starlette + aftercare frontend for simonw llm

Find a file

Charlotte Som 710a6de7bc load the system prompt on-the-fly instead of once at startup this lets us modify it [for new conversations] on disk while the llm server is running		2025-02-26 10:41:59 +00:00
client	fix id state when using new convo	2025-02-26 10:26:03 +00:00
server	load the system prompt on-the-fly instead of once at startup	2025-02-26 10:41:59 +00:00
.gitignore	oops. ignore build output	2025-02-26 08:54:08 +00:00
.prettierrc	write a little frontend	2025-02-26 08:10:58 +00:00
_build_client.ts	write a little frontend	2025-02-26 08:10:58 +00:00
deno.json	improve operational ergonomics	2025-02-26 08:18:38 +00:00
README.md	improve operational ergonomics	2025-02-26 08:18:38 +00:00
requirements.txt	get inference over websocket working	2025-02-26 04:20:28 +00:00

llm-py-web

starlette + aftercare ui for llm by simonw. requires uv, deno.

$ deno task setup
$ # any llm plugins: `uv pip install ...`
$ deno task run