HNHacker News
TopNewBestAskShowJobs

yujonglee

366 karma · joined May 14, 2022

prev: fastrepl.com (YC S25)
submissionscomments
yujonglee··on Launch HN: Hyprnote (YC S25) – An open-source AI meeting notetaker
> How does it choose what's important vs what isn't?

The idea of Hyprnote is that you write chicken-scratch-raw note during the meeting(what you think is important), and AI enhance based on it.

On-device learning is interesting too. For example, Gboard: https://arxiv.org/abs/2305.18465

And yes - we are open to this too

yujonglee··on Launch HN: Hyprnote (YC S25) – An open-source AI meeting notetaker
For individuals:

We have a Pro license implemented in our app. Some non-essential features like custom templates or multi-turn chat are gated behind a paid license. (A custom STT model will also be included soon.) There's still no sign-up required. We use keygen.sh to generate offline-verifiable license keys. Currently, it's priced at $179/year.

For business:

If they want to self-host some kind of admin server with integrations, access control, and SSO, we plan to sell a business license.

yujonglee··on Launch HN: Hyprnote (YC S25) – An open-source AI meeting notetaker
Seems like

https://github.com/fastrepl/hyprnote/blob/d0cb0122556da5f517...

this is invalid on Mac mini. Should be fixed today.

yujonglee··on Launch HN: Hyprnote (YC S25) – An open-source AI meeting notetaker
Super! let us know how it goes! (we have discord channel too)
yujonglee··on Launch HN: Hyprnote (YC S25) – An open-source AI meeting notetaker
That is very strange. Can you launch it from the command line and share what you got?

/Applications/Hyprnote.app/Contents/MacOS/Hyprnote

yujonglee··on Launch HN: Hyprnote (YC S25) – An open-source AI meeting notetaker
What kind of sandboxing you expect? keen to learn more about it since we care about security too. (one reason why we use Tauri over Electron)
yujonglee··on Launch HN: Hyprnote (YC S25) – An open-source AI meeting notetaker
Great! We use AudioTap api
yujonglee··on Launch HN: Hyprnote (YC S25) – An open-source AI meeting notetaker
Also you might find this interesting:

https://github.com/fastrepl/hyprnote/blob/main/packages/util....

yujonglee··on Launch HN: Hyprnote (YC S25) – An open-source AI meeting notetaker
We tried Tauri mobile (few months ago) and had the same disappointment. We will use RN or Dioxus(to share Rust code) for the mobile version. So it will be cool :)
yujonglee··on Launch HN: Hyprnote (YC S25) – An open-source AI meeting notetaker
It can be solved with speaker segmentation/embedding models, although it is not perfect. One thing we do with Hyprnote is that we have a Descript-like transcript editor that allows you to easily edit/assign speakers. Once we integrate a speaker diarization model with that, I think we'll be in good shape.

If you are interested, you can join our Discord and follow updates. :) https://hyprnote.com/discord

yujonglee··on Launch HN: Hyprnote (YC S25) – An open-source AI meeting notetaker
What kind of API/Hooks you expect us to expose? We are down to do that.
yujonglee··on Launch HN: Hyprnote (YC S25) – An open-source AI meeting notetaker
Local-first, controllability(custom endpoint part), and eventually extensibility(VSCode part of the post)

We're putting a lot of effort into making it run smoothly on local machines. There are no signups, and the app works without any internet connection after downloading models.

yujonglee··on Launch HN: Hyprnote (YC S25) – An open-source AI meeting notetaker
Thanks. I learned that running a server on the Rust side and calling it from a TypeScript frontend is a good approach. For example, we run an OpenAI-compatible server using a Tauri plugin (https://github.com/fastrepl/hyprnote/tree/main/plugins/local...) and call it using the Vercel AI SDK.
yujonglee··on Show HN: Debugging LLM Failures Like "9.11 > 9.9" via Interpretability
This is so cool
yujonglee··on Show HN: Self-Hostable Algolia DocSearch Replacement
click cute yellow bird next to the searchbar.
yujonglee··on Show HN: Self-Hostable Algolia DocSearch Replacement
that piece of code is for llm response evaluation, but we are not really using it at the moment.
yujonglee··on Show HN: Self-Hostable Algolia DocSearch Replacement
yes :)
yujonglee··on Show HN: Self-Hostable Algolia DocSearch Replacement
please let me know how it goes! we have Discord link in the top navbar: https://getcanary.dev/
yujonglee··on Show HN: Self-Hostable Algolia DocSearch Replacement
It is not that difficult :)

If you want pagefind-based local search:

Doc: https://getcanary.dev/docs/local/integrations/docusaurus Example PR: https://github.com/microsoft/fast/pull/7031/files

If you want hosted-search: Doc: https://getcanary.dev/docs/cloud/integrations/docusaurus Example PR: https://github.com/BerriAI/litellm/pull/6160/files

yujonglee··on Show HN: Self-Hostable Algolia DocSearch Replacement
No, it use different API with Algolia DocSearch.

> Have been looking for a way to mock the service in development

This is what I wanted too! So we have multiple providers, including `canary-provider-mock`. So you can use it to mock it in the dev.

example:

https://github.com/noxify/renoun-docs-template/blob/055b54/s...

yujonglee··on Show HN: Self-Hostable Algolia DocSearch Replacement
> I dread having to use Algolia search on documentation these days.

agreed.

> but can we please find a way to bring back search _pages_?

could you please explain what do you mean?

yujonglee··on Show HN: Self-Hostable Algolia DocSearch Replacement
nice! lmk if you have any feedback while using it in the litellm docs.
yujonglee··on Show HN: Self-Hostable Algolia DocSearch Replacement
thanks, fixed!
yujonglee··on Show HN: Self-Hostable Algolia DocSearch Replacement
sure - implementing a search-as-you-type experience with an ai-powered feature was what i wanted to do as well. it doesn't use embeddings at the moment. when you type a short query like 'openai,' it simply runs a basic query using Typesense. however, if you enter a question-like query, such as 'how to llimit api cost,' it transforms it into multiple queries, like 'budget' and 'limit.'

in the self-hosted version, it use the CHAT_COMPLETION_MODEL env variable for selecting the llm model. in our cloud version, we use a fine-tuned version of 4o-mini that we will eventually move to a smaller model like llama8b or even 1b.

yujonglee··on Show HN: Self-Hostable Algolia DocSearch Replacement
Yes, we initially started with Paradedb but moved to Typesense for a search-as-you-type experience. We also have an additional layer for query transformation using an LLM though. (only when query is "question-like".

e.g:

if you go to 'https://docs.litellm.ai/' and search for 'how to limit API cost,' it will map the query to 'budget.'

yujonglee··on Show HN: Self-Hostable Algolia DocSearch Replacement
nice catch! just downloaded firework to test it :) will fix it shortly
yujonglee··on Show HN: Self-Hostable Algolia DocSearch Replacement
that's a fair point. I don't think I can rename it at this point, but I'll keep in mind that some people might be confused by the name.

please do try it out, and come to Discord if you want to chat.

yujonglee··on Show HN: Self-Hostable Algolia DocSearch Replacement
Glean is used for searching the workspace (AFAIK, for internal use). Canary is used for searching technical documentation, GitHub issues, etc., and is intended for the users of the project.
yujonglee··on Show HN: Self-Hostable Algolia DocSearch Replacement
got it. I will add some animation in default `canary-modal` implementation.

just FYI - i's very easy to implement custom modal component and swap out the default one.

https://github.com/fastrepl/canary/blob/72723b0/js/apps/docs...

yujonglee··on Show HN: Self-Hostable Algolia DocSearch Replacement
Thanks! Could you point out any specific part of the UI that you think could be improved?
← PreviousPage 3 of 4Next →