Music046 | Nigeria No1. Daily Updates | Contact Us

Wednesday, 23 August 2023

Show HN: E-Ink Powered UK Rail Departure Board Using Badger 2040W https://bit.ly/47HWIZn

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://bit.ly/47H7bEr August 23, 2023 at 08:49PM

Show HN: Chat with GPT about medical issues, get answers from medical literature https://bit.ly/45lLSGG

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://bit.ly/45y61cE August 24, 2023 at 12:15AM

Show HN: Flintable – Fixable ESLint rules Playground https://bit.ly/3KP4VkA

Show HN: Flintable – Fixable ESLint rules Playground Hi community! I am glad to introduce to you my latest project! What? Flintable is a playground for experimenting lint rules, focusing on fixable layout and suggestions rules. I initially focused on ESLint, the most popular JavaScript linter. Flintable allows adding your code and regularly testing it with individual rules or custom configurations, composing your own configuration file. How? I developed Flintable using the PHP Laravel framework for the server side and the Vue framework linking them with Inertia JS, accompanied by Tailwind CSS for the client side. Laravel Horizon manages the queues and jobs, while Laravel Websockets and Laravel Echo enable the dialogue between the queue and the client. I used JSON Schema via AJS and OPIS to manipulate ESLint rule schemas and vue-codemirror for the code editor within the tool. Why? Working on the same code as a team can pose challenges, especially in terms of code conventions and working environments. That's why I created Flintable, which long-term goal is to allow everyone to configure their environment to the fullest without impacting others. Thus, developers can collaborate more effectively while respecting each other's workspaces. The short-term objective of Flintable is to simplify the understanding, the discovery and manipulation of rules with ease. How it works? Select a rule in the list of rules on your right. Activate the rule. Determine some options or not. And lint with this rule or with the configuration you made [ by activating other rules ]. When you're satisfied, download your configuration file. You can also try the rules on your own code by pasting it in the code editor. Next? - Implementing more plugins, more linters, more frameworks, more languages? - Creating custom rules sought by the community? - Storing configuration files online to facilitate reuse on other projects? - Launching lint of local and remote code via a command line throughout the development process, using version control tools like Git? I am thrilled about sharing my newborn project with you and would love to hear your feedback. See you in the comments. I don't know if I can share a post from my blog here about the Flintable journey, so ask me if you want it, and I will share the link in response. https://bit.ly/3YMdqmg August 23, 2023 at 02:35PM

Show HN: Fast vector similarity using Rust and Python https://bit.ly/3Pbhsla

Show HN: Fast vector similarity using Rust and Python I recently found myself computing the similarity between lots of very high dimensional vectors (i.e., sentence embedding vectors from LLMs), and I wanted to try some more powerful measures of similarity/dependency than just Cosine similarity, which seems to be the default for everything nowadays because of its computational efficiency. There are many other more involved measures that can detect more subtle relationships, but the problem is that some of them are quite slow to compute, especially if you're trying to do it in Python. For my favorite measure of statistical dependency, Hoeffding's D, that's true even if you use Numpy. Since I recently learned Rust and wanted to learn how to make Python packages using Rust, I put together this new library that I call Fast Vector Similarity. I was blown away by the performance of Rust and the quality of the tooling while making this. And even though it required a lot of fussing with Github Actions, I was also really impressed with just how easy it was to make a Python library using Rust that could be automatically compiled into wheels for every combination of platform (Linux, Windows, Mac) and Python Version (3.8 through 3.11) and uploaded to PyPi, all triggered by a commit to the repo and handled by Github's servers-- and all for free if you're working on a public repo! Anyway, this library can easily be installed to try out using `pip install fast_vector_similarity`, and you can see some simple demo Python code in the readme to show how to use it. Aside from exposing some very high performance implementations of some very nice similarity measures, I also included the ability to get robust estimates of these measures using the Bootstrap method. Basically, if you have two very high dimensional vectors, instead of using the entire vector to measure similarity, you can take the same random subset of indices from both vectors and compute the similarity of just those elements. Then you repeat the process hundreds or thousands of times and look at the robust average (i.e., throw away the results outside the 25th percentile to 75th percentile and average the remaining ones, to reduce the impact of outliers) and standard deviation of the results. Obviously this is very demanding of performance, but it's still reasonable if you're not trying to compute it for too many vectors. Everything is designed to fully saturate the performance of multi-core machines by extensive use of broadcasting/vectorization and the use of paralell processing via the Rayon library. I was really impressed with how easy and low-overhead it is to make highly parallelized code in Rust, especially compared to coming from Python, where you have to jump through a lot of hoops to use multiprocessing and there is a ton of overhead. Anyway, please let me know what you think. I'm looking to add more measures of similarity if I can find ones that can be efficiently computed (I already gave up on including HSIC because I couldn't get it to go fast enough, even using BLAS/LAPACK). https://bit.ly/3QY7Lrc August 23, 2023 at 01:34PM

Show HN: Make sense of all your files, links and messages in the cloud https://bit.ly/44haVJH

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://bit.ly/3QTKp6b August 23, 2023 at 01:31PM

Show HN: Pip install inference, open source computer vision deployment https://bit.ly/3qEJxb1

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://bit.ly/45lZl1g August 23, 2023 at 12:04PM

Show HN: To mute words on Twitter in batches, I created a browser extension https://bit.ly/45qFmPi

Show HN: To mute words on Twitter in batches, I created a browser extension Hello HN community :) For a while now I've been watching my Twitter feed fill up with more and more crap. The fact that it's now possible to monetise your tweets has made things even crappier. At the same time, adding words to mute is a pain. First you have to find the option, buried deep in Twitter's settings, and then you have to add them one by one. So I came up with the idea of writing a little browser extension that lets you add lists of muted words, which can come from more or less anywhere, as long as they're in a certain format (a multi-line text file or a JSON array). The extension doesn't collect any data, you don't need an account to use it, and you can store your lists anywhere (although I'd recommend Github gist or Pastebin). To be honest, I made this mainly as an exercise to learn how a browser extension works and how to make one, but if it's useful to people, that's great! Feel free to let me know what you think and give it a try. If there's ever an audience for it, I'm thinking of taking it further by adding lists of people to mute, extracting your existing list of muted words from Twitter, etc.If you have any other ideas for development, I'd love to hear from you. https://bit.ly/3sngJEi August 23, 2023 at 12:43PM

Tuesday, 22 August 2023

Show HN: AI Co-Pilot for Reading Earnings Call Transcripts https://bit.ly/45Hj2k7

Show HN: AI Co-Pilot for Reading Earnings Call Transcripts https://bit.ly/3sgcbPY August 23, 2023 at 04:56AM

Show HN: Open-Source Chat AI Platform with Custom Knowledge https://bit.ly/3sv6f5G

Show HN: Open-Source Chat AI Platform with Custom Knowledge https://bit.ly/44gC0N7 August 22, 2023 at 05:08PM

Show HN: UpTrain (YC W23) – open-source tool to evaluate LLM response quality https://bit.ly/3YRzqfG

Show HN: UpTrain (YC W23) – open-source tool to evaluate LLM response quality Hello, we are Shikha and Sourabh, founders of UpTrain(YC W23) - an open-source tool to evaluate the performance of your LLM applications on aspects such as correctness, tonality, hallucination, fluency, etc. The Problem: Unlike traditional Machine learning or Deep learning models where we always have a unique Ground Truth and can define metrics like Precision, Recall, accuracy, etc. to quantify the model’s performance, LLMs are trickier and it is very difficult to estimate if their response is correct or not. If you are using GPT-4 to write a recruitment email, there is no unique correct email to do a word-to-word comparison against. As you build an LLM application, you want to compare it against different model providers, prompt configurations, etc., and figure out the best working combination. Instead of manually skimming through a couple of model responses, you want to run them through hundreds of test cases, aggregate their scores, and make an informed decision. Additionally, as your application generates responses for real user queries, you don’t want to wait for them to complain about the model inaccuracy, instead, you want to monitor the model’s performance over time and get alerted in case of any drifts. Again, at the core of it, you want a tool to evaluate the quality of your LLM response and assign quantitative scores. The Solution: To solve this, we are building UpTrain which has a set of evaluation metrics so that you can know when your application is going wrong. These metrics include traditional NLP metrics like Rogue, Bleu, etc., embeddings similarity metrics as well as model grading scores i.e. where we use LLMs to evaluate different aspects of your response. A few of these evaluation metrics include: 1. Response Relevancy: Measures if the response contains any irrelevant information 2. Response Completeness: Measures if the response answers all aspects of the given question 3. Factual Accuracy: Measures hallucinations i.e. if the response has any made-up information or not with respect to the provided context 4. Retrieved Context Quality: Measures if the retrieved context has sufficient information to answer the given question 5. Response Tonality: Measures if the response aligns with a specific persona or desired tone etc. We have designed workflows so that you can easily add your testing dataset, configure which checks you want to run (you can also define custom checks suitable for your use case) and conveniently access the results via Streamlit dashboards. UpTrain also has experimentation capabilities where you can specify different prompt variations and models to test across and use these quantitative checks to find the best configuration for your application. You can also use UpTrain to monitor your application’s performance and find avenues for improvement. We integrate directly with your databases (BigQuery, Postgres, MongoDB, etc.) and can run daily evaluations. We’ve launched the tool under an Apache 2.0 license to make it easy for everyone to integrate it into their LLM workflows. Additionally, we also provide managed service (with a free trial) where you can run LLM evaluations via an API request or through UpTrain testing console. We would love for you to try it out and give your feedback. Links: Demo: https://bit.ly/3QOYUs4 Github repo: https://bit.ly/3JeFnNP Create an account (free): https://bit.ly/3qzN0aS UpTrain testing console (need an account): https://bit.ly/45AkMLR Website: https://bit.ly/3QMXzlq https://bit.ly/3QOYUs4 August 22, 2023 at 03:08PM

Show HN: Visual DB – Airtable alternative for your own database https://bit.ly/3YH5J0J

Show HN: Visual DB – Airtable alternative for your own database Visual DB combines the familiar interface of a spreadsheet with the robustness and central management of a relational database. Spreadsheets are a popular choice for storing tabular data due to their familiar, row-by-column interface and ease of use. However, they can quickly become unwieldy as data grows. Spreadsheets aren't ideal for large-scale structured data or maintaining data integrity. When individuals copy the spreadsheet and introduce inconsistent updates, it leads to the problem known as "multiple versions of the truth." Visual DB provides a solution. It maintains the familiar interface of spreadsheets, but each row is backed by a database record. Updates sync to a centralized database, ensuring data consistency, scalability, and integrity. Visual DB performs double duty: In addition to providing a spreadsheet interface for updating data, it also has features traditionally seen in business intelligence reporting tools, such as grouping, aggregation, sorting and filtering. Visual DB is very good at helping you locate the record you want to update. It has advanced filtering that supports combining AND/OR conditions. It also has full-text filtering that instantly updates the screen as you type. Visual DB can display up to 100,000 records at a time. If your database table has more rows than that, you can use query parameters to let the user fetch a subset of the records (up to 100K) to the client. To enable this, Visual DB has a query builder and supports parameter prompting. Relational databases frequently function as bridges between various business applications. However, if a database is proprietary and is behind the firewall of another company, its effectiveness as an integration hub is compromised. Visual DB allows users to bring their own databases, ensuring they have complete control and ownership. This ensures interoperability with multiple applications beyond just Visual DB. This flexibility distinguishes Visual DB from competitors like Airtable. Here are the main features of Visual DB: - BYOD (Bring Your Own Database). - Your database can be hosted in any cloud provider, including Azure, AWS and Google cloud. - Supports MySQL, PostgreSQL, Oracle, SQL Server. - No code. Build sheets and forms with zero coding or SQL knowledge. - Role-based access control: Decide who can add/remove columns and who can only enter/update data. - Full-text filtering that instantly updates the screen as you type. - Advanced filtering that supports combining AND/OR conditions. - Grouping with unlimited levels of nesting. - Unlimited number of records per table (compare to 50,000 in Airtable). - Use query parameters to determine which subset of rows (out of millions) to display. - Display columns from lookup tables, not just the main table. - Instant scrolling of up to 100,000 rows. For more information visit https://bit.ly/3YH5JxL or go to https://bit.ly/45gtorp to start using Visual DB right away. https://bit.ly/3YH5JxL August 22, 2023 at 03:15PM

Show HN: Ploter – the all-in-one reader for learning https://bit.ly/45kfG6F

Show HN: Ploter – the all-in-one reader for learning Ploter is an all-in-one reader for your ebooks, audiobooks, pdfs, and more. Take highlights and annotations across all formats (including audio) and have these synced to your favourite note-taking app. https://bit.ly/47JXwg6 August 22, 2023 at 02:48PM

Show HN: Breaklist – A Morning Briefing Printed on a Tiny Thermal Receipt https://bit.ly/3qHdqY8

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://bit.ly/3qwNZbS August 22, 2023 at 12:58PM

Show HN: Speleomorph, Shapeshifting Puzzle Metroidvania https://bit.ly/45idgpf

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://bit.ly/45k4eIn 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://bit.ly/3YRBrZ9 does a great job building mechanics out of the snake+gravity idea - The Plumber Thing https://bit.ly/45hqgLS 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://bit.ly/3PDHlIY August 22, 2023 at 04:11AM

Show HN: Github20k – Learn how to grow your open-source repository https://bit.ly/3sgTWtH

Show HN: Github20k – Learn how to grow your open-source repository Weekly newsletter on how to grow your GitHub repository based on actual use cases we have used over the years. https://bit.ly/3YM0a0V August 22, 2023 at 09:11AM

Music046 | Nigeria No1. Daily Updates | Contact Us - +2349077287056