#NostrFilterRelay module update:
Support custom and hybrid model (Fast Inference for CPU-only device) has been merged. Good news to those who want to self-host in CPU-only device. We've also tested it in mobile phone (using proot and termux) and learn how fast its inference process (milliseconds).
What if when your Nostr client translated a note it would also publish the translated version?
Other users would benefit and we wouldn’t need to spend as much on translation services.
Translated notes could include meta data like the language pair, provider, etc.
cc nostr:npub1gcxzte5zlkncx26j68ez60fzkvtkm9e0vrwdcvsjakxf9mu9qewqlfnj5z nostr:npub1n0sturny6w9zn2wwexju3m6asu7zh7jnv2jt2kx6tlmfhs7thq0qnflahe
Although don't have translation data, there are language classification data for kind1 notes in
wss://nfrelay.app
Can be fetched with filter:
{"kinds":[9978],"#t":["nostr-language-classification"]}
Currently it is in custom kind. It will be migrated into NIP-32 format in the future. Maybe, others can use that.
"Relays are not hot product" - Someone probably.
I think it is probably due to main focus development in Nostr is frontend Nostr clients and some other stuffs. 😅
I think it is probably not. Notes event from mostr bridge has "proxy" tag which linked to original fediverse instance url. If you can query relay manually then you can check based on those proxy tag.
As regular user we can just follow account that we are interested.
blyat - First stable release
Another #nostr relay aggregator after #bostr.
https://github.com/Yonle/blyat/releases/tag/0.0.1
Это первый стабильный релиз блата после многочисленных промышленных тестов
Установите эту версию с помощью следующей команды:
```
go install github.com/Yonle/blyat@v0.0.1
```
После установки вы можете перезапустить существующую установку
Oh finally bostr rewrite or its sibling 👀
Kurangnya tinggal dikasih latar palet warna abu-abu aja ini 😅
Iya, Primal lebih simpel mudah dipahami. Amethyst lengkap paket gado-gado, sayangnya yg awam bakal bingung. Klien Nostr gak cukup satu deh pokoknya 😅
Primal yg belum support Amber. Nostrudel sesama klien web sudah support Amber. Klien lain yg support NIP-46 juga bisa login Amber seharusnya.
Foto dengan figura bunga itu loh 😅
In the last few days, I have some experiments with traditional #MachineLearning algorithms for toxicity classification. Instead of using GPU, the trained model can be utilized only using CPU with fast performance (milliseconds). Good news for those who can't afford GPU.
The performance result is satisfactory and comparable to top state of the art model such as "detoxify/unbiased-small" model. This model will be included for #NostrFilterRelay module https://nostrcheck.me/media/2b67e480b7f99d2835684a8f7276d86edbe8e318ea55cf77ccfd559c5f24f645/d8a67688414deaccc639628633a2c5793cf96949dc16301e113e9678172d889a.webp next update.
Update:
Jupyter Notebook example for training has been merged in main branch including pre-trained model. The model will be integrated into API as additional option in the next update.
Release 1.3.0 nostr-php helper library
https://github.com/nostrver-se/nostr-php/releases/tag/1.3.0
Extending NIP-01 with fetching events from relays.
Initial code PR submitted by nostr:npub1ap9fscjl92zclacmaa0nneurr5js85ymuem6ew0ftu8f6eztvpds8qchga 🙏 All zaps on this note will go to him!
Also a huge shoutout to nostr:npub10pensatlcfwktnvjjw2dtem38n6rvw8g6fv73h84cuacxn4c28eqyfn34f for giving me the opportunity to work on the further development of this library 🫡
#PHP #NostrPHP
Awesome, thank you for the works 🙏
Look between both eyes in the middle
> since keeping the notes in the ram is getting costlier, i want to divide nos.lol into two.
Oh, did you set "noReadAhead = false" in lol and mom strfry.conf? I have change it to "true" since my relay database has already bigger than server RAM 😅
What I did as trick to keep some events fresh in memory cache was running cron script that fetch events every hour:
nosdump --kinds 0,1,6,7,9735 --since 24h ws://172.17.0.100:7777 > /dev/null 2>&1
It will force/trick strfry and makes 24 hour last common events fresh in it's memory cache.
> i need a proxy that does this:
I think the one that probably fulfill some of your requirements is bostr proxy relay. It can read from multiple relays. I'm not sure if it can be set to write only 1 relay but read from 2 relays like you said. If not then you need to modify it a little bit.
https://github.com/yonle/bostr
Unfortunately, the proxy relay I'm using currently only support in one server as it has already fulfill my requirements for now. I think I will also probably implement that in future.
Yes, wss://nfrelay.app (demo relay) has been connected to major relays (20+) including nos.lol, nostr.mom, nostr.band
Yes, currently the code were implemented by looking image url file in notes text -> temporary download -> preprocess/resize image -> classify image using tensorflow pretrained model. Quite exhausting to process all notes 😅
Oh, thank you, if you don't mind to share it by DM. Agree with that, especially for the spammers abuse. I use regex filter and anti duplication policy for spam management.
Yes I have run custom aggregator relay with filter parameters/settings (like filter.nostr.wine )
This is the package code for my relay
https://github.com/atrifat/nostr-filter-relay
which needs several separated modules (Language detection, SFW detection, Toxicity/hate speech detection) listed as its dependencies. All modules can be run using CPU.
Are you Indonesian? Mas Fabian? 👀
Kalau benar, Cc nostr:npub1cdak4q4f3h3k3sgyh0rd5dj4w8k95f3mquzh6z3ew76vqkh60e3slyczgz Nostur klien Nostr buatan anak bangsa 🫡
Interesting. What is your LLM prompt to achieve that?
Have you tried using text transformer embedding model and use vector distance to measure similarity for spam rate limit?
In the last few days, I have some experiments with traditional #MachineLearning algorithms for toxicity classification. Instead of using GPU, the trained model can be utilized only using CPU with fast performance (milliseconds). Good news for those who can't afford GPU.
The performance result is satisfactory and comparable to top state of the art model such as "detoxify/unbiased-small" model. This model will be included for #NostrFilterRelay module https://nostrcheck.me/media/2b67e480b7f99d2835684a8f7276d86edbe8e318ea55cf77ccfd559c5f24f645/d8a67688414deaccc639628633a2c5793cf96949dc16301e113e9678172d889a.webp next update.
To those who want early sneak peek 👀
https://github.com/atrifat/hate-speech-detector-api/tree/wip-train-traditional-ml
Full training code will be pushed in main branch soon.