feat: changed doc_file to docx and update readme (#157)

This commit is contained in:
Sahil Kumar Yadav
2023-07-07 16:18:05 +05:30
committed by GitHub
parent 51adc5c886
commit 0bb3d0afe9
5 changed files with 21 additions and 18 deletions

View File

@@ -0,0 +1,12 @@
from langchain.document_loaders import Docx2txtLoader
class DocxFileLoader:
def load_data(self, url):
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