From 135a40d696c998344df37faf2cbf7149cc8f0c24 Mon Sep 17 00:00:00 2001 From: cuikunyu Date: Fri, 11 Apr 2025 03:10:20 +0000 Subject: [PATCH] Optimize: Use python-docx for better parsing. --- lightrag/api/routers/document_routes.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/lightrag/api/routers/document_routes.py b/lightrag/api/routers/document_routes.py index 8e664006..0111e237 100644 --- a/lightrag/api/routers/document_routes.py +++ b/lightrag/api/routers/document_routes.py @@ -499,7 +499,10 @@ async def pipeline_enqueue_file(rag: LightRAG, file_path: Path) -> bool: content = result.document.export_to_markdown() else: if not pm.is_installed("python-docx"): # type: ignore - pm.install("docx") + try: + pm.install("python-docx") + except Exception: + pm.install("docx") from docx import Document # type: ignore from io import BytesIO