siyuan-note / siyuan

A privacy-first, self-hosted, fully open source personal knowledge management software, written in typescript and golang.
https://b3log.org/siyuan
GNU Affero General Public License v3.0
22.73k stars 1.6k forks source link

Feature: Whole Blog Processing #13160

Closed TomLucidor closed 2 hours ago

TomLucidor commented 2 hours ago

In what scenarios do you need this feature?

There are blogs out there with a fun and long history that can be turned into a knowledge base.

Describe the optimal solution

  1. Crawl the whole blog and index URLs of the article entries
  2. Get the contents of article entries and cache them locally
  3. Run it through AI to summarize each entry (e.g. Chain-of-Density)
  4. If necessary, summarize sections or paragraphs of the article
  5. Custer articles from the same blog based on topic
  6. Extending blog indexing power to blogosphere level (sites with similar topics)

Describe the candidate solution

No response

Other information

No response

88250 commented 2 hours ago

It is recommended to consider using a plug-in to extend this function, thank you.

TomLucidor commented 2 hours ago

@88250 where is the plugin repo then? Not plugin building, but whole repo for the collection of tools made by the community?

88250 commented 2 hours ago

https://github.com/siyuan-note/bazaar

TomLucidor commented 1 hour ago

@88250 thanks but that is a software index, not a human-readable one like an "Awesome" README. Are there anything more legible for community idea-sharing?

88250 commented 1 hour ago

You can see the currently available plugins in SiYuan - Settings - Marketplace