Add Github Action to run mypy / reorder-python-imports / black on all PRs (#251)

Also fixes import ordering (previously, local imports weren't grouped together as they should have been)

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

@@ -0,0 +1,41 @@
+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
+    - run: | 
+        python -m pip install --upgrade pip
+        pip install -r backend/requirements/default.txt
+        pip install -r backend/requirements/dev.txt
+
+    - name: Run MyPy
+      run: |
+        cd backend
+        mypy .
+
+    - 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 .

backend/.pre-commit-config.yaml

@@ -1,12 +1,44 @@
 repos:
--   repo: https://github.com/psf/black
+  - 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
+  - repo: https://github.com/asottile/reorder_python_imports
     rev: v3.9.0
     hooks:
     - id: reorder-python-imports
-      args: ['--py311-plus']
+      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/
+
+  # 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]  

backend/alembic/versions/465f78d9b7f9_larger_access_tokens_for_oauth.py

@@ -10,23 +10,15 @@ import sqlalchemy as sa
 
 
 # revision identifiers, used by Alembic.
-revision = '465f78d9b7f9'
+revision = "465f78d9b7f9"
-down_revision = '3c5e35aa9af0'
+down_revision = "3c5e35aa9af0"
 branch_labels = None
 depends_on = None
 
 
 def upgrade() -> None:
-    op.alter_column(
+    op.alter_column("oauth_account", "access_token", type_=sa.Text())
-        "oauth_account",
-        "access_token",
-        type_=sa.Text()
-    )
 
 
 def downgrade() -> None:
-    op.alter_column(
+    op.alter_column("oauth_account", "access_token", type_=sa.String(length=1024))
-        "oauth_account",
-        "access_token",
-        type_=sa.String(length=1024)
-    )

backend/danswer/background/update.py

@@ -2,6 +2,8 @@ import time
 from datetime import datetime
 from datetime import timezone
 
+from sqlalchemy.orm import Session
+
 from danswer.connectors.factory import instantiate_connector
 from danswer.connectors.interfaces import LoadConnector
 from danswer.connectors.interfaces import PollConnector
@@ -25,7 +27,6 @@ from danswer.db.models import Connector
 from danswer.db.models import IndexAttempt
 from danswer.db.models import IndexingStatus
 from danswer.utils.logger import setup_logger
-from sqlalchemy.orm import Session
 
 logger = setup_logger()
 

backend/danswer/configs/app_configs.py

@@ -47,8 +47,12 @@ VALID_EMAIL_DOMAIN = os.environ.get("VALID_EMAIL_DOMAIN", "")
 # OAuth Login Flow
 ENABLE_OAUTH = os.environ.get("ENABLE_OAUTH", "").lower() != "false"
 OAUTH_TYPE = os.environ.get("OAUTH_TYPE", "google").lower()
-OAUTH_CLIENT_ID = os.environ.get("OAUTH_CLIENT_ID", os.environ.get("GOOGLE_OAUTH_CLIENT_ID", ""))
+OAUTH_CLIENT_ID = os.environ.get(
-OAUTH_CLIENT_SECRET = os.environ.get("OAUTH_CLIENT_SECRET", os.environ.get("GOOGLE_OAUTH_CLIENT_SECRET", ""))
+    "OAUTH_CLIENT_ID", os.environ.get("GOOGLE_OAUTH_CLIENT_ID", "")
+)
+OAUTH_CLIENT_SECRET = os.environ.get(
+    "OAUTH_CLIENT_SECRET", os.environ.get("GOOGLE_OAUTH_CLIENT_SECRET", "")
+)
 OPENID_CONFIG_URL = os.environ.get("OPENID_CONFIG_URL", "")
 MASK_CREDENTIAL_PREFIX = (
     os.environ.get("MASK_CREDENTIAL_PREFIX", "True").lower() != "false"

backend/danswer/connectors/confluence/connector.py

@@ -6,6 +6,7 @@ from typing import Any
 from urllib.parse import urlparse
 
 from atlassian import Confluence  # type:ignore
+
 from danswer.configs.app_configs import INDEX_BATCH_SIZE
 from danswer.configs.constants import DocumentSource
 from danswer.connectors.interfaces import GenerateDocumentsOutput

backend/danswer/connectors/danswer_jira/connector.py

@@ -3,6 +3,9 @@ from datetime import timezone
 from typing import Any
 from urllib.parse import urlparse
 
+from jira import JIRA
+from jira.resources import Issue
+
 from danswer.configs.app_configs import INDEX_BATCH_SIZE
 from danswer.configs.constants import DocumentSource
 from danswer.connectors.interfaces import GenerateDocumentsOutput
@@ -13,8 +16,6 @@ from danswer.connectors.models import ConnectorMissingCredentialError
 from danswer.connectors.models import Document
 from danswer.connectors.models import Section
 from danswer.utils.logger import setup_logger
-from jira import JIRA
-from jira.resources import Issue
 
 
 logger = setup_logger()

backend/danswer/connectors/factory.py

@@ -8,13 +8,13 @@ from danswer.connectors.danswer_jira.connector import JiraConnector
 from danswer.connectors.file.connector import LocalFileConnector
 from danswer.connectors.github.connector import GithubConnector
 from danswer.connectors.google_drive.connector import GoogleDriveConnector
-from danswer.connectors.notion.connector import NotionConnector
 from danswer.connectors.guru.connector import GuruConnector
 from danswer.connectors.interfaces import BaseConnector
 from danswer.connectors.interfaces import EventConnector
 from danswer.connectors.interfaces import LoadConnector
 from danswer.connectors.interfaces import PollConnector
 from danswer.connectors.models import InputType
+from danswer.connectors.notion.connector import NotionConnector
 from danswer.connectors.productboard.connector import ProductboardConnector
 from danswer.connectors.slab.connector import SlabConnector
 from danswer.connectors.slack.connector import SlackLoadConnector

backend/danswer/connectors/github/connector.py

@@ -2,6 +2,10 @@ import itertools
 from collections.abc import Generator
 from typing import Any
 
+from github import Github
+from github.PaginatedList import PaginatedList
+from github.PullRequest import PullRequest
+
 from danswer.configs.app_configs import INDEX_BATCH_SIZE
 from danswer.configs.constants import DocumentSource
 from danswer.connectors.interfaces import GenerateDocumentsOutput
@@ -10,9 +14,6 @@ from danswer.connectors.models import ConnectorMissingCredentialError
 from danswer.connectors.models import Document
 from danswer.connectors.models import Section
 from danswer.utils.logger import setup_logger
-from github import Github
-from github.PaginatedList import PaginatedList
-from github.PullRequest import PullRequest
 
 
 logger = setup_logger()

backend/danswer/connectors/google_drive/connector.py

@@ -7,6 +7,10 @@ from itertools import chain
 from typing import Any
 
 import docx2txt  # type:ignore
+from google.oauth2.credentials import Credentials  # type: ignore
+from googleapiclient import discovery  # type: ignore
+from PyPDF2 import PdfReader
+
 from danswer.configs.app_configs import GOOGLE_DRIVE_INCLUDE_SHARED
 from danswer.configs.app_configs import INDEX_BATCH_SIZE
 from danswer.configs.constants import DocumentSource
@@ -20,9 +24,6 @@ from danswer.connectors.models import Document
 from danswer.connectors.models import Section
 from danswer.connectors.utils import batch_generator
 from danswer.utils.logger import setup_logger
-from google.oauth2.credentials import Credentials  # type: ignore
-from googleapiclient import discovery  # type: ignore
-from PyPDF2 import PdfReader
 
 logger = setup_logger()
 

backend/danswer/connectors/google_drive/connector_auth.py

@@ -4,16 +4,17 @@ from urllib.parse import parse_qs
 from urllib.parse import ParseResult
 from urllib.parse import urlparse
 
+from google.auth.transport.requests import Request  # type: ignore
+from google.oauth2.credentials import Credentials  # type: ignore
+from google_auth_oauthlib.flow import InstalledAppFlow  # type: ignore
+from sqlalchemy.orm import Session
+
 from danswer.configs.app_configs import WEB_DOMAIN
 from danswer.db.credentials import update_credential_json
 from danswer.db.models import User
 from danswer.dynamic_configs import get_dynamic_config_store
 from danswer.server.models import GoogleAppCredentials
 from danswer.utils.logger import setup_logger
-from google.auth.transport.requests import Request  # type: ignore
-from google.oauth2.credentials import Credentials  # type: ignore
-from google_auth_oauthlib.flow import InstalledAppFlow  # type: ignore
-from sqlalchemy.orm import Session
 
 logger = setup_logger()
 

backend/danswer/connectors/guru/connector.py

@@ -4,6 +4,7 @@ from datetime import timezone
 from typing import Any
 
 import requests
+
 from danswer.configs.app_configs import INDEX_BATCH_SIZE
 from danswer.configs.constants import DocumentSource
 from danswer.connectors.interfaces import GenerateDocumentsOutput

backend/danswer/connectors/models.py

@@ -2,9 +2,10 @@ from dataclasses import dataclass
 from enum import Enum
 from typing import Any
 
-from danswer.configs.constants import DocumentSource
 from pydantic import BaseModel
 
+from danswer.configs.constants import DocumentSource
+
 
 class ConnectorMissingCredentialError(PermissionError):
     def __init__(self, connector_name: str) -> None:

backend/danswer/connectors/notion/connector.py

@@ -8,6 +8,7 @@ from typing import List
 from typing import Optional
 
 import requests
+
 from danswer.configs.app_configs import INDEX_BATCH_SIZE
 from danswer.configs.constants import DocumentSource
 from danswer.connectors.interfaces import GenerateDocumentsOutput

backend/danswer/connectors/productboard/connector.py

@@ -5,6 +5,9 @@ from typing import cast
 
 import requests
 from bs4 import BeautifulSoup
+from dateutil import parser
+from retry import retry
+
 from danswer.configs.app_configs import INDEX_BATCH_SIZE
 from danswer.configs.constants import DocumentSource
 from danswer.connectors.interfaces import GenerateDocumentsOutput
@@ -13,8 +16,6 @@ from danswer.connectors.interfaces import SecondsSinceUnixEpoch
 from danswer.connectors.models import Document
 from danswer.connectors.models import Section
 from danswer.utils.logger import setup_logger
-from dateutil import parser
-from retry import retry
 
 
 logger = setup_logger()

backend/danswer/connectors/slab/connector.py

@@ -7,6 +7,8 @@ from typing import Any
 from urllib.parse import urljoin
 
 import requests
+from dateutil import parser
+
 from danswer.configs.app_configs import INDEX_BATCH_SIZE
 from danswer.configs.constants import DocumentSource
 from danswer.connectors.interfaces import GenerateDocumentsOutput
@@ -17,7 +19,6 @@ from danswer.connectors.models import ConnectorMissingCredentialError
 from danswer.connectors.models import Document
 from danswer.connectors.models import Section
 from danswer.utils.logger import setup_logger
-from dateutil import parser
 
 # Fairly generous retry because it's not understood why occasionally GraphQL requests fail even with timeout > 1 min
 SLAB_GRAPHQL_MAX_TRIES = 10

backend/danswer/connectors/slack/connector.py

@@ -6,6 +6,9 @@ from pathlib import Path
 from typing import Any
 from typing import cast
 
+from slack_sdk import WebClient
+from slack_sdk.web import SlackResponse
+
 from danswer.configs.app_configs import INDEX_BATCH_SIZE
 from danswer.configs.constants import DocumentSource
 from danswer.connectors.interfaces import GenerateDocumentsOutput
@@ -20,8 +23,6 @@ from danswer.connectors.slack.utils import make_slack_api_call_paginated
 from danswer.connectors.slack.utils import make_slack_api_rate_limited
 from danswer.connectors.slack.utils import UserIdReplacer
 from danswer.utils.logger import setup_logger
-from slack_sdk import WebClient
-from slack_sdk.web import SlackResponse
 
 logger = setup_logger()
 
@@ -48,7 +49,9 @@ def get_channel_info(client: WebClient, channel_id: str) -> ChannelType:
 def get_channels(client: WebClient, exclude_archived: bool = True) -> list[ChannelType]:
     """Get all channels in the workspace"""
     channels: list[dict[str, Any]] = []
-    for result in _make_slack_api_call(client.conversations_list, exclude_archived=exclude_archived):
+    for result in _make_slack_api_call(
+        client.conversations_list, exclude_archived=exclude_archived
+    ):
         channels.extend(result["channels"])
     return channels
 

backend/danswer/connectors/slack/utils.py

@@ -4,11 +4,12 @@ from collections.abc import Callable
 from typing import Any
 from typing import cast
 
-from danswer.utils.logger import setup_logger
 from slack_sdk import WebClient
 from slack_sdk.errors import SlackApiError
 from slack_sdk.web import SlackResponse
 
+from danswer.utils.logger import setup_logger
+
 logger = setup_logger()
 
 # number of messages we request per page when fetching paginated slack messages

backend/danswer/connectors/web/connector.py

@@ -10,6 +10,13 @@ from urllib.parse import urlparse
 import bs4
 import requests
 from bs4 import BeautifulSoup
+from oauthlib.oauth2 import BackendApplicationClient
+from playwright.sync_api import BrowserContext
+from playwright.sync_api import Playwright
+from playwright.sync_api import sync_playwright
+from PyPDF2 import PdfReader
+from requests_oauthlib import OAuth2Session  # type:ignore
+
 from danswer.configs.app_configs import INDEX_BATCH_SIZE
 from danswer.configs.app_configs import WEB_CONNECTOR_IGNORED_CLASSES
 from danswer.configs.app_configs import WEB_CONNECTOR_IGNORED_ELEMENTS
@@ -22,12 +29,6 @@ from danswer.connectors.interfaces import LoadConnector
 from danswer.connectors.models import Document
 from danswer.connectors.models import Section
 from danswer.utils.logger import setup_logger
-from oauthlib.oauth2 import BackendApplicationClient
-from playwright.sync_api import BrowserContext
-from playwright.sync_api import Playwright
-from playwright.sync_api import sync_playwright
-from PyPDF2 import PdfReader
-from requests_oauthlib import OAuth2Session  # type:ignore
 
 logger = setup_logger()
 

backend/danswer/datastores/qdrant/indexing.py

@@ -2,6 +2,15 @@ import json
 from functools import partial
 from uuid import UUID
 
+from qdrant_client import QdrantClient
+from qdrant_client.http import models
+from qdrant_client.http.exceptions import ResponseHandlingException
+from qdrant_client.http.models.models import UpdateResult
+from qdrant_client.models import CollectionsResponse
+from qdrant_client.models import Distance
+from qdrant_client.models import PointStruct
+from qdrant_client.models import VectorParams
+
 from danswer.chunking.models import EmbeddedIndexChunk
 from danswer.configs.constants import ALLOWED_GROUPS
 from danswer.configs.constants import ALLOWED_USERS
@@ -21,14 +30,6 @@ from danswer.datastores.datastore_utils import get_uuid_from_chunk
 from danswer.datastores.datastore_utils import update_doc_user_map
 from danswer.utils.clients import get_qdrant_client
 from danswer.utils.logger import setup_logger
-from qdrant_client import QdrantClient
-from qdrant_client.http import models
-from qdrant_client.http.exceptions import ResponseHandlingException
-from qdrant_client.http.models.models import UpdateResult
-from qdrant_client.models import CollectionsResponse
-from qdrant_client.models import Distance
-from qdrant_client.models import PointStruct
-from qdrant_client.models import VectorParams
 
 
 logger = setup_logger()

backend/danswer/datastores/qdrant/store.py

@@ -1,5 +1,12 @@
 from uuid import UUID
 
+from qdrant_client.http.exceptions import ResponseHandlingException
+from qdrant_client.http.exceptions import UnexpectedResponse
+from qdrant_client.http.models import FieldCondition
+from qdrant_client.http.models import Filter
+from qdrant_client.http.models import MatchAny
+from qdrant_client.http.models import MatchValue
+
 from danswer.chunking.models import EmbeddedIndexChunk
 from danswer.chunking.models import InferenceChunk
 from danswer.configs.app_configs import NUM_RETURNED_HITS
@@ -15,12 +22,6 @@ from danswer.search.search_utils import get_default_embedding_model
 from danswer.utils.clients import get_qdrant_client
 from danswer.utils.logger import setup_logger
 from danswer.utils.timing import log_function_time
-from qdrant_client.http.exceptions import ResponseHandlingException
-from qdrant_client.http.exceptions import UnexpectedResponse
-from qdrant_client.http.models import FieldCondition
-from qdrant_client.http.models import Filter
-from qdrant_client.http.models import MatchAny
-from qdrant_client.http.models import MatchValue
 
 logger = setup_logger()
 

backend/danswer/datastores/typesense/store.py

@@ -4,6 +4,8 @@ from typing import Any
 from uuid import UUID
 
 import typesense  # type: ignore
+from typesense.exceptions import ObjectNotFound  # type: ignore
+
 from danswer.chunking.models import EmbeddedIndexChunk
 from danswer.chunking.models import IndexChunk
 from danswer.chunking.models import InferenceChunk
@@ -27,7 +29,6 @@ from danswer.datastores.interfaces import IndexFilter
 from danswer.datastores.interfaces import KeywordIndex
 from danswer.utils.clients import get_typesense_client
 from danswer.utils.logger import setup_logger
-from typesense.exceptions import ObjectNotFound  # type: ignore
 
 
 logger = setup_logger()

backend/danswer/db/auth.py

@@ -2,12 +2,6 @@ from collections.abc import AsyncGenerator
 from typing import Any
 from typing import Dict
 
-from danswer.auth.schemas import UserRole
-from danswer.db.engine import get_async_session
-from danswer.db.engine import get_sqlalchemy_async_engine
-from danswer.db.models import AccessToken
-from danswer.db.models import OAuthAccount
-from danswer.db.models import User
 from fastapi import Depends
 from fastapi_users.db import SQLAlchemyUserDatabase
 from fastapi_users.models import UP
@@ -16,6 +10,13 @@ from sqlalchemy import func
 from sqlalchemy.ext.asyncio import AsyncSession
 from sqlalchemy.future import select
 
+from danswer.auth.schemas import UserRole
+from danswer.db.engine import get_async_session
+from danswer.db.engine import get_sqlalchemy_async_engine
+from danswer.db.models import AccessToken
+from danswer.db.models import OAuthAccount
+from danswer.db.models import User
+
 
 async def get_user_count() -> int:
     async with AsyncSession(get_sqlalchemy_async_engine()) as asession:

backend/danswer/db/connector.py

@@ -1,5 +1,12 @@
 from typing import cast
 
+from fastapi import HTTPException
+from sqlalchemy import and_
+from sqlalchemy import func
+from sqlalchemy import select
+from sqlalchemy.orm import aliased
+from sqlalchemy.orm import Session
+
 from danswer.configs.constants import DocumentSource
 from danswer.connectors.models import InputType
 from danswer.db.models import Connector
@@ -8,12 +15,6 @@ from danswer.server.models import ConnectorBase
 from danswer.server.models import ObjectCreationIdResponse
 from danswer.server.models import StatusResponse
 from danswer.utils.logger import setup_logger
-from fastapi import HTTPException
-from sqlalchemy import and_
-from sqlalchemy import func
-from sqlalchemy import select
-from sqlalchemy.orm import aliased
-from sqlalchemy.orm import Session
 
 logger = setup_logger()
 

backend/danswer/db/connector_credential_pair.py

@@ -1,5 +1,9 @@
 from datetime import datetime
 
+from fastapi import HTTPException
+from sqlalchemy import select
+from sqlalchemy.orm import Session
+
 from danswer.db.connector import fetch_connector_by_id
 from danswer.db.credentials import fetch_credential_by_id
 from danswer.db.models import ConnectorCredentialPair
@@ -7,9 +11,6 @@ from danswer.db.models import IndexingStatus
 from danswer.db.models import User
 from danswer.server.models import StatusResponse
 from danswer.utils.logger import setup_logger
-from fastapi import HTTPException
-from sqlalchemy import select
-from sqlalchemy.orm import Session
 
 logger = setup_logger()
 

backend/danswer/db/credentials.py

@@ -1,14 +1,15 @@
 from typing import Any
 
+from sqlalchemy import select
+from sqlalchemy.orm import Session
+from sqlalchemy.sql.expression import or_
+
 from danswer.db.engine import get_sqlalchemy_engine
 from danswer.db.models import Credential
 from danswer.db.models import User
 from danswer.server.models import CredentialBase
 from danswer.server.models import ObjectCreationIdResponse
 from danswer.utils.logger import setup_logger
-from sqlalchemy import select
-from sqlalchemy.orm import Session
-from sqlalchemy.sql.expression import or_
 
 
 logger = setup_logger()

backend/danswer/db/engine.py

@@ -3,12 +3,6 @@ from collections.abc import Generator
 from datetime import datetime
 from datetime import timezone
 
-from danswer.configs.app_configs import POSTGRES_DB
-from danswer.configs.app_configs import POSTGRES_HOST
-from danswer.configs.app_configs import POSTGRES_PASSWORD
-from danswer.configs.app_configs import POSTGRES_PORT
-from danswer.configs.app_configs import POSTGRES_USER
-from danswer.utils.logger import setup_logger
 from sqlalchemy import text
 from sqlalchemy.engine import create_engine
 from sqlalchemy.engine import Engine
@@ -17,6 +11,13 @@ from sqlalchemy.ext.asyncio import AsyncSession
 from sqlalchemy.ext.asyncio import create_async_engine
 from sqlalchemy.orm import Session
 
+from danswer.configs.app_configs import POSTGRES_DB
+from danswer.configs.app_configs import POSTGRES_HOST
+from danswer.configs.app_configs import POSTGRES_PASSWORD
+from danswer.configs.app_configs import POSTGRES_PORT
+from danswer.configs.app_configs import POSTGRES_USER
+from danswer.utils.logger import setup_logger
+
 logger = setup_logger()
 
 SYNC_DB_API = "psycopg2"

backend/danswer/db/index_attempt.py

@@ -1,10 +1,11 @@
-from danswer.db.models import IndexAttempt
-from danswer.db.models import IndexingStatus
-from danswer.utils.logger import setup_logger
 from sqlalchemy import desc
 from sqlalchemy import select
 from sqlalchemy.orm import Session
 
+from danswer.db.models import IndexAttempt
+from danswer.db.models import IndexingStatus
+from danswer.utils.logger import setup_logger
+
 
 logger = setup_logger()
 

backend/danswer/db/models.py

@@ -4,9 +4,6 @@ from typing import Any
 from typing import List
 from uuid import UUID
 
-from danswer.auth.schemas import UserRole
-from danswer.configs.constants import DocumentSource
-from danswer.connectors.models import InputType
 from fastapi_users.db import SQLAlchemyBaseOAuthAccountTableUUID
 from fastapi_users.db import SQLAlchemyBaseUserTableUUID
 from fastapi_users_db_sqlalchemy.access_token import SQLAlchemyBaseAccessTokenTableUUID
@@ -24,6 +21,10 @@ from sqlalchemy.orm import Mapped
 from sqlalchemy.orm import mapped_column
 from sqlalchemy.orm import relationship
 
+from danswer.auth.schemas import UserRole
+from danswer.configs.constants import DocumentSource
+from danswer.connectors.models import InputType
+
 
 class IndexingStatus(str, PyEnum):
     NOT_STARTED = "not_started"

backend/danswer/direct_qa/__init__.py

@@ -1,13 +1,14 @@
 from typing import Any
 
+from openai.error import AuthenticationError
+from openai.error import Timeout
+
 from danswer.configs.app_configs import QA_TIMEOUT
 from danswer.configs.model_configs import INTERNAL_MODEL_VERSION
 from danswer.direct_qa.exceptions import UnknownModelError
 from danswer.direct_qa.interfaces import QAModel
 from danswer.direct_qa.open_ai import OpenAIChatCompletionQA
 from danswer.direct_qa.open_ai import OpenAICompletionQA
-from openai.error import AuthenticationError
-from openai.error import Timeout
 
 # Imports commented out temporarily due to incompatibility of gpt4all with M1 Mac hardware currently
 # from danswer.direct_qa.gpt_4_all import GPT4AllChatCompletionQA

backend/danswer/direct_qa/gpt_4_all.py

@@ -1,6 +1,8 @@
 from collections.abc import Generator
 from typing import Any
 
+from gpt4all import GPT4All  # type:ignore
+
 from danswer.chunking.models import InferenceChunk
 from danswer.configs.model_configs import GEN_AI_MAX_OUTPUT_TOKENS
 from danswer.configs.model_configs import GEN_AI_MODEL_VERSION
@@ -15,7 +17,6 @@ from danswer.direct_qa.qa_utils import process_answer
 from danswer.direct_qa.qa_utils import process_model_tokens
 from danswer.utils.logger import setup_logger
 from danswer.utils.timing import log_function_time
-from gpt4all import GPT4All  # type:ignore
 
 
 logger = setup_logger()

backend/danswer/direct_qa/open_ai.py

@@ -10,6 +10,9 @@ from typing import TypeVar
 
 import openai
 import tiktoken
+from openai.error import AuthenticationError
+from openai.error import Timeout
+
 from danswer.chunking.models import InferenceChunk
 from danswer.configs.app_configs import INCLUDE_METADATA
 from danswer.configs.app_configs import OPENAI_API_KEY
@@ -31,8 +34,6 @@ from danswer.dynamic_configs import get_dynamic_config_store
 from danswer.dynamic_configs.interface import ConfigNotFoundError
 from danswer.utils.logger import setup_logger
 from danswer.utils.timing import log_function_time
-from openai.error import AuthenticationError
-from openai.error import Timeout
 
 
 logger = setup_logger()

backend/danswer/direct_qa/qa_utils.py

@@ -7,6 +7,7 @@ from typing import Optional
 from typing import Tuple
 
 import regex
+
 from danswer.chunking.models import InferenceChunk
 from danswer.configs.app_configs import QUOTE_ALLOWED_ERROR_PERCENT
 from danswer.configs.constants import BLURB

backend/danswer/dynamic_configs/file_system/store.py

@@ -3,10 +3,11 @@ import os
 from pathlib import Path
 from typing import cast
 
+from filelock import FileLock
+
 from danswer.dynamic_configs.interface import ConfigNotFoundError
 from danswer.dynamic_configs.interface import DynamicConfigStore
 from danswer.dynamic_configs.interface import JSON_ro
-from filelock import FileLock
 
 
 FILE_LOCK_TIMEOUT = 10

backend/danswer/listeners/slack_listener.py

@@ -1,5 +1,11 @@
 import os
 
+from retry import retry
+from slack_sdk import WebClient
+from slack_sdk.socket_mode import SocketModeClient
+from slack_sdk.socket_mode.request import SocketModeRequest
+from slack_sdk.socket_mode.response import SocketModeResponse
+
 from danswer.configs.app_configs import DANSWER_BOT_NUM_DOCS_TO_DISPLAY
 from danswer.configs.app_configs import DANSWER_BOT_NUM_RETRIES
 from danswer.configs.app_configs import QDRANT_DEFAULT_COLLECTION
@@ -10,11 +16,6 @@ from danswer.server.models import QAResponse
 from danswer.server.models import QuestionRequest
 from danswer.server.models import SearchDoc
 from danswer.utils.logger import setup_logger
-from retry import retry
-from slack_sdk import WebClient
-from slack_sdk.socket_mode import SocketModeClient
-from slack_sdk.socket_mode.request import SocketModeRequest
-from slack_sdk.socket_mode.response import SocketModeResponse
 
 logger = setup_logger()
 

backend/danswer/main.py

@@ -1,18 +1,26 @@
 import nltk  # type:ignore
 import uvicorn
+from fastapi import FastAPI
+from fastapi import Request
+from fastapi.exceptions import RequestValidationError
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.responses import JSONResponse
+
 from danswer.auth.schemas import UserCreate
 from danswer.auth.schemas import UserRead
 from danswer.auth.schemas import UserUpdate
 from danswer.auth.users import auth_backend
 from danswer.auth.users import fastapi_users
 from danswer.auth.users import oauth_client
-from danswer.configs.app_configs import APP_HOST, OAUTH_TYPE, OPENID_CONFIG_URL
+from danswer.configs.app_configs import APP_HOST
 from danswer.configs.app_configs import APP_PORT
 from danswer.configs.app_configs import DISABLE_AUTH
 from danswer.configs.app_configs import DISABLE_GENERATIVE_AI
 from danswer.configs.app_configs import ENABLE_OAUTH
 from danswer.configs.app_configs import OAUTH_CLIENT_ID
 from danswer.configs.app_configs import OAUTH_CLIENT_SECRET
+from danswer.configs.app_configs import OAUTH_TYPE
+from danswer.configs.app_configs import OPENID_CONFIG_URL
 from danswer.configs.app_configs import QDRANT_DEFAULT_COLLECTION
 from danswer.configs.app_configs import SECRET
 from danswer.configs.app_configs import TYPESENSE_DEFAULT_COLLECTION
@@ -29,11 +37,6 @@ from danswer.server.health import router as health_router
 from danswer.server.manage import router as admin_router
 from danswer.server.search_backend import router as backend_router
 from danswer.utils.logger import setup_logger
-from fastapi import FastAPI
-from fastapi import Request
-from fastapi.exceptions import RequestValidationError
-from fastapi.middleware.cors import CORSMiddleware
-from fastapi.responses import JSONResponse
 
 
 logger = setup_logger()
@@ -50,7 +53,7 @@ def validation_exception_handler(
 
 def value_error_handler(_: Request, exc: ValueError) -> JSONResponse:
     try:
-        raise(exc)
+        raise (exc)
     except:
         # log stacktrace
         logger.exception("ValueError")
@@ -93,6 +96,9 @@ def get_application() -> FastAPI:
         tags=["users"],
     )
     if ENABLE_OAUTH:
+        if oauth_client is None:
+            raise RuntimeError("OAuth is enabled but no OAuth client is configured")
+
         if OAUTH_TYPE == "google":
             # special case for google
             application.include_router(
@@ -124,9 +130,7 @@ def get_application() -> FastAPI:
             tags=["auth"],
         )
         application.include_router(
-            fastapi_users.get_oauth_associate_router(
+            fastapi_users.get_oauth_associate_router(oauth_client, UserRead, SECRET),
-                oauth_client, UserRead, SECRET
-            ),
             prefix="/auth/associate/oauth",
             tags=["auth"],
         )
@@ -161,7 +165,9 @@ def get_application() -> FastAPI:
                 if not OAUTH_CLIENT_ID:
                     logger.warning("OAuth is turned on but OAUTH_CLIENT_ID is empty")
                 if not OAUTH_CLIENT_SECRET:
-                    logger.warning("OAuth is turned on but OAUTH_CLIENT_SECRET is empty")
+                    logger.warning(
+                        "OAuth is turned on but OAUTH_CLIENT_SECRET is empty"
+                    )
                 if OAUTH_TYPE == "openid" and not OPENID_CONFIG_URL:
                     logger.warning("OpenID is turned on but OPENID_CONFIG_URL is emtpy")
                 else:

backend/danswer/search/danswer_helper.py

@@ -1,5 +1,7 @@
 import numpy as np
 import tensorflow as tf  # type:ignore
+from transformers import AutoTokenizer  # type:ignore
+
 from danswer.search.keyword_search import remove_stop_words
 from danswer.search.models import QueryFlow
 from danswer.search.models import SearchType
@@ -9,7 +11,6 @@ from danswer.search.search_utils import get_default_tokenizer
 from danswer.server.models import HelperResponse
 from danswer.utils.logger import setup_logger
 from danswer.utils.timing import log_function_time
-from transformers import AutoTokenizer  # type:ignore
 
 logger = setup_logger()
 

backend/danswer/search/keyword_search.py

@@ -1,15 +1,16 @@
 import json
 from uuid import UUID
 
+from nltk.corpus import stopwords  # type:ignore
+from nltk.stem import WordNetLemmatizer  # type:ignore
+from nltk.tokenize import word_tokenize  # type:ignore
+
 from danswer.chunking.models import InferenceChunk
 from danswer.configs.app_configs import NUM_RETURNED_HITS
 from danswer.datastores.interfaces import IndexFilter
 from danswer.datastores.interfaces import KeywordIndex
 from danswer.utils.logger import setup_logger
 from danswer.utils.timing import log_function_time
-from nltk.corpus import stopwords  # type:ignore
-from nltk.stem import WordNetLemmatizer  # type:ignore
-from nltk.tokenize import word_tokenize  # type:ignore
 
 logger = setup_logger()
 

backend/danswer/search/search_utils.py

@@ -1,13 +1,14 @@
+from sentence_transformers import CrossEncoder  # type: ignore
+from sentence_transformers import SentenceTransformer  # type: ignore
+from transformers import AutoTokenizer  # type: ignore
+from transformers import TFDistilBertForSequenceClassification  # type: ignore
+
 from danswer.configs.model_configs import CROSS_EMBED_CONTEXT_SIZE
 from danswer.configs.model_configs import CROSS_ENCODER_MODEL_ENSEMBLE
 from danswer.configs.model_configs import DOC_EMBEDDING_CONTEXT_SIZE
 from danswer.configs.model_configs import DOCUMENT_ENCODER_MODEL
 from danswer.configs.model_configs import INTENT_MODEL_VERSION
 from danswer.configs.model_configs import QUERY_MAX_CONTEXT_SIZE
-from sentence_transformers import CrossEncoder  # type: ignore
-from sentence_transformers import SentenceTransformer  # type: ignore
-from transformers import AutoTokenizer  # type: ignore
-from transformers import TFDistilBertForSequenceClassification  # type: ignore
 
 
 _TOKENIZER: None | AutoTokenizer = None

backend/danswer/search/semantic_search.py

@@ -2,6 +2,8 @@ import json
 from uuid import UUID
 
 import numpy
+from sentence_transformers import SentenceTransformer  # type: ignore
+
 from danswer.chunking.models import EmbeddedIndexChunk
 from danswer.chunking.models import IndexChunk
 from danswer.chunking.models import InferenceChunk
@@ -18,7 +20,6 @@ from danswer.search.search_utils import get_default_reranking_model_ensemble
 from danswer.server.models import SearchDoc
 from danswer.utils.logger import setup_logger
 from danswer.utils.timing import log_function_time
-from sentence_transformers import SentenceTransformer  # type: ignore
 
 logger = setup_logger()
 

backend/danswer/server/event_loading.py

@@ -1,10 +1,11 @@
 from typing import Any
 
-from danswer.utils.logger import setup_logger
 from fastapi import APIRouter
 from pydantic import BaseModel
 from pydantic import Extra
 
+from danswer.utils.logger import setup_logger
+
 router = APIRouter()
 
 logger = setup_logger()

backend/danswer/server/health.py

@@ -1,6 +1,7 @@
-from danswer.server.models import StatusResponse
 from fastapi import APIRouter
 
+from danswer.server.models import StatusResponse
+
 
 router = APIRouter()
 

backend/danswer/server/manage.py

@@ -2,6 +2,16 @@ from datetime import datetime
 from datetime import timedelta
 from typing import cast
 
+from fastapi import APIRouter
+from fastapi import Depends
+from fastapi import HTTPException
+from fastapi import Request
+from fastapi import Response
+from fastapi import UploadFile
+from fastapi_users.db import SQLAlchemyUserDatabase
+from sqlalchemy.ext.asyncio import AsyncSession
+from sqlalchemy.orm import Session
+
 from danswer.auth.schemas import UserRole
 from danswer.auth.users import current_admin_user
 from danswer.auth.users import current_user
@@ -61,15 +71,6 @@ from danswer.server.models import StatusResponse
 from danswer.server.models import UserByEmail
 from danswer.server.models import UserRoleResponse
 from danswer.utils.logger import setup_logger
-from fastapi import APIRouter
-from fastapi import Depends
-from fastapi import HTTPException
-from fastapi import Request
-from fastapi import Response
-from fastapi import UploadFile
-from fastapi_users.db import SQLAlchemyUserDatabase
-from sqlalchemy.ext.asyncio import AsyncSession
-from sqlalchemy.orm import Session
 
 
 router = APIRouter(prefix="/manage")

backend/danswer/server/models.py

@@ -6,6 +6,9 @@ from typing import Optional
 from typing import TypeVar
 from uuid import UUID
 
+from pydantic import BaseModel
+from pydantic.generics import GenericModel
+
 from danswer.configs.constants import DocumentSource
 from danswer.connectors.models import InputType
 from danswer.datastores.interfaces import IndexFilter
@@ -13,8 +16,6 @@ from danswer.db.models import Connector
 from danswer.db.models import IndexingStatus
 from danswer.search.models import QueryFlow
 from danswer.search.models import SearchType
-from pydantic import BaseModel
-from pydantic.generics import GenericModel
 
 
 DataT = TypeVar("DataT")

backend/danswer/server/search_backend.py

@@ -1,6 +1,10 @@
 import json
 from collections.abc import Generator
 
+from fastapi import APIRouter
+from fastapi import Depends
+from fastapi.responses import StreamingResponse
+
 from danswer.auth.users import current_user
 from danswer.chunking.models import InferenceChunk
 from danswer.configs.app_configs import DISABLE_GENERATIVE_AI
@@ -25,9 +29,6 @@ from danswer.server.models import QuestionRequest
 from danswer.server.models import SearchResponse
 from danswer.utils.logger import setup_logger
 from danswer.utils.timing import log_generator_function_time
-from fastapi import APIRouter
-from fastapi import Depends
-from fastapi.responses import StreamingResponse
 
 logger = setup_logger()
 

backend/danswer/utils/clients.py

@@ -1,4 +1,6 @@
 import typesense  # type: ignore
+from qdrant_client import QdrantClient
+
 from danswer.configs.app_configs import QDRANT_API_KEY
 from danswer.configs.app_configs import QDRANT_HOST
 from danswer.configs.app_configs import QDRANT_PORT
@@ -6,7 +8,6 @@ from danswer.configs.app_configs import QDRANT_URL
 from danswer.configs.app_configs import TYPESENSE_API_KEY
 from danswer.configs.app_configs import TYPESENSE_HOST
 from danswer.configs.app_configs import TYPESENSE_PORT
-from qdrant_client import QdrantClient
 
 
 _qdrant_client: QdrantClient | None = None

backend/danswer/utils/text_processing.py

@@ -1,4 +1,5 @@
 from bs4 import BeautifulSoup
+
 from danswer.configs.constants import HTML_SEPARATOR
 
 

backend/scripts/reset_indexes.py

@@ -1,12 +1,13 @@
 # This file is purely for development use, not included in any builds
+from qdrant_client.http.models import Distance
+from qdrant_client.http.models import VectorParams
+from typesense.exceptions import ObjectNotFound  # type: ignore
+
 from danswer.configs.model_configs import DOC_EMBEDDING_DIM
 from danswer.datastores.typesense.store import create_typesense_collection
 from danswer.utils.clients import get_qdrant_client
 from danswer.utils.clients import get_typesense_client
 from danswer.utils.logger import setup_logger
-from qdrant_client.http.models import Distance
-from qdrant_client.http.models import VectorParams
-from typesense.exceptions import ObjectNotFound  # type: ignore
 
 logger = setup_logger()
 

backend/scripts/reset_postgres.py

@@ -1,4 +1,5 @@
 import psycopg2
+
 from danswer.configs.app_configs import POSTGRES_DB
 from danswer.configs.app_configs import POSTGRES_HOST
 from danswer.configs.app_configs import POSTGRES_PASSWORD

backend/scripts/save_load_state.py

@@ -6,6 +6,9 @@ import subprocess
 from datetime import datetime
 
 import requests
+from qdrant_client.http.models.models import SnapshotDescription
+from typesense.exceptions import ObjectNotFound  # type: ignore
+
 from alembic import command
 from alembic.config import Config
 from danswer.configs.app_configs import POSTGRES_DB
@@ -23,8 +26,6 @@ from danswer.datastores.typesense.store import create_typesense_collection
 from danswer.utils.clients import get_qdrant_client
 from danswer.utils.clients import get_typesense_client
 from danswer.utils.logger import setup_logger
-from qdrant_client.http.models.models import SnapshotDescription
-from typesense.exceptions import ObjectNotFound  # type: ignore
 
 logger = setup_logger()
 

backend/scripts/simulate_frontend.py

@@ -5,6 +5,7 @@ import urllib
 from pprint import pprint
 
 import requests
+
 from danswer.configs.app_configs import APP_PORT
 from danswer.configs.app_configs import QDRANT_DEFAULT_COLLECTION
 from danswer.configs.constants import SOURCE_TYPE