eUgEntOptIc44/MarginaliaSearch
1
1
Fork 0
mirror of https://github.com/MarginaliaSearch/MarginaliaSearch.git synced 2025-10-05 21:22:39 +02:00
Code Issues Activity

Update ROADMAP.md

Browse Source
This commit is contained in:
Viktor
2025-06-07 14:01:01 +02:00
committed by GitHub
parent 37aaa90dc9
commit 39a055aa94
1 changed files with 8 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
ROADMAP.md
View File

@@ -38,14 +38,6 @@ associated with each language added, at least a models file or two, as well as s
It would be very helpful to find a speaker of a large language other than English to help in the fine tuning.
## Support for binary formats like PDF
The crawler needs to be modified to retain them, and the conversion logic needs to parse them.
The documents database probably should have some sort of flag indicating it's a PDF as well.
PDF parsing is known to be a bit of a security liability so some thought needs to be put in
that direction as well.
## Custom ranking logic
Stract does an interesting thing where they have configurable search filters.
@@ -66,6 +58,14 @@ One of the search engine's biggest limitations right now is that it does not ind
# Completed
## Support for binary formats like PDF (COMPLETED 2025-05)
The crawler needs to be modified to retain them, and the conversion logic needs to parse them.
The documents database probably should have some sort of flag indicating it's a PDF as well.
PDF parsing is known to be a bit of a security liability so some thought needs to be put in
that direction as well.
## Web Design Overhaul (COMPLETED 2025-01)
The design is kinda clunky and hard to maintain, and needlessly outdated-looking.