tiennm99/DocsGPT
1
0 Fork 0
mirror of https://github.com/tiennm99/DocsGPT.git synced 2026-10-15 14:16:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix packaging and imports and introduce tests with pytest.

Browse Source 
still issues with celery worker.
This commit is contained in:
Anton Larin committed 2023-08-14 18:20:25 +02:00
1 parent 9a393b4f74
commit 98a97f34f5
23 files changed
+107 -37
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

application/parser/file/bulk.py
+9 -9
View File
@@ -3,15 +3,15 @@ import logging
from pathlib import Path
from typing import Callable, Dict, List, Optional, Union
from parser.file.base import BaseReader
from parser.file.base_parser import BaseParser
from parser.file.docs_parser import DocxParser, PDFParser
from parser.file.epub_parser import EpubParser
from parser.file.html_parser import HTMLParser
from parser.file.markdown_parser import MarkdownParser
from parser.file.rst_parser import RstParser
from parser.file.tabular_parser import PandasCSVParser
from parser.schema.base import Document
from application.parser.file.base import BaseReader
from application.parser.file.base_parser import BaseParser
from application.parser.file.docs_parser import DocxParser, PDFParser
from application.parser.file.epub_parser import EpubParser
from application.parser.file.html_parser import HTMLParser
from application.parser.file.markdown_parser import MarkdownParser
from application.parser.file.rst_parser import RstParser
from application.parser.file.tabular_parser import PandasCSVParser
from application.parser.schema.base import Document
DEFAULT_FILE_EXTRACTOR: Dict[str, BaseParser] = {
".pdf": PDFParser(),