KeyArgo
/
private-gpt
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

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

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