From 37aa171924053898f1c4b571571f07106b300d5a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nielson=20Jann=C3=A9?= Date: Sat, 15 Mar 2025 15:35:09 +0100 Subject: [PATCH] Add filetype key for web chunk --- generic_rag/parsers/parser.py | 1 + 1 file changed, 1 insertion(+) 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)