Merge pull request #2029 from abfeb8/main

feat: add Microsoft Entra ID integration

application/api/connector/routes.py

@@ -113,10 +113,14 @@ class ConnectorsCallback(Resource):
                 session_token = str(uuid.uuid4())
 
                 try:
-                    credentials = auth.create_credentials_from_token_info(token_info)
-                    service = auth.build_drive_service(credentials)
-                    user_info = service.about().get(fields="user").execute()
-                    user_email = user_info.get('user', {}).get('emailAddress', 'Connected User')
+                    if provider == "google_drive":
+                        credentials = auth.create_credentials_from_token_info(token_info)
+                        service = auth.build_drive_service(credentials)
+                        user_info = service.about().get(fields="user").execute()
+                        user_email = user_info.get('user', {}).get('emailAddress', 'Connected User')
+                    else:
+                        user_email = token_info.get('user_info', {}).get('email', 'Connected User')
+
                 except Exception as e:
                     current_app.logger.warning(f"Could not get user info: {e}")
                     user_email = 'Connected User'

application/core/settings.py

@@ -55,6 +55,11 @@ class Settings(BaseSettings):
         "http://127.0.0.1:7091/api/connectors/callback"  ##add redirect url as it is to your provider's console(gcp)
     )
 
+    # Microsoft Entra ID (Azure AD) integration
+    MICROSOFT_CLIENT_ID: Optional[str] = None  # Azure AD Application (client) ID
+    MICROSOFT_CLIENT_SECRET: Optional[str] = None  # Azure AD Application client secret
+    MICROSOFT_TENANT_ID: Optional[str] = "common"  # Azure AD Tenant ID (or 'common' for multi-tenant)
+    MICROSOFT_AUTHORITY: Optional[str] = None  # e.g., "https://login.microsoftonline.com/{tenant_id}"
     # GitHub source
     GITHUB_ACCESS_TOKEN: Optional[str] = None # PAT token with read repo access
 

application/parser/connectors/connector_creator.py

@@ -1,5 +1,7 @@
 from application.parser.connectors.google_drive.loader import GoogleDriveLoader
 from application.parser.connectors.google_drive.auth import GoogleDriveAuth
+from application.parser.connectors.share_point.auth import SharePointAuth
+from application.parser.connectors.share_point.loader import SharePointLoader
 
 
 class ConnectorCreator:
@@ -12,10 +14,12 @@ class ConnectorCreator:
 
     connectors = {
         "google_drive": GoogleDriveLoader,
+        "share_point": SharePointLoader,
     }
 
     auth_providers = {
         "google_drive": GoogleDriveAuth,
+        "share_point": SharePointAuth,
     }
 
     @classmethod

application/parser/connectors/share_point/__init__.py

@@ -0,0 +1,10 @@
+"""
+Share Point connector package for DocsGPT.
+
+This module provides authentication and document loading capabilities for Share Point.
+"""
+
+from .auth import SharePointAuth
+from .loader import SharePointLoader
+
+__all__ = ['SharePointAuth', 'SharePointLoader']

application/parser/connectors/share_point/auth.py

@@ -0,0 +1,91 @@
+import logging
+import datetime
+from typing import Optional, Dict, Any
+
+from msal import ConfidentialClientApplication
+
+from application.core.settings import settings
+from application.parser.connectors.base import BaseConnectorAuth
+
+
+class SharePointAuth(BaseConnectorAuth):
+    """
+    Handles Microsoft OAuth 2.0 authentication.
+
+    # Documentation:
+    - https://learn.microsoft.com/en-us/entra/identity-platform/v2-oauth2-auth-code-flow
+    - https://learn.microsoft.com/en-gb/entra/msal/python/
+    """
+
+    # Microsoft Graph scopes for SharePoint access
+    SCOPES = [
+        "User.Read",
+    ]
+
+    def __init__(self):
+        self.client_id = settings.MICROSOFT_CLIENT_ID
+        self.client_secret = settings.MICROSOFT_CLIENT_SECRET
+
+        if not self.client_id or not self.client_secret:
+            raise ValueError(
+                "Microsoft OAuth credentials not configured. Please set MICROSOFT_CLIENT_ID and MICROSOFT_CLIENT_SECRET in settings."
+            )
+
+        self.redirect_uri = settings.CONNECTOR_REDIRECT_BASE_URI
+        self.tenant_id = settings.MICROSOFT_TENANT_ID
+        self.authority = getattr(settings, "MICROSOFT_AUTHORITY", f"https://{self.tenant_id}.ciamlogin.com/{self.tenant_id}")
+
+        self.auth_app = ConfidentialClientApplication(
+            client_id=self.client_id, client_credential=self.client_secret, authority=self.authority
+        )
+
+    def get_authorization_url(self, state: Optional[str] = None) -> str:
+        return self.auth_app.get_authorization_request_url(
+            scopes=self.SCOPES, state=state, redirect_uri=self.redirect_uri
+        )
+
+    def exchange_code_for_tokens(self, authorization_code: str) -> Dict[str, Any]:
+        result = self.auth_app.acquire_token_by_authorization_code(
+            code=authorization_code, scopes=self.SCOPES, redirect_uri=self.redirect_uri
+        )
+
+        if "error" in result:
+            logging.error(f"Error acquiring token: {result.get('error_description')}")
+            raise ValueError(f"Error acquiring token: {result.get('error_description')}")
+
+        return self.map_token_response(result)
+
+    def refresh_access_token(self, refresh_token: str) -> Dict[str, Any]:
+        result = self.auth_app.acquire_token_by_refresh_token(refresh_token=refresh_token, scopes=self.SCOPES)
+
+        if "error" in result:
+            logging.error(f"Error acquiring token: {result.get('error_description')}")
+            raise ValueError(f"Error acquiring token: {result.get('error_description')}")
+
+        return self.map_token_response(result)
+
+    def is_token_expired(self, token_info: Dict[str, Any]) -> bool:
+        if not token_info or "expiry" not in token_info:
+            # If no expiry info, consider token expired to be safe
+            return True
+
+        # Get expiry timestamp and current time
+        expiry_timestamp = token_info["expiry"]
+        current_timestamp = int(datetime.datetime.now().timestamp())
+
+        # Token is expired if current time is greater than or equal to expiry time
+        return current_timestamp >= expiry_timestamp
+
+    def map_token_response(self, result) -> Dict[str, Any]:
+        return {
+            "access_token": result.get("access_token"),
+            "refresh_token": result.get("refresh_token"),
+            "token_uri": result.get("id_token_claims", {}).get("iss"),
+            "scopes": result.get("scope"),
+            "expiry": result.get("id_token_claims", {}).get("exp"),
+            "user_info": {
+                "name": result.get("id_token_claims", {}).get("name"),
+                "email": result.get("id_token_claims", {}).get("preferred_username"),
+            },
+            "raw_token": result,
+        }

application/parser/connectors/share_point/loader.py

@@ -0,0 +1,44 @@
+from typing import List, Dict, Any
+from application.parser.connectors.base import BaseConnectorLoader
+from application.parser.schema.base import Document
+
+
+class SharePointLoader(BaseConnectorLoader):
+    def __init__(self, session_token: str):
+        pass
+
+    def load_data(self, inputs: Dict[str, Any]) -> List[Document]:
+        """
+        Load documents from the external knowledge base.
+
+        Args:
+            inputs: Configuration dictionary containing:
+                - file_ids: Optional list of specific file IDs to load
+                - folder_ids: Optional list of folder IDs to browse/download
+                - limit: Maximum number of items to return
+                - list_only: If True, return metadata without content
+                - recursive: Whether to recursively process folders
+
+        Returns:
+            List of Document objects
+        """
+        pass
+
+    def download_to_directory(self, local_dir: str, source_config: Dict[str, Any] = None) -> Dict[str, Any]:
+        """
+        Download files/folders to a local directory.
+
+        Args:
+            local_dir: Local directory path to download files to
+            source_config: Configuration for what to download
+
+        Returns:
+            Dictionary containing download results:
+                - files_downloaded: Number of files downloaded
+                - directory_path: Path where files were downloaded
+                - empty_result: Whether no files were downloaded
+                - source_type: Type of connector
+                - config_used: Configuration that was used
+                - error: Error message if download failed (optional)
+        """
+        pass

application/requirements.txt

@@ -40,6 +40,7 @@ markupsafe==3.0.2
 marshmallow==3.26.1
 mpmath==1.3.0
 multidict==6.4.3
+msal==1.34.0
 mypy-extensions==1.0.0
 networkx==3.4.2
 numpy==2.2.1
@@ -87,4 +88,4 @@ werkzeug>=3.1.0,<3.1.2
 yarl==1.20.0
 markdownify==1.1.0
 tldextract==5.1.3
-websockets==14.1
+websockets==14.1