mirror of
https://github.com/Mintplex-Labs/anything-llm.git
synced 2024-11-04 22:10:12 +01:00
38 lines
1.3 KiB
Python
38 lines
1.3 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()
|
|
|
|
if len(content) == 0:
|
|
print(f"Resulting text content was empty for {filename}{ext}.")
|
|
return(False, f"No text content found in {filename}{ext}")
|
|
|
|
print(f"-- Working {fullpath} --")
|
|
data = {
|
|
'id': guid(),
|
|
'url': "file://"+os.path.abspath(f"{parent_dir}/processed/{filename}{ext}"),
|
|
'title': f"{filename}{ext}",
|
|
'docAuthor': 'Unknown', # TODO: Find a better author
|
|
'description': 'Unknown', # TODO: Find a better description
|
|
'chunkSource': f"{filename}{ext}",
|
|
'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")
|
|
return(True, None)
|