Looking for an RSS aggregator/summarizer/maybe-LLM thing
-
Basically I want a self-hosted version of Google News. If 10 feeds have near-identical coverage of the same story, I want just 1 item, with an option to see the other 9.
I went looking for something like this a couple years ago and found ~nothing. Checked again today and now there are Entirely Too Many Things.
Hoping to find something a bit more established than somebody's abandoned weekend project. There seems to be an awful lot of that out there right now.
Looking for XML or similar output. Do not need or necessarily want any sort of front end.
-
Basically I want a self-hosted version of Google News. If 10 feeds have near-identical coverage of the same story, I want just 1 item, with an option to see the other 9.
I went looking for something like this a couple years ago and found ~nothing. Checked again today and now there are Entirely Too Many Things.
Hoping to find something a bit more established than somebody's abandoned weekend project. There seems to be an awful lot of that out there right now.
Looking for XML or similar output. Do not need or necessarily want any sort of front end.
I've been using miniflux in docker with a miniflux-ai container I found on GitHub, I seem to recall I had issues out of the box and had to tweak it but that was quite a while ago, can't remember the details. I have it configured to generate summaries of a list of feeds in miniflux when it sees new items. Works pretty well, needs to be restarted occasionally but has been just fine for the amount of time it took to setup.
-
Basically I want a self-hosted version of Google News. If 10 feeds have near-identical coverage of the same story, I want just 1 item, with an option to see the other 9.
I went looking for something like this a couple years ago and found ~nothing. Checked again today and now there are Entirely Too Many Things.
Hoping to find something a bit more established than somebody's abandoned weekend project. There seems to be an awful lot of that out there right now.
Looking for XML or similar output. Do not need or necessarily want any sort of front end.
I've been really happy with Fresh-RSS. Someone else on here put me onto about 6 months ago and it's changed how I consume news.
I find the most time consuming part was/is curating my feed but with tools like RSS-Bridge I can really get fine grain control on what makes it through.
On your LLM summarizer question, yes they have several plug-ins. I've recently started piping the whole feed into Gemini and telling it to pick the top 5 and summarize. But I do that in bash and emacs :
-
I've been using miniflux in docker with a miniflux-ai container I found on GitHub, I seem to recall I had issues out of the box and had to tweak it but that was quite a while ago, can't remember the details. I have it configured to generate summaries of a list of feeds in miniflux when it sees new items. Works pretty well, needs to be restarted occasionally but has been just fine for the amount of time it took to setup.
Using Miniflux for more than year now with 0 issue so far.
-
Just found this thread from March looking for the exact same thing, with no helpful suggestions unfortunately. I think folks either don't understand what's being asked or don't understand how Google News works.
-
Basically I want a self-hosted version of Google News. If 10 feeds have near-identical coverage of the same story, I want just 1 item, with an option to see the other 9.
I went looking for something like this a couple years ago and found ~nothing. Checked again today and now there are Entirely Too Many Things.
Hoping to find something a bit more established than somebody's abandoned weekend project. There seems to be an awful lot of that out there right now.
Looking for XML or similar output. Do not need or necessarily want any sort of front end.
N8n can do a lot of this, easy too.
-
Basically I want a self-hosted version of Google News. If 10 feeds have near-identical coverage of the same story, I want just 1 item, with an option to see the other 9.
I went looking for something like this a couple years ago and found ~nothing. Checked again today and now there are Entirely Too Many Things.
Hoping to find something a bit more established than somebody's abandoned weekend project. There seems to be an awful lot of that out there right now.
Looking for XML or similar output. Do not need or necessarily want any sort of front end.
I've searched for something like this in the past and didn't find anything.
I've though of hacking together a few scripts or 8n8 to interface with freshrss to do this but it's far down my list
-
Basically I want a self-hosted version of Google News. If 10 feeds have near-identical coverage of the same story, I want just 1 item, with an option to see the other 9.
I went looking for something like this a couple years ago and found ~nothing. Checked again today and now there are Entirely Too Many Things.
Hoping to find something a bit more established than somebody's abandoned weekend project. There seems to be an awful lot of that out there right now.
Looking for XML or similar output. Do not need or necessarily want any sort of front end.
Why though? The joy is reading not reading bad versions of the same content?
-
Why though? The joy is reading not reading bad versions of the same content?
I'm with OP on this one.
I enjoy reading quality content, not just the act of reading.
I think the idea is that by using an LLM to help sort through the drivel you have more time to do the reading of the quality content.And really, I'm always suspicious of the why when an algorithm suggests me an article... Having something less tied directly to a companies bottom line might help me trust the content more.
-
Just found this thread from March looking for the exact same thing, with no helpful suggestions unfortunately. I think folks either don't understand what's being asked or don't understand how Google News works.
Then can you explain how google news works? I never used it, maybe a lot others have also no idea.
From google reader i switched to feedly after google shut it down in 2013, when I started self hosting switched to ttrss, then to freshrss when it became apparent the developer of ttrss is an actual neonazi. It was always working for me so i never looked for a replacement.
-
Basically I want a self-hosted version of Google News. If 10 feeds have near-identical coverage of the same story, I want just 1 item, with an option to see the other 9.
I went looking for something like this a couple years ago and found ~nothing. Checked again today and now there are Entirely Too Many Things.
Hoping to find something a bit more established than somebody's abandoned weekend project. There seems to be an awful lot of that out there right now.
Looking for XML or similar output. Do not need or necessarily want any sort of front end.
Honestly Brave News is the only solution I've found for that. Just go to Brave search and search for "news". It will aggregate the top stories of the day, group the different sources, then provide an AI generated digest of the stories upon request.
-
Then can you explain how google news works? I never used it, maybe a lot others have also no idea.
From google reader i switched to feedly after google shut it down in 2013, when I started self hosting switched to ttrss, then to freshrss when it became apparent the developer of ttrss is an actual neonazi. It was always working for me so i never looked for a replacement.
@infeeeee@lemmy.zip It's a matter of duplication.
Say you have 10 feeds from major news publishers in your reader, BBC, NY Times, Le Monde, etc. because you value wide coverage. When the King of England dies you will have 10 nearly identical articles in your feed with the facts of his death from those outlets, plus at least another 10 nearly identical ones reminiscing about his life and impact, and dozens more related ones from various contributors. Your feed will be clogged for days with repeated info about one old dead guy. This is an annoying reality of RSS.
On Google News there will be one box dedicated to His Royal Corpse showing maybe a few stories, semi-randomly selected for relevance by an algorithm. If you want the fire hose coverage it's a click away, but on the front page it's contained and doesn't dominate everything else. I want that for RSS.
-
Basically I want a self-hosted version of Google News. If 10 feeds have near-identical coverage of the same story, I want just 1 item, with an option to see the other 9.
I went looking for something like this a couple years ago and found ~nothing. Checked again today and now there are Entirely Too Many Things.
Hoping to find something a bit more established than somebody's abandoned weekend project. There seems to be an awful lot of that out there right now.
Looking for XML or similar output. Do not need or necessarily want any sort of front end.
Go check out network chucks review of N8N.
He builds a small news aggregator with LLM that crap stuff into discord but you could easily put it anywhere.
-
@infeeeee@lemmy.zip It's a matter of duplication.
Say you have 10 feeds from major news publishers in your reader, BBC, NY Times, Le Monde, etc. because you value wide coverage. When the King of England dies you will have 10 nearly identical articles in your feed with the facts of his death from those outlets, plus at least another 10 nearly identical ones reminiscing about his life and impact, and dozens more related ones from various contributors. Your feed will be clogged for days with repeated info about one old dead guy. This is an annoying reality of RSS.
On Google News there will be one box dedicated to His Royal Corpse showing maybe a few stories, semi-randomly selected for relevance by an algorithm. If you want the fire hose coverage it's a click away, but on the front page it's contained and doesn't dominate everything else. I want that for RSS.
Are you telling us we should put a bet on Charlie copping it soon?
-
I've been really happy with Fresh-RSS. Someone else on here put me onto about 6 months ago and it's changed how I consume news.
I find the most time consuming part was/is curating my feed but with tools like RSS-Bridge I can really get fine grain control on what makes it through.
On your LLM summarizer question, yes they have several plug-ins. I've recently started piping the whole feed into Gemini and telling it to pick the top 5 and summarize. But I do that in bash and emacs :
This looks amazing , appreciate the steer on it.
I don't suppose you know if Kindle delivery is supported at all? I use my own dockerized fork of news-sender-kindle which works well in terms of folding everything down into a .epub, but the RSS control is a little fiddly, it doesn't let me preview the articles and amending feeds involves SSHing into an txt file on my server (not ideal).
-
I'm with OP on this one.
I enjoy reading quality content, not just the act of reading.
I think the idea is that by using an LLM to help sort through the drivel you have more time to do the reading of the quality content.And really, I'm always suspicious of the why when an algorithm suggests me an article... Having something less tied directly to a companies bottom line might help me trust the content more.
LLMs aren't sorting algorithms, they're fancy keyboard predictions.
-
Basically I want a self-hosted version of Google News. If 10 feeds have near-identical coverage of the same story, I want just 1 item, with an option to see the other 9.
I went looking for something like this a couple years ago and found ~nothing. Checked again today and now there are Entirely Too Many Things.
Hoping to find something a bit more established than somebody's abandoned weekend project. There seems to be an awful lot of that out there right now.
Looking for XML or similar output. Do not need or necessarily want any sort of front end.
Remember that Google News has RSS feeds! They are very well hidden, but they are there.
However, they are also a bit bad.
I started https://github.com/las-noticias/news-rss to postprocess a bit Google News RSS feeds and also play with categorization. I found spaCy worked well to find "topics", but unfortunately I lost steam.
