Show HN: Yet Another Notepad App for macOS Any suggestion is welcomed and appreciated! https://ift.tt/kWnI9C6 August 31, 2023 at 03:07PM
Show HN: Vanity Git commit hash generator Hi HN! This is just a fun little tool I made after I got nerdsniped by noticing that one of my commits naturally started with "fae". I thought that was cute, so I looked up existing tools that make vanity commit hashes, but none of them seemed great to me (and none supporting signing commits). I learned a fair deal about how git actually stores commits while making this, and I think I came up with a novel way to generate a vanity hash: adding an extra header to the commit file. This was just a quick project to satisfy my curiosity, but I thought you all might find it neat. Notice that all the commits in that repo start with "fae0"! - Anna https://ift.tt/yh2WMQX August 31, 2023 at 12:43PM
Show HN: Chatmate: Discover and create chatbots Chatmate.dev allows you to easily make gpt4 based chatbots by combining multiple chat completions and/or document retrievals. You can chain different components together or run them in parallel and then use their responses in future prompts/components. To get started, create a project and then create a chat component. A single chat component is the same as one chat completion. You can add more chat or document components that use the responses of previous components in their prompts. There are some simple demos in the "discover" page. You can also publish your own chatbots and share them at the share url. The first demo is a simple document extraction. I copied a few posts from today's hackernews and fed it as a pdf. I then used the document retireval in the prompt for the final chat completion. The second demo is a teaching assistant chatbot for a data structures course. It is made up of 4 components, 1) Standalone query, which converts the user input to a standalone question (so that the document retrieval can be improved) 2) Thought generator, generates a sentiment based on the user's input (i.e. the user seems stressed about their data structures homework) 3) Document retrieval, retrieves lecture notes from over 400 documents 4) combines all the components into one system prompt for a better response. Roadmap: 1) Code components - run any code (including network calls) 2) Conditional components - uses gpt functions to decide which components to run (components are the functions) 3) Multitenancy (i.e. publish your bot at {botname}.chatmate.dev 4) Verisoning - chat with multiple versions of your bot (easy comparison of prompts) If you have any feedback, feel free to reach out at "jmiran15@jhu.edu". https://ift.tt/0XPLTgl August 30, 2023 at 09:52AM
Show HN: Open Interpreter – CodeLlama in your terminal, executing code Hey HN. Over the summer I built Open Interpreter, a CLI that lets you ask Code-Llama or GPT-4 to write/run code. It runs multiple languages (Python, Shell, HTML/CSS, Node JS rn) then sends the output back to the language model. It’s essentially an open-source, local implementation of OpenAI’s Code Interpreter. No limits on file size, runtime timeouts, or web access. Everything is streamed beautifully, rendered with Markdown, and syntax highlighted. Try it out and let me know what you tried! - Killian https://ift.tt/Sx6BLOv August 30, 2023 at 05:33AM
Show HN: Query your database using plain English on premise Hi folks, My friend Sami and I recently built Vizly, a Mac application that allows anyone to query their databases using plain English. Vizly is built on Llama 2, llama.cpp, and runs fully on-premise. We are running two Llama models, one for natural language to SQL translation, and another that uses the results from the SQL to render visualizations. That means there are no external APIs and all the AI models are running locally on your MacBook. We tried to make Vizly very easy to share as well. Every Vizly instance creates a share link that can be accessed by anyone on the same network as you. Just send the share link to anyone on the same network and they will be immediately able to run AI-powered queries, hosted from your device. Vizly previously used to be a hosted solution for querying CSVs and now we are on-premise specifically focussed on databases. Would love if you could try it out and give us any feedback! https://www.vizly.fyi/ August 30, 2023 at 05:10AM
Show HN: Mu – A Micro App Platform Hey all Sharing a new piece of work I've been doing with a friend. Mu is a new micro web app platform which enables building and sharing apps instantly with storage, auth and payments built in. Apps are single file, built in the browser and rendered as an iframe. They're "micro" because they're quite literally tiny single purpose utilities like a hackernews reader or old school guest book. It's mostly at this point something that scratches a personal itch. Making app development super simple and lightweight. Sort of like living GitHub gists. And trying to build a simpler, cleaner place to consume the web. Right now nothing more than a cool hack I'm sharing. Feedback obviously welcome. Cheers Asim https://mu.app August 29, 2023 at 05:12PM
Show HN: Toybox – A Laravel TALL starter kit for solopreneurs Hey peeps! Here's a project I've been working on for the last two months. It initially started as trying to be a simplified boilerplate for Laravel, but I think it's gone a bit beyond that. With recent tooling releases in the Laravel ecosystem, there's a ton of exciting tools to work with, but it's either annoying to set it all up every time, or it's difficult to try and gather it all up for every piece you'll need for your SaaS. To that end, Toybox attempts to collate what is in my opinion the best of modern Laravel, and while being simple to start, run and launch with. This is how I also came up with the name - pick and choose all your favourite Laravel toys and see how quickly you can build products with it. I've never been a fan of Docker and similar tools. While I see their value, I've generally not had a good experience and it always felt like a waste of my time trying to debug infrastructure instead of writing application code. So on that front Toybox goes back to basics - it targets only one stack, and is made to be able to initialise its repository, provision the server it is currently on, and deploy itself from your local machine, all with Bash scripts. Lastly, I tried to include guidance and support for scaling beyond an MVP and Bash scripts: The README includes tons of recommendations for various services & tools for all manner of things you need for your SaaS. https://ift.tt/QDlbgJf August 29, 2023 at 02:26PM
Show HN: Mail Organizer for Gmail This Google Apps Script labels emails accoding to the address the email was sent to. For example, you own the domain name "example.com", and you set up an email forwarding service such as Forward Email or ImprovMX to relay all emails sent to "*@relay.example.com" to your Gmail account. The script will label your emails according to a set of rules. For example: - "hello@relay.example.com" will be labeled "hello" - "hello-world@relay.example.com" will be labeled "hello" and "world" - "hello.world@relay.example.com" will be labeled "hello/world" ("world" as a sublabel of "hello") - "hello.world-yo.wassup@relay.example.com" will be labeled "hello/world" and "yo/wassup" https://ift.tt/kwhTU9Q August 28, 2023 at 11:35AM
Show HN: MoodMinder – Swift Anger Regulation for Better Emotional Well-Being Hey Hacker News community! We're excited to showcase MoodMinder, a mental health app MVP that empowers individuals to swiftly regulate anger and enhance emotional well-being. MoodMinder was born out of a desire to provide quick anger regulation solutions for busy individuals. Unique Features: Rapid Mood Identification: Identify anger triggers and tension levels swiftly. Instant Personalized meditations: Receive tailored meditations for immediate anger control. Cognitive Reappraisal: Shift perspectives to defuse triggers in real-time. Quick Interactive Games: Engage in games designed for anger regulation in just minutes. As an MVP, we're seeking insights from the Hacker News community to shape our app's development. Your feedback is pivotal. Thank you for being part of our journey! https://ift.tt/mR1V4vA August 27, 2023 at 09:42PM
Show HN: Hermes – SMM backdoor and client for usermode privilege escalation Hermes is an open source system management mode backdoor which allows a user mode application to elevate its own privileges and interact with memory without any direct access at smm level. https://ift.tt/6e3SoBN August 27, 2023 at 10:26PM
Show HN: RISC-V Linux Terminal emulated via WASM Weekend creation: A Linux terminal on top of a RISC-V emulator running in the browser via WebAssembly, powered by the Cartesi Machine. Check cool commands to experiment in the project page https://ift.tt/InYlzNA https://ift.tt/MSCFbfZ August 28, 2023 at 01:21AM
Show HN: Sounds of Space – Hear comets, planets, black holes, and more Most audios are data translated and processed into hearable sounds in a process called sonification. Not all sounds are sonifications, though. For instance, the sound of Mars' wind is real. Every audio has a source link attached to it that will point you to the place I got the sound from. Tools: Svelte https://ift.tt/HuntrKT August 27, 2023 at 05:01PM
Show HN: Email Enricher, a Free, Offline Clearbit Alternative At my prior employer, we got Slack alerts for big company sign-ups I wanted the same for my new startup ( https://fillout.com ) but quickly found that Clearbit would cost us $7,000 / mo... Instead, I made this free npm package `email-enricher` the returns if an email is likely from a Fortune 1000 company Hope it's useful to someone else! https://ift.tt/ymNJVc4 August 26, 2023 at 02:51AM
Show HN: AhaApple – AI Idea Generator. One Click, Many Creative and Novel Ideas AhaApple. AI Idea Generator. One click, Many Creative and Novel Ideas. Leveraging AI, many brainstorming techniques, and many innovative techniques, AhaApple make it easy for you to gain more inspirations and ideas. https://ift.tt/6nJzMXs August 26, 2023 at 10:22AM
Show HN: Mail Memories – Export your email photos Hey HN, I’m Carlos, the maker behind Mail Memories ( https://ift.tt/1Du7rHW ), a web app that helps you find and save photos from your (Gmail) email. The app connects with your email account, finds all the images you’ve received and shows them in a gallery where you can view and download the ones you want to save. I made this out of curiosity, just to see what pictures were in my account when I first signed up for Gmail 18 years ago. I ended up finding photos of my grandmother and other family members, and old friends and colleagues I’d completely forgotten about. I was surprised by what I found, I hope you will be too. Can’t wait to hear your thoughts. Demo: https://ift.tt/z7ujDk8 https://ift.tt/1Du7rHW August 26, 2023 at 12:42AM
Show HN: A simple web app to combat phone addiction When I'm stuck on coding something, I find myself reaching for my phone even if I don't have any particular reason to do so. Inspired by Calm's DoNothingFor2Minutes.com which launched on HN 13 years ago [1], I made this simple webapp to see if my friends and I could go an hour without touching our phones. It is surprisingly difficult. According to a 2022 survey [2], the average US adult picks up their phone 352 times per day, or approximately once every 2m43s while they're awake. On browsers that support it (iOS 16.4+, most versions of Android Chrome), it uses the Screen Wake Lock API [3] to keep the page open, and falls back to nosleep.js [4] otherwise. From testing on my iPhone 14 Pro Max running iOS 16.6, battery life only went down 3 or 4 percentage points after an hour with the wake lock. Made this as a web app as a quick demo to be compatible across all mobile devices. As an app, we can probably save more on battery + not have the screen on. One caveat is that on iOS this will actually increase your Screen Time (although hopefully reduce your other category usage). I currently only track time on page through Google Analytics 4. No other calls are made to a server, although if we actually wanted to verify that you kept the page open vs. javascript/inspector-system clock-fu, we could add a verified mode that pings the server every X minutes. As a PWA, possibly due to an iOS/Mobile Safari quirk/bug [5], neither wake lock nor nosleep.js appear to work . [1] https://ift.tt/nFYLeAS [2] https://ift.tt/z3YeMb6 [3] https://ift.tt/A6KFq8Y... [4] https://ift.tt/csvzlbg [5] https://ift.tt/j7fwcD0 https://ift.tt/AqaXJsD August 25, 2023 at 02:15AM
Show HN: Collie – A minimal RSS reader just for you Collie is a minimal RSS feed reader application running on your desktop. With Collie, you can subscribe to multiple RSS/Atom feeds to organize your own news feed, receive a real-time notification when a new item is added to the subscribed feed, and save the items to read again or later. All you need is a local machine and the Internet. No virtual machine, no cloud infrastructures, no always-on database, and no account registration with privacy information required. I've been getting tech news from HackerNews, Lobsters, etc. on Twitter (It's X now, but I'll keep calling it Twitter anyway), but many of them have been terminated due to changes in Twitter's API policy. I went from place to place: Bluesky, Mastodon, Slack, and newsletter. However, I couldn't settle anywhere. The social media services such as Bluesky and Mastodon had too many unnecessary features as news feed. Slack RSS was good to get the news in real-time, but the notifications mixed with other workspaces overwhelmed me. The newsletters gave me a lot of high-quality information, but not in real-time. Then, I remembered Miniflux, the "minimalist and opinionated feed reader" that I had used past. This is the best option for my goal, but I had to pay for the hosted version or keep running docker machine on my local computer which did not have enough resources. Additionally, I didn't need a system that maintains multi-user sessions. Eventually, I had no choice but to create my own application, and that's why I made Collie, the minimal RSS reader just for me. https://ift.tt/1YUnxrH August 25, 2023 at 10:58AM
Show HN: OnePrompt – Personal Assistant ChatBot Using GPT OnePrompt is an iOS application similar to ChatGPT, utilizing the OpenAI API. OnePrompt offers unique plugins of utilizing iOS native features through "function calling." It also allows users to create their own custom plugins. You can find more information about creating custom plugins for OnePrompt at https://ift.tt/LZqAS4m . https://ift.tt/aBCTnHN August 24, 2023 at 08:57AM
Show HN: E-Ink Powered UK Rail Departure Board Using Badger 2040W Hey HN community, I've recently embarked on a tinkering project that merges the versatility of the Badger 2040W with the practicality of an E-ink display. Inspired by the UK Rail departure boards, I've created an E-ink version that updates in real-time with departure information. Would love to hear your thoughts, suggestions, or similar projects you've come across! https://ift.tt/FJN1UYP August 24, 2023 at 01:19AM
Show HN: Chat with GPT about medical issues, get answers from medical literature Clint is an open-sourced medical information lookup and reasoning tool. Clint enables a user to have an interactive dialogue about medical conditions, symptoms, or simply to ask medical questions. Clint helps connect regular health concerns with complex medical information. It does this by converting colloquial language into medical terms, gathering and understanding information from medical resources, and presenting this information back to the user in an easy-to-understand way. One of the key features of Clint is that its processing is local. It's served using GitHub pages and utilizes the user's OpenAI API key to make requests to directly to GPT. All processing, except for that done by the LLM, happens in the user's browser. I recently had a need to lookup detailed medical information and found myself spending a lot of time translating my understanding into the medical domain, then again trying to comprehend the medical terms. That gave me the idea that this could be a task for an LLM. The result is Clint. It's a proof-of-concept. I currently have no further plans for the tool. If it is useful to you as-is, great! If it is useful only to help share some ideas, that's fine too. https://ift.tt/THgkwiA August 24, 2023 at 04:45AM
Show HN: I made danluu's blog easier to read Hi, I'm Alex! I believe most of the knowledge is nowadays stored and hidden in personal blogs. I have a list of blogs that I read recurrently, and I have benefited myself a lot from this practice. One of the blogs that are usually recommended is the one by Dan Luu. Dan writes about a variety of topics in his blog, and I usually enjoy what he writes. But besides from the content Dan's blog stands out for the complete lack of CSS. IMHO this makes the content difficult to read (it's like reading text from a windows text editor). I believe more people will read and enjoy his blog if a pinch of CSS was added to the blog, so I've taken the liberty to enhance the reading experience. I wrote a script that periodically checks Dan's blog and publish the content in a static webpage (hosted using GitHub Pages). Regarding the CSS I just copied the CSS proposed in https://ift.tt/gfYWpdT and changed the font family. Give it a look and see what you think! Enjoy the improved readability. P.S. The code that does all this magic might not win any awards for beauty, but it gets the job done. If time permits, I "promise" to tidy it up in the future. Your understanding is appreciated! https://ift.tt/RTdBZah August 24, 2023 at 03:48AM
Show HN: Dataherald AI – Natural Language to SQL Engine Hi HN community. We are excited to open source Dataherald’s natural-language-to-SQL engine today ( https://ift.tt/JMDHbkA ). This engine allows you to set up an API from your structured database that can answer questions in plain English. GPT-4 class LLMs have gotten remarkably good at writing SQL. However, out-of-the-box LLMs and existing frameworks would not work with our own structured data at a necessary quality level. For example, given the question “what was the average rent in Los Angeles in May 2023?” a reasonable human would either assume the question is about Los Angeles, CA or would confirm the state with the question asker in a follow up. However, an LLM translates this to: select price from rent_prices where city=”Los Angeles” AND month=”05” AND year=”2023” This pulls data for Los Angeles, CA and Los Angeles, TX without getting columns to differentiate between the two. You can read more about the challenges of enterprise-level text-to-SQL in this blog post I wrote on the topic: https://ift.tt/tKPypZA... Dataherald comes with “batteries-included.” It has best-in-class implementations of core components, including, but not limited to: a state of the art NL-to-SQL agent, an LLM-based SQL-accuracy evaluator. The architecture is modular, allowing these components to be easily replaced. It’s easy to set up and use with major data warehouses. There is a “Context Store” where information (NL2SQL examples, schemas and table descriptions) is used for the LLM prompts to make the engine get better with usage. And we even made it fast! This version allows you to easily connect to PG, Databricks, BigQuery or Snowflake and set up an API for semantic interactions with your structured data. You can then add business and data context that are used for few-shot prompting by the engine. The NL-to-SQL agent in this open source release was developed by our own Mohammadreza Pourreza, whose DIN-SQL algorithm is currently top of the Spider ( https://ift.tt/V7jZsp8 ) and Bird ( https://ift.tt/SkVdN93 ) NL 2 SQL benchmarks. This agent has outperformed the Langchain SQLAgent anywhere from 12%-250%.5x (depending on the provided context) in our own internal benchmarking while being only ~15s slower on average. Needless to say, this is an early release and the codebase is under swift development. We would love for you to try it out and give us your feedback! And if you are interested in contributing, we’d love to hear from you! https://ift.tt/JMDHbkA August 24, 2023 at 12:08AM
Show HN: Cashe - A money library written in Ada Introducing Cashe: a Money library written in Ada 2022! The purpose of Cashe is to give Money its own high-precision datatype taking advantage of Ada's fixed type decimal system[1]. This allows storing money, associated with a currency, at a defined precision with the choice of utilizing fuzzy or exact equality (see readme for more details). It supports ISO Currencies[2] as well as Custom-defined currencies[3], and even a working Currency Exchange[4]. You can install it using Alire, which is Ada's package manager with a simple `alr with cashe` There's quite a bit of examples in the readme if you would like to see what the code looks like, but I also gave full code examples for almost all of the functions in the API Documentation[5]. [1] https://ift.tt/FTwjslm [2] https://ift.tt/ZoWc72t [3] https://ift.tt/rCUludo... [4] https://ift.tt/pgYJj4R... [5] https://ift.tt/9lvQ07a https://ift.tt/jcVi3Y9 August 23, 2023 at 09:51PM
Show HN: Make sense of all your files, links and messages in the cloud Hello everyone! Like most of you, we also use a lot of tools and have all our files, links and messages scattered over all those different tools in the cloud. Which often leads to not knowing where that one file is that you need. At best this means you waste 5 minutes looking for a file or link and at worst it means that valuable knowledge gets lost in a company. That’s why we created a place for you to connect all your tools, organize your files, and allow you to search across all your apps. Right now, you can connect up to 8 different tools, but there are a lot more to come! Give it a try and let me know your feedback! https://ift.tt/6PHg9Kp August 23, 2023 at 06:01PM
Show HN: Pip install inference, open source computer vision deployment Deploying vision models is time consuming and tedious. Setting up dependencies. Fixing conflicts. Configuring TRT acceleration. Flashing (and re-flashing) NVIDIA Jetsons. A streamlined, developer-friendly solution for inference is needed. We, the Roboflow team, have been hard at work open sourcing Inference, an open source vision deployment solution. Our solution is designed with developers in mind, offering a HTTP-based interface. Run models on your hardware without having to write architecture-specific inference code. Here's a demo showing how to go from a model to GPU inference on a video of a football game in ~10 minutes: https://www.youtube.com/watch?v=at-yuwIMiN4 Inference powers millions of daily API calls for global sports broadcasts, one of the world’s largest railways, a leading electric car manufacturer, and multiple other Fortune 500 companies, along with countless hackers’ hobby and research projects. Inference works in Docker and supports CPU (ARM and x86), NVIDIA GPU, and TRT. Inference manages dependencies and the environment. All you need to do is make HTTP requests to the server. YOLOv5, YOLOv8, YOLACT, CLIP, SAM, and other popular vision models are supported (some models need to be hosted on Roboflow first, see the docs; we're working on bring your own model weights!). Try it out and tell us what you think! https://ift.tt/Ogw35P8 August 23, 2023 at 04:34PM
Show HN: A CLI tool and controller to access K8s network through WireGuard Hi everyone! k8s-insider is a CLI tool to manage VPN networks and access Kubernetes workload and service resources directly through a WireGuard tunnel. It started as a simple Helm chart with a linuxserver/wireguard-like container image but, possibly due to my neurodivergence getting the better of me, evolved into a toolbox that, depending on the cluster configuration, can more or less automagically configure multiple networks with dynamic IP assignments and netpol-limited access to the cluster. I’ve found it to be a perfect middle ground between juggling multiple port-forwards and deploying something like Tailscale to the cluster. And it’s written in Rust, which made it oh-so-lovely to work on. :> https://ift.tt/Qq3IdHx August 22, 2023 at 09:00PM
Show HN: Breaklist – A Morning Briefing Printed on a Tiny Thermal Receipt I built Breaklist to organize the essential info I need to start my day. It generates a personalized morning briefing, optimized for thermal printers. The morning report currently includes: Task list Reminders Weather forecast Summary of latest top articles on Hacker News The result is a tidy, receipt-sized report that I can print and take on-the-go each morning. https://ift.tt/AN3W812 August 22, 2023 at 05:28PM
Show HN: Speleomorph, Shapeshifting Puzzle Metroidvania This was my entry for a Metroidvania Month game jam last year. I like how Metroidvanias make you rethink movement as the game goes on, and since I didn't want to design combat I focused on that. But I didn't want the different mechanics to be objects you pick up. The theme for the jam was "shapeshifting", which suggested the unusual mechanic seen here. Fortunately I'd forgotten about Snakebird or I might not have been bold enough to make the gravity+snake parts so prominent. And in the year since this came out, there have been at least three cool puzzle games nearby in design space: - Tetronimeow https://ift.tt/LbZkutP has a heavy focus on rotation (which I skipped to avoid confusion), it gets much more Metroidvania mileage out of the central idea - Growmi https://ift.tt/JtSLqif does a great job building mechanics out of the snake+gravity idea - The Plumber Thing https://ift.tt/HcMlDCQ If this looks familiar, I did post a Show HN last year, but dang invited me to re-submit it. I kept putting it off in hopes I could make a big splash when launching a new version: I have some ideas for touchscreens (currently keyboard only) and for an earlier game with more restricted abilities (no free transformation, then swapping with just one previous shape). But it's looking unlikely that I'll revisit it. https://ift.tt/rcGL2n8 August 22, 2023 at 08:41AM
Show HN: superwhisper – AI powered offline voice to text for macOS Hey HN, I built superwhisper out of frustration with the native dictation capabilities of macOS. Inaccurate, required manual punctuation, didnt activate in some contexts or would have audio capture issues. I wanted a replacement that worked offline, had cross language support, was configurable and worked in any application. Under the hood the app is using whisper.cpp, which runs really well on the Apple Silicon chips. You can use the base and standard size models for free, larger models sizes and languages other than english are paid. Let me know what you think! For context, I launched this just one month ago and have been rapidly adding features and making fixes. If you want to follow along with development, I post release info on twitter ( https://ift.tt/S7gjnxm ) or you can subscribe to emails via the form on the website (very bottom). https://ift.tt/vR8Nfnx August 21, 2023 at 07:33AM
Show HN: Fake Hacker News – See what HN has to say before you post Hi HN! I’ve been lurking for a while, but out of fear of being steamrolled by HN readers or maybe just natural introversion, I’ve always been too scared to post or comment. Which is why 1. this is my first real Hacker News submission 2. my friend Michael and I built "Fake" Hacker News, a place to post and see what AI-generated HN comments might say. Here’s a video of me using fakeHN to test this very submission: https://ift.tt/dhj2UOq?... And an example of one of our generated posts: https://ift.tt/T4MDqm6 To try it, submit a title and text, and depending on traffic and the powers that be, after ~5 seconds, you’ll see some Fake HN comments and replies. We don’t support url submissions yet, but we’re happy to build it if the community wants it! Other features to knock out: deeply nested replies, streamed comments, and higher-fidelity comments mapping to real readers, since the generations now are still pretty shallow. Instead of the quick and dirty system in place now, we think it’d be really cool to see how more nuanced AI agents with the opinions and biases of real individual HN readers might respond. I’d love to see what fakeHN posts you’ve tried and hear any feedback, whether you feel like it’s more of a nifty toy or could eventually solve real problems. If nothing else, it’s been funny to try random posts and see the results. :) - Justin and Michael https://www.fakehn.com/ August 21, 2023 at 02:56AM
Show HN: Talk to AI Models in Terminal Hi everyone, nice to meet you and I am a newcomer of HN. I have made a binary tool Aih that could communicate with Bard, ChatGPT, Claude, and Llama(HuggingChat) from the terminal. https://ift.tt/bil6AEu Since CAPTCHA challenges and bots detecting have become increasingly difficult, I've changed my strategy from hacking the APIs to simulating a real browser's action. The tool first takes the logged-in cookies of Google, ChatGPT, Claude, and HuggingChat accounts from the real Chrome browser, then it opens an invisible instance of Chromium for communication, then displays the answers in terminal. I think it's useful especially when I am researching some topics and need to compare answers of those AI models at the same time. Feel free to test and welcome provide feedback! https://ift.tt/bil6AEu August 20, 2023 at 05:40PM
Show HN: Just intonation keyboard – play music without knowing music This is a keyboard in just intonation. It can play the notes a piano can. The big difference from a piano is that all the notes become consonant. You can play without knowing any music theory. Hit arbitrary notes with the rhythm you want, and the pitches will work. Not understanding the buttons is fine. Even rolling your elbow around your keyboard is fine. If you are a musician and press the wrong key while playing a song, it will still fit. It will sound like you made an intelligent, conscious choice to play another note, even though you know in your heart it was an accident. Beginner jazz musicians rejoice. It's not an AI making choices for you; it's just a very elegant interface. What makes this possible is several new discoveries in psychoacoustics about how harmony works. While a piano lays out notes in pitch space, this keyboard is able to lay out notes in consonance space. When you play random notes, they tend to be "close together" on the physical keyboard. Distance on the keyboard maps well to distance in consonance space, so those random notes are close together in consonance space and sound good together. According to Miles Davis, a "wrong" note becomes correct in the right context. If you try to play a wrong note, the purple buttons you press will automatically land you in the right context, even if you don't know what that context is yourself. So you can stumble your way through an improv and the keyboard will offer the right notes without needing you to think about it. Harmonic consonance of chords can be read directly off the numbers in the keyboard, which implies that these numbers are a good language to think about music with. It doesn't take years of training, just reading the rules. The subset of playable songs is different from a piano, which means that songs in your existing piano repertoire will snip off some notes. Hardware for thumb keys would fix this, so you could play your existing piano songs in full, plus other songs a piano can't play. I don't have such hardware so I haven't implemented this. The other way is to have two keyboards and a partner. The remaining issue is that there is no sheet music in just intonation. Unfortunately, I have had no success in finding piano sheet music in a common, interpretable format. So while I do have a converter from 12 equal temperament to just intonation, there are no input files to use it with... https://ift.tt/p6udvz2 August 20, 2023 at 04:19AM
Show HN: Rivet (YC W23) – Open-Source Game Server Management with Nomad and Rust Hey HN! Rivet is an OSS game server management tool that enables game developers to easily deploy their dedicated servers without any infra experience. We recently open-sourced Rivet after working on it for the past couple of years. I wanted to share some of my favorite things about our experience building this with the HN community. My cofounder and I have been building multiplayer games together since middle school for fun (and not much profit [1]). In HS, I stumbled into building the entire infrastructure powering [Krunker.io]( http://Krunker.io ) (acq by FRVR) & other popular multiplayer web games. After wasting months rebuilding dedicated server infrastructure + DDoS/bot mitigation over and over, we started building Rivet as a side project. Some interesting tidbits: - ~99% Rust and a smidgeon of Lua. - Bolt [2] – Cluster dev & management toolchain for super configurable self-hosted Rivet clusters. It’s way over-engineered. - The entire repo is usable as a library. Our EE repo uses OSS as a submodule. - Traefik used as an edge proxy for low-latency UDP, TCP+TLS, & WSS traffic. - Apache Traffic Server is under-appreciated as a large file cache. Used as an edge Docker pull-through cache to improve cold starts & as a CDN cache to lower our S3 bill. - ClickHouse used for analytics & game server logs. It’s so simple, I have nothing more to say. - Serving Docker images with Apache TS is simpler & cheaper than running a Docker pull-through cache. - Nebula has been rock solid & easy to operate as our overlay network. - We use Redis Lua scripts for complex, atomic, in-memory operations. - Obviously, we love Nix. - We keep a rough SBOM [3]. - Licensed under Apache 2.0 (OSI-approved). We seriously want people to run & tinker with Rivet themselves. We get a lot of questions about this: [4] [5] Some HN-flavored FAQ: > Why not build on top of Agones or Kubernetes? Nomad is simpler & more flexible than Agones/Kubernetes out of the box, which let us get up and running faster. For example, Nomad natively supports multiple task drivers, edge workloads, and runs as a standalone binary. > [Fly.io]( http://Fly.io ) migrated off of Nomad, how will you scale? Nomad can support 2M containers [6]. Some quick math: avg 8 players per lobby * 2M lobbies * 8 regional clusters = ~128M CCU. That’s well above PUBG’s 3.2m CCU peak. Roblox’s game servers also run on top of Nomad [7]. We’re in good company. > Are you affected by the recent Nomad BSL relicensing [8]? Maybe, see [9]. > How do you compare to $X? Our core goal is to get developers up and running as fast as possible. We provide extra services like our matchmaker [10], CDN [11], and KV [12] to make shipping a fully-fledged multiplayer game require only a couple of lines of code. No other project provides a comparably accessible, OSS, and comprehensive game server manager. > Do you handle networking logic? No. We work with existing tools like FishNet, Mirror, NGO, Unreal & Godot replication, and anything else you can run in Docker. > Is anyone actually using this? Yes, we’ve been running in closed beta since Jan ‘22 and currently support millions of MAU across many titles. [1]: https://ift.tt/jutMsaG [2]: https://ift.tt/L3Vw8HN... [3]: https://ift.tt/Q17EY2q... [4]: https://ift.tt/9ve32fF... [5]: https://ift.tt/9ve32fF... [6]: https://ift.tt/uGbXCPj [7]: https://ift.tt/nmNEwf3 [8]: https://ift.tt/YOHQAcg... [9]: https://ift.tt/jo7GKh2 [10]: https://ift.tt/UvYgE6L [11]: https://ift.tt/A82YwRk [12]: https://ift.tt/ZedYPSN https://ift.tt/azDEJXg August 19, 2023 at 07:08PM
Show HN: Saf – simple, reliable, rsync-based, battle tested, rounded backup I had this backup code working reliably for years, using local file system, vps/dedicated server, or remote storage for backup, then I finally get time to wrap README, iron few missing switches and publish. Should be production ready and reliable, so it could be useful to others. Contributors are welcome. < https://github.com/dusanx/saf > https://ift.tt/V79NnqY August 19, 2023 at 02:49AM
Show HN: AI chatbot to reduce support costs by 80% Hey, HN! We have developed a bot for technical support. The task was set to reach the next level of chatbots. The thing is that nowadays bots too often redirect customers to support staff when a question was not found in the bot's presets database or the customer requires some kind of interaction with the company (for example, wants to buy a product). We have succeeded in reducing the percentage of situations where the bot transfers the customer to the operator. At the same time, it can still ask for help from a real person if the case requires it. 1. the bot is capable of answering complex questions that require analyzing the company's knowledge base (especially the technical part). 2. the possibility to leave a request for some action was introduced. For example, a customer can leave a request for connection to a tariff plan . An example of such a bot for the fictitious company BananaCom is given on the site, you can test it. After the request is made, the company receives the necessary information. Of course, if the client really wants to talk to an employee, he will be transferred to the employee. When to transfer to employees is a matter to be discussed with the individual company, so now a bot on the site will try to answer all your questions. We did a lot of work before the product was ready, we can't reveal all the secrets, but for connoisseurs we'll give you a hint: https://ift.tt/1vWIiMG https://ift.tt/TtlYmLj August 18, 2023 at 11:47PM
Show HN: An Open-Source Collaborative Database Development Tool A couple of years ago, we had an interesting idea. When a development team within an organization consists of around 10 members or fewer, controlling the risks associated with database changes might be achieved through trust and real-time communication. However, as the team grows, the responsibilities within the team become more specialized. Imagine a scenario where different branches of the business exist, each with its own set of developers, team leads, testers, testing leads, DBAs, and more. Relying solely on traditional communication methods becomes increasingly challenging when it comes to managing change risks. Envision a platform where a change request goes through a sequence of checks: it's first reviewed by colleagues familiar with the business, then approved by the business lead, followed by scrutiny from the database lead, and finally assessed for security by the security lead. Does this approach effectively control the risk associated with that change when it's executed? In 2019, we embarked on building the first piece of this puzzle: ODC. Fast forward to today, after more than three years of development, ODC has evolved from a specialized developer tool designed for OceanBase (OB) into an enterprise-grade collaborative control platform, with plans to support multiple data sources. And today, we are thrilled to announce that we are open-sourcing our project. You can find the entire four-year code history on GitHub ( https://ift.tt/lV6oJ5q ). We're excited to hear your thoughts on this concept and whether you identify any potential challenges or opportunities that lie ahead. Your insights will play a crucial role in shaping the future of this project. Looking forward to your feedback! https://ift.tt/lV6oJ5q August 18, 2023 at 04:06PM
Show HN: Run globally distributed full-stack apps on high-performance MicroVMs Hi HN! We’re Yann, Edouard, and Bastien from Koyeb ( https://www.koyeb.com/ ). We’re building a platform to let you deploy full-stack apps on high-performance hardware around the world, with zero configuration. We provide a “global serverless feeling”, without the hassle of re-writing all your apps or managing k8s complexity [1]. We built Scaleway, a cloud service provider where we designed ARM servers and provided them as cloud servers. During our time there, we saw customers struggle with the same issues while trying to deploy full-stack applications and APIs resiliently. As it turns out, deploying applications and managing networking across a multi-data center fleet of machines (virtual or physical) requires an overwhelming amount of orchestration and configuration. At the time, that complexity meant that multi-region deployments were simply out-of-reach for most businesses. When thinking about how we wanted to solve those problems, we tried several solutions. We briefly explored offering a FaaS experience [2], but from our first steps, user feedback made us reconsider whether it was the correct abstraction. In most cases, it seemed that functions simply added complexity and required learning how to engineer using provider-specific primitives. In many ways, developing with functions felt like abandoning all of the benefits of frameworks. Another popular option these days is to go with Kubernetes. From an engineering perspective, Kubernetes is extremely powerful, but it also involves massive amounts of overhead. Building software, managing networking, and deploying across regions involves integrating many different components and maintaining them over time. It can be tough to justify the level of effort and investment it takes to keep it all running rather than work on building out your product. We believe you should be able to write your apps and run them without modification with simple scaling, global distribution transparently managed by the provider, and no infrastructure or orchestration management. Koyeb is a cloud platform where you come with a git repository or a Docker image, we build the code into a container (when needed), run the container inside of Firecracker microVMs, and deploy it to multiple regions on top of bare metal servers. There is an edge network in front to accelerate delivery and a global networking layer for inter-service communication (service mesh/discovery) [3]. We took a few steps to get the Koyeb platform to where it is today: we built our own serverless engine [4]. We use Nomad and Firecracker for orchestration, and Kuma for the networking layer. In the last year, we spawned six regions in Washington, DC, San Francisco, Singapore, Paris, Frankfurt and Tokyo, added support for native workers, gRPC, HTTP/2 [5], WebSockets, and custom health checks. We are working next on autoscaling, databases, and preview environments. We’re super excited to show you Koyeb today and we’d love to hear your thoughts on the platform and what we are building in the comments. To make getting started easy, we provide $5.50 in free credits every month so you can run up to two services for free. P.S. A payment method is required to access the platform to prevent abuse (we had hard months last year dealing with that). If you’d like to try the platform without adding a card, reach out at support@koyeb.com or @gokoyeb on Twitter. [1] https://ift.tt/OXSHpKh... [2] https://ift.tt/3kypxIi... [3] https://ift.tt/4VYovf7... [4] https://ift.tt/bNgYJG1... [5] https://ift.tt/OWo6btN... https://www.koyeb.com/ August 17, 2023 at 04:15PM
Show HN: Interactive exercises for GNU grep, sed and awk Hello! For the past few months, I've been using a Python framework called Textual to create TUI apps for interactive exercises. Released the app for GNU awk earlier today, so thought I'd create a post here. If you already know how to manage Python packages, you can use the following command to get all the three apps: pip install grepexercises sedexercises awkexercises `pipx` should also work, but I haven't tested it. The GitHub repo has the source code as well as more detailed installation instructions. You can use alternative CLI tools to solve these exercises as well. For example, Perl instead of GNU awk or ripgrep instead of GNU grep and so on. Hope you find these TUI apps useful. I'd highly appreciate your feedback. Happy learning :) https://ift.tt/hQRti4l August 17, 2023 at 03:43PM
Show HN: I resurrected one of the top dead Show HNs OneView was first posted to HN in 2017, but died sometime around late 2019. Using the web archive I cobbled together something that works. According to this[0], oneview is the #5 top dead show hn. [0] https://ift.tt/D75RUfQ... https://ift.tt/5srQbHU August 17, 2023 at 08:26PM
Show HN: Create your own Discover Weekly Choose a few playlists to get new tracks from, and they'll be filtered out every Monday to a new playlist. Kind of like Discover Weekly, but you get to choose the music sources. Hope you enjoy, and I would love feedback! https://ift.tt/uAKbLyP August 17, 2023 at 08:17PM
Show HN: Strich – Barcode scanning for web apps Hi, I'm Alex - the creator of STRICH ( https://strich.io ), a barcode scanning library for web apps. Barcode scanning in web apps is nothing new. In my previous work experience, I've had the opportunity to use both high-end commercial offerings (e.g. Scandit) and OSS libraries like QuaggaJS or ZXing-JS in a wide range of customer projects, mainly in logistics. I became dissatisfied with both. The established commercial offerings had five- to six-figure license fees and the developer experience was not always optimal. The web browser as a platform also seemed not to be the main priority for these players. The open source libraries are essentially unmaintained and not suitable for commercial use due to the lack of support. Also the recognition performance is not enough for some cases - for a detailed comparison see https://ift.tt/Ylh9ad0 Having dabbled a bit in Computer Vision topics before, and armed with an understanding of the market situation, I set out to build an alternative to fill the gap between the two worlds. After almost two years of on-and-off development and 6 months of piloting with a key customer, STRICH launched at beginning of this year. STRICH is built exclusively for web browsers running on smartphones. I believe the vast majority of barcode scanning apps are in-house line of business apps that benefit from distribution outside of app stores and a single codebase with abundant developer resources. Barcode scanning in web apps is efficient and avoids platform risk and unnecessary costs associated with developing and publishing native apps. https://strich.io August 17, 2023 at 06:54PM
Show HN: How to use LLMs to generate accurate SQL for real-world data Hey HN, We are Zain and Ashish, founders of Vanna AI. We recently embarked on an experiment to see if large language models (specifically LLMs) could help in generating SQL queries for real-world datasets. We initially started this project as a web app but realized that it was most useful and had broadest applicability as a Python package since you can then incorporate it into an existing workflow (Jupyter notebook, Slackbot, etc). We've had some good success with customer datasets but we've generally heard a lot of skepticism so we decided to write a paper about the methodology we're using and how various LLMs compare. Let us know if you have any questions or requests. The underlying Python package is open source. There is a server component to store and retrieve metadata but by next week there will be a fully open-source and locally runnable version. Cheers! https://ift.tt/Be2O5xi August 17, 2023 at 05:47PM
Show HN: Rules – Shortcuts Automation Based on Calendar Events Read and thought once too often that "This would be trivial if Calendar Events were triggers for Personal Shortcuts Automations". So decided to create a Mac app for it. The app works similar to Rules in Mail: - Specify some conditions (e.g. Calendar is "Work", Location contains "zoom") - Choose shortcuts to run on events that meet the conditions - you can have multiple actions, each with a different offset and custom input Good to know: - The app can only trigger automations while your Mac is awake (missed actions can be triggered on wake up) - The free version offers full functionality, but is limited to a max of 2 rules. Pro is a one-time purchase - All your data stays on device + no ads or data collection I would appreciate any feedback, especially what automations you might use the app for https://ift.tt/0NeIy5Q August 17, 2023 at 02:23PM
Show HN: Marqo – Vectorless Vector Search Marqo is an end-to-end vector search engine. It contains everything required to integrate vector search into an application in a single API. Here is a code snippet for a minimal example of vector search with Marqo: mq = marqo.Client() mq.create_index("my-first-index") mq.index("my-first-index").add_documents([{"title": "The Travels of Marco Polo"}]) results = mq.index("my-first-index").search(q="Marqo Polo") Why Marqo? Vector similarity alone is not enough for vector search. Vector search requires more than a vector database - it also requires machine learning (ML) deployment and management, preprocessing and transformations of inputs as well as the ability to modify search behavior without retraining a model. Marqo contains all these pieces, enabling developers to build vector search into their application with minimal effort. Why not X, Y, Z vector database? Vector databases are specialized components for vector similarity. They are “vectors in - vectors out”. They still require the production of vectors, management of the ML models, associated orchestration and processing of the inputs. Marqo makes this easy by being “documents in, documents out”. Preprocessing of text and images, embedding the content, storing meta-data and deployment of inference and storage is all taken care of by Marqo. We have been running Marqo for production workloads with both low-latency and large index requirements. Marqo features: - Low-latency (10’s ms - configuration dependent), large scale (10’s - 100’s M vectors). - Easily integrates with LLM’s and other generative AI - augmented generation using a knowledge base. - Pre-configured open source embedding models - SBERT, Huggingface, CLIP/OpenCLIP. - Pre-filtering and lexical search. - Multimodal model support - search text and/or images. - Custom models - load models fine tuned from your own data. - Ranking with document meta data - bias the similarity with properties like popularity. - Multi-term multi-modal queries - allows per query personalization and topic avoidance. - Multi-modal representations - search over documents that have both text and images. - GPU/CPU/ONNX/PyTorch inference support. See some examples here: Multimodal search: [1] https://ift.tt/NPGH1IB... Refining image quality and identifying unwanted content: [2] https://ift.tt/LsESyAx... Question answering over transcripts of speech: [3] https://ift.tt/nVigR5S Question and answering over technical documents and augmenting NPC's with a backstory: [4] https://ift.tt/bRZpS8f... https://ift.tt/M0i96cI August 16, 2023 at 07:31PM
Show HN: Prompt-Compose.js Use Axioms and Compositions to Build Modular Prompts This JS library provides basic axioms for building and managing GPT prompts. It helps you build small and reusable prompt components and then let you compose them together to build larger ones. https://ift.tt/jvWMuGt August 16, 2023 at 05:49PM
Show HN: WorkPhotos – A simplified approach to job recording for physical trades Hello, we are Ross, Craig, Alan, and Pawel, the co-founders of WorkPhotos (https://ift.tt/WlHjPY0). WorkPhotos is a mobile-first job recording app designed for physical trades, with a focus on taking and sharing images at work without cluttering your personal photo gallery. The idea for our app was born in a 103-year-old engineering workshop during one of those famous WTF moments. Believe it or not, Ross's grandad used to fix cart wheels, though, unfortunately, we don't have any pictures of that era. After a considerable period of development, numerous iterations, and valuable user testing, we launched an early build in January this year. Since then, we've been hard at work, making further improvements and engaging with our users. We are thrilled to announce that we are now preparing for the official launch next week. At WorkPhotos, we believe in simplicity as the cornerstone of our design philosophy. Our long-term vision revolves around integrating with other products rather than adding complexity directly to the app. You can easily find our app on the local Apple and Play stores; just search for "WorkPhotos." We are currently available in several locations: Australia, Canada, New Zealand, South Africa, the UK, and the US. To access the app, users can log in using their phone number or email. Concerned about onboarding emails? Simply add the prefix 'HN' to your username or workspace, and we will ensure you don't receive any marketing communications. Deactivating your account will instantly delete your data. While our existing users have provided positive feedback, we genuinely value the perspective of the Tech community. We invite you to try out the WorkPhotos app and share your feedback with us! Your input will be immensely helpful as we strive to improve our app further. We are here to answer any questions and we look forward to hearing from you! August 16, 2023 at 01:30PM
Show HN: Watermelon – Source-available passive documentation search engine Hey there HN! We're a pair of devs and we are looking to get feedback for our source-available passive documentation search engine. Passive documentation is the code context devs are generating as they talk about code in systems such as GitHub, Slack, Notion and Jira. Our search engine serves both our IDE extension (for individuals) and GitHub app (for teams). As devs we know that there are certain PRs that stay unmerged for weeks or even months, not because of the technical complexity, but because of the debate that they produce around changes in the business logic: "Will this change really improve our metrics?" We know that non-technical stakeholders (managers and designers) can bring a more holistic view to these debates but code review is too technical for them. So we decided to build this with the premise of "let's contextualize devs with business logic". We’re starting with a GitHub app that contextualizes Pull Requests with pieces of related passive documentation. Our big vision is to build a copilot for engineering leaders, starting by automating code review. If we're already indexing passive documentation tied to a new PR, we suspect that we can provide a "first health check" to a PR and say whether or not it's meeting the business requirements. Here's the repo if you want to check it out: https://ift.tt/hDmcWGj And here's a blog post explaining why we made our search engine source-available: https://ift.tt/j4WQ29w... Please give us your feedback! Thanks. https://ift.tt/hDmcWGj August 14, 2023 at 08:17PM
Show HN: Lottielab – Create product animations in the browser easily Hi HN! Today we are releasing Lottielab, a web-based animation tool, to the public as an open beta. The main tool for editing and exporting Lottie animations today is Adobe After Effects, a 30-year-old visual effects tool that’s not fit for this purpose, has a steep learning curve, and requires a patchwork of error-prone plugins. With Lottielab, we are aiming to reduce the friction of creating and editing product animations by providing an easy-to-use editor with out-of-the-box support for import and export of the Lottie format and many others. Feel free to play around with the tool and let me know what you think - I'm here to answer your questions. Happy animating! https://ift.tt/O5v1w64 August 15, 2023 at 05:58PM
Show HN: LLM Connected with REST APIs Hey, folks here is a peek into Jujutsu. We at Poozle are working with hundreds of APIs and it has been always frustrating to 1. Search the API in the documentation or ask ChatGPT 2. Then copy it to the postman and understand/test the API 3. Generate code to integrate into the codebase We thought how about having all of this at one place. We currently fine-tuned LLM on public REST APIs to reduce hallucination and then combined it with ChatGPT and Postman. I look forward to feedback, feature requests and discussions! https://ift.tt/j9N4AUR August 15, 2023 at 04:02AM
Show HN: I resurrected one of the top dead Show HNs OneView was first posted to HN in 2017, but died sometime around late 2019. Using the web archive I cobbled together something that works. Open to hearing people's thoughts on whether this is ethical or not... https://ift.tt/gKjkhsZ August 14, 2023 at 11:54PM
Show HN: I made a tool that turns images into videos to boost our Twitter reach Recently there were some changes to the Twitter algorithm and one of the most important ones was boosting video content even more in the feed, which got me thinking: "Why shouldn't we benefit from the algo changes and get a boost every time we are sharing some visuals?" So I spent the weekend building a tool that: - Turns your images into videos - Has 30 beautiful animated gradients that we can pick from - Is completely FREE I'd love to know your thoughts about it! https://ift.tt/oqtL5jT August 14, 2023 at 04:49PM
Show HN: Awayto v2 short demo; an actual all-in-one framework Hey folks, just putting this up as a demo link for people to try out. It's a project I've been working on since January and in light of recent framework posts lately I figured I'd start talking about my own. The link is a demo site of Awayto v2 [1] (ignore the front page info that's all from version 1). Awayto [0] started out as a quick deploy app which grew to exist via AWS. I felt the need to make something that wasn't so closely tied to cloud infra, and Awayto v2 is that. Currently deployed on hetzner vms, using Tailscale for networking, there is a great deal of things going on. There is a local installation path planned, as long as you provide your own servers, etc, as it all just works on Tailscale anyway. I'm still working on docs, but the goal is to spit out _everything_ a dev might want to control in their stack. My current version of deploying to hetzner sets up 7 servers (2 ns, exit, build, app, db, svc). Git profile [2] for more info, tech stack info. This is just a short demo and will only be up a limited time. There's no email validation or anything, gibberish is welcome. You are not being tracked. I know I need how-to docs, video assists, and all that. Slow and steady. It's being hosted from a single warehouse in the Pacific Northwest, be kind. Caching is in play and not perfectly tuned so maybe wait a few minutes if something doesn't automatically show up. Any feedback is awesome. Cheers! [0] https://ift.tt/IVcSs8k [1] https://ift.tt/9XEUZGM [2] https://ift.tt/PeI84N7 https://awayto.store/ August 13, 2023 at 05:28PM
Show HN: Mixtape of 200 “futuristic” songs circa 1980 I'm posting this long mix of 200 "futuristic" music recordings, in chronological order (from the mid 1970's to the mid 1980's). Some are obvious (eg: "She Blinded Me With Science") while others are long forgotten (eg: G.G. Tonet's "Dedicated To Norbert Wiener" or Jyl's "Silicon Valley") --- Circa 1980 Mixtape https://ift.tt/7KjJIAb --- While the theme of the linked mix (ie: tech) probably interests some here, it is likely too fluffy for many others so apologies for that. This thing took me almost two years to finish, so in a moment of weakness I am going ahead and posting it here. There actually is a tech angle to why it took so long. After I gathered the 200 audio tracks I wanted, I wound up stymied for several months because trying to match the timbre and loudness of 200 songs overwhelmed me. During that time I began writing a program in my spare time to band-split all the files and match their perceived loudness. I got around half-way through that when OpenAI released GPT4. On a whim, I asked it to write a BASH script to perform the auto-EQ: a couple evenings of minor tweaks and it was done https://ift.tt/TUSgGsC so I went ahead and completed the mix. The final mixing together of songs - I am not a DJ and have no experience beat-matching - was also done programmatically (wrote a program that takes start- and end- times of the regions to crossfade, and then ramps samplerate up or down for the two tracks. August 13, 2023 at 01:32PM
Show HN: FalkorDB fork from RedisGraph bringing it back to life The team behind RedisGraph decided to take a stab at bringing this disruptive technology back to market. We plan to rebrand it and release it as a stand alone product, following the same guidelines we have followed for the last 6 years: * Working in the open with the community * Always provide superior performance. * Easy to adapt https://ift.tt/hgyFeKO August 13, 2023 at 02:32AM
Show HN: Graffiti, Hyper-Local Anonymous Message Boards (No App Required) Hello HN! I'm Phil, the creator of Graffiti - A web-based hyper-local anonymous message board (think YikYak but with no app required and the frontend aesthetics of Craigslist). It's meant to be pretty lightweight and run on almost anything with a browser and basic location services. It's built mostly in Python and Svelte, and currently running on a small Ubuntu VM + Postgres DB. I originally started this project to leave geo-located comments for my brother and his friends around town since we all were fans of long meandering walks. I saw some friends-of-friends leave posts as well so I started to add additional features like: -Replies: Start your message with "@@CommentID" to get added to a thread below the parent post. -Hashtags: Use a URL like https://ift.tt/TGvr4fV to see only comments including #parks. -Distance filters: Currently Graffiti supports sorting distances between 100M and 5KM, though I'd like to build better ways to support more granular radii and other geo-based options. -Tripcodes (optional): Use an imageboard-style tripcode to identify yourself to friends and build a reputation without having to keep the same username. -Basic Search: Search the text of a post, username, or tripcode to filter posts. There's plenty more to work on, and I'm really interested in what HN thinks would be useful features to prioritize next. Sometimes I get asked about toxicity and other moderation issues with a project like Graffiti. As this is fairly new project I haven't developed a robust formalized moderation framework or the tools to manage auto-removal of certain content. I think early on a few pieces work to limit the toxicity seen by any given user: -Granular location filters (400M -> 5KM) practically limit what content you're seeing since people will have to be right nearby. I'd like to make this even more advanced in future updates. Adding better drawable bounding-boxes, rate-limiting around specific areas where toxicity may be high, etc. -Filtering the feed based on arbitrary hashtags. For example your friends could all post under https://ift.tt/3B8kT9r (the # auto populates in the message when accessed through that URL). You'd only see content using that hashtag, effectively limiting a majority of posts. A few updates I hope to have soon: -A basic reporting function -A basic blacklist/whitelist based on keywords (this is a little tricky given no logins, but would love any ideas). I'm thinking an early safe search on/off type button could be an option to filter what is in your feed. Most people probably won't see many posts outside major cities like Boston, New York, DC, etc. but we're always looking for new use-cases and to see how people interact with Graffiti so I encourage playing around! Here's a simple Google slide deck with some getting started tips and tricks: https://ift.tt/DTXxlPC ... I'd love to hear your feedback on Graffiti! I'm happy to discuss any comments here, but feel free to send an email to GraffitiHQ@protonmail.com to chat with me directly. Thanks! https://ift.tt/9mZV16x August 12, 2023 at 02:53AM
Show HN: Tetris, but the blocks are ARM instructions that execute in the browser OFRAK Tetris is a project I started at work about two weeks ago. It's a web-based game that works on desktop and mobile. I made it for my company to bring to events like DEF CON, and to promote our binary analysis and patching framework called OFRAK. In the game, 32-bit, little-endian ARM assembly instructions fall, and you can modify the operands before executing them on a CPU emulator. There are two segments mapped – one for instructions, and one for data (though both have read, write, and execute permissions). Your score is a four byte signed integer stored at the virtual address pointed to by the R12 register, and the goal is to use the instructions that fall to make the score value in memory as high as possible. When it's game over, you can download your game as an ELF to relive the glory in GDB on your favorite ARM device. The CPU emulator is a version of Unicorn ( https://ift.tt/x8MT9mk ) that has been cross-compiled to WebAssembly ( https://ift.tt/mVr4dUh ), so everything on the page runs in the browser without the need for any complicated infrastructure on the back end. Since I've only been working on this for a short period of time leading up to its debut at DEF CON, there are still many more features I'd eventually like to implement. These include adding support for other ISAs besides ARM, adding an instruction reference manual, and lots of little cleanups, bug fixes, and adjustments. My highest score is 509,644,979, but my average is about 131,378. I look forward to feedback, bug reports, feature requests, and strategy discussions! https://ift.tt/wGtHMnA August 11, 2023 at 05:26AM
Show HN: VectorFlow – Open-Source Vector Embedding Pipeline Hey HN We've just released the initial version of our open-source vector embedding pipeline. It's designed to embed large volumes of data. While embedding a few documents for Q&A is straightforward, consistently ingesting gigabytes of unstructured data is a whole different ballgame. By using our API, you can embed raw data and store vectors in your vector database, sidestepping the complexities of cloud infrastructure. Now, in true YC spirit, we're launching before everything is polished. Our Github repo ( https://ift.tt/aeZ7ijz ) is a work in progress, and we're eager to get it in front of the community early on. Check out our Github repo and let us know what you think. Your feedback, suggestions, and critiques will be highly appreciated as we continue to refine and develop. https://ift.tt/aeZ7ijz August 10, 2023 at 11:05PM
Show HN: Q&A with AI Trained on Bankruptcy Law I crawled a #$%^ ton of bankruptcy case law and pointed a LLM at it to answer bankruptcy legal questions. I just tried it on the Supreme Court's request today in its order stopping the Purdue Pharma settlement[1], and it gives a decent answer. > The parties are directed to brief and argue the > following question: Whether the Bankruptcy Code authorizes a > court to approve, as part of a plan of reorganization under > Chapter 11 of the Bankruptcy Code, a release that extinguishes > claims held by nondebtors against nondebtor third parties, > without the claimants’ consent. ChatLaw's answer: The Bankruptcy Code does not explicitly authorize a court to approve, as part of a plan of reorganization under Chapter 11, a release that extinguishes claims held by non-debtors against non-debtor third parties, without the claimants’ consent. However, courts have interpreted certain provisions of the Bankruptcy Code to permit such non-consensual third-party releases under certain circumstances. The relevant provisions of the Bankruptcy Code include Section 105(a), which empowers the court to issue any order, process, or judgment that is necessary or appropriate to carry out the provisions of this title, and Section 1123(b)(6), which allows a plan to include any other appropriate provision not inconsistent with the applicable provisions of this title. In the case of In re: Mallinckrodt PLC, (District of Delaware, 02/08/2022), the court noted that while Section 524(e) of the Bankruptcy Code should be read to preclude non-debtor releases, releases are not the equivalent of a discharge. The court also noted that the Third Circuit has recognized that bankruptcy courts do have statutory and constitutional authority to approve a plan of reorganization that contains non-consensual third-party releases, albeit, only in extraordinary cases. In the case of In Re: 18-13374-mew Aegean Marine Petroleum Network Inc. (Southern District ofNew York, 2019-04-08), the court noted that some Circuit Courts of Appeal have held that bankruptcy courts lack the power to grant nonconsensual third-party releases of the kind that the Debtors seek here. However, other Courts of Appeal, including the Second Circuit Court of Appeals, have held that bankruptcy courts have the power to impose involuntary releases, but that such involuntary releases should be imposed only in rare cases. In the case of 22-110 In re: Purdue Pharma L.P. (Second Circuit Court of Appeals, 5/30/2023), the court concluded that two sections of the Bankruptcy Code, 11 U.S.C. 105(a), 1123(b)(6), jointly provide the statutory basis for the bankruptcy courts authority to approve a plan that includes nonconsensual releases of third-party claims against non-debtors. The court further held that the bankruptcy courts inclusion of the releases is equitable and appropriate under the specific factual circumstances of this case. In the same case, in a concurring opinion, Judge Richard C. Wesley agreed that a bankruptcy court has the authority to approve a Chapter 11 reorganization plan that includes nonconsensual nondebtor releases, based on the court's precedent in In re Drexel Burnham Lambert Grp., Inc., 960 F.2d 285, 293 (2d Cir. 1992). However, he expressed concerns about the lack of explicit statutory basis for such releases in the Bankruptcy Code. In conclusion, while the Bankruptcy Code does not explicitly authorize non-consensual third-party releases, courts have interpreted certain provisions of the Code to permit such releases under certain circumstances. The permissibility of such releases often depends on the specific facts and circumstances of the case, and courts have cautioned that such releases should be approved only in rare cases. [1] https://ift.tt/oHbyGCt... https://www.chatlaw.us August 11, 2023 at 05:28AM
Show HN: Easiest way to convert PDF tables to Excel We built a Windows app to convert PDF tables to Excel. You just have to take a screenshot of the table. Why try another app when there's so many PDF to Excel converters? It is: - Faster - More convenient - More accurate than other converters (including Excel's Power Query). Feel free to test it with complex tables (like the ones found in financial documents). https://table2xl.com August 10, 2023 at 06:05AM
Show HN: Bubblic – end loneliness together using the power of your voice We have gotten over 1000 voice messages left by the users of our platform. We take privacy seriously, so all data are anonymized and are not sold to anyone. So far, we had a user who said that 'had it not been for Bubblic, I might not be here today'. This gives us so much drive to carry on with our project! We'd appreciate any feedback you have :) https://bubblic.co/ August 10, 2023 at 08:01AM
Show HN: Remindme – A tool to set short-term reminders from the terminal Hello there! The idea behind this CLI tool is to use it for short-term reminders, e.g. to remind you (via OS-specific notifications) to do something in 2 hours or in 10 minutes. The app is supposed to be cross-platform compatible. Still, I have limited access to platforms, so it was tested only on MacOS, Ubuntu (via VirtualBox), Fedora (via VirtualBox) and Windows 10 Home. I'd appreciate any feedback on how it works on these and other OS-es. Also, I have never tested it outside my time zone (GMT+2), so it would be nice to hear from folks from other parts of the world. Any feedback, comments, and questions are greatly appreciated, as it's just a tool built for fun. Here is a short intro on how to use it: Once installed (via Homebrew, APT, YUM or binary), the usage is pretty simple: - to run the app: remindme start - to set a reminder in 5 minutes: remindme in --min 5 --about "Rewatch LOTR editors cut" Use `--sec` and `--hr` flags to set reminders in seconds or hours, respectively. - to set a reminder at a specific time: remindme at --time "22:20" --about "Replay Gothic video games" Use `--am` or `--pm` flags with 12-hour A.M./P.M. format time value if you from this way of setting time. - to see the list of incoming reminders: remindme list - to stop the app: remindme stop Please, check the GitHub repo README.md file to see the full list of available commands. Thanks, and have fun! https://ift.tt/vLSWDbs August 10, 2023 at 12:56AM
Show HN: Automatically convert your GPT-3.5 prompt to Llama 2 Hey HN! I'm working on OpenPipe, an open source prompt workshop. I wanted to share a feature we recently released: prompt translations. Prompt translations allow you to quickly convert a prompt between GPT 3.5, Llama 2, and Claude 1/2 compatible formats. The common case would be if you’re using GPT 3.5 in production and are interested in evaluating a Claude or Llama 2 model for your use case. Here's a screen recording to show how it works in our UI: https://twitter.com/OpenPipeLab/status/1687875354311180288 We’ve found a lot of our users are interested in evaluating Claude or Llama 2, but weren’t sure what changes they need to make to their prompts to get the best performance out of those models. Prompt translations make that easier. A bit more background: OpenPipe is an open-source prompt studio that lets you test your LLM prompts against scenarios from your real workloads. We currently support GPT 3.5/4, Claude 1/2, and Llama 2. The full codebase (including prompt translations) is available at https://ift.tt/Ba2twTo. If you’d prefer a managed experience, you can also sign up for our hosted version at at https://openpipe.ai/. Happy to answer any questions! August 10, 2023 at 01:47AM
Show HN: MagicQuit – closes apps when you don't use them anymore (free) I often end up having 15+ applications open in my Dock. And, unfortunately, I tend to never close them. While Arc Browser does a great job for browser tabs, I didn’t find any fully satisfying solution for MacOS. One used way too much power and the other one would have taken quite some time to set it up. So instead I decided to develop an app which took x times more of my free time. MagicQuit is entirely free, open source, 100% offline and closes apps that you haven’t been using in the last 12 hours (customizable). Feature-wise I wanted to keep it as clean and simple as possible. It also uses nearly ~0% of cpu usage. Give it a try if you’re a Mac user and also having the same issue with many open applications: https://magicquit.com https://magicquit.com August 9, 2023 at 05:18PM
Show HN: The Population Project Two years ago, I turned 50. After a successful career as an entrepreneur, a business angel and a novelist, I set out to start a philanthropic venture under the following constraints: - it had to be global. - it had to be beautiful (in my eyes, at least). - it had to be technology and stats driven. I decided I would try to list the full name and date of birth of all humans alive. While some may find the concept pointless, I immediately knew I had struck gold: - it was global and incredibly hard. - it had an almost artistic quality to it, like an ever-changing installation. - as a libertarian, I resent that states conduct censuses and then sit on the data. - One billion people in the world aren't officially registered. At least someone would acknowledge their existence. I created a non-profit called The Population Project. I would never make a dime off it, but at least my costs would be tax-deductible. I then started researching lists of names online. I quickly adopted two principles. First I would collect a minimal set of information : full name, birth date, and birth place. Second, I would only scrape public information, i.e. nothing behind a password. After a few months, I realized I needed help from more experienced developers. I chose to work on 4D, a platform I had used in the past to develop my company's information system. It was a tough choice: 4D is not a leading player in the back-end world, but I figured the growth of API tooling would make language choice less critical. The first iteration of our database was frustrating - way too slow to publish a website. I learned the power of incremental change, with each marginal improvement saving you a few percent of speed or space. I also got to implement concepts I had heard about but never implemented, such as mirroring, partitioning, or hash-indexing. Then I hired a team of six data processors in Madagascar who clean up and process the lists found online. Lots of Python and Excel macros in their day-to-day. I have instilled in them an obsession with quality. A bad record will sit in our base forever. After trying dozens of softwares, we've settled on Adobe Acrobat and Octoparse. The final piece was the website. I lucked out in finding a strong team in Romania. They build with Next.js and deploy on Vercel. I gave them Wikipedia as the model to aim for. We/they haven't been able to match Wikipedia's simplicity. Our pages are too heavy. But I find the site user-friendly, pleasing to the eye and reasonably fast. We can and we will do better. A word about privacy. Some people complain that because it publishes names and DOBs, the Population Project infringes on their privacy. We obviously don't see it that way. - All our info is public. That DOB you find on the site is probably in the voter list of your state, a list that anyone can request or plainfully download. - The info we publish is minimal. Basically, we say that you exist. No one will find anything about your race, religion, sexual preferences, job or income. - We have adopted Wikipedia's privacy policy. We do not record your IP, unless you create or edit a record. - We're using Matomo for our Analytics. Great stuff. It's not free but they do not use your data like GA. Why am I telling you all this? From the beginning, I've envisioned a three-step process: 1) Build the database and populate it with millions of Western profiles. 2) Launch the site, where anybody can create or edit records and share them with their family. 3) When we've reached critical mass (1B records?), start making deals with NGOs and governments, and venture into other alphabets. We have just completed step 1. Step 2 is daunting as hell. I have grown a business but I have never grown a website. While I am ready to spend a bit of money on PR or SEO, I am not delusional: to reach the level of success we have in mind, we need this thing to go (somewhat) viral. How do you do that? https://ift.tt/MfAdBZu August 7, 2023 at 09:16PM
Show HN: Ggml.js – Serverless AI Inference on Browser with Web Assembly What is ggml.js? Run any ggml ported ML models directly on your web browser with ggml.js This project provides JavaScript bindings on ggml models, so that you can embed GGML models to your web apps to build serverless AI inferencing. Currently the framework supports following model types: - Dolly v2 - GPT2 - GPT J - GPT NEO X - MPT - Replit - StarCoder You can find more details about the framework: https://ift.tt/jNuOkVq For live demo examples, you can visit here: https://ift.tt/WOcRDBJ Source Code: https://ift.tt/koMcjSK Please do provide any feedback/questions/suggestions in the comments. I'll be happy to take it up :) https://ift.tt/jNuOkVq August 9, 2023 at 12:50AM
Show HN: Building an Audio Journaling App – Looking for Community Insights I am a product designer by profession, and recently, I ventured into coding and started developing applications. Today, I'm excited to share a project I've been passionately working on. The concept is a voice-activated journal: just voice-record your thoughts, and the app will transcribe them into text. I built this to help those like me who struggle to build a journaling habit. Also has features that encourage habbit building like a streak/tracker and a threshold marker encouraging you to record a minimum amount. I used OpneAI Whisper to power the transcriptions which means you can record journals in most common languages and it will transcribe it accurately. I am hoping to get feedback from all of you: Would you use this? If Yes, how often? If No, What would hold you back? Would you pay for this? If yes: How much, If no: what if added would make you want to pay for it? Screenshots: https://ift.tt/U8GSkQ9 https://ift.tt/7uSGxmd August 8, 2023 at 12:45PM
Show HN: Ready to Send – a Gmail add-on that automatically drafts email replies Hi HN! Ready to Send works seamlessly with Gmail, crafting draft responses for your new, unread emails. You can add personalized info for each contact, ensuring every message sounds genuine. LMK your feedback below! https://ift.tt/kuOD8wZ August 8, 2023 at 06:49AM
Show HN: An AI Textbook Hi HN, Introducing Inquistory, the world's first AI textbook for history. Unlike a textbook, students don’t passively read through long chapters of content. Inquistory briefly explains a high level ideas a student, and student's must inquire about the content to advance. Like a textbook, Inquistory utilizes both primary and secondary sources create content. This involves displaying relevant images inline with text and providing citations for the sources referenced. Read the wild story how we got started: https://ift.tt/bVXtF4u Currently in private beta, you can sign up on our website: https://inquistory.com/ https://inquistory.com/ August 8, 2023 at 03:10AM
Show HN: I created an app to transfer files from my PC to any device wirelessly I found transferring images from my PC to my phone very tedious. Using Whatsapp and other such apps reduced image quality and had limitations on the file size. Using online file transfer solutions were too slow for my taste. Hence, I created a desktop app to send all sorts of files - images, PDFs, lengthy videos, etc. to any device connected to the same Wi-Fi network. You also don't need to download a separate mobile app. There's only 3 steps involved - select your files, scan a QR code, download your files. You can download it now for free via https://fyldrop.com August 7, 2023 at 12:23AM
Show HN: Api2ai – create an API agent from any OpenAPI Spec api2ai parses OpenAPI Spec to generate an agent that can make API calls. For context, I recently need to explore a handful of API suites and thought LLMs can help expedite this process. After some digging, I found OpenAPI Specs are perfect fit for function calling. Based on a text prompt, api2ai can select the right endpoint and properly parse request params and make api calls. It also handles authentication, currently it supports basic auth, api keys, and bearer token schemes. The tool has helped me explore and see APIs in action without a deep dive into the docs or using postman. It’s open source and hopefully can be useful for you, too. Please let me know if you have any questions or feedback. https://ift.tt/H9Pr6DO August 6, 2023 at 04:38PM
Show HN: Briefed – Summaries for Hard Paywalled Content Hey HN! Briefed developer here. Briefed creates summaries for (mostly hard) paywalled content. I built it because it's something that I wanted, but couldn't find (specifically the hard paywalled part). Why did I want this? 1. There are a lot of publications that I'm only tangentially interested in. Not enough to warrant a full subscription but enough to want to get the gist of what they're saying. A step between reading the title and reading the full article. Here's a list of the publications we currently create summaries for: https://ift.tt/rFaN4Kk 2. I often don't have the time to read entire articles. I can save an article as "read later" in my rss app, but I've often lost interest by the time I get to it. Briefed creates two summaries for each article: one detailed, and one tldr. Here is an example of one: https://ift.tt/7tzsxro... 3. Sometimes I've read the full paywalled article and want to read comments here on HN, but hard paywalls limit the engagement those posts will get. Hopefully a detailed summary is enough to start meaningful and curious conversation. I'm still kicking the tires, so the first 500 people to sign up will get the first year free (normal price is $12/year; the price that I felt I would personally pay for such a service). Use the promo code LAUNCH500 at checkout. The code will be automatically invalidated after 500 people use it. Let me know what you think! Any feedback , issues, or questions are welcome. Thanks, Brandon https://briefed.news/ August 6, 2023 at 12:53AM
Show HN: Matrix. A Sci-Fi Comic On the occasion of completing 100 short stories in Matrix, I thought of sharing it with the wider audience. Matrix is a culmination of my 9 months of travel across India and 2 days that I spent in Barcelona. I started the project with an aim to improve my writing. But now I feel like the project is directing me on how it wants to take shape. And as I continued, The project took a shape of its own. I believe it is in a good enough shape to be considered as a mockumentary on life and meaning. It still only has me as a primary contributor because of which it has my limitations and my biases. If you like to contribute, Please feel free to create a pull request on the दुनिया(World in Hindi) branch. जय श्री राम| https://ift.tt/NAwbSDg August 5, 2023 at 03:27PM
Show HN: Custom Haskell handlers for Nginx This is rather a mature project. It began out of curiosity: I wanted to test if Haskell FFI was powerful and expressive enough to interconnect C and Haskell code flawlessly. Particularly, if C strings generated inside Nginx can be shared within Haskell code and what must be done to respect their lifetimes etc. Recently, I released version 3.2.0 with revamped README (with a lot of examples) and a new approach to building Haskell handlers using the modernized cabal v2-build for dependencies. https://ift.tt/o7SRYWg August 4, 2023 at 04:49PM
Show HN: Gdańsk AI – full stack AI voice chatbot Hi! It's a complete product with integrations to Auth0, OpenAI, Google Cloud and Stripe, which consists of Next.js Web App, Node.js + Express Web API and Python + FastAPI AI API I've built this software, because I wanted to make money by selling tokens to enable users talking with the chatbot. But I think Google / Apple will include such AI-powered assistant in their products soon, so nobody will pay me for using it So I open source the product today and share it as a GNU GPL-2 licensed software I'm happy to assist in case if something is unclear or requires additional docs and answer any questions about Gdańsk AI :) Thanks https://ift.tt/zSwI7lf August 5, 2023 at 12:59AM
Show HN: Open-access book on platform governance Hi there, I'm a political theorist, a professor at Northwestern law school and a founding fellow, board member, etc. of the Integrity Institute. I also was the in-house democratic theorist on Facebook's "civic integrity" (election protection) team for a while, and helped out with the research supporting the creation of the Meta Oversight Board. I just published an academic book with Cambridge University Press bringing together those experiences with research in political science to argue that the way forward for mitigating the harms of big internet platforms and governing user behavior on them is to create global direct democratic institutions for them. You can read the whole book for free on Cambridge's website or by downloading the open-access (license CC-BY-NC-ND 4.0) PDF at the link. If you want a hard copy, you can also buy it in paperback or hardcover. https://ift.tt/aicXzr6 August 5, 2023 at 12:21AM
Show HN: Open-source library to manage todo items in Python code I made this library that collects all TODO items from a python project, creates automated summaries and notifies them over email, SNS or SES etc. It is highly customizable allowing to add custom summaries, custom notifier and integration with downstream applications. https://ift.tt/0AgFXwB August 4, 2023 at 11:04PM
Show HN: Try my new Bash prompt PS1='\$ ' # short and sweet prompt old_cmdno=${old_cmdno-0} old_lines=${old_lines-0} old_cols=${old_cols-0} prepare_terminal() { stty rows $((LINES - 1)) printf "\n\033[1A" old_lines=$LINES old_cols=$COLUMNS } update_status_line() { local exit=$? local getcmdno='\#' local cmdno=${getcmdno@P} local esc=$(printf "\033") local pwd=$PWD local dots= [ $LINES -eq $old_lines -a $COLUMNS -eq $old_cols ] || prepare_terminal local status_esc="$esc[7m$esc[m" while true; do [ "${pwd#/*/}" == "$pwd" ] && break local status="$esc[7m$(date +%m-%d/%H:%M)$esc[m $HOSTNAME $dots$pwd" local status_len=$((${#status} - ${#status_esc})) [ $status_len -le $COLUMNS ] && break pwd=${pwd#/} pwd=/${pwd#*/} dots='...' done status_len=$((${#status} - ${#status_esc})) [ $status_len -gt $COLUMNS ] && status= printf "${esc}7$esc[%s;1H$esc[K%s$esc[1;%sr${esc}8" $((LINES + 1)) "$status" $LINES if [ $exit -ne 0 -a $cmdno -ne $old_cmdno ] ; then printf "!%s!\n" $exit fi old_cmdno=$cmdno } PROMPT_COMMAND='update_status_line' August 4, 2023 at 08:50AM
Show HN: ChatMyFiles, Open Source ChatPDF ChatMyFiles is an open-source alternative to ChatPDF: you upload any PDF or Microsoft Office document and ask questions about it. Unlike other "chat with your documents" solutions, ChatMyFiles can be self hosted using a one-click deploy script that uses Terraform to deploy a - Vector database - Server - (Optional) Open-source LLM such as Falcon, Llama, or GPT4All to your virtual private cloud (VPC). We used Langchain to interface with open source LLMs and Ragstack to deploy to Google Cloud: https://ift.tt/W15bhpl https://ift.tt/OWBsH6E August 4, 2023 at 01:40AM
संदेश
