Introducing embedding.store β Hosted Embedding Marketplace π
Weβre building a single destination to discover, evaluate, and access relevant embeddings. Move from large expensive models to leaner open-source models without reducing accuracy.
Comment π for early access
11 replies
0 recasts
0 reactions
you know you have grown up when you realize the difference between building side projects and a business
0 replies
0 recasts
0 reactions
Top casts
GPT-4 cost and latency is staggering as you scale, and its often not worth it. You donβt need a sledgehammer to crack a nut.
Most use cases are served with a smaller model that has access to the right context. We are making this access seamless
1 reply
0 recasts
0 reactions
Introducing embedding.store β Hosted Embedding Marketplace π
Weβre building a single destination to discover, evaluate, and access relevant embeddings. Move from large expensive models to leaner open-source models without reducing accuracy.
Comment π for early access
11 replies
0 recasts
0 reactions
I am definitely hooked - came in with a lot of expectations, none were fulfilled, but still hooked because of the story :)
1 reply
0 recasts
0 reactions
Hereβs how it works
1. Choose your base model
2. Connect to a range of embeddings
3. Retrieve context in your go-to framework
We'll handle all the infra for finding, indexing, and provisioning high-quality embeddings π