Mine bailed out on a Baseband error due to which i am not even able to boot it anymore :(

looks nice, wonder what would take to hook this to a database connection directly

Can see it happening for sure. Perhaps porting it to electron and taking in dbms type and host url for the connection will do it

This is cool, haven't run this yet but seems really promising. Am thinking how this can be a super useful to hook with internal corporate search engines and then get answers from that.

Good to see more of these non API key products being built (connected to local llms)

I might try to hook this into our internal confluence, shouldn't be a problem

this is first time i have read something completely in a long span of time !!

I agree, I really enjoyed the author’s curiosity and writing style!

have been following the development of this very closely for this library, and love the fact that we can script load individual web component in html as bare bones.

Can you please elaborate on what this means ?

Add the script tag to your page for any of the components and you can use them. No building, compiling or initializing anything.

exactly, and pair that with css variables for customizations if needed for ad-hoc projects/prototypes or full products

cool concept, love the idea. Might be fun to integrate with local llama to get most privacy

100% and local embeddings. This is the area i want to explore next.

The demo i showed with chatgpt works just as well with openhermes2.5-mistral. But is instant with chatgpt instead of 20s

This is an amazing idea as well as execution providing best use of resources to end users.

Soon Samsung would be like able to show moon and Saturn twogether in their photos

This is amazing, kudos to the team

This is why i love HN comments, Good luck for your product !