mirror of
https://github.com/Mintplex-Labs/anything-llm.git
synced 2025-03-25 23:24:43 +00:00
3e78476739
* cosmetic changes to be compatible to hadolint * common configuration for most editors until better plugins comes up * Changes on PDF metadata, using PyMuPDF (faster and more compatible) * small changes on other file ingestions in order to try to keep the fields equal * Lint, review, and review * fixed unknown chars * Use PyMuPDF for pdf loading for 200% speed increase linting --------- Co-authored-by: Francisco Bischoff <franzbischoff@gmail.com> Co-authored-by: Francisco Bischoff <984592+franzbischoff@users.noreply.github.com>
66 lines
2.4 KiB
Python
66 lines
2.4 KiB
Python
import os
|
|
from langchain.document_loaders import Docx2txtLoader, UnstructuredODTLoader
|
|
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_docx(**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}"
|
|
|
|
loader = Docx2txtLoader(fullpath)
|
|
data = loader.load()[0]
|
|
content = data.page_content
|
|
|
|
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 bescription
|
|
'docSource': 'Docx Text file uploaded by the user.',
|
|
'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")
|
|
|
|
def as_odt(**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}"
|
|
|
|
loader = UnstructuredODTLoader(fullpath)
|
|
data = loader.load()[0]
|
|
content = data.page_content
|
|
|
|
print(f"-- Working {fullpath} --")
|
|
data = {
|
|
'id': guid(),
|
|
'url': "file://"+os.path.abspath(f"{parent_dir}/processed/{filename}{ext}"),
|
|
'title': f"{filename}{ext}",
|
|
'author': 'Unknown', # TODO: Find a better author
|
|
'description': 'Unknown', # TODO: Find a better bescription
|
|
'docSource': 'ODT Text file uploaded by the user.',
|
|
'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")
|