Skip to content
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

Readable and structured Markdown #7

Open
damienlaine opened this issue Feb 3, 2025 · 2 comments · May be fixed by #12
Open

Readable and structured Markdown #7

damienlaine opened this issue Feb 3, 2025 · 2 comments · May be fixed by #12
Assignees
Labels

Comments

@damienlaine
Copy link
Member

Summary: Implement a feature that converts transcriptions into well-structured and readable Markdown documents, enhancing accessibility and readability. This should be a new class of "Service" in LLM-Gateway. We have "summary" already. Maybe "Structured Document".

Description: Drawing inspiration from yt2doc, this feature aims to:

  • Structured Formatting: Organize transcriptions with appropriate line breaks and paragraphs to improve readability.

  • Topic Segmentation: Automatically detect and segment topics within the transcription, adding relevant headings and subheadings.

  • Table of Contents: Generate a table of contents based on the identified sections and headings for easy navigation.

  • Timestamping: Include timestamps for each section or paragraph to reference the original content easily.

@damienlaine damienlaine added the 🏡 LINAGORA Roadmap Voted features label Feb 3, 2025
@damienlaine damienlaine moved this to Considering in LinTO Roadmap Feb 3, 2025
@damienlaine damienlaine moved this from Considering to Investigating in LinTO Roadmap Feb 3, 2025
@damienlaine damienlaine moved this from Investigating to Doing in LinTO Roadmap Mar 11, 2025
@damienlaine
Copy link
Member Author

@htagourti Shall we close this issue ?

@tjiho tjiho moved this from Doing to In preview / Experimental in LinTO Roadmap Mar 13, 2025
@htagourti htagourti self-assigned this Mar 13, 2025
@htagourti htagourti linked a pull request Mar 13, 2025 that will close this issue
@htagourti
Copy link

@damienlaine PR linked. This is the version that i showed you last time. Still haven't had the time to run performance benchmarks on the semantic chunker.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
Status: In preview / Experimental
Development

Successfully merging a pull request may close this issue.

2 participants