github/privateGPT
1
0
Fork 1
mirror of https://github.com/imartinez/privateGPT.git synced 2025-06-27 15:58:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add .doc .ppt (Word and PowerPoint 97/2003 formats)

Browse Source
This commit is contained in:
Fabio Rossini Sluzala 2023-05-17 12:04:16 -03:00
parent 355b4be7c0
commit 66a9f9cde0
No known key found for this signature in database
GPG Key ID: F9D569BBF49F437B
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
ingest.py
View File

@ -32,6 +32,7 @@ LOADER_MAPPING = {
".csv": (CSVLoader, {}),
# ".docx": (Docx2txtLoader, {}),
".docx": (UnstructuredWordDocumentLoader, {}),
".doc": (UnstructuredWordDocumentLoader, {}),
".enex": (EverNoteLoader, {}),
".eml": (UnstructuredEmailLoader, {}),
".epub": (UnstructuredEPubLoader, {}),
@ -40,6 +41,7 @@ LOADER_MAPPING = {
".odt": (UnstructuredODTLoader, {}),
".pdf": (PDFMinerLoader, {}),
".pptx": (UnstructuredPowerPointLoader, {}),
".ppt": (UnstructuredPowerPointLoader, {}),
".txt": (TextLoader, {"encoding": "utf8"}),
# Add more mappings for other file extensions and loaders as needed
}