diff --git a/generic_rag/parsers/parser.py b/generic_rag/parsers/parser.py index 11d9bef..ac59d4b 100644 --- a/generic_rag/parsers/parser.py +++ b/generic_rag/parsers/parser.py @@ -52,6 +52,7 @@ def add_urls(vector_store: Chroma, urls: list[str], chunk_size: int) -> None: for split in splits: split.metadata["source"] = url + split.metadata["filetype"] = "web" all_splits.extend(splits)