Show HN: I built an open-source unit testing suite for prompts inputs https://bit.ly/3NDJd3Q

Show HN: I built an open-source “unit testing” suite for prompts ⮂ inputs Hi HN, I'm pleased to share Promptspot, an open-source (Apache License 2.0) project that helps automate testing of large language model (LLM) prompts against an array of input data. Modern LLMs offer an enormous amount of leverage if you "teach the bot to fish" — i.e. simply prompt it with both a "system prompt" (which typically doesn't change often) and a dynamic input, which is often application state, search results, recent activity, user profile data, etc. Existing playgrounds and prompt management systems often lack the rigor and flexibility required for this dynamic approach — and as more teams adopt this pattern, I hope Promptspot can become a useful tool for testing, monitoring, and centralizing this data. Promptspot currently supports text-davinci-003 from OpenAI, but I hope to add support for more models soon. Contributions welcome! https://bit.ly/44273x6 June 29, 2023 at 02:07PM

Show HN: Hivekit Geospatial App Platform https://bit.ly/432JzXd

Show HN: Hivekit, Geospatial App Platform Hey everyone, We’re Adam & Wolfram, the founders of Hivekit ( https://bit.ly/3xMRrjo ), a geospatial app platform to track people and vehicles, stream updates, and execute logic based on spatial events. This allows teams in logistics, ride-sharing, delivery, construction, agriculture or AR gaming to fully concentrate on what makes their offering unique without having to worry about the complex infrastructure required to run large scale geospatial apps. We both have a long history of building realtime data services for industries like financial trading, gaming or app development - but there’s something interesting about that. We were repeatedly approached by companies in mines, food delivery networks, ride sharing companies, mines and even farm-equipment manufacturers who were willing to twist our purpose-built solutions into a pretzel to make them work for geospatial tracking. Recognizing this lack of commodity tech, we started meeting with tech folk from around the world, went to onsite visits in English mines, Italian mozzarella plants and German construction yards (one of my favorite parts of the job) and learned that there’s a huge need for a low level realtime data platform for geospatial apps. Hivekit is that platform. It lets you send location and other data from large numbers of vehicles and devices, subscribe to realtime update feeds from apps and websites, store routes and historic data, run scriptable logic in response to spatial events and comes with all the bits needed to build a successful geospatial app such as online status, geofencing, rich auth and permissions, fulltext search or pubsub notifications. But we want to do more: We’re already working on a 3D world map that lets you track all workers, vehicles and objects, add custom UIs and interactive map overlays, pause and rewind time and - most importantly - control your workforce Command & Conquer style: Simply select a few units, assign a task and Hivekit will translate it into individual instructions, send them out and track their progress. But our real goal isn’t for human operators to control their workforce, but for an AI to automate and optimize operations. Now, before everyone gets too excited: this won’t be an AI in the GPT sense, but more “traditional” ML, optimizing for individual value sets, e.g. “ensure that my taxi drivers are positioned optimally during the course of the day to ensure the lowest possible time to pick up.” You can read more about our plans here: https://bit.ly/44ijX9G Who are we? Wolfram previously built https://bit.ly/44GPX7Z , https://bit.ly/437dgXb and https://bit.ly/44ksvgs , Adam is Director of Engineering for a trading tech company. https://bit.ly/3xMRrjo June 29, 2023 at 01:13PM

Show HN: Papyrus A simple paper backup tool https://bit.ly/3PBeZ46

Show HN: Papyrus – A simple paper backup tool https://bit.ly/42YjQ28 June 29, 2023 at 10:13AM

Show HN: Tweak your chord progressions for practice or composition https://bit.ly/46stRaD

Show HN: Tweak your chord progressions for practice or composition I'm excited to share with HN a new pet project I've been working on to explore how AI can create and explain harmonic chord progressions - Chord Variations. The project uses GPT-4 to generate unique and interesting chord combinations based on user input chord progression. It's akin to having a virtual musical assistant that can help non-musicians and musicians alike explore and create harmonious sound without needing any prior knowledge of music theory. The generated chord suggestions maintain a similar vibe to the user input. Alternative chord progression includes extended chords, chord substitutions, unique passing chords, and more. Additionally, musical theory explanations within the tool is helpful for users not just to create music, but understand the underlying structure it's built on a bit better. These chord progression suggestions can be used for practice or composition. As a musician myself, I am having quite a lot of fun playing around with it. One of the things I'm proud of is how the application really dips into music theory. It includes nuanced aspects such as dominant chords, secondary dominant chords, and the famous 2-5-1 chord progressions. That said, the development journey was full of lessons. Dealing with the latency of the GPT-4 API was particularly challenging. I used a Celery based queue system + client polling to manage the delay between request and response (from OpenAI API). Additionally, to keep the chord names consistent, I used a combination of prompting and regex. There are still some bugs that need to be squashed but overall I am pretty happy with the results. I'd love to hear your thoughts and feedback on the project. Also, if you're curious about anything, I am happy to delve into the details in comments. Feel free to take Chord Variations for a spin here: https://bit.ly/3r6c9K5 Looking forward to some interesting discussions! https://bit.ly/3r6c9K5 June 27, 2023 at 08:17PM

Show HN: Everything you need to stay up-to-date with your stock investments https://bit.ly/3pnVdOJ

Show HN: Everything you need to stay up-to-date with your stock investments https://bit.ly/3JB0bi5 June 28, 2023 at 09:45AM

Show HN: Long-form content generator (plus AI-assisted KW research) https://bit.ly/3CMENCF

Show HN: Long-form content generator (plus AI-assisted KW research) https://bit.ly/3JvUO3l June 28, 2023 at 12:48PM

Show HN: Playground for OpenAI Function Calling https://bit.ly/3Pu6Xd7

Show HN: Playground for OpenAI Function Calling Hey everyone, I'm Petr. I'm excited to share LangTale Playground ( https://bit.ly/3PvARxF ), a first-of-its-kind tool enabling anyone to experiment with OpenAI function calls without coding. Born out of a hackathon project, it's now a part of our broader LangTale platform aimed at tackling common developer challenges with Language Learning Models (LLM). These include prompt integration, testing and debugging, version control, auditing, and usage/cost management. Here's our tech stack: Next.js by Vercel, Tailwind CSS, OpenAI, PlanetScale's Vitess database, and the Radix UI & Shadcn's component library. We're eager to hear your feedback as we launch LangTale Playground today. Give it a spin and let us know what you think. https://bit.ly/3PvARxF June 28, 2023 at 10:59AM

Show HN: Langchain-Serve Bringing LangChain Apps Closer to Your Users https://bit.ly/3pk0DdE

Show HN: Langchain-Serve – Bringing LangChain Apps Closer to Your Users https://bit.ly/3r4G19H June 28, 2023 at 04:45AM

Show HN: The IT contractor's Swiss army knife https://bit.ly/44lVvEI

Show HN: The IT contractor's Swiss army knife Billr is an all-in-one platform that helps IT professionals manage their business. We take care of client and contract management, invoicing, and provide you with the hottest rates that companies pay. This way you always go into negotiations with an upper hand. https://bit.ly/3prYOeD June 27, 2023 at 03:02PM

Show HN: BillaBear Self-Hosted SaaS Subscription Management and Billing https://bit.ly/44kHEhH

Show HN: BillaBear – Self-Hosted SaaS Subscription Management and Billing https://bit.ly/43Ys2Rl June 27, 2023 at 01:46PM

Show HN: An Interactive Guide to Teach Derivatives and Backpropagation https://bit.ly/3pmgjwM

Show HN: An Interactive Guide to Teach Derivatives and Backpropagation https://bit.ly/3CQjRug June 27, 2023 at 05:01AM

Show HN: Tournacat Sync esports schedules to Google Calendar https://bit.ly/3phIcGv

Show HN: Tournacat – Sync esports schedules to Google Calendar I created Tournacat, a micro-SaaS add-on designed for esports enthusiasts. The goal is to keep esports fans alike informed and organized about upcoming tournaments, all while seamlessly integrating with Google Calendar. https://bit.ly/42WZ0QF June 27, 2023 at 03:27AM

Show HN: Get structured and typed JSON outputs via GPT-3.5/4 functions https://bit.ly/3JwTa1A

Show HN: Get structured and typed JSON outputs via GPT-3.5/4 functions https://bit.ly/3JyuUMJ June 27, 2023 at 02:11AM

Show HN: Latent Workers: AI Platform for Simplified Financial Decision Making https://bit.ly/46oTWrd

Show HN: Latent Workers: AI Platform for Simplified Financial Decision Making https://bit.ly/3Pwou4d June 26, 2023 at 01:55PM

Show HN: Content-aware fill for audio to change a song to any duration https://bit.ly/3pmAg6O

Show HN: Content-aware fill for audio to change a song to any duration I worked on a web service that allows you to import a song and define a target length that the song will be shortened or lengthened to. It does this by analyzing the song and finding repeating audio patterns. This is helpful for making any song match a video or performance with a set duration. You can also specify areas of the song to prefer or avoid. An example is available here: https://bit.ly/3pfzqJ3... The cool thing is that after the song is analyzed on the server, the client can recompute and preview the results completely client-side through an implementation that uses Web Workers and WebAssembly. The audio previewing uses Tone.js. I am thinking of writing up some more details about the implementation in the future. I'm still working on a way to explain this easily, but I like the idea of carrying over the concept of content-aware fill from images to audio. Please let me know if you have any comments or questions! https://bit.ly/3XoQaKg June 26, 2023 at 04:12PM

Show HN: Curry functions with a type-safe fluent API https://bit.ly/3Pv9oMk

Show HN: Curry functions with a type-safe fluent API https://bit.ly/43ZEMHj June 26, 2023 at 03:18PM

Show HN: I built a website to buy and sell used clothes in Indonesia https://bit.ly/43Z6SCr

Show HN: I built a website to buy and sell used clothes in Indonesia https://bit.ly/3JvtqCK June 26, 2023 at 09:29AM

Show HN: A community to share ChatGPT chats https://bit.ly/3CKo6HI

Show HN: A community to share ChatGPT chats https://bit.ly/44jp9dK June 26, 2023 at 05:35AM

Show HN: Shark Tank At-Home Plastic Surgery Kit [video] https://bit.ly/3Pvyk6x

Show HN: Shark Tank – At-Home Plastic Surgery Kit [video] https://www.youtube.com/watch?v=mKSwrhh_kwk June 26, 2023 at 03:01AM

Show HN: Open-source resume builder and parser https://bit.ly/3CJU1Iz

Show HN: Open-source resume builder and parser Hi HN, I recently created and published an open-source resume builder as a weekend project. The idea came to me while I was mentoring students and noticing common mistakes they made in their resumes that I had also made in the past. I thought to build a tool to help people easily create a modern professional resume with built-in best practices to avoid those mistakes. Top highlights of the resume builder are: 1. Real time UI update as you type 2. ATS friendly to top ATS platforms, e.g. Greenhouse, Lever 3. Privacy focus - no sign up is required and data is stored locally in browser that only users have access 4. Support import from existing resume PDF The tool also includes a resume parser to help people test their existing resumes’ ATS readability if they might not be interested in using the builder. I also explained the parser algorithm in an article with interactive tables that might be an interesting read to see the steps and logics it uses ( https://bit.ly/3pg0xDQ ). I hope others might find this tool useful and I look forward to hearing any feedback the community has. Thanks all. Home Page: https://bit.ly/3Jw2ToT Github Repo: https://bit.ly/3CNhbxE Product Hunt: https://bit.ly/3PAFrLb https://bit.ly/3Jtwdw4 June 25, 2023 at 06:00PM