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

• illusionist@lemmy.zip ⁨3⁩ ⁨weeks⁩ ago

  Are you a trollm?

  source

  • eager_eagle@lemmy.world ⁨3⁩ ⁨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

    • prenatal_confusion@feddit.org ⁨2⁩ ⁨weeks⁩ ago

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

      source
• 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