diff --git a/app/rag/importer.py b/app/rag/importer.py index 67e68a8..b97729e 100644 --- a/app/rag/importer.py +++ b/app/rag/importer.py @@ -387,7 +387,7 @@ async def _index_file( ) -> None: """Upsert one file: doc row + chunk rows + embeddings, one transaction.""" settings = llm.settings - content = full_path.read_text(encoding="utf-8", errors="replace") + content = full_path.read_text(encoding="utf-8", errors="replace").replace("\x00", "") digest = hashlib.sha256(content.encode("utf-8")).hexdigest() doc = session.scalar(select(Document).where(Document.source == source, Document.path == rel)) if doc is not None and doc.content_hash == digest: