wip

llama-index-core/llama_index/core/readers/file/base.py

@@ -816,3 +816,9 @@ def iter_data(
 
             if len(documents) > 0:
                 yield documents
+
+    def get_file_name(self, resource_id: str) -> str:
+        return Path(resource_id).name
+
+    def get_file_path(self, resource_id: str) -> str:
+        return resource_id

llama-index-integrations/readers/llama-index-readers-azstorage-blob/llama_index/readers/azstorage_blob/base.py

@@ -7,6 +7,7 @@
 import logging
 import math
 import os
+from pathlib import Path
 import tempfile
 import time
 from typing import Any, Dict, List, Optional, Union
@@ -229,3 +230,9 @@ def load_data(self) -> List[Document]:
             logger.info("Document creation starting")
 
             return self._load_documents_with_metadata(files_metadata, temp_dir)
+
+    def get_file_name(self, resource_id: str) -> str:
+        return Path(resource_id).name
+
+    def get_file_path(self, resource_id: str) -> str:
+        return resource_id

llama-index-integrations/readers/llama-index-readers-box/llama_index/readers/box/BoxReader/base.py

@@ -378,3 +378,12 @@ def _download_files(self, box_files: List[File], temp_dir: str) -> List[File]:
             file.downloaded_file_path = local_path
             box_files_with_path.append(file)
         return box_files_with_path
+
+    def get_file_name(self, resource_id: str) -> str:
+        box_file = get_box_files_details(
+            box_client=self._box_client, file_ids=[resource_id]
+        )
+        return box_file[0].name
+
+    def get_file_path(self, resource_id: str) -> str:
+        return self.get_file_name(resource_id)

llama-index-integrations/readers/llama-index-readers-gcs/llama_index/readers/gcs/base.py

@@ -273,3 +273,9 @@ def read_file_content(self, resource_id: str, **kwargs) -> bytes:
         except Exception as e:
             logger.error(f"Error reading file content from GCS: {e!s}")
             raise
+
+    def get_file_name(self, resource_id: str) -> str:
+        return Path(resource_id).name
+
+    def get_file_path(self, resource_id: str) -> str:
+        return resource_id

llama-index-integrations/readers/llama-index-readers-google/llama_index/readers/google/drive/base.py

@@ -689,3 +689,25 @@ def read_file_content(self, resource_id: str, **kwargs) -> bytes:
             downloaded_file = self._download_file(resource_id, temp_file)
             with open(downloaded_file, "rb") as file:
                 return file.read()
+
+    def get_file_name(self, resource_id: str) -> str:
+        """Get the file name from the resource ID."""
+        from googleapiclient.discovery import build
+
+        self._creds = self._get_credentials()
+
+        service = build("drive", "v3", credentials=self._creds)
+        file = service.files().get(fileId=resource_id, supportsAllDrives=True).execute()
+        return file["name"]
+
+    def get_file_path(self, resource_id: str) -> str:
+        """Get the file path from the resource ID."""
+        from googleapiclient.discovery import build
+
+        self._creds = self._get_credentials()
+
+        service = build("drive", "v3", credentials=self._creds)
+
+        return self._get_relative_path(
+            service, file_id=resource_id, folder_id=self.folder_id
+        )

llama-index-integrations/readers/llama-index-readers-microsoft-onedrive/llama_index/readers/microsoft_onedrive/base.py

@@ -2,6 +2,7 @@
 
 import logging
 import os
+from pathlib import Path
 import tempfile
 import time
 from typing import Any, Dict, List, Optional, Union
@@ -835,3 +836,9 @@ def read_file_content(self, resource_id: str, **kwargs) -> bytes:
 
     async def aread_file_content(self, resource_id: str, **kwargs) -> bytes:
         return self.read_file_content(resource_id, **kwargs)
+
+    def get_file_name(self, resource_id: str) -> str:
+        return Path(resource_id).name
+
+    def get_file_path(self, resource_id: str) -> str:
+        return resource_id

llama-index-integrations/readers/llama-index-readers-microsoft-sharepoint/llama_index/readers/microsoft_sharepoint/base.py

@@ -863,3 +863,9 @@ def read_file_content(self, resource_id: str, **kwargs) -> bytes:
                 "An error occurred while reading file content from SharePoint: %s", exp
             )
             raise
+
+    def get_file_name(self, resource_id: str) -> str:
+        return Path(resource_id).name
+
+    def get_file_path(self, resource_id: str) -> str:
+        return resource_id

llama-index-integrations/readers/llama-index-readers-s3/llama_index/readers/s3/base.py

@@ -213,3 +213,9 @@ def load_resource(self, resource_id: str, **kwargs) -> List[Document]:
     def read_file_content(self, resource_id: str, **kwargs) -> bytes:
         simple_directory_reader = self._get_simple_directory_reader()
         return simple_directory_reader.read_file_content(Path(resource_id), **kwargs)
+
+    def get_file_name(self, resource_id: str) -> str:
+        return Path(resource_id).name
+
+    def get_file_path(self, resource_id: str) -> str:
+        return resource_id