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.

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

Implement Smart Truncation for extracted article content #29608

Closed
Tracked by #35733
nullhook opened this issue Apr 10, 2023 · 3 comments
Closed
Tracked by #35733

Implement Smart Truncation for extracted article content #29608

nullhook opened this issue Apr 10, 2023 · 3 comments
Assignees
@nullhook
Labels
browser-ai closed/duplicate Issue has already been reported feature/leo/context-size OS/Desktop priority/P4 Planned work. We expect to get to it "soon". QA/No

Comments

@nullhook
Copy link

nullhook commented Apr 10, 2023 •
edited
Loading

Currently, the article distiller feature truncates the content naively to 9k characters. However, this can lead to summaries that look incomplete and cut off from sentence run-ons.

To improve the quality of the generated summaries, it would be beneficial to implement smart truncation in the article summary feature. This would involve in capturing all parts of the content necessary for a coherent summary, while still meeting the character limitation requirements.

One possible implementation of smart truncation would be to extract a sentence from each paragraph of the content, ensuring that the summary includes key information from all parts of the article. Additionally, the feature could prioritize summarizing the introduction and conclusion sections of the article, as they typically provide a good overview of the content.
@nullhook nullhook changed the title Implement Smart Truncation for Article Summaries Implement Smart Truncation for Article content Apr 10, 2023
@nullhook nullhook changed the title Implement Smart Truncation for Article content Implement Smart Truncation for extracted article content Apr 10, 2023
@bbondy bbondy moved this to Todo in Browser AI May 10, 2023
@nullhook nullhook self-assigned this May 30, 2023
@rebron rebron added the priority/P4 Planned work. We expect to get to it "soon". label Jun 28, 2023
@AlecoDigitalCreator
Copy link

👍

@bbondy bbondy added the QA/No label Sep 4, 2023
@stevelaskaridis
Copy link

Related: https://github.com/brave/aichat/issues/11#issuecomment-1687622659

@mattmcalister mattmcalister mentioned this issue Jan 31, 2024
Closed
18 tasks
@mattmcalister mattmcalister added the closed/duplicate Issue has already been reported label May 29, 2024
@mattmcalister
Copy link

Duplicate #36801

@github-project-automation github-project-automation bot moved this from Todo to Done in Browser AI May 29, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@nullhook nullhook

Labels
browser-ai closed/duplicate Issue has already been reported feature/leo/context-size OS/Desktop priority/P4 Planned work. We expect to get to it "soon". QA/No
Projects
Browser AI
Status: Done
Milestone
No milestone
Development

No branches or pull requests
6 participants
@mattmcalister @bbondy @stevelaskaridis @rebron @nullhook @AlecoDigitalCreator