这是indexloc提供的服务，不要输入任何密码
Skip to content

Split large PDFS into subfolder in documents #176

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Aug 4, 2023
Merged

Split large PDFS into subfolder in documents #176

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions collector/scripts/watch/convert/as_pdf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
import os
import os, time
from langchain.document_loaders import PyPDFLoader
from slugify import slugify
from ..utils import guid, file_creation_time, write_to_server_documents, move_source
Expand All @@ -11,6 +11,7 @@ def as_pdf(**kwargs):
ext = kwargs.get('ext', '.txt')
remove = kwargs.get('remove_on_complete', False)
fullpath = f"{parent_dir}/{filename}{ext}"
destination = f"../server/storage/documents/{slugify(filename)}-{int(time.time())}"

loader = PyPDFLoader(fullpath)
pages = loader.load_and_split()
Expand All @@ -31,7 +32,7 @@ def as_pdf(**kwargs):
'pageContent': content,
'token_count_estimate': len(tokenize(content))
}
write_to_server_documents(data, f"{slugify(filename)}-pg{pg_num}-{data.get('id')}")
write_to_server_documents(data, f"{slugify(filename)}-pg{pg_num}-{data.get('id')}", destination)

move_source(parent_dir, f"{filename}{ext}", remove=remove)
print(f"[SUCCESS]: {filename}{ext} converted & ready for embedding.\n")
4 changes: 2 additions & 2 deletions collector/scripts/watch/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,8 +28,8 @@ def move_source(working_dir='hotdir', new_destination_filename='', failed=False,
os.replace(f"{working_dir}/{new_destination_filename}", f"{destination}/{new_destination_filename}")
return

def write_to_server_documents(data, filename):
destination = f"../server/storage/documents/custom-documents"
def write_to_server_documents(data, filename, override_destination = None):
destination = f"../server/storage/documents/custom-documents" if override_destination == None else override_destination
if os.path.exists(destination) == False: os.makedirs(destination)
with open(f"{destination}/{filename}.json", 'w', encoding='utf-8') as file:
json.dump(data, file, ensure_ascii=True, indent=4)