github/privateGPT
1
0
Fork 1
mirror of https://github.com/imartinez/privateGPT.git synced 2025-09-08 10:39:33 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #254 from Fabio3rs/formatOffice97-2003

Browse Source 
Add .doc .ppt (Word and PowerPoint 97/2003 formats)
This commit is contained in:
Iván Martínez
2023-05-18 23:49:40 +02:00
committed by GitHub
parent 1590c5890f ec126b51d8
commit b9f8dc312f
2 changed files with 4 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ingest.py
View File

@@ -28,6 +28,7 @@ from constants import CHROMA_SETTINGS
LOADER_MAPPING = {
".csv": (CSVLoader, {}),
# ".docx": (Docx2txtLoader, {}),
".doc": (UnstructuredWordDocumentLoader, {}),
".docx": (UnstructuredWordDocumentLoader, {}),
".enex": (EverNoteLoader, {}),
".eml": (UnstructuredEmailLoader, {}),
@@ -36,6 +37,7 @@ LOADER_MAPPING = {
".md": (UnstructuredMarkdownLoader, {}),
".odt": (UnstructuredODTLoader, {}),
".pdf": (PDFMinerLoader, {}),
".ppt": (UnstructuredPowerPointLoader, {}),
".pptx": (UnstructuredPowerPointLoader, {}),
".txt": (TextLoader, {"encoding": "utf8"}),
# Add more mappings for other file extensions and loaders as needed