Ready to store your embeddings on the server? 👉 database.new
@kevinkkirimii
20 күн бұрын
Dog is food 😊
@catoshimeowmoto
20 күн бұрын
Reminds me of the "Not a hot dog 🌭" from Silicon valley tv series 😂
@imdevbutok
18 күн бұрын
Dependendo das circunstâncias tudo é comida.
@ctbwx
20 күн бұрын
I don't think "sleeping" is what the model was referring to for the "bed" result on the "fun" query... 😏
@Supabase
20 күн бұрын
Oh, you mean like jumping on the bed? Yah, that's fun too 😉
@kirilkirchev285
20 күн бұрын
Cool & useful as always. Such videos really boosts my knowledge over new technologies and applying them in my apps. Thanks Supabase team!
@dshukertjr
20 күн бұрын
This is awesome! I always wanted to create something cool with transformers.js
@allanandliftedhands2669
20 күн бұрын
Does this add any additional costs from supabase or its just the cost for the llm one will be using. Also are the dependency kotlin/android compatible?
@Supabase
20 күн бұрын
This specific example is a static / client-side only application and doesn't incur any cost except for the electricity powering the computer it is running on. If you wanted to store the embeddings in a server environment somewhere, then you would need a Postgres instance for example, which you can get on the free tier with Supabase 👉 database.new
@intebuddy
20 күн бұрын
Everywhere I go, I see his face (claude).
@eliglanz
19 күн бұрын
I wonder tho- any way to essentially restrict the semantic search not to return something far fetched if the available options are not a 'real' match? Because it essentially performs ranking in order to return values. And it will return 3 items, even tho they have no semantic sense, since they're the closest available...
@takeshikriang
20 күн бұрын
Super cool❤
@andy111007
14 күн бұрын
any plans to have python version of it?
@eliglanz
19 күн бұрын
If you sell enough databases, you could buy yourself a boat..
Пікірлер: 16