is Github dead btw? when I look at repos that should be popular, they have single digit stars. where did people go?
Timeline
Post
Remote status
Context
3
@kaia got an example of such repo?
@Arwalk
when I looked at https://github.com/reasv/panoptikon it had fewer stars and I was unsure whether it was any good. so I looked at other repos in that space and 95% have zero stars. maybe this was always normal idk
when I looked at https://github.com/reasv/panoptikon it had fewer stars and I was unsure whether it was any good. so I looked at other repos in that space and 95% have zero stars. maybe this was always normal idk
Replies
1
@icedquinn @Arwalk @kaia In fact, in this case there's no generative LLM involved at least at search time.
Although most of the models (some of the embedding and OCR and taggers/classifier models) are actually some form of Transformer. The trend over time has been that transformer-based architectures outperform everything else in more and more tasks.
There's also the captioning models which are just generating text. All in all Panoptikon has configuration for several dozen models built in, for different purposes, and many ways of combining filters that search through their data. But the idea is that you can plug your own weights and models.
In the API, you can even combine filters with AND/OR/NOT operators, basically queries are written in a JSON-based "language" I call PQL, which gets compiled to SQLite SQL queries. The UI is more rigid, but it does have a lot of filters. It's a bit busy though, and even I sometimes struggle to find the right switch.
I'd like to improve on that at some point, when I have time. Overall I like the UI though, and I use it every day so it's not that bad.
Although most of the models (some of the embedding and OCR and taggers/classifier models) are actually some form of Transformer. The trend over time has been that transformer-based architectures outperform everything else in more and more tasks.
There's also the captioning models which are just generating text. All in all Panoptikon has configuration for several dozen models built in, for different purposes, and many ways of combining filters that search through their data. But the idea is that you can plug your own weights and models.
In the API, you can even combine filters with AND/OR/NOT operators, basically queries are written in a JSON-based "language" I call PQL, which gets compiled to SQLite SQL queries. The UI is more rigid, but it does have a lot of filters. It's a bit busy though, and even I sometimes struggle to find the right switch.
I'd like to improve on that at some point, when I have time. Overall I like the UI though, and I use it every day so it's not that bad.