anything-llm/collector/scripts/watch/convert/as_text.py
Timothy Carambat c4eb46ca19
Upload and process documents via UI + document processor in docker image (#65)
* implement dnd uploader
show file upload progress
write files to hotdirector
build simple flaskAPI to process files one off

* move document processor calls to util
build out dockerfile to run both procs at the same time
update UI to check for document processor before upload
* disable pragma update on boot
* dockerfile changes

* add filetype restrictions based on python app support response and show rejected files in the UI

* cleanup

* stub migrations on boot to prevent exit condition

* update CF template for AWS deploy
2023-06-16 16:01:27 -07:00

29 lines
1.1 KiB
Python

import os
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_text(**kwargs):
parent_dir = kwargs.get('directory', 'hotdir')
filename = kwargs.get('filename')
ext = kwargs.get('ext', '.txt')
remove = kwargs.get('remove_on_complete', False)
fullpath = f"{parent_dir}/{filename}{ext}"
content = open(fullpath).read()
print(f"-- Working {fullpath} --")
data = {
'id': guid(),
'url': "file://"+os.path.abspath(f"{parent_dir}/processed/{filename}{ext}"),
'title': f"{filename}{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)}-{data.get('id')}")
move_source(parent_dir, f"{filename}{ext}", remove=remove)
print(f"[SUCCESS]: {filename}{ext} converted & ready for embedding.\n")