alita-sdk 0.3.405__tar.gz → 0.3.406__tar.gz

{alita_sdk-0.3.405 → alita_sdk-0.3.406}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: alita_sdk
-Version: 0.3.405
+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-0.3.405 → alita_sdk-0.3.406}/alita_sdk/tools/sharepoint/api_wrapper.py

@@ -156,11 +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-0.3.405 → alita_sdk-0.3.406}/alita_sdk/tools/sharepoint/authorization_helper.py

@@ -1,5 +1,5 @@
 from datetime import datetime, timezone
-from urllib.parse import urlparse
+from urllib.parse import unquote, urlparse
 
 import jwt
 import requests
@@ -117,6 +117,7 @@ class SharepointAuthorizationHelper:
             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")
             #
@@ -137,9 +138,12 @@ class SharepointAuthorizationHelper:
             #
             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.get('name'),
-                    'Path': file.get('webUrl'),
+                    'Name': file_name,
+                    'Path': '/'.join([part for part in parts if part]),
                     'Created': file.get('createdDateTime'),
                     'Modified': file.get('lastModifiedDateTime'),
                     'Link': file.get('webUrl'),
@@ -154,3 +158,28 @@ class SharepointAuthorizationHelper:
             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-0.3.405 → alita_sdk-0.3.406}/alita_sdk.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: alita_sdk
-Version: 0.3.405
+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-0.3.405 → alita_sdk-0.3.406}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "alita_sdk"
-version = "0.3.405"
+version = "0.3.406"
 description = "SDK for building langchain agents using resources from Alita"
 readme = "README.md"
 requires-python = ">=3.10"