LLM/DocsGPT
1
0
Fork 0
mirror of https://github.com/arc53/DocsGPT.git synced 2025-12-01 17:43:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

new: added ExcelParser(tested) to read .xlsx files

Browse Source
This commit is contained in:
devendra.parihar
2024-10-01 22:03:10 +05:30
parent af1b81097f
commit 7794129929
8 changed files with 116 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
application/parser/file/bulk.py
View File

@@ -10,13 +10,14 @@ 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.file.tabular_parser import PandasCSVParser,ExcelParser
from application.parser.schema.base import Document
DEFAULT_FILE_EXTRACTOR: Dict[str, BaseParser] = {
".pdf": PDFParser(),
".docx": DocxParser(),
".csv": PandasCSVParser(),
".xlsx":ExcelParser(),
".epub": EpubParser(),
".md": MarkdownParser(),
".rst": RstParser(),