sij/khoj
1
0
Fork 0
mirror of https://github.com/khoj-ai/khoj.git synced 2024-11-23 23:48:56 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 16

Fix randint import from random when creating filenames for tmp

Browse source
This commit is contained in:
sabaimran 2024-11-09 19:17:18 -08:00
parent 92b6b3ef7b
commit bd55028115
2 changed files with 4 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
src/khoj/processor/content/docx/docx_to_entries.py
View file

@ -1,7 +1,7 @@
import logging import logging
import os import os
from datetime import datetime from datetime import datetime
from random import random from random import randint
from typing import Dict, List, Tuple from typing import Dict, List, Tuple
from langchain_community.document_loaders import Docx2txtLoader from langchain_community.document_loaders import Docx2txtLoader
@ -95,7 +95,7 @@ class DocxToEntries(TextToEntries):
"""Extract text from specified DOCX file""" """Extract text from specified DOCX file"""
try: try:
timestamp_now = datetime.utcnow().timestamp() timestamp_now = datetime.utcnow().timestamp()
random_suffix = random.randint(0, 1000) random_suffix = randint(0, 1000)
tmp_file = f"tmp_docx_file_{timestamp_now}_{random_suffix}.docx" tmp_file = f"tmp_docx_file_{timestamp_now}_{random_suffix}.docx"
docx_entry_by_pages = [] docx_entry_by_pages = []
with open(tmp_file, "wb") as f: with open(tmp_file, "wb") as f:

4
src/khoj/processor/content/pdf/pdf_to_entries.py
View file

@ -2,7 +2,7 @@ import base64
import logging import logging
import os import os
from datetime import datetime from datetime import datetime
from random import random from random import randint
from typing import Dict, List, Tuple from typing import Dict, List, Tuple
from langchain_community.document_loaders import PyMuPDFLoader from langchain_community.document_loaders import PyMuPDFLoader
@ -99,7 +99,7 @@ class PdfToEntries(TextToEntries):
try: try:
# Write the PDF file to a temporary file, as it is stored in byte format in the pdf_file object and the PDF Loader expects a file path # Write the PDF file to a temporary file, as it is stored in byte format in the pdf_file object and the PDF Loader expects a file path
timestamp_now = datetime.utcnow().timestamp() timestamp_now = datetime.utcnow().timestamp()
random_suffix = random.randint(0, 1000) random_suffix = randint(0, 1000)
tmp_file = f"tmp_pdf_file_{timestamp_now}_{random_suffix}.pdf" tmp_file = f"tmp_pdf_file_{timestamp_now}_{random_suffix}.pdf"
pdf_entry_by_pages = [] pdf_entry_by_pages = []
with open(f"{tmp_file}", "wb") as f: with open(f"{tmp_file}", "wb") as f: