jack vor 1 Tag
Ursprung
Commit
03f37081ca
1 geänderte Dateien mit 2 neuen und 1 gelöschten Zeilen
  1. 2 1
      py/core/providers/ingestion/unstructured/base.py

+ 2 - 1
py/core/providers/ingestion/unstructured/base.py

@@ -307,7 +307,8 @@ class UnstructuredIngestionProvider(IngestionProvider):
         # TODO - Cleanup this approach to be less hardcoded
         # TODO - Remove code duplication between Unstructured & R2R
         logger.info(f"Parser overrides: {parser_overrides}")
-        if document.document_type.value in parser_overrides or document.document_type.value in self.R2R_FALLBACK_PARSERS.keys():
+        logger.info(f"R2R fallback parsers: {document.document_type.value in self.EXTRA_PARSERS.keys()}")
+        if document.document_type.value in parser_overrides or document.document_type.value in self.EXTRA_PARSERS.keys():
             logger.info(
                 f"Using parser_override for {document.document_type} with input value {parser_overrides[document.document_type.value]}"
             )