Thursday, November 30, 2023
Wednesday, November 29, 2023
Show HN: Domino – open-source GUI platform for creating data and AI workflows https://ift.tt/7gO9BQD
Show HN: Domino – open-source GUI platform for creating data and AI workflows Domino is an open source platform dedicated to visually creating and managing data and AI workflows. The goal is for anyone to be able to effortlessly construct complex workflows by piecing together modular operators, no coding required! Additionally, Domino provides developers with a standard to bundle their Python functions into self-containing, reusable, shareable modules, that can be readily incorporated in the visual workflows. We've been working hard on this as a side project for a while, now we believe it has great potential to be used by the data / ML / Python community! https://ift.tt/5Lcmgqv November 29, 2023 at 09:12PM
Show HN: I built a fast, accurate translation API for 1/30th the price of Google https://ift.tt/BLO2NqS
Show HN: I built a fast, accurate translation API for 1/30th the price of Google Hey HN, I built an alternative to Google translate that's fast, accurate, and 1/30th the price. 20+ supported languages, not billed until 100k tokens, and already used thousands of times with real language learning users. The landing page has a demo for you to test performance yourself for free with no card required. (Also landing page says 1/13 the price because had to account for all 3 big names, with varying prices each). I built this as a workaround for my language learning startup, and it was perfect at a fraction of the cost. Hopefully it can help other devs in accessibility and language learning apps. Thanks, https://ift.tt/LV4GHYP November 29, 2023 at 06:49PM
Tuesday, November 28, 2023
Monday, November 27, 2023
Sunday, November 26, 2023
Show HN: Dreamachines.ai https://ift.tt/7i9plqO
Show HN: Dreamachines.ai AI image generation, management, and sharing platform. Built on top of a cloud OS. Provides a range of mechanisms for sharing. Free, no commercial tier. https://ift.tt/HxMSc91 November 26, 2023 at 10:30PM
Saturday, November 25, 2023
Friday, November 24, 2023
Thursday, November 23, 2023
Show HN: InsiderXTrade – Yahoo Finance-Influenced Site for SEC Insider Tradings https://ift.tt/bcHuehn
Show HN: InsiderXTrade – Yahoo Finance-Influenced Site for SEC Insider Tradings https://ift.tt/i4mg9jn November 23, 2023 at 05:53PM
Wednesday, November 22, 2023
Show HN: Plantarium – Create 3D Plant Models with Blender-Style Nodes https://ift.tt/DFuqiCT
Show HN: Plantarium – Create 3D Plant Models with Blender-Style Nodes Plantarium is my open source side project that allows you to created procedural 3D plants in your browser using blender style nodes. Recently I added a public gallery so you can share your plant designs and download others. https://ift.tt/hRvfETP https://ift.tt/g9uGAe8 November 22, 2023 at 04:02PM
Tuesday, November 21, 2023
Show HN: I built local copilot alternative using Codellama https://ift.tt/waJv9l1
Show HN: I built local copilot alternative using Codellama Hey, HN! I was trying to find a good Copilot alternative since my experience with copilot degraded a lot and recent OpenAI drama leaves me no hope for improvement and i decided to take a look at self-hosting options. At the same time Copilot net is a small one - just 12b parameters and 2k of context. You can run much bigger networks locally in 2023. I have figured out that there are no good local options: most of the VS Code plugins simply connect neural networks to the code while copilot has extensive post and pre processing steps. Some of them still work with original copilot plugin (ie sends data to MS), some require complicated setup to make it work. I implemented very basic ones to check if this would work and in my experience it works really good and i wanted to share it on HN. Feedback is appreciated! Sources are here: https://ift.tt/yYTUgvk https://ift.tt/ucN0Cjm November 21, 2023 at 11:32PM
Show HN: Neum AI – Open-source large-scale RAG framework https://ift.tt/JFpmlwb
Show HN: Neum AI – Open-source large-scale RAG framework Over the last couple months we have been supporting developers in building large-scale RAG pipelines to process millions of pieces of data. We documented our approach in an HN post ( https://ift.tt/2pnotFI ) a couple weeks ago. Today, we are open sourcing the framework we have developed. The framework focuses on RAG data pipelines and provides scale, reliability, and data synchronization capabilities out of the box. For those newer to RAG, it is a technique to provide context to Large Language Models. It consists of grabbing pieces of information (i.e. pieces of news articles, papers, descriptions, etc.) and incorporating them into prompts to help contextualize the responses. The technique goes one level deeper in finding the right pieces of information to incorporate. The search for relevant information is done through the use of vector embeddings and vector databases. Those pieces of news articles, papers, etc. are transformed into a vector embedding that represents the semantic meaning of the information. These vector representations are organized into indexes where we can quickly search for the pieces of information that most closely resembles (from a semantic perspective) a given question or query. For example, if I take news articles from this year, vectorize them, and add them to an index, I can quickly search for pieces of information about the US elections. To help achieve this, the Neum AI framework features: Starting with built-in data connectors for common data sources, embedding services and vector stores, the framework provides modularity to build data pipelines to your specification. The connectors support pre-processing capabilities to define loading, chunking and selecting strategies to optimize content to be embedded. This also includes extracting metadata that is going to be associated to a given vector. The generated pipelines support large scale jobs through a high throughput distributed architecture. The connectors allow you to parallelize tasks like downloading documents, processing them, generating embedding and ingesting data into the vector DB. For data sources that might be continuously changing, the framework supports data scheduling and synchronization. This includes delta syncs where only new data is pulled. Once data is transformed into a vector database, the framework supports querying of the data including hybrid search using the available metadata added during pre-processing. As part of the querying process, the framework provides capabilities to capture feedback on retrieved data as well as run evaluations against different pipeline configurations. Try it out and if interested in chatting more about this shoot us an email founders@tryneum.com https://ift.tt/Gp0I5cy November 21, 2023 at 11:20PM
Monday, November 20, 2023
Show HN: Hotlist, a Tauri powered daily todo list for your Mac menu bar https://ift.tt/6AbCM1k
Show HN: Hotlist, a Tauri powered daily todo list for your Mac menu bar https://ift.tt/Wi378eZ November 20, 2023 at 09:20PM
Sunday, November 19, 2023
Show HN: "Awesome" Engineering Games (List) https://ift.tt/NIbkt0R
Show HN: "Awesome" Engineering Games (List) I've spent way too much time both playing and finding engineering-focused games, and haven't been able to find very detailed or comprehensive lists online. So I made one :) These games are both fun and often quite educational, presenting gamified versions of real-world challenges and professions. There's a lot of different sub-genres of "engineering game", such as: * Factory automation (Factorio, Dyson Sphere Program) * City builders (Cities: Skylines, Anno series) * Route-builders (Mini Motorways, Railway Empire) * Comp sci (TIS-100, Bitburner) All games on the list are very highly reviewed. I've played most (but not all) of them, and provided personal recommendations alongside the reviews. Many of them are also playable on GeForce Now (if you don't have a gaming PC). Please contribute if you know of more, or have any comments/suggestions! https://ift.tt/lHngKGA November 19, 2023 at 11:22PM
Saturday, November 18, 2023
Friday, November 17, 2023
Show HN: Challenge Your AI Agents/custom GPTs – Can They Survive My Tester? https://ift.tt/RpTwnZJ
Show HN: Challenge Your AI Agents/custom GPTs – Can They Survive My Tester? I've pivoted to create AI Agent Tester, a SaaS platform dedicated to testing and validating AI agents from OpenAI, Character.ai, and FlowGPT.com. The platform offers: - Hassle-Free Setup: Get your first simulation up and running in just 5 minutes. - Realistic Simulations: Rigorous user interaction tests to prep your AI agent for real-world scenarios. - Intelligent Scoring: Each response is meticulously evaluated, scoring from 0 to 100(GPT-4 smart enough to evaluate it for you). - Broad Platform Support: Initially rolling out with OpenAI, Character.ai, and FlowGPT.com compatibility. The link: https://ift.tt/oITkMbN Eager to hear your thoughts and discuss improvements! https://ift.tt/oITkMbN November 17, 2023 at 06:16PM
Thursday, November 16, 2023
Show HN: Version code, models, & datasets together in GitHub https://ift.tt/g815B2k
Show HN: Version code, models, & datasets together in GitHub Hi HN! We just launched a GitHub integration that scales your Git repos to handle 100 terabytes of files in a single repo. XetData enables data scientists and machine learning engineers to version code, models, and datasets together. Most teams have glued together clunky workflows using S3, DVC, Git, Git LFS, and other tools and make true reproducibility difficult: https://ift.tt/Qarov8c We instead embrace and extend Git so end-users don’t need to learn a new tool and a new set of commands. Our implementation is similar to Git LFS, where we take over the .gitattributes file, push pointers to large files in GitHub, and push the raw, large files to us. We have a few distinct features that we’re proud of that improve the user experience: - Our XetData bot comments on your pull requests to provide links to useful dataset views and model diffs. We’re working on rendering these inside GitHub itself using browser extensions. - Git LFS and similar tools only implement file-level deduplication. We created a new technique called block-based deduplication (published in CIDR’23 conference) specifically for data and ML workflows. The ML lifecycle consists of making lots of iterative changes and our technique helps save storage and time spent downloading and uploading changes. - You can mount large repos to your local machine using git-xet mount for exploratory work. Individual files that are needed are streamed in just in time behind the scenes. We open sourced our implementation of mount and it was well received here on HN: https://ift.tt/bTtkIF0 - To give more users access to your data, just add them to your GitHub repo. This is a beta product and we would love all of your feedback. You can find all instructions to try this out here: https://ift.tt/sq7vS0u While we’re in beta, our product is completely free to use. We have a Slack you can join or a GitHub issue tracker. - Slack: https://ift.tt/Mizo2Jj - GitHub: https://ift.tt/IMmX3LN November 16, 2023 at 10:26PM
Wednesday, November 15, 2023
Show HN: Multi-Object Tracking in Python https://ift.tt/6MIFEWj
Show HN: Multi-Object Tracking in Python Hello! I've created a small library for tracking, along with a tutorial. I plan to continue developing it. Tracking is an important topic, closely related to object detection. However, I've noticed that it doesn't receive as much attention compared to machine learning approaches. Or, the focus is on filters like the Kalman filter. This tutorial begins with single object tracking and progressively complicates the tasks, introducing various models and a hypothesis tree to solve them. https://ift.tt/MuL931K November 15, 2023 at 10:36PM
Show HN: Movis – A Video Editing Library in Python https://ift.tt/n7ZQoeU
Show HN: Movis – A Video Editing Library in Python Originally, this library was created due to my motivation to make videos in Python. Of course, I considered other Python libraries, but I decided to create a new library for video editing because I needed the following features and also for study purposes: - The existence of composition. Especially, the ability to perform advanced video editing by inserting compositions within compositions. - The ability to add animations based on keyframes. - Effects like chroma key and drop shadow. - A caching mechanism to render the same frame quickly. - Various blending modes. These features, despite being standard in proprietary video editing software, were not present in previous Python libraries. Currently, I am using this library to automatically generate videos from raw materials. I would be grateful for any comments, thoughts, or requests. https://ift.tt/aFkmybN November 15, 2023 at 09:20PM
Tuesday, November 14, 2023
Show HN: Find hidden engineering bottlenecks with LLMs https://ift.tt/Hg1YLrD
Show HN: Find hidden engineering bottlenecks with LLMs https://ift.tt/cdMIJXb November 14, 2023 at 11:02PM
Show HN: Interactive Demo of a Tag-Based Bookmark Manager https://ift.tt/rHxet5O
Show HN: Interactive Demo of a Tag-Based Bookmark Manager https://ift.tt/p5QWZwq November 14, 2023 at 08:38PM
Monday, November 13, 2023
Show HN: Twogether AI – Multi-Person Photo Generation API https://ift.tt/PExQfuH
Show HN: Twogether AI – Multi-Person Photo Generation API Hey everyone, at Magicflow (YC W23) we're helping our customers run AI image generation in production, enabling them to produce high-quality photos at scale. We are launching a scalable API today that makes it possible to create multi-person portrait photos: which means the ability to create real-looking photos of any two persons interacting with each other in some way only by providing a prompt and the person's pose. Generating this kind of photo requires a deep understanding of the AI ecosystem, a knowledge gap many companies face. In order to make the photos look real with high consistency and for a low cost, chaining of many models is required, and an excellent understanding of how to tweak with the various params of each one. We also handle the infrastructure required to generate the photos, which can be a challenge when dealt with alone, especially for companies with a small backend team (we can scale to thousands of requests per day and generate 100 photos in about 3 minutes). Our customers today use this technology for the following use cases: creating new photo albums from old-scanned albums, providing personalized content for user acquisition campaigns, enabling new kinds of experiences in physical venues, and creating humorous photos with celebrities. There is a significant tradeoff between creating a robust abstraction layer on top of Stable Diffusion capabilities and providing customers with more control over various options. The API currently allows you to manipulate the following parameters: the pose of the couple (hugging, taking a selfie, etc.), their facial expressions, the style of the photo (realistic, cartoon, painting, etc.), as well as the location, theme, and outfits (e.g., ski vacation, on the beach) We created a free demo app for you to view examples and try live: https://ift.tt/db5OsJP (no user or payment needed). For full API access, contact me at yardenst@magicflow.ai. We can typically set you up within a day, but an onboarding session is required to ensure responsible API usage. https://ift.tt/STHJIry November 13, 2023 at 07:07PM
Sunday, November 12, 2023
Saturday, November 11, 2023
Show HN: Koelsynth – a simple FM synthesis library https://ift.tt/2RSKoya
Show HN: Koelsynth – a simple FM synthesis library This is part of my journey on pybind11. I wrote a tiny FM Synthesis library in C++ and a Python wrapper for that using pybind11. There is a command-line piano app in the examples directory if you want to play with it. Here is the link: https://ift.tt/AKZ07Uy... My next target is to attach this to some kind of physics simulation - like a bunch of balls moving around in a box with some internal walls. When the ball hits certain trigger points, it produces the sound. https://ift.tt/TjKB5Fl November 12, 2023 at 12:52AM
Friday, November 10, 2023
Thursday, November 9, 2023
Show HN: Moodflix – a movie recommendation engine based on your mood https://ift.tt/f1k8l0i
Show HN: Moodflix – a movie recommendation engine based on your mood Last week I released Moodflix ( https://ift.tt/xpmTtLy ), a movie recommendation engine based to find movies based on your mood. Moodflix was created on top of a movie dataset of 10k movies from The Movie Database. I vectorised the films using Hugging Face's T5 model ( https://ift.tt/t8ruEXj ) using the film's plot synopsis, genres and languages. Then I indexed the vectors using hnswlib ( https://ift.tt/YAktf1U ). LLMs can understand a movie's plot pretty well and distill the similarities between a user's query (mood) to the movie's plot and genres. I have got feedback from close friends around linking movies to other review sites like IMDB or Rotten Tomatoes, linking movies to sites to stream the movie and adding movie posters. I would also love to hear from the community what things you like, what you want to see and what things you consider can be improved. https://ift.tt/zUmCbWg November 9, 2023 at 11:35PM
Wednesday, November 8, 2023
Tuesday, November 7, 2023
Show HN: Unreal Engine 4 WASM space game https://ift.tt/26wld71
Show HN: Unreal Engine 4 WASM space game Note that the demo may take up to 30 seconds to load, and initially present a white screen. I can assure you - it's worth the wait! https://ift.tt/IdHigyE November 7, 2023 at 11:52PM
Monday, November 6, 2023
Show HN: Inshellisense – IDE style shell autocomplete https://ift.tt/IVLfrC5
Show HN: Inshellisense – IDE style shell autocomplete I built this terminal native runtime for Fig's autocomplete to support Windows and Linux. Would appreciate any feedback on it! https://ift.tt/Y9QA0gM November 6, 2023 at 11:15PM
Show HN: Open-source model and scorecard for measuring hallucinations in LLMs https://ift.tt/yu1624C
Show HN: Open-source model and scorecard for measuring hallucinations in LLMs Hi all! This morning, we released a new Apache 2.0 licensed model on HuggingFace for detecting hallucinations in retrieval augmented generation (RAG) systems. What we've found is that even when given a "simple" instruction like "summarize the following news article," every LLM that's available hallucinates to some extent, making up details that never existed in the source article -- and some of them quite a bit. As a RAG provider and proponents of ethical AI, we want to see LLMs get better at this. We've published an open source model, a blog more thoroughly describing our methodology (and some specific examples of these summarization hallucinations), and a GitHub repository containing our evaluation from the most popular generative LLMs available today. Links to all of them are referenced in the blog here, but for the technical audience here, the most interesting additional links might be: - https://ift.tt/L3fBxXq... - https://ift.tt/n0u74kI We hope that releasing these under a truly open source license and detailing the methodology, we hope to increase the viability of anyone really quantitatively measuring and improving the generative LLMs they're publishing. https://ift.tt/pXd4C6H November 6, 2023 at 11:11PM
Show HN: DIY Hacking Chair https://ift.tt/vtaKpyY
Show HN: DIY Hacking Chair https://ift.tt/jOrdJ4B November 6, 2023 at 09:45PM
Sunday, November 5, 2023
Show HN: SaaS back end template repo written using server-side Swift https://ift.tt/4WmHwqI
Show HN: SaaS back end template repo written using server-side Swift There've been some discussions about swift on the server recently, so I thought that I'd pasete here my template repo to spin up a backend for an SAAS type backend using server-side Swift and Vapor framework that I've just open sourced. https://ift.tt/8A9HqBx November 5, 2023 at 08:38PM
Saturday, November 4, 2023
Friday, November 3, 2023
Show HN: Chat with Garry Tan using RAG on his YouTube channel https://ift.tt/rXgQF34
Show HN: Chat with Garry Tan using RAG on his YouTube channel https://ift.tt/VRMIpt3 November 3, 2023 at 11:59PM
Thursday, November 2, 2023
Wednesday, November 1, 2023
Show HN: An AI courthouse to resolve arguments with your friends https://ift.tt/xO2B0Ws
Show HN: An AI courthouse to resolve arguments with your friends An AI judge will rule on your dispute between friends, roommates, or lovers (ok, maybe not lovers). https://ift.tt/CiXbwDa November 1, 2023 at 11:00PM
Subscribe to:
Posts (Atom)