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.

Sign up for GitHub

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

Jump to bottom

Add Video Metadata to Summary #1

Open

finnless opened this issue Jul 12, 2023 · 0 comments · May be fixed by #5

Owner

finnless commented Jul 12, 2023 •

edited

Loading

Possible approaches:

Change video loader to a custom loader class that inherits from langchain's YoutubeLoader
https://github.com/hwchase17/langchain/blob/560c4dfc98287da1bc0cfc1caebbe86d1e66a94d/langchain/document_loaders/youtube.py#L142-L250
YoutubeLoader creates a document from transcript instead of transcript_pieces.
Or I could just call YoutubeLoader._get_video_info(self) where self only needs a self.video_id

Additional metadata would give the model additional context about the video.

finnless linked a pull request

that will close this issue

Add metadata retrieval #5

Draft

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment