highperfocused/danswer
1
0
Fork 0
mirror of https://github.com/danswer-ai/danswer.git synced 2025-05-15 06:10:15 +02:00
Code Issues Packages Projects Releases Wiki Activity

Fix import location and mypy issue (#249)

Browse Source
This commit is contained in:
Yuhong Sun 2023-07-28 16:06:25 -07:00 committed by GitHub
parent 2a339ec34b
commit 55adde5e27
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
backend/danswer/connectors/google_drive/connector.py
View File

@ -6,6 +6,7 @@ from collections.abc import Sequence
from itertools import chain from itertools import chain
from typing import Any from typing import Any
import docx2txt # type:ignore
from danswer.configs.app_configs import GOOGLE_DRIVE_INCLUDE_SHARED from danswer.configs.app_configs import GOOGLE_DRIVE_INCLUDE_SHARED
from danswer.configs.app_configs import INDEX_BATCH_SIZE from danswer.configs.app_configs import INDEX_BATCH_SIZE
from danswer.configs.constants import DocumentSource from danswer.configs.constants import DocumentSource
@ -151,8 +152,6 @@ def extract_text(file: dict[str, str], service: discovery.Resource) -> str:
mime_type mime_type
== "application/vnd.openxmlformats-officedocument.wordprocessingml.document" == "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
): ):
import docx2txt
response = service.files().get_media(fileId=file["id"]).execute() response = service.files().get_media(fileId=file["id"]).execute()
word_stream = io.BytesIO(response) word_stream = io.BytesIO(response)
with tempfile.NamedTemporaryFile(delete=False) as temp: with tempfile.NamedTemporaryFile(delete=False) as temp: