alita-sdk 0.3.404__py3-none-any.whl → 0.3.406__py3-none-any.whl

alita_sdk/tools/sharepoint/api_wrapper.py

@@ -127,8 +127,23 @@ class SharepointApiWrapper(NonCodeIndexerToolkit):
                 result.append(temp_props)
             return result if result else ToolException("Can not get files or folder is empty. Please, double check folder name and read permissions.")
         except Exception as e:
-            logging.error(f"Failed to load files from sharepoint: {e}")
-            return ToolException("Can not get files. Please, double check folder name and read permissions.")
+            # attempt to get via graph api
+            try:
+                # attempt to get files via graph api
+                from .authorization_helper import SharepointAuthorizationHelper
+                auth_helper = SharepointAuthorizationHelper(
+                    client_id=self.client_id,
+                    client_secret=self.client_secret.get_secret_value(),
+                    tenant="", # optional for graph api
+                    scope="", # optional for graph api
+                    token_json="", # optional for graph api
+                )
+                files = auth_helper.get_files_list(self.site_url, folder_name, limit_files)
+                return files
+            except Exception as graph_e:
+                logging.error(f"Failed to load files from sharepoint via base api: {e}")
+                logging.error(f"Failed to load files from sharepoint via graph api: {graph_e}")
+                return ToolException(f"Can not get files. Please, double check folder name and read permissions: {e} and {graph_e}")
 
     def read_file(self, path,
                   is_capture_image: bool = False,
@@ -141,11 +156,28 @@ class SharepointApiWrapper(NonCodeIndexerToolkit):
             self._client.load(file).execute_query()
 
             file_content = file.read()
+            file_name = file.name
             self._client.execute_query()
         except Exception as e:
-            logging.error(f"Failed to load file from SharePoint: {e}. Path: {path}. Please, double check file name and path.")
-            return ToolException("File not found. Please, check file name and path.")
-        return parse_file_content(file_name=file.name,
+            # attempt to get via graph api
+            try:
+                # attempt to get files via graph api
+                from .authorization_helper import SharepointAuthorizationHelper
+                auth_helper = SharepointAuthorizationHelper(
+                    client_id=self.client_id,
+                    client_secret=self.client_secret.get_secret_value(),
+                    tenant="",  # optional for graph api
+                    scope="",  # optional for graph api
+                    token_json="",  # optional for graph api
+                )
+                file_content = auth_helper.get_file_content(self.site_url, path)
+                file_name = path.split('/')[-1]
+            except Exception as graph_e:
+                logging.error(f"Failed to load file from SharePoint via base api: {e}. Path: {path}. Please, double check file name and path.")
+                logging.error(f"Failed to load file from SharePoint via graph api: {graph_e}. Path: {path}. Please, double check file name and path.")
+                return ToolException(f"File not found. Please, check file name and path: {e} and {graph_e}")
+        #
+        return parse_file_content(file_name=file_name,
                                   file_content=file_content,
                                   is_capture_image=is_capture_image,
                                   page_number=page_number,

alita_sdk/tools/sharepoint/authorization_helper.py

@@ -1,4 +1,5 @@
 from datetime import datetime, timezone
+from urllib.parse import unquote, urlparse
 
 import jwt
 import requests
@@ -54,4 +55,131 @@ class SharepointAuthorizationHelper:
         except jwt.ExpiredSignatureError:
             return False
         except jwt.InvalidTokenError:
-            return False
+            return False
+
+
+    def generate_token_and_site_id(self, site_url: str) -> tuple[str, str]:
+        try:
+            parsed = urlparse(site_url)
+            domain = parsed.hostname
+            site_path = parsed.path.strip('/')
+            if not domain or not site_path:
+                raise ValueError(f"site_url missing domain or site path: {site_url}")
+            #
+            app_name = domain.split('.')[0]
+            openid_config_url = f"https://login.microsoftonline.com/{app_name}.onmicrosoft.com/v2.0/.well-known/openid-configuration"
+            response = requests.get(openid_config_url)
+            if response.status_code != 200:
+                raise RuntimeError(f"Failed to get OpenID config: {response.status_code} {response.text}")
+            token_url = response.json().get("token_endpoint")
+            if not token_url:
+                raise KeyError("'token_endpoint' missing in OpenID config response")
+            #
+            token_data = {
+                "grant_type": "client_credentials",
+                "client_id": self.client_id,
+                "client_secret": self.client_secret,
+                "scope": "https://graph.microsoft.com/.default"
+            }
+            token_response = requests.post(token_url, data=token_data)
+            if token_response.status_code != 200:
+                raise RuntimeError(f"Failed to get access token: {token_response.status_code} {token_response.text}")
+            access_token = token_response.json().get("access_token")
+            if not access_token:
+                raise KeyError("'access_token' missing in token response")
+            #
+            graph_site_url = f"https://graph.microsoft.com/v1.0/sites/{domain}:/{site_path}"
+            headers = {"Authorization": f"Bearer {access_token}"}
+            site_response = requests.get(graph_site_url, headers=headers)
+            if site_response.status_code != 200:
+                raise RuntimeError(f"Failed to get site info: {site_response.status_code} {site_response.text}")
+            site_id = site_response.json().get("id")
+            if not site_id:
+                raise KeyError("'id' missing in site response")
+            #
+            return access_token, site_id
+        except Exception as e:
+            raise RuntimeError(f"Error while obtaining access_token and site_id: {e}")
+
+    def get_files_list(self, site_url: str, folder_name: str = None, limit_files: int = 100):
+        if not site_url or not site_url.startswith("https://"):
+            raise ValueError(f"Invalid site_url format: {site_url}")
+        if limit_files is not None and (not isinstance(limit_files, int) or limit_files <= 0):
+            raise ValueError(f"limit_files must be a positive integer, got: {limit_files}")
+        try:
+            access_token, site_id = self.generate_token_and_site_id(site_url)
+            headers = {"Authorization": f"Bearer {access_token}"}
+            drives_url = f"https://graph.microsoft.com/v1.0/sites/{site_id}/drives"
+            drives_response = requests.get(drives_url, headers=headers)
+            if drives_response.status_code != 200:
+                raise RuntimeError(f"Failed to get drives: {drives_response.status_code} {drives_response.text}")
+            drives_json = drives_response.json()
+            if "value" not in drives_json or not drives_json["value"]:
+                raise KeyError("'value' missing or empty in drives response")
+            drive_id = drives_json["value"][0].get("id")
+            drive_path = unquote(urlparse(drives_json["value"][0].get("webUrl")).path)
+            if not drive_id:
+                raise KeyError("'id' missing in drive object")
+            #
+            # Build the correct endpoint for folder or root
+            if folder_name:
+                # Validate folder_name for safe URL usage
+                if any(c in folder_name for c in ['..', '//', '\\']):
+                    raise ValueError(f"Unsafe folder_name: {folder_name}")
+                url = f"https://graph.microsoft.com/v1.0/sites/{site_id}/drives/{drive_id}/root:/{folder_name}:/children?$top={limit_files}"
+            else:
+                url = f"https://graph.microsoft.com/v1.0/sites/{site_id}/drives/{drive_id}/root/children?$top={limit_files}"
+            response = requests.get(url, headers=headers)
+            if response.status_code != 200:
+                raise RuntimeError(f"Failed to get files list: {response.status_code} {response.text}")
+            files_json = response.json()
+            if "value" not in files_json:
+                raise KeyError("'value' missing in files response")
+            #
+            result = []
+            for file in files_json["value"]:
+                file_name = file.get('name', '')
+                parts = [drive_path.strip('/'), folder_name.strip('/') if folder_name else '', file_name.strip('/')]
+                #
+                temp_props = {
+                    'Name': file_name,
+                    'Path': '/'.join([part for part in parts if part]),
+                    'Created': file.get('createdDateTime'),
+                    'Modified': file.get('lastModifiedDateTime'),
+                    'Link': file.get('webUrl'),
+                    'id': file.get('id')
+                }
+                if not all([temp_props['Name'], temp_props['Path'], temp_props['id']]):
+                    raise KeyError(f"Missing required file fields in: {file}")
+                result.append(temp_props)
+            # If API doesn't respect $top, slice in Python
+            if limit_files is not None:
+                result = result[:limit_files]
+            return result
+        except Exception as e:
+            raise RuntimeError(f"Error in get_files_list: {e}")
+
+    def get_file_content(self, site_url: str, path: str):
+        try:
+            access_token, site_id = self.generate_token_and_site_id(site_url)
+            headers = {"Authorization": f"Bearer {access_token}"}
+            drives_url = f"https://graph.microsoft.com/v1.0/sites/{site_id}/drives"
+            drives_response = requests.get(drives_url, headers=headers)
+            if drives_response.status_code != 200:
+                raise RuntimeError(f"Failed to get drives: {drives_response.status_code} {drives_response.text}")
+            drives_json = drives_response.json()
+            if "value" not in drives_json or not drives_json["value"]:
+                raise KeyError("'value' missing or empty in drives response")
+            drive_id = drives_json["value"][0].get("id")
+            if not drive_id:
+                raise KeyError("'id' missing in drive object")
+            #
+            # Build the endpoint for file content
+            url = f"https://graph.microsoft.com/v1.0/drives/{drive_id}/root:/{path}:/content"
+            response = requests.get(url, headers=headers)
+            if response.status_code != 200:
+                raise RuntimeError(f"Failed to get files list: {response.status_code} {response.text}")
+            #
+            return response.content
+        except Exception as e:
+            raise RuntimeError(f"Error in get_files_list: {e}")

{alita_sdk-0.3.404.dist-info → alita_sdk-0.3.406.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: alita_sdk
-Version: 0.3.404
+Version: 0.3.406
 Summary: SDK for building langchain agents using resources from Alita
 Author-email: Artem Rozumenko <artyom.rozumenko@gmail.com>, Mikalai Biazruchka <mikalai_biazruchka@epam.com>, Roman Mitusov <roman_mitusov@epam.com>, Ivan Krakhmaliuk <lifedj27@gmail.com>, Artem Dubrovskiy <ad13box@gmail.com>
 License-Expression: Apache-2.0

{alita_sdk-0.3.404.dist-info → alita_sdk-0.3.406.dist-info}/RECORD

@@ -317,8 +317,8 @@ alita_sdk/tools/servicenow/__init__.py,sha256=ziEt2juPrGFyB98ZXbGf25v6gZo4UJTHsz
 alita_sdk/tools/servicenow/api_wrapper.py,sha256=WpH-bBLGFdhehs4g-K-WAkNuaD1CSrwsDpdgB3RG53s,6120
 alita_sdk/tools/servicenow/servicenow_client.py,sha256=Rdqfu-ll-qbnclMzChLZBsfXRDzgoX_FdeI2WLApWxc,3269
 alita_sdk/tools/sharepoint/__init__.py,sha256=5z2iSmm-0kbHKf70wN6OOgS4Px7tOzwkIpHXz0Vrbj4,4045
-alita_sdk/tools/sharepoint/api_wrapper.py,sha256=6D0pGsCx33KxfbZkG331I1gucmqLToI2qBMonFZtl6o,12245
-alita_sdk/tools/sharepoint/authorization_helper.py,sha256=n-nL5dlBoLMK70nHu7P2RYCb8C6c9HMA_gEaw8LxuhE,2007
+alita_sdk/tools/sharepoint/api_wrapper.py,sha256=d8B0I4C9x8qt1dvmLjsfYnas98T_gXueJAWrNykZP0U,14075
+alita_sdk/tools/sharepoint/authorization_helper.py,sha256=-wNPxkKcg42o5Z3tkmzIr6rrrCMkA-Og2j6GbDjq7yU,9166
 alita_sdk/tools/sharepoint/utils.py,sha256=fZ1YzAu5CTjKSZeslowpOPH974902S8vCp1Wu7L44LM,446
 alita_sdk/tools/slack/__init__.py,sha256=YiPAoRc6y6uVpfHl0K1Qi-flcyPlWFIMVcVbhicGWXY,3990
 alita_sdk/tools/slack/api_wrapper.py,sha256=5VrV7iSGno8ZcDzEHdGPNhInhtODGPPvAzoZ9W9iQWE,14009
@@ -353,8 +353,8 @@ alita_sdk/tools/zephyr_scale/api_wrapper.py,sha256=kT0TbmMvuKhDUZc0i7KO18O38JM9S
 alita_sdk/tools/zephyr_squad/__init__.py,sha256=0ne8XLJEQSLOWfzd2HdnqOYmQlUliKHbBED5kW_Vias,2895
 alita_sdk/tools/zephyr_squad/api_wrapper.py,sha256=kmw_xol8YIYFplBLWTqP_VKPRhL_1ItDD0_vXTe_UuI,14906
 alita_sdk/tools/zephyr_squad/zephyr_squad_cloud_client.py,sha256=R371waHsms4sllHCbijKYs90C-9Yu0sSR3N4SUfQOgU,5066
-alita_sdk-0.3.404.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-alita_sdk-0.3.404.dist-info/METADATA,sha256=KvmNI9txwowkZbaBsfmquBSNCrTRkagGpMSM3_M_8rw,19071
-alita_sdk-0.3.404.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-alita_sdk-0.3.404.dist-info/top_level.txt,sha256=0vJYy5p_jK6AwVb1aqXr7Kgqgk3WDtQ6t5C-XI9zkmg,10
-alita_sdk-0.3.404.dist-info/RECORD,,
+alita_sdk-0.3.406.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+alita_sdk-0.3.406.dist-info/METADATA,sha256=qKUH3FgZr8aK9zs2JOuh5VCEoRswwX5frgyDYb2Vszo,19071
+alita_sdk-0.3.406.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+alita_sdk-0.3.406.dist-info/top_level.txt,sha256=0vJYy5p_jK6AwVb1aqXr7Kgqgk3WDtQ6t5C-XI9zkmg,10
+alita_sdk-0.3.406.dist-info/RECORD,,