Dataview:
list from [[]] and !outgoing([[]])🧲 Published
Deployment:
GitHub:
🎟 Features
Existing
Todo
🧾 Project Description
Blurt
This is a continuation of the Course-Content-Vectorizer, I want to make a tool with which I can search through a large corpus of text to find relevant passages, and resources.
To do this, im going to tackle it in stages:
Part 1:
Resource scraping. I already did a part of this with the Course-Content-Vectorizer, but now I want to extend it to parsing PDFs, and maybe scraping text from youtube playlists too?
Part 2:
Set up a text extraction pipeline. I want to support smart text extraction, vectorization, and search for:
- Raw transcripts
- Lecture Slides
- Research Paper pdfs
- and more as I come up with things I want to put in the DB!
Part 3:
A easy to distribute and download frontend!
I plan on doing this through Tauri
📂 Project Logs
Resources
Tauri Learn Page
Tauri Guide Book
🔗 -> Links
Resources
- Put useful links here
Connections
- Link all related words