[HN Gopher] Show HN: Recommendarr - AI Driven Recommendations Ba...
___________________________________________________________________
Show HN: Recommendarr - AI Driven Recommendations Based on
Sonarr/Radarr Media
Hello HN! I've built a web app that helps you discover new shows
and movies you'll actually enjoy by: - Connecting to your
Sonarr/Radarr/Plex instances to understand your media library -
Leveraging your Plex watch history for personalized recommendations
- Using the LLM of your choice to generate intelligent suggestions
- Simple setup: Easy integration with your existing media stack -
Flexible AI options: Works with OpenAI-compatible APIs like
OpenRouter, or run locally via LM Studio, Ollama, etc. -
Personalized recommendations: Based on what you actually watch.
While it's still a work in progress, it's already quite functional
and I'd love your feedback!
Author : fingerthieff
Score : 53 points
Date : 2025-03-02 14:25 UTC (8 hours ago)
(HTM) web link (github.com)
(TXT) w3m dump (github.com)
| freedomben wrote:
| Looks super neat! A great idea as well.
|
| Any plans to support jellyfin?
| fingerthieff wrote:
| Thanks!
|
| Jellyfin is definitely on the list to be added, it's probably
| next in line actually. If it's as simple as Plex integration
| I'll be very happy.
|
| Edit - Support Added
| nickthegreek wrote:
| Trakt.tv is the integration you need.
|
| What is the largest library of watched media that this has been
| tested at? I can see this choking on media fanatics watch
| histories.
| fingerthieff wrote:
| Interesting, I've never used Trakt before but that looks pretty
| cool. I could see adding support for that. I'll definitely be
| looking into it.
|
| As for the largest library, I only really know of my own which
| is around 250 series and 250 movies. Not small but not huge.
| Passing all of that info is fine enough, but I'm also curious
| how truly massive libraries or watch histories are handled.
|
| I imagine you would hit the LLM token input limit first if you
| had thousands of series and movies. Definitely need some
| further testing in those cases.
| nickthegreek wrote:
| Ahh ya. Big libraries can have over 30k movies. Emby,
| jellyfin, and plex can also integrate into Trakt. So it's
| already being used in these apps for many users.
| fingerthieff wrote:
| That's good to know, there are ways around the limit of
| course by breaking up the prompt into multiple messages and
| then you're at the mercy of the models context window which
| can be anywhere from 4k to millions.
|
| At some point though like you say, it's going to become
| ineffective and you'd probably want to use the "Sampling"
| mode that is available to only send a random subset of your
| library to model as a general representation. Though how
| well this works on massive library remains to be seen.
| richjdsmith wrote:
| This is really cool, and very well done! Would love to see it
| more on a per-user basis, as I share access with my family and do
| not have similar tastes at all. Perhaps tied in with Overseer API
| and Tautulli to see what users are requesting, then actually
| watching?
| fingerthieff wrote:
| Tautulli proved troublesome in my first attempt at integrating
| it and got put on the back-burner unfortunately. I would really
| like to get it integrated properly so per user recommendations
| could become a thing.
|
| I haven't looked at integrating Overseer yet but that is a good
| idea as well and worth a try at implementing. I'll be adding
| that to my list, thanks for suggestion!
| CharlesW wrote:
| I'm excited to try this! I'd love support for music
| recommendations via Plex music libraries. (Currently, I use a
| script to export my music library to a format suitable for LLM
| analysis.)
| nvarsj wrote:
| Interesting... any more details on how you do that?
| CharlesW wrote:
| With the caveat that it's imperfect and not packaged
| correctly, you can check out music2json.ts at
| https://github.com/CharlesWiltgen/music2json to get the idea.
| In short, I just dump a JSON of artists, albums (with
| genres), and tracks, feed that to an LLM, and then ask it to
| recommend other artists and albums I might like (e.g. "Please
| recommend additional compilations, artists, and albums I may
| like based on this music library"). The biggest problem at
| the moment is that it will often recommend things that are
| already in my library.
| phito wrote:
| This sounds amazing, giving it a try right now
| fingerthieff wrote:
| Hopefully it works well for you! I just pushed up changes for
| adding Jellyfin integration as well, so that should be
| available through the docker hub here soon as well.
| monkaiju wrote:
| I'd love to see support for lidarr, I need way more help with
| music recommendations than TV/Movies
| phinnaeus wrote:
| I wonder if there's way to get access to the music genome data
| that Pandora uses. Would happily pay for an API and it could be
| available outside the US since licensing the music itself to
| stream it isn't needed.
| fingerthieff wrote:
| I'm definitely not opposed to adding Lidarr support, I've never
| personally used it so I may tinker around with it here soon and
| think on how to structure prompts for that etc...
| Nelkins wrote:
| Cool project! Can you explain a little more about how the
| recommendation algorithm works?
| fingerthieff wrote:
| It's hard to really explain how the LLM decides what to
| recommend if I'm honest.
|
| The general idea is I generate a prompt to feed into the LLM
| with specific instructions to use the Sonarr (for example)
| library info which is passed in as a list of series titles. I
| also provide some general guidelines on what it should take
| into account when choosing media to suggest.
|
| After that it's in the hand of the LLM, it will internally
| analyze and recommend shows based on what it believe someone
| might enjoy based on their media library...Given that every LLM
| model is different, how they internally decide what shows to
| recommend will be unique to them. So if you have bad
| suggestions etc..It's best to try a different model.
|
| it provides nice flexibility but in reality my control of the
| actual recommendations are limited to the initial prompt that
| is passed in.
| HyprMusic wrote:
| Does this mean it is limited to the model's internal memory?
| Meaning newer shows won't be in the recommendations because
| they're past the training cut-off?
| fingerthieff wrote:
| That is a likely true to an extent, though it's hard to say
| at what point it cuts off.
|
| If a model was trained 6 months ago for example it will
| likely have some info on shows that came out this month due
| to various data points talking about that show as
| "upcoming" but not released. Due to that it may still
| recommend "new" shows that have just released.
|
| All that being said, I have to imagine that suggesting
| shows that have just now been released is likely the weak
| point of the system for sure.
| tills13 wrote:
| The entire product is a wrapper around a well written ChatGPT
| prompt.
| fingerthieff wrote:
| An LLM Prompt, not ChatGPT specific. But yeah pretty much
| that is the core of everything.
| hi_hi wrote:
| Has there been any research on how LLMs perform as recommendation
| engines?
|
| I'd assume there isn't any algorithms provided weighted
| comparisons based on my viewing habits, but rather a fairly
| random list that looks like its based on my viewing habits.
|
| Perhaps, in practice, the difference between those two is
| academic, but I'm really not keen on leveraging such a heavy
| everything model for such a specific use case, when something
| much simpler, and private, would suffice.
| fingerthieff wrote:
| I haven't looked into it too deep if I'm honest, I built this
| app solely because I find LLM TV and Movie recommendations to
| be leaps and bounds better than any other recommendation
| service I've ever used, I find most of them terrible
| unfortunately.
|
| I just got tired of manually inputting the data and wanted a
| more automated approach. This recommendations system isn't
| extracting loads of data yet (like how often things are watched
| etc..) but instead a more birds eye view of your library and
| watch history to analyze.
| silvanocerza wrote:
| Cool project but why use an LLM for this?
|
| Recommendation systems exist well before LLMs and have been in
| use for a while, wouldn't it better and more efficient even?
___________________________________________________________________
(page generated 2025-03-02 23:00 UTC)