anything-llm/collector/scripts/watch/convert/as_pdf.py

37 lines
1.3 KiB
Python
Raw Normal View History

2023-06-04 04:28:07 +02:00
import os
from langchain.document_loaders import PyPDFLoader
from slugify import slugify
from ..utils import guid, file_creation_time, write_to_server_documents, move_source
from ...utils import tokenize
# Process all text-related documents.
def as_pdf(**kwargs):
parent_dir = kwargs.get('directory', 'hotdir')
filename = kwargs.get('filename')
ext = kwargs.get('ext', '.txt')
remove = kwargs.get('remove_on_complete', False)
2023-06-04 04:28:07 +02:00
fullpath = f"{parent_dir}/{filename}{ext}"
loader = PyPDFLoader(fullpath)
pages = loader.load_and_split()
print(f"-- Working {fullpath} --")
for page in pages:
pg_num = page.metadata.get('page')
print(f"-- Working page {pg_num} --")
content = page.page_content
data = {
'id': guid(),
'url': "file://"+os.path.abspath(f"{parent_dir}/processed/{filename}{ext}"),
'title': f"{filename}_pg{pg_num}{ext}",
'description': "a custom file uploaded by the user.",
'published': file_creation_time(fullpath),
'wordCount': len(content),
'pageContent': content,
'token_count_estimate': len(tokenize(content))
}
write_to_server_documents(data, f"{slugify(filename)}-pg{pg_num}-{data.get('id')}")
move_source(parent_dir, f"{filename}{ext}", remove=remove)
2023-06-04 04:28:07 +02:00
print(f"[SUCCESS]: {filename}{ext} converted & ready for embedding.\n")