From a63550944ba5dc4df813f6e66ab4ccad82e1baa9 Mon Sep 17 00:00:00 2001
From: yichuan520030910320 <yichuan_wang@berkeley.edu>
Date: Thu, 13 Nov 2025 14:57:28 -0800
Subject: [PATCH] update pkg name

---
 pyproject.toml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/pyproject.toml b/pyproject.toml
index 30ade7d..f67c4cc 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -59,7 +59,6 @@ dependencies = [
     "torchvision>=0.23.0",
     "einops",
     "seaborn",
-    "docx2text"
 ]
 
 [project.optional-dependencies]
@@ -70,7 +69,8 @@ diskann = [
 # Add a new optional dependency group for document processing
 documents = [
     "beautifulsoup4>=4.13.0",  # For HTML parsing
-    "python-docx>=0.8.11",     # For Word documents
+    "python-docx>=0.8.11",     # For Word documents (creating/editing)
+    "docx2txt>=0.9",           # For Word documents (text extraction)
     "openpyxl>=3.1.0",         # For Excel files
     "pandas>=2.2.0",           # For data processing
 ]