OpenRAG 0.5.1.dev5__py3-none-any.whl → 0.5.1.dev7__py3-none-any.whl

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.dev5.dist-info → openrag-0.5.1.dev7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: openrag
-Version: 0.5.1.dev5
+Version: 0.5.1.dev7
 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.dev5.dist-info → openrag-0.5.1.dev7.dist-info}/RECORD

@@ -68,10 +68,10 @@ connectors/sharepoint/utils.py,sha256=OBNEbXb8uAfR-iR-ML0aOojGfGj03vJnKm9DbYf2hW
 mcp_http/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 mcp_http/server.py,sha256=JutP94fQRCizeCN69kKkdYDFE71L3DqLTCcb397T8Eo,7738
 models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-models/processors.py,sha256=1EDaMugIigfSu31Yxf54VRNrag1KXVE9Gdxl6VwFNZc,42351
+models/processors.py,sha256=a5q6E33OU0TVwU-jS2D9qP6u5VdKhjNOTYhhgLVqgyk,44361
 models/tasks.py,sha256=EySl0-h2YHG0QfKDswVvO3v4tKyz_t_9e6z8IwKj61Y,1951
 models/url.py,sha256=92rsrLLyIqUErYipYz5QwUNTdHwJ2jBRV7PIVpncTyo,5764
-openrag-0.5.1.dev5.dist-info/licenses/LICENSE,sha256=jWcnPXkUxEinX60Yn-_zjsY9i84vz2QSb0fi53djOkg,11334
+openrag-0.5.1.dev7.dist-info/licenses/LICENSE,sha256=jWcnPXkUxEinX60Yn-_zjsY9i84vz2QSb0fi53djOkg,11334
 services/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 services/api_key_service.py,sha256=HFULyy47ixp38XBx-BVmCA1Wggv9v98HBTZT4XLTr8M,11923
 services/auth_service.py,sha256=nAKTvMyX-YUtiNfKF06Dq4E4iwHPBhfKR6nliqGpOSs,22090
@@ -158,8 +158,8 @@ utils/telemetry/__init__.py,sha256=xoStY8hoYWnVe0B_jNthSdzRb7AxCT0rhM8ba9Q0Obg,2
 utils/telemetry/category.py,sha256=wei3V5WyUaiadYjEE5s0ys9PY0TjnebIvTykQU0P_2k,1114
 utils/telemetry/client.py,sha256=RhjW1a27w7W6gHt9X7AxdRPdZGmCEQDPskkxj5nsuiQ,12500
 utils/telemetry/message_id.py,sha256=IAu0wBVNOGPcSlQ0bAzvqIYr1Ac_n8wSTSxXzq_tiV0,9634
-openrag-0.5.1.dev5.dist-info/METADATA,sha256=WoJv2AhRDbcKcjMGBhkOiy6RTB-X8WiRyIXzqEhuSOw,7818
-openrag-0.5.1.dev5.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
-openrag-0.5.1.dev5.dist-info/entry_points.txt,sha256=ArKNHB63I3K8vynNkogvZOLmmQFpIsHDL7MvreCmju4,45
-openrag-0.5.1.dev5.dist-info/top_level.txt,sha256=5vfLBIkzuwBJrizhCSZiXV7NTzTRIMlNLsyzYDEeCF8,125
-openrag-0.5.1.dev5.dist-info/RECORD,,
+openrag-0.5.1.dev7.dist-info/METADATA,sha256=dzzY0WHIhAmyQRM1_Ld-X4299UB3OfFAhHcKba8kP5Y,7818
+openrag-0.5.1.dev7.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
+openrag-0.5.1.dev7.dist-info/entry_points.txt,sha256=ArKNHB63I3K8vynNkogvZOLmmQFpIsHDL7MvreCmju4,45
+openrag-0.5.1.dev7.dist-info/top_level.txt,sha256=5vfLBIkzuwBJrizhCSZiXV7NTzTRIMlNLsyzYDEeCF8,125
+openrag-0.5.1.dev7.dist-info/RECORD,,