yujunjun/haystack
1
0
Fork 0
mirror of https://github.com/deepset-ai/haystack.git synced 2025-09-25 08:04:49 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: do not reference package directory in PDFToTextOCRConverter.convert() (#3478)

Browse Source 
* remove weird temp path from PDFToTextOCRConverter.convert()

* remove debug lines

* remove os import
This commit is contained in:
Sara Zan 2022-10-31 12:48:43 +01:00 committed by GitHub
parent 17cd79e2c8
commit adc982a624
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
haystack/nodes/file_converter/pdf.py
View File

@ -1,6 +1,5 @@
from typing import List, Optional, Dict, Any
import os
import logging
import tempfile
import subprocess
@ -252,7 +251,7 @@ class PDFToTextOCRConverter(BaseConverter):
try:
images = convert_from_path(file_path)
for image in images:
temp_img = tempfile.NamedTemporaryFile(dir=os.path.dirname(os.path.realpath(__file__)), suffix=".jpeg")
temp_img = tempfile.NamedTemporaryFile(suffix=".jpeg")
image.save(temp_img.name)
pages.append(self.image_2_text.convert(file_path=temp_img.name)[0].content)
except Exception as exception: