UPDATE: ThreadPoolExecutor

functions.py

@@ -292,13 +292,13 @@ def getLinks(url: str, timeout = 30):
  return list(set([x[:len(x) - 1] if x[-1] == "/" else x for x in uniqueLinks]))
 
 
-def getText(image):
- global reader
- return "\n".join([text[1] for text in reader.readtext(np.array(image.resize((500, 500))), paragraph=True)])
 
 def getTextFromImagePDF(pdfBytes):
+ def getText(image):
+ global reader
+ return "\n".join([text[1] for text in reader.readtext(np.array(image), paragraph=True)])
  allImages = convert_from_bytes(pdfBytes)
- with ThreadPoolExecutor(max_workers = 25) as p:
+ with ThreadPoolExecutor(max_workers = 32) as p:
  texts = list(p.map(getText, allImages))
  return "\n\n\n".join(texts)