-
Notifications
You must be signed in to change notification settings - Fork 1.4k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
feat: Add MP3Reader class for mp3 file reader #194
base: main
Are you sure you want to change the base?
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Hi @Deepchavda007,
I believe this PR is not finished yet. Please add the Reader to the list of file extractors and make it visible in the UI.
References:
kotaemon/libs/kotaemon/kotaemon/indices/ingests/files.py
Lines 38 to 54 in e2bd78e
KH_DEFAULT_FILE_EXTRACTORS: dict[str, BaseReader] = { | |
".xlsx": PandasExcelReader(), | |
".docx": unstructured, | |
".pptx": unstructured, | |
".xls": unstructured, | |
".doc": unstructured, | |
".html": HtmlReader(), | |
".mhtml": MhtmlReader(), | |
".png": unstructured, | |
".jpeg": unstructured, | |
".jpg": unstructured, | |
".tiff": unstructured, | |
".tif": unstructured, | |
".pdf": PDFThumbnailReader(), | |
".txt": TxtReader(), | |
".md": TxtReader(), | |
} |
@cin-albert Implemented the changes as per your suggestion. Please review the updated code. Thank you! |
@taprosoft @cin-albert Is there anything else needed from my end, or any additional feedback before it can be merged? Thanks for your time! |
Description
Summary: This PR introduces a new feature that adds the
MP3Reader
class for reading and processing MP3 files to extract text data.Related Issue: This feature was developed to enhance the capability of the project to handle audio input, specifically MP3 files, and convert them into a textual format
Type of change
Checklist