Mercurial

view love/README.md @ 275:78699f810817

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Add Qwen3-VL and WebRTC dictation services Add Bazel targets for the CUDA-backed Qwen3-VL server and a local WebRTC faster-whisper dictation service. Co-authored-by: Copilot <[email protected]> Copilot-Session: e3d8cb06-6c95-4ae0-9757-651d3796ab00
author MrJuneJune <me@mrjunejune.com>
date Mon, 17 Aug 2026 10:58:47 -0700
parents cf9caa4abc3e
children
line wrap: on
line source

# AI (Love)

This is where I create AI chat bot. Code goes like below

- Epi
  - FE repo
  - Vite and tanstack routers
  - Mostly using tailswind

- Poppy
  - BE repo
  - python with fastAPI

Code is pretty much self explanatory.

## How to start

`docker-compose up` or `docker compose up`

I don't really use the redis anymore, but I can see that being an improvement if there is more than 2000 RPS, but it will never get there so it should be fine.

## TODO

- proper chain of thoughts?
- maybe expose the mcp
- use local LLM. I wonder if I can get free API keys that I can use with threshold vlaues.