mirror of
https://github.com/tiennm99/DocsGPT.git
synced 2026-10-03 20:12:55 +00:00
Alex
574f96341e
The backend import package is now docsgpt, the name it will carry on PyPI; application was far too generic to install into anyone's site-packages. git mv plus a mechanical rewrite of every import, dotted string and path reference: 734 Python files, the compose files, Dockerfile, workflows, docs, setup scripts, devcontainer, k8s manifests, vscode config, pytest and coverage config, .gitignore. Behaviour is unchanged. Kept for one release: - A top-level application package whose meta-path finder resolves application.x.y to the already-imported docsgpt.x.y object, so old imports and entry points (celery -A application.app.celery, uvicorn application.asgi:asgi_app) keep working with a FutureWarning. - Celery registers every application.* task name as an alias of its docsgpt.* task on start-up, so messages queued by the previous release still run. The redbeat key prefix moves to redbeat:docsgpt:v2: so schedule entries the previous release wrote are left unread instead of firing twice. The backend image builds from the repository root (docker build -f docsgpt/Dockerfile .) so it can ship the alias package; a root .dockerignore allow-lists docsgpt/ and application/ and keeps caches, local data, .env files, the sample index files and the Dockerfile out. Compose and the image workflows point at the new context.
70 lines
2.0 KiB
Python
70 lines
2.0 KiB
Python
"""Docs parser.
|
|
|
|
Contains parsers for docx, pdf files.
|
|
|
|
"""
|
|
from pathlib import Path
|
|
from typing import Dict
|
|
|
|
from docsgpt.parser.file.base_parser import BaseParser
|
|
from docsgpt.core.settings import settings
|
|
import requests
|
|
|
|
class PDFParser(BaseParser):
|
|
"""PDF parser."""
|
|
|
|
def _init_parser(self) -> Dict:
|
|
"""Init parser."""
|
|
return {}
|
|
|
|
def parse_file(self, file: Path, errors: str = "ignore") -> str:
|
|
"""Parse file."""
|
|
if settings.PARSE_PDF_AS_IMAGE:
|
|
doc2md_service = "https://llm.arc53.com/doc2md"
|
|
# alternatively you can use local vision capable LLM
|
|
with open(file, "rb") as file_loaded:
|
|
files = {'file': file_loaded}
|
|
response = requests.post(doc2md_service, files=files, timeout=100)
|
|
data = response.json()["markdown"]
|
|
return data
|
|
|
|
try:
|
|
from pypdf import PdfReader
|
|
except ImportError:
|
|
raise ValueError("pypdf is required to read PDF files.")
|
|
text_list = []
|
|
with open(file, "rb") as fp:
|
|
# Create a PDF object
|
|
pdf = PdfReader(fp)
|
|
|
|
# Get the number of pages in the PDF document
|
|
num_pages = len(pdf.pages)
|
|
|
|
# Iterate over every page
|
|
for page_index in range(num_pages):
|
|
# Extract the text from the page
|
|
page = pdf.pages[page_index]
|
|
page_text = page.extract_text()
|
|
text_list.append(page_text)
|
|
text = "\n".join(text_list)
|
|
|
|
return text
|
|
|
|
|
|
class DocxParser(BaseParser):
|
|
"""Docx parser."""
|
|
|
|
def _init_parser(self) -> Dict:
|
|
"""Init parser."""
|
|
return {}
|
|
|
|
def parse_file(self, file: Path, errors: str = "ignore") -> str:
|
|
"""Parse file."""
|
|
try:
|
|
import docx2txt
|
|
except ImportError:
|
|
raise ValueError("docx2txt is required to read Microsoft Word files.")
|
|
|
|
text = docx2txt.process(file)
|
|
|
|
return text |