Lumos

Yup, still working on it! Open PR: https://github.com/andrewnguonly/Lumos/pull/34

The app doesn't have this functionality, but I think it's a great idea. It's a nice (precision) alternative to the current scraping implementation. Tracking issue here: https://github.com/andrewnguonly/Lumos/issues/40

Got it, you're right. I created a release that includes the packaged code (so you don't need to run `npm`, etc): https://github.com/andrewnguonly/Lumos/releases/tag/1.0.0 Unzip `lumos_1_0_0.zip` and you can load the unpacked extension.

I had similar ideas on the back burner for per site scripts. MV3 sure makes things annoying at times! I want to build something that's kind of a mix between what you're doing here and what I've been experimenting with. Did you experiment with the sidePanel api yet? You can open it, but the <input> will not get focus like with the popups. You'd think at least with the commands keybindings, or reacting to the browser action icon click this should be possible?! I asked Lumos some questions and it's hitting the embeddings endpoint many times, and then when I asked a follow up question, it hit the same endpoints again, each taking a few hundred ms. It's not caching them? TBD? p.s. iirc There's some way to set the key in the manifest such that you'll get a static id, useful for OLLAMA_ORIGINS where you don't need * in the examples. p.p.s starli

I haven't tried it, but in general, it accepts any text. Or are you asking if it can automatically get the transcript from a YouTube video? At the moment, it can't do the latter. I do plan to support multi-modal LLMs (llava via Ollama), but I'm not sure how the mechanics of the extension will work yet. Open issue: https://github.com/andrewnguonly/Lumos/issues/27

For installation, there's nothing else you need to do. It's ready to go. If you want to configure a custom content parser for a specific website (i.e. websites you visit frequently), you'll need to modify `contentConfig.ts` according to the instructions here: https://github.com/andrewnguonly/Lumos?tab=readme-ov-file#cu... Sorry, I realize these instructions are probably unclear. My approach for parsing content is a bit hacky. I need to create a video tutorial/documentation to show how to inspect the webpage and pick out content to parse. Created this issue to track: https://github.com/andrewnguonly/Lumos/issues/37

I didn't build a dedicated Firefox version, but I suspect there's a way to install it without significant code changes. I actually just tried and I ran into an error: `background.service_worker is currently disabled` I'll figure out a workaround and document the steps to install: https://github.com/andrewnguonly/Lumos/issues/36

Great idea. I created an issue to keep track of this. https://github.com/andrewnguonly/Lumos/issues/35

I have been looking for something like this! I noticed you suggest setting the ollama host as a variable (I personally run ollama on a beefier desktop and query remotely), hopefully that will translate over to the options page as well (I noticed the options page seems to have the ollama host hardcoded, though https://github.com/andrewnguonly/Lumos/pull/34/files#diff-83...)

Lumos is an LLM co-pilot for browsing the web, powered by local LLMs (Ollama). - Summarize long threads on issue tracking sites, forums, and social media sites - Summarize news articles - Ask questions about reviews on business and product pages - Ask questions about long, technical documentation - What else?