support images and tables extract from docx (#4619)

This commit is contained in:
Jyong 2024-05-23 18:05:23 +08:00 • committed by GitHub
commit 233c4150d1
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
10 changed files with 163 additions and 23 deletions

View file

@ -94,7 +94,7 @@ class TextSplitter(BaseDocumentTransformer, ABC):
documents.append(new_doc)
return documents
def split_documents(self, documents: Iterable[Document] ) -> list[Document]:
def split_documents(self, documents: Iterable[Document]) -> list[Document]:
"""Split documents."""
texts, metadatas = [], []
for doc in documents: