Hacker News Reader

andrewnguonlyon Show HN: Lumos, a local LLM Chrome extension

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

andrewnguonlyon Show HN: Lumos, a local LLM Chrome extension

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

andrewnguonlyon Show HN: Lumos, a local LLM Chrome extension

I did not look into the sidePanel API yet. I will look though. I'm still fairly new to Chrome extension development. I just discovered the Options page heh...

Regarding the caching -- the entire RAG workflow needs an update. I'll spend some time on it. Thanks for calling out and thanks for the PR!

andrewnguonlyon Show HN: Lumos, a local LLM Chrome extension

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.

andrewnguonlyon Show HN: Lumos, a local LLM Chrome extension

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

andrewnguonlyon Show HN: Lumos, a local LLM Chrome extension

Thanks!

I elaborate a little bit more on my thinking and approach for parsing in this blog post (4 min read): https://medium.com/@andrewnguonly/local-llm-in-the-browser-p...

andrewnguonlyon Show HN: Lumos, a local LLM Chrome extension

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

andrewnguonlyon Show HN: Lumos, a local LLM Chrome extension

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

andrewnguonlyon Show HN: Lumos, a local LLM Chrome extension

Very cool! Have you considered local LLMs for a free/lite tier?

I do agree that 3rd party LLM services (e.g. OpenAI) are much more powerful. For basic tasks (e.g. summarization, Q&A), local LLMs seem to perform decently.

andrewnguonlyon Show HN: Lumos, a local LLM Chrome extension

Someone else mentioned Slack as well. I guess web apps for chat products are actually a big use case.

andrewnguonlyon Show HN: Lumos, a local LLM Chrome extension

Great idea. I created an issue to keep track of this.

https://github.com/andrewnguonly/Lumos/issues/35

andrewnguonlyon Show HN: Lumos, a local LLM Chrome extension

I hadn't considered Discord, but good idea! I personally use the Discord Mac app.

I'll look into figuring out how to parse the chats.

andrewnguonlyon Show HN: Lumos, a local LLM Chrome extension

Yes! I'm planning to migrate the Ollama hostname configuration to the Options page as well.