Comment on I built a local AI movie recommender for Radarr using Ollama

• illusionist@lemmy.zip ⁨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

  source

  • eager_eagle@lemmy.world ⁨2⁩ ⁨weeks⁩ ago

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

    source

    • illusionist@lemmy.zip ⁨2⁩ ⁨weeks⁩ ago

      Are you a trollm?

      source

      • eager_eagle@lemmy.world ⁨2⁩ ⁨weeks⁩ ago

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

        source

        • -> View More Comments
    • bandwidthcrisis@lemmy.world ⁨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.

      source