|
@@ -22,6 +22,7 @@ from langchain_community.document_loaders import (
|
|
UnstructuredWordDocumentLoader,
|
|
UnstructuredWordDocumentLoader,
|
|
UnstructuredMarkdownLoader,
|
|
UnstructuredMarkdownLoader,
|
|
UnstructuredXMLLoader,
|
|
UnstructuredXMLLoader,
|
|
|
|
+ UnstructuredRSTLoader,
|
|
)
|
|
)
|
|
from langchain.text_splitter import RecursiveCharacterTextSplitter
|
|
from langchain.text_splitter import RecursiveCharacterTextSplitter
|
|
from langchain_community.vectorstores import Chroma
|
|
from langchain_community.vectorstores import Chroma
|
|
@@ -178,6 +179,8 @@ def store_doc(
|
|
loader = Docx2txtLoader(file_path)
|
|
loader = Docx2txtLoader(file_path)
|
|
elif file_ext=="csv":
|
|
elif file_ext=="csv":
|
|
loader = CSVLoader(file_path)
|
|
loader = CSVLoader(file_path)
|
|
|
|
+ elif file_ext=="rst":
|
|
|
|
+ loader = UnstructuredRSTLoader(file_path, mode="elements")
|
|
elif file_ext in text_xml:
|
|
elif file_ext in text_xml:
|
|
loader=UnstructuredXMLLoader(file_path)
|
|
loader=UnstructuredXMLLoader(file_path)
|
|
elif file_ext in known_source_ext or file.content_type.find("text/")>=0:
|
|
elif file_ext in known_source_ext or file.content_type.find("text/")>=0:
|