mirror of
https://github.com/hwchase17/langchain.git
synced 2025-06-19 05:13:46 +00:00
community[minor]: Implement lazy_load() for OutlookMessageLoader (#18668)
Integration test: `tests/integration_tests/document_loaders/test_email.py`
This commit is contained in:
parent
ae167fb5b2
commit
2d96803ddd
@ -1,5 +1,5 @@
|
|||||||
import os
|
import os
|
||||||
from typing import Any, List
|
from typing import Any, Iterator, List
|
||||||
|
|
||||||
from langchain_core.documents import Document
|
from langchain_core.documents import Document
|
||||||
|
|
||||||
@ -99,19 +99,16 @@ class OutlookMessageLoader(BaseLoader):
|
|||||||
"`pip install extract_msg`"
|
"`pip install extract_msg`"
|
||||||
)
|
)
|
||||||
|
|
||||||
def load(self) -> List[Document]:
|
def lazy_load(self) -> Iterator[Document]:
|
||||||
"""Load data into document objects."""
|
|
||||||
import extract_msg
|
import extract_msg
|
||||||
|
|
||||||
msg = extract_msg.Message(self.file_path)
|
msg = extract_msg.Message(self.file_path)
|
||||||
return [
|
yield Document(
|
||||||
Document(
|
page_content=msg.body,
|
||||||
page_content=msg.body,
|
metadata={
|
||||||
metadata={
|
"source": self.file_path,
|
||||||
"source": self.file_path,
|
"subject": msg.subject,
|
||||||
"subject": msg.subject,
|
"sender": msg.sender,
|
||||||
"sender": msg.sender,
|
"date": msg.date,
|
||||||
"date": msg.date,
|
},
|
||||||
},
|
)
|
||||||
)
|
|
||||||
]
|
|
||||||
|
Loading…
Reference in New Issue
Block a user