Near real time feedback to provide new output

The setup I was talking about:

Categories indexes:

Hotels->0
Restaurants->1
Beaches->2

User preferences:
0->0.98
1->0.56
2->1

Suggestion category vectors:

Hotels:
0->cosine_similarity(vector(‘hotels’),vector(‘hotels’))
1->cosine_similarity(vector(‘hotels’),vector(‘restaurants’))
2->cosine_similarity(vector(‘hotels’),vector(‘beaches’))

$should_suggest_item_probs = cosine_similarity($user_preferences, $suggestion_category_vector);

The vector() can be embedding with any engine, ada will do perfectly. Just don’t embed the suggested item category directly. That’s what I meant.

1 Like

Feels like you are still stuck in using completion as the engine to retrieve the suggestion instead of database. Am I missing something in your use case? Do you have the suggestions data ready or do you expect the AI to generate you a suggestion from scratch?

If the second, how do you plan to overcome the hallucination issue?

Feels like you are still stuck in using completion as the engine to retrieve the suggestion instead of database. Am I missing something in your use case? Do you have the suggestions data ready or do you expect the AI to generate you a suggestion from scratch?

I was reading again my messages and I think i was not clear enough to you all about this point: I do not have a pre-defined number of categories. It means that if a customer likes ‘Hiking’ and ‘Restaurant’, I’d be glad to the model suggest something like ‘Healthy restaurants to go after your hiking activities’. This would be a new topic that was not designed at first. If the customer likes it, i will also be glad to use ‘Healthy restaurants to go after your hiking activities’ as a new input

If the second, how do you plan to overcome the hallucination issue?

I didn’t think about this, to be honest. Maybe feedback might help to show the model about absurd topics and avoid this situation. For example, a customer loves ‘Hiking’ and ‘Museum’, then it comes a absurd recomendations like ‘Hiking spots inside museums’. Customer will tag it with a dislike, then I expect it not to come through this theme again. How does it sound to you?