Merge 1d354b85db705226f9fd29ccf73efbbbb59f01e2 into 99546e4a4d60d3d9f29587c153998eeeeae62ef5

backend/onyx/connectors/confluence/connector.py

@@ -65,20 +65,6 @@ _RESTRICTIONS_EXPANSION_FIELDS = [
 
 _SLIM_DOC_BATCH_SIZE = 5000
 
-_ATTACHMENT_EXTENSIONS_TO_FILTER_OUT = [
-    "gif",
-    "mp4",
-    "mov",
-    "mp3",
-    "wav",
-]
-_FULL_EXTENSION_FILTER_STRING = "".join(
-    [
-        f" and title!~'*.{extension}'"
-        for extension in _ATTACHMENT_EXTENSIONS_TO_FILTER_OUT
-    ]
-)
-
 
 class ConfluenceConnector(
     LoadConnector,
@@ -207,7 +193,6 @@ class ConfluenceConnector(
     def _construct_attachment_query(self, confluence_page_id: str) -> str:
         attachment_query = f"type=attachment and container='{confluence_page_id}'"
         attachment_query += self.cql_label_filter
-        attachment_query += _FULL_EXTENSION_FILTER_STRING
         return attachment_query
 
     def _get_comment_string_for_page_id(self, page_id: str) -> str:
@@ -372,11 +357,13 @@ class ConfluenceConnector(
                 if not validate_attachment_filetype(
                     attachment,
                 ):
+                    logger.info(f"Skipping attachment: {attachment['title']}")
                     continue
 
+                logger.info(f"Processing attachment: {attachment['title']}")
+
                 # Attempt to get textual content or image summarization:
                 try:
-                    logger.info(f"Processing attachment: {attachment['title']}")
                     response = convert_attachment_to_content(
                         confluence_client=self.confluence_client,
                         attachment=attachment,

backend/onyx/file_processing/file_validation.py

@@ -15,6 +15,7 @@ EXCLUDED_IMAGE_TYPES = [
     "image/tiff",
     "image/gif",
     "image/svg+xml",
+    "image/avif",
 ]