openrag 0.5.1.dev4__tar.gz → 0.5.1.dev6__tar.gz

{openrag-0.5.1.dev4/src/openrag.egg-info → openrag-0.5.1.dev6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: openrag
-Version: 0.5.1.dev4
+Version: 0.5.1.dev6
 Summary: OpenRAG is a comprehensive Retrieval-Augmented Generation platform that enables intelligent document search and AI-powered conversations.
 Classifier: Development Status :: 4 - Beta
 Classifier: Environment :: Console

{openrag-0.5.1.dev4 → openrag-0.5.1.dev6}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "openrag"
-version = "0.5.1.dev4"
+version = "0.5.1.dev6"
 description = "OpenRAG is a comprehensive Retrieval-Augmented Generation platform that enables intelligent document search and AI-powered conversations."
 readme = "README.md"
 requires-python = ">=3.13"

{openrag-0.5.1.dev4 → openrag-0.5.1.dev6}/src/connectors/onedrive/connector.py

@@ -636,7 +636,7 @@ class OneDriveConnector(BaseConnector):
 
         # Check if ID contains '!' which indicates driveId!itemId format
         if "!" in file_id:
-            parts = file_id.rsplit("!", 1)
+            parts = file_id.split("!", 1)
             if len(parts) == 2:
                 drive_id = parts[0]
                 item_id = parts[1]
@@ -735,7 +735,7 @@ class OneDriveConnector(BaseConnector):
 
             # Build URL based on ID format
             if "!" in file_id:
-                parts = file_id.rsplit("!", 1)
+                parts = file_id.split("!", 1)
                 if len(parts) == 2:
                     drive_id = parts[0]
                     item_id = parts[1]
@@ -747,11 +747,8 @@ class OneDriveConnector(BaseConnector):
                             return content
 
                     # Try drives endpoint for driveId!itemId format
-                    if not item_id.startswith("s"):
-                        url = f"{self._graph_base_url}/drives/{drive_id}/items/{item_id}/content"
-                        logger.info(f"Downloading via drives endpoint: {url}")
-                    else:
-                        url = f"{self._graph_base_url}/me/drive/items/{file_id}/content"
+                    url = f"{self._graph_base_url}/drives/{drive_id}/items/{file_id}/content"
+                    logger.info(f"Downloading via drives endpoint: {url}")
                 else:
                     url = f"{self._graph_base_url}/me/drive/items/{file_id}/content"
             else:
@@ -886,18 +883,7 @@ class OneDriveConnector(BaseConnector):
         files: list[dict[str, Any]] = []
 
         try:
-            drive_id = None
-            if "!" in folder_id:
-                parts = folder_id.rsplit("!", 1)
-                if len(parts) == 2:
-                    potential_drive_id, item_id = parts
-                    if not item_id.startswith("s"):
-                        drive_id = potential_drive_id
-                        url = f"{self._graph_base_url}/drives/{drive_id}/items/{item_id}/children"
-
-            if not drive_id:
-                url = f"{self._graph_base_url}/me/drive/items/{folder_id}/children"
-
+            url = f"{self._graph_base_url}/me/drive/items/{folder_id}/children"
             params = dict(self._default_params)
 
             response = await self._make_graph_request(url, params=params)

{openrag-0.5.1.dev4 → openrag-0.5.1.dev6}/src/models/processors.py

@@ -27,6 +27,15 @@ from .tasks import FileTask, TaskStatus, UploadTask
 
 logger = get_logger(__name__)
 
+# Image file extensions that require OCR
+IMAGE_EXTENSIONS = {"bmp", "jpeg", "jpg", "png", "tiff", "tif", "webp"}
+
+
+def is_image_file(filename: str) -> bool:
+    """Check if a file is an image based on its extension."""
+    ext = filename.split(".")[-1].lower() if "." in filename else ""
+    return ext in IMAGE_EXTENSIONS
+
 if TYPE_CHECKING:
     from connectors.base import DocumentACL
 
@@ -455,6 +464,18 @@ class DocumentFileProcessor(TaskProcessor):
         file_task.updated_at = time.time()
 
         try:
+            # Check if OCR is disabled and file is an image
+            filename = os.path.basename(item)
+            config = get_openrag_config()
+            ocr_enabled = config.knowledge.ocr
+            
+            if not ocr_enabled and is_image_file(filename):
+                file_task.status = TaskStatus.FAILED
+                file_task.error = f"The file '{filename}' is an image file and cannot be ingested because OCR is disabled."
+                file_task.updated_at = time.time()
+                upload_task.failed_files += 1
+                return
+
             # Compute hash
             file_hash = hash_id(item)
 
@@ -578,6 +599,17 @@ class ConnectorFileProcessor(TaskProcessor):
                     file_task.updated_at = time.time()
                     upload_task.failed_files += 1
                     return
+                
+                # Check if OCR is disabled and file is an image
+                config = get_openrag_config()
+                ocr_enabled = config.knowledge.ocr
+                
+                if not ocr_enabled and is_image_file(file_task.filename):
+                    file_task.status = TaskStatus.FAILED
+                    file_task.error = f"The file '{file_task.filename}' is an image file and cannot be ingested because OCR is disabled."
+                    file_task.updated_at = time.time()
+                    upload_task.failed_files += 1
+                    return
 
             # Get file content from connector
             try:
@@ -642,6 +674,17 @@ class ConnectorFileProcessor(TaskProcessor):
                 file_task.updated_at = time.time()
                 upload_task.failed_files += 1
                 return
+            
+            # Check if OCR is disabled and file is an image
+            config = get_openrag_config()
+            ocr_enabled = config.knowledge.ocr
+            
+            if not ocr_enabled and is_image_file(name):
+                file_task.status = TaskStatus.FAILED
+                file_task.error = f"The file '{name}' is an image file and cannot be ingested because OCR is disabled."
+                file_task.updated_at = time.time()
+                upload_task.failed_files += 1
+                return
 
             if not self.user_id:
                 raise ValueError("user_id not provided to ConnectorFileProcessor")

{openrag-0.5.1.dev4 → openrag-0.5.1.dev6/src/openrag.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: openrag
-Version: 0.5.1.dev4
+Version: 0.5.1.dev6
 Summary: OpenRAG is a comprehensive Retrieval-Augmented Generation platform that enables intelligent document search and AI-powered conversations.
 Classifier: Development Status :: 4 - Beta
 Classifier: Environment :: Console