fix SimpleFileNodeParser throw error on unsupported extensions

Fix for: run-llama#13152
yukikwi · Apr 29, 2024 · 9d83432 · 9d83432
1 parent 4091384
commit 9d83432
Showing 1 changed file with 13 additions and 2 deletions.
diff --git a/llama-index-core/llama_index/core/node_parser/file/simple_file.py b/llama-index-core/llama_index/core/node_parser/file/simple_file.py
@@ -2,12 +2,14 @@
 from typing import Any, Dict, List, Optional, Sequence, Type
 
 from llama_index.core.callbacks.base import CallbackManager
+from llama_index.core.node_parser.node_utils import build_nodes_from_splits
 from llama_index.core.node_parser.file.html import HTMLNodeParser
 from llama_index.core.node_parser.file.json import JSONNodeParser
 from llama_index.core.node_parser.file.markdown import MarkdownNodeParser
 from llama_index.core.node_parser.interface import NodeParser
-from llama_index.core.schema import BaseNode
+from llama_index.core.schema import BaseNode, MetadataMode
 from llama_index.core.utils import get_tqdm_iterable
+from llama_index.core.schema import TextNode
 
 FILE_NODE_PARSERS: Dict[str, Type[NodeParser]] = {
     ".md": MarkdownNodeParser,
@@ -77,6 +79,15 @@ def _parse_nodes(
                 all_nodes.extend(nodes)
             else:
                 # What to do when file type isn't supported yet?
-                all_nodes.extend(document)
+                all_nodes.extend(
+                    # build node from document
+                    build_nodes_from_splits(
+                        [
+                            document.get_content(metadata_mode=MetadataMode.NONE)
+                        ],
+                        document,
+                        id_func=self.id_func
+                    )
+                )
 
         return all_nodes