Popular Posts

Popular Content

Powered by Blogger.

Search This Blog

Follow on Google+

Recent Posts

About us

July 28, 2024

Hi HN,

I've created a tool called Alertfor that scours the open web to find the most relevant and up-to-date answers for complex questions. You can set up alerts to receive continuous updates whenever there are changes or new information becomes available for a given question.

I used an agent framework (Autogen + Sibyl) to collect and answer questions, and I schedule a Celery job to run the same query continuously every six hours.

I would love to hear your feedback, suggestions, or anything else you’d like to say.

Note: I'm submitting this for a second time; I'm not sure if this is against HN policy.

Comments URL: https://news.ycombinator.com/item?id=41093161

Points: 14

# Comments: 7



from Hacker News: Front Page https://ift.tt/JVNxPZH
Continue Reading
July 27, 2024

Much improved new version. Search for words similar to the query. For example, "death" will find "death", "dying", "dead", "killing"... Incredibly useful for exploring large text datasets where exact matches are too restrictive.

Comments URL: https://news.ycombinator.com/item?id=41088273

Points: 7

# Comments: 1



from Hacker News: Front Page https://ift.tt/rjh8Esz
Continue Reading
July 23, 2024

This started out as a weekend hack with gpt-4-mini, using the very basic strategy of "just ask the ai to ocr the document".

But this turned out to be better performing than our current implementation of Unstructured/Textract. At pretty much the same cost.

I've tested almost every variant of document OCR over the past year, especially trying things like table / chart extraction. I've found the rules based extraction has always been lacking. Documents are meant to be a visual representation after all. With weird layouts, tables, charts, etc. Using a vision model just make sense!

In general, I'd categorize this solution as slow, expensive, and non deterministic. But 6 months ago it was impossible. And 6 months from now it'll be fast, cheap, and probably more reliable!

Comments URL: https://news.ycombinator.com/item?id=41048194

Points: 7

# Comments: 1



from Hacker News: Front Page https://ift.tt/V6fh23u
Continue Reading
July 17, 2024

Hi, everyone. I created a note-taking website for electronics and circuits where you can draw circuit diagrams and write text notes at the same time.

I am a Digital IC designer, and I self-study different types of analog and digital circuits a lot. However, I found a problem. Circuits have many different architectures and are hard to memorize due to numerous experiential tips. I want to document what I learn in my note app, but I found there is no method for me to easily draw circuit and block diagrams alongside text notes.

This issue has bothered me for a long time, from my master's school to my current working life. I decided to solve it, so I created a note-taking website specifically for electronics and circuits, called VisCircuit.

With VisCircuit, you can easily draw circuit diagrams, block diagrams, and write text notes simultaneously. I have already used it for two weeks and have noted down things I find hard to remember, such as SRAM, amplifier circuits, and PCB components of Arduino and Raspberry Pi. I found this tool really useful for memorizing knowledge about electronics and circuits.

Currently, I have opened VisCircuit for alpha testing, and I want to let some people use it and give me feedback. Feel free to try it, and I will really appreciate what you think about this project. Leave any suggestions for improvement. Thank you very much.

Comments URL: https://news.ycombinator.com/item?id=40987770

Points: 7

# Comments: 0



from Hacker News: Front Page https://viscircuit.com
Continue Reading
July 14, 2024

Hey HN. I’m Ivan, hacker from Ukraine.

For about a year, I was working on Listenly — an app to listen to text content with OpenAI's natural-sounding text-to-speech model.

At some moment, I realized that it would be cool to take all the public domain e-books and create audio versions for them. So I did it... kind-of.

It would cost an immense amount of money to generate all the audio right away (OpenAI TTS costs approximately $0.84/hour of audio; 11labs, for comparison, is 10 times more expensive). So, I took a more gradual approach.

I took all the metadata from the Project Gutenberg catalog (it's about 70GB of dirty XML), cleaned it, put it into my database, and created a browsable catalog. When the first user visits a book page on Listenly, I download the full text of the book, save it in my cloud storage, and calculate the price for audio generation based on the book's length. Then, if the user decides to purchase it, we generate the audio.

I know it’s not perfect.

I've burned out a couple of times already while doing it.

But still, I need to show it to the world. And I’ll be glad to hear your feedback.

Peace.

Comments URL: https://news.ycombinator.com/item?id=40961385

Points: 10

# Comments: 8



from Hacker News: Front Page https://ift.tt/SvfmVqk
Continue Reading
July 07, 2024

Hi all! Excited to share rss2newsletter after completing dev work for the initial release.

The idea for this project came out of necessity, as I wanted to share my articles via email newsletter. I was looking for a super minimal, lightweight, and open source solution, and when none existed, I decided to create one.

For any sizable number of email recipients, a popular platform like Mailchimp will easily cost you hundreds or even thousands per month in per-contact fees. rss2newsletter, on the other hand, allows you to use Amazon SES, so you can reach your audience at pennies on the dollar.

Beyond these factors, I also wanted something that could run on an internet-connected potato it's so easy on your system and fully automated so you can set it and forget it.

So, I created (and put under a free software license):

https://github.com/ElliotKillick/rss2newsletter

rss2newsletter (integrating with Listmonk and Amazon SES for ultra-low-cost emails) is a drop-in solution that requires almost no setup besides connecting with SES and styling your emails. It's also competitive at what it does with proprietary self-hosted solutions like Sendy, which requires your system/VPS to have some rather beefy specs to run well.

Let me know if there are any other features you would like to see. I hope you can find my project helpful to you!

Comments URL: https://news.ycombinator.com/item?id=40898313

Points: 8

# Comments: 4



from Hacker News: Front Page https://ift.tt/X57JRUc
Continue Reading
July 01, 2024

I took a small break from coding SumatraPDF and wrote a note taking application that is perfect for me: https://edna.arslexis.io/

Edna is a note taking app for developers and power users. A cross between Obsidian and Notational Velocity.

Markdown, plain text, code, works in browser so no installation required, private (notes are stored in your browser or disk) and secure (can encrypt notes with a password).

The story so far.

I was always attracted to editors with minimalistic UI, like https://mak.ink/, simplenote, Notational Velocity. I like having most of the screen estate for writing because writing and editing is what note taking apps are for.

But: most of them are very thin on features and UI.

I saw Heynote and it was one of those minimalistic writing UIs with not many features.

I liked their concept of dividing notes into blocks so I forked Heynote and started coding.

The goal was to combine writing-oriented, minimalistic main UI while also providing on-demand UI for features and efficient operation. Things like context menu, type-down note switcher, command palette, quick access shortcuts, plenty of keyboard shortcuts.

Another goal was privacy and security. The notes never leave your computer and can be encrypted with a password. It also makes the code simpler because I don't need any backend storage, user accounts and auth etc.

Sadly, only Chrome and Edge provide the necessary file system api, on other browser you can only store notes in local storage, which means no sharing between computers or accessing the notes with other software.

40 working days and 528 commits later, here's what I've added:

  * added support for multiple notes
  * ability to store notes on disk
  * and if you store notes in a directory managed by DropBox, OneDrive etc., you get sharing of notes between computers
  * Ctrl + P: UI for switching between notes, creating new notes, deleting notes, inspired by Notational Velocity
  * Ctrl + Shift + P: command palette like in vs code
  * context menu to access frequently used functionality
  * Ctrl + E to open note from history (list of recently opened notes)
  * ability to assign Alt + 0 ... Alt + 9 quick access shortcuts 
  * ability to encrypt notes with a password
  * export all notes to a .zip file
  * automatic, daily backup of notes to a .zip file (optiona, see Settings)
  * Ctrl + B to navigate between blocks
  * re-designed Settings UI
  * added ability to execute Go blocks
  * support Svelte and Vue in code blocks
  * ported the UI code from Vue to Svelte 5, just because I could
  * converted from desktop app to run in the browser
(Ctrl is on Windows, on Mac it's ⌘).

I've been using it daily while working on it. 94 notes and counting.

I still have ideas for improvements but it has all the core features for productive work.

The app: https://edna.arslexis.io/

The code: https://github.com/kjk/edna

Comments URL: https://news.ycombinator.com/item?id=40846242

Points: 6

# Comments: 0



from Hacker News: Front Page https://ift.tt/U9pwklX
Continue Reading
Subscribe to: Posts (Atom)