I got it working when I provided an image of a Model F keyboard. This is the strength of the model, provide it an input image and it will do some magic
Oh yes good point, it's because at first I was using a local embedding model and then decided to use JinaAI as they have good embeddings.
Jina AI is doing different things but one of them is having embeddings and I use their English/ German embeddings as in one demo I am working with German data.
You can use pip as well but yes, let me add something about Poetry in case people don't know about it :)
On top of my head, pgvector only supports 2 indexes, those are running in memory only. They don't support GPU indexing, nor Disk based indexing, they also don't have separation of query and insertions.
Also with different people I've talked to, they struggle with scale past 100K-1M vector.
Cool to see that Supabase is adding S3 protocol! Nice to see more and more storage solutions available.
We, at Milvus, I've integrated S3, Parquet and other ones to make it possible for developers to use their data no matter what they use.
For those who have used both, how do you find the performance and ease of integration compares between Supabase and other solutions like Milvus that have had these features for some time?
I am French originally and on my side what worked well was to speak to myself in English all the time. At home I would actually speak English out loud and it helped a lot with practicing my pronunciation and also to learn new words.
Also reading books in English out loud can be really helpful.
It might be the first time that I see a phone number on a Github Repo, I wonder how many phone calls they will actually receive. It's probably the last thing I'd like to do when looking at an open source repository.