18
Local AI Companion for Radarr: Uses Ollama to Understand Your Taste (Vibe, Atmosphere, Mood), Auto-Complete Sagas, Explore Filmographies, and Add Movies Seamlessly (lemmy.world)
submitted 2 weeks ago* (last edited 1 week ago) by nikodindon@lemmy.world to c/selfhosted@lemmy.world
50 comments fedilink hide all child comments

I just pushed v22 of my project : a local AI companion for Radarr, that goes beyond generic genre or TMDb lists.

This isn't "yet another recommender". It's your personal taste explorer that actually gets the vibe you want in natural language and builds recommendations starting from your existing library.

Key highlights from a real recent run:

  • Command: --mood "dystopian films like Idiocracy, Gattaca or In Time"
  • Output: Metropolis (1927), V for Vendetta, Children of Men, Brazil (1985), Minority Report, Dark City, Equilibrium, Upgrade, The Road... → oppressive/surveillance/inequality/societal critique atmosphere, not just "dark sci-fi".

How it works :

  • Starts by sampling random movies from your Radarr collection (or uses your mood/like/saga input).
  • Asks a local Ollama LLM (e.g. mistral-small:22b) for 25 thematic suggestions based on atmosphere/vibe.
  • Validates each via OMDb (IMDb rating, genres, plot, director, cast...).
  • Scores intelligently: IMDb rating + genre match + director/actor bonus + plot embedding similarity (cosine on Ollama embeddings).
  • Adds the top ones directly to Radarr (with confirmation: all / one-by-one / no).
  • Persistent blacklist to avoid repeats.

Different modes :

  • --mood "dark psychological thrillers with unreliable narrators" , any vibe you describe
  • --like "Parasite" --mood "mind-bending class warfare" (or just --like "Whiplash")
  • --saga (auto-detects incomplete sagas in your library and suggests missing entries) or --saga "Star Wars"
  • --director "Kubrick" / --actor "De Niro" / --cast "Pacino De Niro" (movies where they co-star)
  • --analyze → full library audit + gaps (e.g. "You're missing Kurosawa classics and French New Wave")
  • --watchlist → import from Letterboxd/IMDb
  • --auto → perfect for daily cron / Task Scheduler (wake up to 10 fresh additions)

Standout features:

  • 100% local + privacy-first (Ollama + free OMDb API only)
  • No cloud AI, no tracking
  • colored console output, logs, stats, HTML/CSV exports
  • Synopsis preview before adding
  • Configurable quality profile, min IMDb, availability filters
  • Works on Windows, Linux, Mac

GitHub (clean single-file Python script + detailed README):
https://github.com/nikodindon/radarr-movie-recommender

If you're tired of generic Discover lists, Netflix-style randomness, or manual hunting give it a spin. The vibe/mood mode + auto saga completion really change how you expand your collection.

Let me know what you think, any weird mood examples you'd like to test, or features you'd want added!

top 50 comments
sorted by: hot top controversial new old
[-] circuscritic@lemmy.ca 19 points 2 weeks ago* (last edited 2 weeks ago)

Since no one is leaving critical comments that might explain all the downvotes, I'm going to assume they're reflexively anti-AI, which frankly, is a position that I'm sympathetic to.

But one of the benign useful things I already use AI for, is giving it criterias for shows and asking it to generate lists.

So I think your project is pretty neat and well within the scope of actually useful things that AI models, especially local ones, can provide the users.

[-] webkitten@piefed.social 4 points 2 weeks ago

Seriously; local AI use is what everyone should strive for not only for privacy but because it's better than using a large data centre and the power use for Ollama is negligible.

[-] u_tamtam@programming.dev 1 points 2 weeks ago

LLMs are not the tool for a recommender job

[-] FerCR@kbin.earth 1 points 2 weeks ago

The local LLM here is, if I'm not mistaken @nikodindon@lemmy.world , just used as a feature extraction tool. It's not like asking ChatGPT what to watch next but rather asking it to sumarise the movie as an excel file, that you then process to compute which movie(s) is(are) similar.

[-] illusionist@lemmy.zip -5 points 2 weeks ago

Huh? There are other ways to link similarities of movies without the use of a llm. You may use ai to find similar movies but it's nonsense that everyone has to ask a llm to link movies.

[-] eager_eagle@lemmy.world 4 points 2 weeks ago

no one is saying everyone has to ask an LLM for movie recommendations

[-] illusionist@lemmy.zip 0 points 2 weeks ago

OP wrote a python script that call a llm to ask for a recommendation.

But you are right, op doesn't say that everyone shall do it

[-] eager_eagle@lemmy.world 4 points 2 weeks ago* (last edited 2 weeks ago)

No, it also doesn't do that. It gets embeddings from an LLM and uses that to rank candidates.

[-] bandwidthcrisis@lemmy.world 1 points 2 weeks ago

I had to look up embeddings: so this is comparing the encoding of movies as a similarity test?

Which can work because the encoding methods can indicate closeness of meaning.

And that's why this isn't running an llm in any way.

[-] illusionist@lemmy.zip -2 points 2 weeks ago* (last edited 2 weeks ago)

Are you a trollm?

If not, I'm just too stupid to understand op.

I Built a Python script that uses a local Ollama LLM to automatically find and add movies to Radarr.

OP wrote a python script that call a llm to ask for a recommendation.

If that's not the same, I don't know what is. Gotta go back to school, I guess.

[-] eager_eagle@lemmy.world 7 points 2 weeks ago* (last edited 2 weeks ago)

It's not, I read the code. It's not merely asking the LLM for recommendations, it's using embeddings to compute scores based on similarities.

It's a lot closer to a more traditional natural language processing than to how my dad would use GPT to discuss philosophy.

[-] prenatal_confusion@feddit.org 4 points 2 weeks ago

I love how you actually did something instead of jumping on the generalization train. I hate that about Lemmy right now.

[-] eager_eagle@lemmy.world 9 points 2 weeks ago

that's pretty cool, this is just the wrong crowd, don't worry about the downvotes

[-] meldrik@lemmy.wtf 7 points 2 weeks ago

This is a cool tool. Thanks for sharing. Don’t worry about the downvotes. The Fediverse has a few anti-AI zealots who love to brigade.

[-] fubarx@lemmy.world 4 points 2 weeks ago

The more local inference, the better. Nice work!

[-] Scrath@lemmy.dbzer0.com 3 points 2 weeks ago

I remember building something vaguely related in a university course on AI before ChatGPT was released and the whole LLM thing hadn't taken off.

The user had the option to enter a couple movies (so long as they were present in the weird semantic database thing our professor told us to use) and we calculated a similarity matrix between them and all other movies in the database based on their tags and by putting the description through a natural language processing pipeline.

The result was the user getting a couple surprisingly accurate recommendations.

Considering we had to calculate this similarity score for every movie in the database it was obviously not very efficient but I wonder how it would scale up against current LLM models, both in terms of accuracy and energy efficiency.

One issue, if you want to call it that, is that our approach was deterministic. Enter the same movies, get the same results. I don't think an LLM is as predictable for that

[-] LiveLM@lemmy.zip 2 points 2 weeks ago

One issue, if you want to call it that, is that our approach was deterministic. Enter the same movies, get the same results. I don't think an LLM is as predictable for that

Maybe lowering the temperature will help with this?
Besides, a tinge of randomness could even be considered a fun feature.

[-] four@lemmy.zip 1 points 2 weeks ago

I'm not an expert, but LLMs should still be deterministic. If you run the model with 0 creativity (or whatever the randomness setting is called) and provide exactly the same input, it should provide the same output. That's not how it's usually configured, but it should be possible. Now, if you change the input at all (change order of movies, misspell a title, etc) then the output can change in an unpredictable way

[-] hendrik@palaver.p3x.de 1 points 2 weeks ago* (last edited 2 weeks ago)

Yes. I think determinism a misunderstood concept. In computing, it means exact same input leads to always the same output. Could be a correct result or entirely wrong, though. As long as it stays the same, it's deterministic. There's some benefit in introducing randomness to AI. But it can be run in an entirely deterministic way as well. Just depends on the settings. (It's called "temperature".)

[-] pfr@piefed.social 3 points 2 weeks ago

Anti-AI evangelism is at its peak rn.

[-] Andres4NY@social.ridetrans.it 1 points 2 weeks ago* (last edited 2 weeks ago)

@pfr @nikodindon That assumes it won't get worse, which I hope it does. AI companies have forced me to take down web stuff that I had running for almost 2 decades, because their scrapers are so aggressive.

[-] timestatic@feddit.org 3 points 2 weeks ago

Sorry OP that you're getting downvote bombed. This is actually really neat. People go nuts when they hear AI but this is fully local so I think this reaction is unjust. This has nothing to do with ram prices since that stems from data centers or corpos pushing AI on you. Thank you for sharing

[-] Overspark@piefed.social 2 points 2 weeks ago

A recommendation for Moonrise Kingdom based on Mickey 17? The genres might match, but those are totally different movies.

[-] Janx@piefed.social 2 points 2 weeks ago

Also, A Bug's Life from Mickey 17!?

[-] borari@lemmy.dbzer0.com 2 points 2 weeks ago

That made me lol so hard. Like what’s the fucking point of this thing when it comes up with shit like that?

[-] Alvaro@lemmy.blahaj.zone 1 points 2 weeks ago

A bugs life from mickey 17?

Explain OP

[-] RIotingPacifist@lemmy.world 0 points 2 weeks ago

How does this compare to an ML approach?

are you training or just using an LLM for this?

[-] eager_eagle@lemmy.world 3 points 2 weeks ago* (last edited 2 weeks ago)

There's no training, the LLM embeddings are used to compare the plots via a cosine similarity, then a simple weighted score with other data sources is used to rank the candidates. There's no training, evaluation, or ground-truth, it's just a simple tool to start using.

[-] FerCR@kbin.earth 1 points 2 weeks ago

Exactly! This has been done plenty of times in the past (there's a reason why some movies datasets are used as toy example for data analysis). For the unfamiliar with the field, the LLM part here is simply that, instead of building a feature space from predefined tags or variables, it makes a "fuzzier" feature space where it embeds the movies based on the text tokens the model sees. In essence, the way to compute which movie to recommend is the same (a.k.a no LLM) it is just that the data used for the computation is generated differently.

[-] hendrik@palaver.p3x.de 0 points 2 weeks ago

Did you build it, though, or did Claude code it?

[-] prettygorgeous@aussie.zone 4 points 2 weeks ago

Built with Claude by the looks of things. Not sure if Claude was used to generate the boilerplate and whether the dev reviewed it after or whether Claude did all of it, but definitely Claude was used for some of it. I recognise the coding style that Claude outputs and the bugs that it implements that will cause TypeErrors if not handled.

FWIW, I'm not against using AI as an assistant for coding (I do it too, using Claude and Vercel as assistants) just as long as the code is reviewed and understood in full by the dev before publishing.

[-] irmadlad@lemmy.world 1 points 2 weeks ago

FWIW, I’m not against using AI as an assistant for coding (I do it too, using Claude and Vercel as assistants) just as long as the code is reviewed and understood in full* by the dev before publishing. *my emphasis

A very sane take. I do wish devs would fully disclose this on their github or other. That way, if the project is seasoned, well starred, et al, and the dev used AI as an assistant, then the user gets to decide. Given all the criteria are met, I would deploy it.

I will say that I have observed what seems like a pretty decent up tick in selfhosted apps, and I would be willing to bet a goodly amount of them have at the very least, used AI in some capacity, if not most/all code. I don't have any solid evidence to back that up but it just seems that way to me.

[-] prettygorgeous@aussie.zone 4 points 2 weeks ago* (last edited 2 weeks ago)

I think the problem is a cyclical one. Some devs are afraid to admit that they used AI to help them code because there's so much hatred towards using AI to code. But the hatred only grows because some devs are not disclosing that they've had help from AI to code and it seems like they're hiding something which then builds distrust. And of course, that's not helped by the influx of slop too where an AI has been used and the code has not been reviewed and understood before its released.

I don't mind more foss projects, even if they're vibe coded, but please PLEASE understand your code IN FULL before releasing it, if at least so you can help troubleshoot the bugs people experience when they happen!

[-] november@piefed.blahaj.zone 2 points 2 weeks ago

Some devs are afraid to admit that they used AI to help them code because there’s so much hatred towards using AI to code.

Cowards. "Some devs" would not survive five minutes in the real world as a queer person.

[-] hendrik@palaver.p3x.de 3 points 2 weeks ago* (last edited 2 weeks ago)

Yeah. Maybe it's time to adopt some new rule in the selfhosted community. Mandating disclosure. Because we got several AI coded projects in the last few days or weeks.

I just want some say in what I install on my computer. And not be fooled by someone into using their software.

I mean I know why people deliberately hide it, and say "I built ..." when they didn't. Because otherwise there's an immediate shitstorm coming in. But deceiving people about the nature of the projects isn't a proper solution either. And it doesn't align well with the traditional core values of Free Software. I think a lot of value is lost if honesty (and transparency) isn't held up anymore within our community.

[-] timwa@lemmy.snowgoons.ro 1 points 2 weeks ago

Warning, anecdote:

I was unexpectedly stuck in Asia for the last month (because of the impact of the war), turning an in-person dev conference I was organising into an "in-person except for me" one at a few days notice.

I needed a simple countdown timer/agenda display I could mix into the video with OBS; a simple requirement, so I tried a few from the standard package repos (apt, snap store, that kind of thing.)

None of them worked the way I wanted or at all - one of them written in Python installed about 100 goddamned dependencies (because, Python,) and then crashed because, well, Python.

So I gave up and asked my local hosted LLM model to write it for me in Rust. In less than 10 minutes I had exactly what I wanted, in a few hundred lines of Rust. And yeah, I did tidy it up and publish it to the snap store as well, because it's neat and it might help someone else.

Which is more secure? The couple of hundred lines of Rust written by my LLM, or the Python or node.js app that the developer pinky-promises was written entirely by human hand, and which downloads half the Internet as dependencies that I absolutely am not going to spend time auditing just to display a goddamned countdown clock in a terminal window?

The solution to managing untrusted code isn't asking developers for self-declared purity test results. It's sandboxing, containers, static analysis... All the stuff that you are doing already with all the code/apps you download if you're actually concerned. You are doing those things, right?

[-] timwa@lemmy.snowgoons.ro 0 points 2 weeks ago

Honestly, any developer that isn't using an LLM as an assistant these days is an idiot and should be fired/shunned as such; it's got all the rational sense of "I refuse to use compilers and I hand-write my assembly code in vi."

(And I speak as someone who has a .emacs file that's older than most programmers alive today and finally admitted I should stop using csh as my default shell this year.)

Here's the disclosure you need: all projects you see have involved AI somewhere, whether the developers like to admit it or not. End of. The genie is out of the bottle, and it's not going back in. Railing against it really isn't going to change anything.

[-] hendrik@palaver.p3x.de 1 points 2 weeks ago* (last edited 2 weeks ago)

Haha. I think there's often a rough idea on what kind of programmer people are, judging by their opinion on these AI tools.

Have you tried arguing with your AI assistant for 2.5h straight about memory allocation, and why it can't just take some example code from some documentation? And it keeps doing memory allocation wrong? Scold it over and over again to use linear algebra instead of trigonometric functions which won't cut it? Have you tried connecting Claude Code to your oscilloscope and soldering iron to see what kind of mess its code produces?

I'm fairly sure there are reasons to use AI in software development. And there are also good reasons to do without AI, just use your brain and be done with it in one or two hours instead of wasting half a workday arguing and then still ending up doing it yourself 😅

I don't think these programmers are idiots. There's a lot of nuance to it. And it's not easy at all to apply AI correctly so it ends up saving you time.

[-] rako@tarte.nuage-libre.fr 0 points 2 weeks ago

ai;dr

[-] november@piefed.blahaj.zone -2 points 2 weeks ago

Y'all need LLMs to tell you what to watch, now?

[-] webkitten@piefed.social 2 points 2 weeks ago

Is it any different that getting movies based on recommendations from employees at video stores?

[-] Somecall_metim@lemmy.dbzer0.com -5 points 2 weeks ago

Screw AI.

this post was submitted on 20 Mar 2026
18 points (69.6% liked)

Selfhosted

58268 readers
73 users here now

A place to share alternatives to popular online services that can be self-hosted without giving up privacy or locking you into a service you don't control.

Rules:

  1. Be civil: we're here to support and learn from one another. Insults won't be tolerated. Flame wars are frowned upon.

  2. No spam posting.

  3. Posts have to be centered around self-hosting. There are other communities for discussing hardware or home computing. If it's not obvious why your post topic revolves around selfhosting, please include details to make it clear.

  4. Don't duplicate the full text of your blog or github here. Just post the link for folks to click.

  5. Submission headline should match the article title (don’t cherry-pick information from the title to fit your agenda).

  6. No trolling.

  7. No low-effort posts. This is subjective and will largely be determined by the community member reports.

Resources:

Any issues on the community? Report it using the report flag.

Questions? DM the mods!

founded 2 years ago
MODERATORS
ruud@lemmy.world
Loki@lemmy.world
CannaVet@lemmy.world
devve@lemmy.world
HybridSarcasm@lemmy.world
HybridSarcasm@lemmy.hybridsarcasm.xyz