Feature to support doc and docx files

nishchhal-shrestha · Jul 1, 2023 · 0114604 · 0114604
1 parent 3c0b8ff
commit 0114604
Showing 1 changed file with 3 additions and 1 deletion.
diff --git a/constants.py b/constants.py
@@ -4,7 +4,7 @@
 from chromadb.config import Settings
 
 # https://python.langchain.com/en/latest/modules/indexes/document_loaders/examples/excel.html?highlight=xlsx#microsoft-excel
-from langchain.document_loaders import CSVLoader, PDFMinerLoader, TextLoader, UnstructuredExcelLoader
+from langchain.document_loaders import CSVLoader, PDFMinerLoader, TextLoader, UnstructuredExcelLoader, Docx2txtLoader
 
 # load_dotenv()
 ROOT_DIRECTORY = os.path.dirname(os.path.realpath(__file__))
@@ -30,6 +30,8 @@
     ".csv": CSVLoader,
     ".xls": UnstructuredExcelLoader,
     ".xlxs": UnstructuredExcelLoader,
+    ".docx": Docx2txtLoader,
+    ".doc": Docx2txtLoader,
 }
 
 # Default Instructor Model