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!
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.
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.
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.
no one is saying everyone has to ask an LLM for movie recommendations
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
No, it also doesn’t do that. It gets embeddings from an LLM and uses that to rank candidates.
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.
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.
I love how you actually did something instead of jumping on the generalization train. I hate that about Lemmy right now.
LLMs are not the tool for a recommender job
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.
No LLM use is benign. The effects on the environment, the internet, and society are real, and that cannot be ignored.
You can make the argument that in some cases it is justified, e.g.: for scientific research.
chill, this is extracting text embeddings from a local model, not generating feature-length films
that’s like saying “no jet use is benign” meant for comparing a private jet to a jet-ski
the generative aspect is not even used here
So running a local model is unforgivable, but “scientific research” running on hyperscalers, can be justified?
Do You drive a car? Eat meat? Fly for holidays?
Nothing is black and white.
Saw it was already commented about CO2, so I thought I’d counter-point your environment claim regarding water usage (since that is something I’ve seen a lot of too).
The ISSA had a call to action due to the AI water use “crisis”: https://www.issa.com/industry-news/ai-data-center-water-consumption-is-creating-an-unprecedented-crisis-in-the-united-states/
68 billion gallons of water by 2028! That’s a lot…right? Well, what I found is that this is somewhat of a bad faith argument. 68 billion gallons annually is a lot for one town, but those are numbers from a national level and it isn’t compared to usage from anything else. So, lets look at US agriculture (that’s something that’s tracked very well by the USDA): https://www.nass.usda.gov/Publications/Highlights/2024/Census22_HL_Irrigation_4.pdf
That’s 26.4 trillion gallons of water annually. So, AI datacenter represents 0.26% of agriculture consumption. If AI datacenter consumption is a crisis, why is agriculture consumption not a crisis? You could argue that agriculture produces “something useful”, but usefulness doesn’t factor into the scarcity of a resource. So, either its not a crisis, or you are cherry picking something that has no meaningful outcome to solving the problem.
yeah, I think the whole “water” argument really dilutes the case against data centers.
On a serious note, the argument works for areas that already struggle to supply enough water for consumers. Otherwise, we should be focusing more on the power stress to the grid, and the domino effect on supply chain of hardware cost increases that it’s happening across many industries. It started with GPUs, now it’s CPU, storage, networking equipment, and other components.
If these prices are too high for a couple of years, we’ll start seeing generalized price increases as companies need to pass along the costs to consumers.
The effects on the environment
Didn’t down vote you. I hear this line of complaint in conjunction with AI, especially if the person saying it is anti-AI. Without even calculating in AI, some 25 million metric tons of CO2 emissions annually from streaming and content consumption. Computers, smartphones, and tablets can emit around 200 million metric tons CO2 per year in electrical consumption. Take data centers for instance. If they are powered by fossil fuels, this can add about 100 million metric tons of CO2 emissions. Infrastructure contributes around 50 million metric tons of CO2 per year.
Now…who wants to turn off their servers and computers? Volunteers? While it is true that AI does contribute, we’re already pumping out some significant CO2 without it. Until we start switching to renewable energy globally, this will continue to climb with or without AI. It seems tho, that we will have to deplete the fossil fuel supply globally before renewables become the de facto standard.
Anti-AI evangelism is at its peak rn.
@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.
20 decades
Found the time traveler!
Like what and what have you tried to block it?
@meldrik They’re impossible to block based on IP ranges alone. It’s why all the FOSS git forges and bug trackers have started using stuff like anubis. But yes, I initially tried to block them (this was before anubis existed).
It was a few things that I had to take down; a gitweb instance with some of my own repos, for example. And a personal photo gallery. The scrapers would do pathological things like running repeated search queries for random email addresses or strings.
I’m hosting several things, including Lemmy and PeerTube. I haven’t really been aware of any scrapers, but do you know of any software that can help block it?
The more local inference, the better. Nice work!
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
that’s pretty cool, this is just the wrong crowd, don’t worry about the downvotes
thanks ! ^^
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.
Thank you ! :)
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
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.
How does this compare to an ML approach?
are you training or just using an LLM for this?
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.
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.
Did you build it, though, or did Claude code it?
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.
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.
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!
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.
I would say there is a lot of truth to that statement. The backlash is immediate and punishing. I’ve said before, I think there are a lot of young devs who would like to contribute to the opensource/selfhosting community, but lack the experience.
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.
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
.emacsfile that’s older than most programmers alive today and finally admitted I should stop usingcshas 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.
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.
I’ve said it before, AI is here to stay. It’s not a fad. Kind of like when the internet first started to become publicly available. Lots of people deemed it a fad. It’s now a global phenom and it is the basis by which we do business on the daily, minute by minute, globally. I do think that AI needs some heavy governmental regulation. It would be great if we could all play nicely together without involving the government(s). Alas, we don’t seem to be able to do that, and so, government(s) has to step in, unfortunately. The problem with that is, imho, surveillance capitalism has worked so well that governments also want to take a peek at that data too. I have nothing to back up that conspiracy theory, it’s just a feeling I get.
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.
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?
Y’all need LLMs to tell you what to watch, now?
Is it any different that getting movies based on recommendations from employees at video stores?
Screw AI.
