )
+
+    if any(
+        constraint["name"] == "fk_index_attempt_connector_id"
+        for constraint in constraints
+    ):
+        op.drop_constraint(
+            "fk_index_attempt_connector_id", "index_attempt", type_="foreignkey"
+        )
+
+    op.drop_column("index_attempt", "credential_id")
+    op.drop_column("index_attempt", "connector_id")
+    op.drop_table("connector_credential_pair")
+    op.drop_table("credential")
+    op.drop_table("connector")

backend/alembic/versions/30c1d5744104_persona_datetime_aware.py

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

backend/alembic/versions/325975216eb3_add_icon_color_and_icon_shape_to_persona.py

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

backend/alembic/versions/3879338f8ba1_add_tool_table.py

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

backend/alembic/versions/38eda64af7fe_add_chat_session_sharing.py

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

backend/alembic/versions/3a7802814195_add_alternate_assistant_to_chat_message.py

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

backend/alembic/versions/3b25685ff73c_move_is_public_to_cc_pair.py

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

backend/alembic/versions/3c5e35aa9af0_polling_document_count.py

@@ -0,0 +1,52 @@
+"""Polling Document Count
+
+Revision ID: 3c5e35aa9af0
+Revises: 27c6ecc08586
+Create Date: 2023-06-14 23:45:51.760440
+
+"""
+import sqlalchemy as sa
+from alembic import op
+
+
+# revision identifiers, used by Alembic.
+revision = "3c5e35aa9af0"
+down_revision = "27c6ecc08586"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "connector_credential_pair",
+        sa.Column(
+            "last_successful_index_time",
+            sa.DateTime(timezone=True),
+            nullable=True,
+        ),
+    )
+    op.add_column(
+        "connector_credential_pair",
+        sa.Column(
+            "last_attempt_status",
+            sa.Enum(
+                "NOT_STARTED",
+                "IN_PROGRESS",
+                "SUCCESS",
+                "FAILED",
+                name="indexingstatus",
+                native_enum=False,
+            ),
+            nullable=False,
+        ),
+    )
+    op.add_column(
+        "connector_credential_pair",
+        sa.Column("total_docs_indexed", sa.Integer(), nullable=False),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("connector_credential_pair", "total_docs_indexed")
+    op.drop_column("connector_credential_pair", "last_attempt_status")
+    op.drop_column("connector_credential_pair", "last_successful_index_time")

backend/alembic/versions/401c1ac29467_add_tables_for_ui_based_llm_.py

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

backend/alembic/versions/43cbbb3f5e6a_rename_index_origin_to_index_recursively.py

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

backend/alembic/versions/44f856ae2a4a_add_cloud_embedding_model.py

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

backend/alembic/versions/4505fd7302e1_added_is_internet_to_dbdoc.py

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

backend/alembic/versions/465f78d9b7f9_larger_access_tokens_for_oauth.py

@@ -0,0 +1,24 @@
+"""Larger Access Tokens for OAUTH
+
+Revision ID: 465f78d9b7f9
+Revises: 3c5e35aa9af0
+Create Date: 2023-07-18 17:33:40.365034
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "465f78d9b7f9"
+down_revision = "3c5e35aa9af0"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.alter_column("oauth_account", "access_token", type_=sa.Text())
+
+
+def downgrade() -> None:
+    op.alter_column("oauth_account", "access_token", type_=sa.String(length=1024))

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/473a1a7ca408_add_display_model_names_to_llm_provider.py

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

backend/alembic/versions/47433d30de82_create_indexattempt_table.py

@@ -0,0 +1,73 @@
+"""Create IndexAttempt table
+
+Revision ID: 47433d30de82
+Revises:
+Create Date: 2023-05-04 00:55:32.971991
+
+"""
+import sqlalchemy as sa
+from alembic import op
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision = "47433d30de82"
+down_revision: None = None
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "index_attempt",
+        sa.Column("id", sa.Integer(), nullable=False),
+        # String type since python enum will change often
+        sa.Column(
+            "source",
+            sa.String(),
+            nullable=False,
+        ),
+        # String type to easily accomodate new ways of pulling
+        # in documents
+        sa.Column(
+            "input_type",
+            sa.String(),
+            nullable=False,
+        ),
+        sa.Column(
+            "connector_specific_config",
+            postgresql.JSONB(),
+            nullable=False,
+        ),
+        sa.Column(
+            "time_created",
+            sa.DateTime(timezone=True),
+            server_default=sa.text("now()"),
+            nullable=True,
+        ),
+        sa.Column(
+            "time_updated",
+            sa.DateTime(timezone=True),
+            server_default=sa.text("now()"),
+            server_onupdate=sa.text("now()"),  # type: ignore
+            nullable=True,
+        ),
+        sa.Column(
+            "status",
+            sa.Enum(
+                "NOT_STARTED",
+                "IN_PROGRESS",
+                "SUCCESS",
+                "FAILED",
+                name="indexingstatus",
+                native_enum=False,
+            ),
+            nullable=False,
+        ),
+        sa.Column("document_ids", postgresql.ARRAY(sa.String()), nullable=True),
+        sa.Column("error_msg", sa.String(), nullable=True),
+        sa.PrimaryKeyConstraint("id"),
+    )
+
+
+def downgrade() -> None:
+    op.drop_table("index_attempt")

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/4a951134c801_moved_status_to_connector_credential_.py

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

backend/alembic/versions/4ea2c93919c1_add_type_to_credentials.py

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

backend/alembic/versions/50b683a8295c_add_additional_retrieval_controls_to_.py

@@ -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

@@ -0,0 +1,36 @@
+"""Add docs_indexed_column + time_started to index_attempt table
+
+Revision ID: 5e84129c8be3
+Revises: e6a4bbc13fe4
+Create Date: 2023-08-10 21:43:09.069523
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "5e84129c8be3"
+down_revision = "e6a4bbc13fe4"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "index_attempt",
+        sa.Column("num_docs_indexed", sa.Integer()),
+    )
+    op.add_column(
+        "index_attempt",
+        sa.Column(
+            "time_started",
+            sa.DateTime(timezone=True),
+            nullable=True,
+        ),
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("index_attempt", "time_started")
+    op.drop_column("index_attempt", "num_docs_indexed")

backend/alembic/versions/5f4b8568a221_add_removed_documents_to_index_attempt.py

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

backend/alembic/versions/5fc1f54cc252_hybrid_enum.py

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

backend/alembic/versions/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

@@ -0,0 +1,92 @@
+"""Basic Auth
+
+Revision ID: 6d387b3196c2
+Revises: 47433d30de82
+Create Date: 2023-05-05 14:40:10.242502
+
+"""
+import fastapi_users_db_sqlalchemy
+import sqlalchemy as sa
+from alembic import op
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision = "6d387b3196c2"
+down_revision = "47433d30de82"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "user",
+        sa.Column("id", fastapi_users_db_sqlalchemy.generics.GUID(), nullable=False),
+        sa.Column("email", sa.String(length=320), nullable=False),
+        sa.Column("hashed_password", sa.String(length=1024), nullable=False),
+        sa.Column("is_active", sa.Boolean(), nullable=False),
+        sa.Column("is_superuser", sa.Boolean(), nullable=False),
+        sa.Column("is_verified", sa.Boolean(), nullable=False),
+        sa.Column(
+            "role",
+            sa.Enum("BASIC", "ADMIN", name="userrole", native_enum=False),
+            default="BASIC",
+            nullable=False,
+        ),
+        sa.PrimaryKeyConstraint("id"),
+    )
+    op.create_index(op.f("ix_user_email"), "user", ["email"], unique=True)
+    op.create_table(
+        "accesstoken",
+        sa.Column(
+            "user_id",
+            fastapi_users_db_sqlalchemy.generics.GUID(),
+            nullable=False,
+        ),
+        sa.Column("token", sa.String(length=43), nullable=False),
+        sa.Column(
+            "created_at",
+            fastapi_users_db_sqlalchemy.generics.TIMESTAMPAware(timezone=True),
+            nullable=False,
+        ),
+        sa.ForeignKeyConstraint(["user_id"], ["user.id"], ondelete="cascade"),
+        sa.PrimaryKeyConstraint("token"),
+    )
+    op.create_index(
+        op.f("ix_accesstoken_created_at"),
+        "accesstoken",
+        ["created_at"],
+        unique=False,
+    )
+    op.alter_column(
+        "index_attempt",
+        "time_created",
+        existing_type=postgresql.TIMESTAMP(timezone=True),
+        nullable=False,
+        existing_server_default=sa.text("now()"),  # type: ignore
+    )
+    op.alter_column(
+        "index_attempt",
+        "time_updated",
+        existing_type=postgresql.TIMESTAMP(timezone=True),
+        nullable=False,
+    )
+
+
+def downgrade() -> None:
+    op.alter_column(
+        "index_attempt",
+        "time_updated",
+        existing_type=postgresql.TIMESTAMP(timezone=True),
+        nullable=True,
+    )
+    op.alter_column(
+        "index_attempt",
+        "time_created",
+        existing_type=postgresql.TIMESTAMP(timezone=True),
+        nullable=True,
+        existing_server_default=sa.text("now()"),  # type: ignore
+    )
+    op.drop_index(op.f("ix_accesstoken_created_at"), table_name="accesstoken")
+    op.drop_table("accesstoken")
+    op.drop_index(op.f("ix_user_email"), table_name="user")
+    op.drop_table("user")

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/7477a5f5d728_added_model_defaults_for_users.py

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

backend/alembic/versions/7547d982db8f_chat_folders.py

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

backend/alembic/versions/767f1c2a00eb_count_chat_tokens.py

@@ -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 +1,36 @@
+"""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:
+    op.create_unique_constraint(
+        "connector_credential_pair__name__key", "connector_credential_pair", ["name"]
+    )
+    op.alter_column(
+        "connector_credential_pair", "name", existing_type=sa.String(), nullable=True
+    )

backend/alembic/versions/776b3bbe9092_remove_remaining_enums.py

@@ -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/795b20b85b4b_add_llm_group_permissions_control.py

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

backend/alembic/versions/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/8a87bd6ec550_associate_index_attempts_with_ccpair.py

@@ -0,0 +1,103 @@
+"""associate index attempts with ccpair
+
+Revision ID: 8a87bd6ec550
+Revises: 4ea2c93919c1
+Create Date: 2024-07-22 15:15:52.558451
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "8a87bd6ec550"
+down_revision = "4ea2c93919c1"
+branch_labels: None = None
+depends_on: None = None
+
+
+def upgrade() -> None:
+    # Add the new connector_credential_pair_id column
+    op.add_column(
+        "index_attempt",
+        sa.Column("connector_credential_pair_id", sa.Integer(), nullable=True),
+    )
+
+    # Create a foreign key constraint to the connector_credential_pair table
+    op.create_foreign_key(
+        "fk_index_attempt_connector_credential_pair_id",
+        "index_attempt",
+        "connector_credential_pair",
+        ["connector_credential_pair_id"],
+        ["id"],
+    )
+
+    # Populate the new connector_credential_pair_id column using existing connector_id and credential_id
+    op.execute(
+        """
+        UPDATE index_attempt ia
+        SET connector_credential_pair_id =
+            CASE
+                WHEN ia.credential_id IS NULL THEN
+                    (SELECT id FROM connector_credential_pair
+                     WHERE connector_id = ia.connector_id
+                     LIMIT 1)
+                ELSE
+                    (SELECT id FROM connector_credential_pair
+                     WHERE connector_id = ia.connector_id
+                     AND credential_id = ia.credential_id)
+            END
+        WHERE ia.connector_id IS NOT NULL
+        """
+    )
+
+    # Make the new connector_credential_pair_id column non-nullable
+    op.alter_column("index_attempt", "connector_credential_pair_id", nullable=False)
+
+    # Drop the old connector_id and credential_id columns
+    op.drop_column("index_attempt", "connector_id")
+    op.drop_column("index_attempt", "credential_id")
+
+    # Update the index to use connector_credential_pair_id
+    op.create_index(
+        "ix_index_attempt_latest_for_connector_credential_pair",
+        "index_attempt",
+        ["connector_credential_pair_id", "time_created"],
+    )
+
+
+def downgrade() -> None:
+    # Add back the old connector_id and credential_id columns
+    op.add_column(
+        "index_attempt", sa.Column("connector_id", sa.Integer(), nullable=True)
+    )
+    op.add_column(
+        "index_attempt", sa.Column("credential_id", sa.Integer(), nullable=True)
+    )
+
+    # Populate the old connector_id and credential_id columns using the connector_credential_pair_id
+    op.execute(
+        """
+        UPDATE index_attempt ia
+        SET connector_id = ccp.connector_id, credential_id = ccp.credential_id
+        FROM connector_credential_pair ccp
+        WHERE ia.connector_credential_pair_id = ccp.id
+        """
+    )
+
+    # Make the old connector_id and credential_id columns non-nullable
+    op.alter_column("index_attempt", "connector_id", nullable=False)
+    op.alter_column("index_attempt", "credential_id", nullable=False)
+
+    # Drop the new connector_credential_pair_id column
+    op.drop_constraint(
+        "fk_index_attempt_connector_credential_pair_id",
+        "index_attempt",
+        type_="foreignkey",
+    )
+    op.drop_column("index_attempt", "connector_credential_pair_id")
+
+    op.create_index(
+        "ix_index_attempt_latest_for_connector_credential_pair",
+        "index_attempt",
+        ["connector_id", "credential_id", "time_created"],
+    )

backend/alembic/versions/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/91ffac7e65b3_add_expiry_time.py

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

backend/alembic/versions/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")