Posts by ahyatt@urbanists.social
 (DIR) Post #AYm69D6iHftmHUtzto by ahyatt@urbanists.social
       2023-08-16T02:46:53Z
       
       0 likes, 0 repeats
       
       @simon This is great, the 13b model went from taking about an hour to being almost instantaneous on my M1 macbook.  The 70b model crashed my machine though, lol.
       
 (DIR) Post #AaThO3UmE1g7MskHuy by ahyatt@urbanists.social
       2023-10-05T23:56:44Z
       
       0 likes, 0 repeats
       
       @simon is there a way to just output an embedding given a string, from your llm tool?  In other words, no storage needed.  I'm trying to hook up your llm tool to my llm tool (similar, but simpler, and for emacs: https://github.com/ahyatt/llm)
       
 (DIR) Post #Acmirss0P4bszVs2xE by ahyatt@urbanists.social
       2023-12-14T01:29:39Z
       
       0 likes, 0 repeats
       
       @simon According to the press release, you can also get embeddings, but I don't see any new APIs.  Have you found anything out?  Also, gotta say I'm super happy that they did not re-use their old Vertex APIs, the streaming REST API was especially bizarre.
       
 (DIR) Post #Acn5bC12GUiYOR6XUu by ahyatt@urbanists.social
       2023-12-14T05:44:12Z
       
       0 likes, 0 repeats
       
       @simon Thank you for finding that!  But that's very different than the other API they documented, with a completely different endpoint.  https://cloud.google.com/vertex-ai/docs/generative-ai/start/quickstarts/quickstart-multimodal is the one I've been looking at (which doesn't seem to have embeddings).  Do they really have two different APIs, one for Cloud Vertex and one for API Studio?  The API Studio is much easier though, so maybe best to switch to that.