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 + great 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!

    • Eager Eagle@lemmy.worldEnglish
      7·
      3 days 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·
        3 days 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.