Files
t6_mem0/embedchain/loaders/docx_file.py
2023-07-26 23:14:57 +05:30

17 lines
505 B
Python

from langchain.document_loaders import Docx2txtLoader
from embedchain.loaders.base_loader import BaseLoader
class DocxFileLoader(BaseLoader):
def load_data(self, url):
"""Load data from a .docx file."""
loader = Docx2txtLoader(url)
output = []
data = loader.load()
content = data[0].page_content
meta_data = data[0].metadata
meta_data["url"] = "local"
output.append({"content": content, "meta_data": meta_data})
return output