Show HN: Open sourcing Restly – GPT-4 powered tutorials from your OpenAPI spec https://ift.tt/2mQEtVx

Show HN: Open sourcing Restly – GPT-4 powered tutorials from your OpenAPI spec Hi HN - Marius (mbuleandra) and I built Restly as a side project. Restly generates a user-friendly tutorial against any OpenAPI spec. While building public-facing APIs, we found that writing these guides by hand took a lot of work. Many OpenAPI specs were too large to send to GPT-4 / Claude directly, and even when we could send them, we experienced lost-in-the-middle and hallucination issues. The project is very alpha but works against the Vocode API when we specify well-defined goals. Let us know your thoughts; we would love your contribution to the project! [1] https://getrestly.com/ [2] https://ift.tt/pDRiMqr https://ift.tt/pDRiMqr December 9, 2023 at 04:04AM

Show HN: We've built an Open Source plugin to make using AI easier for VFX https://ift.tt/e3LAWU4

Show HN: We've built an Open Source plugin to make using AI easier for VFX Hi, I’m Bryan Lyon, the CTO of DeepMake. We’re making plugins for VFX software suites (Right now we have a pre-release of our After Effects plugin ready) that enable you to use Open Source AI tools without leaving the workflow. It makes all the AI tools work just like another plugin in the VFX software. In the past, I worked on VFX adjacent AI and was more than once asked to make AI tools easier to use so the VFX experts could use them. In many cases my job was little more than making it easy to install and make sense to use. After writing dozens of “one-off” scripts that made an AI tool usable I decided there should be a better way. To that end we’ve simplified the process. Right now our public release is still not the easiest to install, but once you’ve installed one plugin and the backend, installing new plugins is as simple as extracting a zip file or cloning a repo (and we’re going to make it even easier). Our target audience isn’t non-technical people, but rather people who don’t have the time or experience to go through installing an AI tool which may not even include an easy way to send your own data through the pipeline. We hope to make VFX easier for people who can’t really do VFX now due to either a lack of time or experience. We also want to make VFX more powerful for VFX experts. We’ve built the backend to make plugins extremely easy to make and hope that the community will be able to take advantage of an easy way to integrate with VFX tools. IN the spirit of open source we’ve released our code as open source (We’re cleaning up the AE plugin side, but it’ll be released too). We plan on monetizing based on managing massive plugins across compute farms for big VFX shops and other features that benefit those larger teams, the core of the system will remain open source and freely available. So far, we’ve released a Stable Diffusion plugin, and have more including Masking, Super Resolution, and more coming up in the pipeline. I hope you like our software and look forward to hearing from you. https://ift.tt/mfBJW4P December 9, 2023 at 03:15AM

Show HN: Eliminate video buffering with a Chrome extension https://ift.tt/hKxyJuw

Show HN: Eliminate video buffering with a Chrome extension This extension will replace videos on websites with a custom one that use download acceleration to prebuffer as you watch. It works on most websites, including Youtube. Fortuitously, it is also able to bypass Youtube's anti-adblock shenanigans. I started this project in high school to fix the terrible video players used on most websites. Since then, I've received a lot of feedback from my users and FastStream has improved significantly. Now that most bugs have been ironed out, I think I am ready to share it here on HN. It is still undergoing rapid development (multiple releases every week), so let me know if you see any bugs or have feature suggestions. I usually address such requests on Github within 2-3 days. https://ift.tt/4FzbBco Web Based Demo: (some features not available) https://ift.tt/4himjsk... https://ift.tt/dR1cfOK December 9, 2023 at 12:18AM

Show HN: I created an extension for direct streaming of videos, bypassing ads https://ift.tt/gWVs5vR

Show HN: I created an extension for direct streaming of videos, bypassing ads https://ift.tt/pu5sSdP December 8, 2023 at 11:48PM

Show HN: Open-Source AI Adventure Game https://ift.tt/WTrCRaA

Show HN: Open-Source AI Adventure Game Hi HN! I'd love your feedback for this AI storytelling game. Remember when you used to read choose-your-own adventure books as a kid? We're trying to re-create that. The site lets you create adventures by seeding them with parameters that end up feeding LLMs: title, genre, writing style, etc. Once you've done that, you can play your book like a game: with custom chapters, illustrations, voice narration, choices, and dice rolls. We’re really into the idea of merging the open-ended generative AI with goal-directed story arcs that the game author can control. Everything is open source (links below) and we’d love your contributions & ideas. I know there's a lot of great work in this space, and the whole team that built this is eager to learn. Agent Source Code: https://ift.tt/AK8lP1n Web Source Code: https://ift.tt/c79Ko8E Video playthrough: https://youtu.be/r5iJkELa-kk https://ift.tt/BCTVt2b December 7, 2023 at 10:38PM

Show HN: Biblos – Semantic Search the Church Fathers https://ift.tt/7oHDLRI

Show HN: Biblos – Semantic Search the Church Fathers I'm pleased to present an update to Biblos, a semantic search tool designed for biblical research. This release incorporates instructor-large embeddings to enhance the precision of verse retrieval. Introducing some key features including historical church writings and commentaries alongside the main biblical corpus. Available for use at https://biblos.app/ Technical Insights: - Utilizes Chroma for vector search, now powered by instructor-large embeddings for improved semantic accuracy. - Features Anthropic's Claude LLM model to generate summaries that provide context and clarity for search results. - Developed with a Retrieval Augmented Generation (RAG) architecture, the app offers a streamlined user experience through a Streamlit Web UI, all orchestrated with Python. https://biblos.app/ December 7, 2023 at 11:38PM

Show HN: Open-Source Data Replication and Anonymization https://ift.tt/at0vXcp

Show HN: Open-Source Data Replication and Anonymization Hey HN, we're Evis and Nick, we're excited to be launching Neosync on HN! Neosync is an open source data replication and anonymization project that helps developers create safe, anonymized test data and sync it across all environments for high-quality local, stage and CI testing. This is how it works: 1. You select a job type. Today we support data sync jobs (these sync data between two databases and run on a schedule you define) and a data generation job (this generates synthetic data from scratch and sends it to a destination). 2. Next you define your source database and a destination(s) database (you can connect multiple destinations). 3. Next we pull in the schema from the source DB and then you can decide how to you to want transform your data. We ship with 40+ transformers (email, first name, address, random int64, random string, random float64, etc). You can create your own custom transformations as well. We've designed our transformers to be as flexible as possible so you can use them across almost any data type. You could also use Neosync in passthrough mode which means that none of the data will be transformed and you can use it for data replication. 4. Lastly, you can defined subsets. This is a way to filter the data that gets sent to the destination. You can provide a custom SQL query or filters to do this. For example, you can filter the data by an id, customerType, column, date, etc. This is very flexible. And that's it! The job will run on the schedule you determine. We handle things like retries and backoffs and referential integrity between tables. We also ship with APIs, a CLI and Github action so that you can use Neosync to hydrate a CI database in your CI pipeline. We're working on releasing a Terraform provider shortly. Deployment is pretty straightforward. You can deploy Neosync using Docker Compose (we provide a script) or on Kubernetes using our helm chart. So what's next? Here's a brief overview: Real time mode (hook up Neosync to Kafka/SQS and anonymize and send the data to destinations in real time) and more connections (MongoDB, Snowflake, CSV). On the ML side, supporting use-cases like consistent data generation (providing a seed value), statistically consistent data and more. You can check out our roadmap in our Github project. Here's a brief loom demo: https://ift.tt/4xGKayj?... We'd love your feedback and contributions. We strongly believe that your data should be yours and it should stay on your infrastructure and open source is the best way to bring that vision to life. https://ift.tt/VOTW19Y December 8, 2023 at 12:09AM

Show HN: Turn emails into PDFs (as easy as it gets) https://ift.tt/DvKVQ6r

Show HN: Turn emails into PDFs (as easy as it gets) Our customers (mostly B2B) have been asking for PDF version of invoices, receipts and whatnot instead of the ones sent as email. Tapdone, my side project. It's like a PDF agent listening to your emails. `Bcc` the service when you send out an invoice, and it flips that email into a PDF and shoots it back to you and your customer. Zero fancy stuff, just a neat trick to keep the PDF-demanding crowd happy while you hack away at the real work. Happy to share and please let me know if you find it useful. Email to PDF https://www.tapdone.com and in exchange just drop me a line with your thoughts. If it smooths out even one wrinkle in your day, I'm counting it as a win. December 6, 2023 at 09:08PM

Show HN: Lume – automate data mappings using AI https://ift.tt/tHsuBYT

Show HN: Lume – automate data mappings using AI Hi HN! I'm Nicolas, co-founder of Lume, a seed-stage startup ( https://www.lume.ai/ ). At Lume, we use AI to automatically transform your source data into any desired target schema in seconds, making onboarding client data or integrating with new systems take seconds rather than days or weeks. In other words, we use AI to automatically map data between any two data schemas, and output the transformed data to you. We are live with customers and are just beginning to open up our product to more prospects. Although we do not have a sandbox yet, here is a video walkthrough of how the product works: https://ift.tt/gKxkrPw?... . And, here is our documentation: https://docs.lume.ai . We would love to get you set up to test it, so please reach out. Using Lume: we do not have self-serve yet. In the meantime, you can request full access to our API through the Request Access button in https://www.lume.ai . The form asks for quick information e.g. email so that I can reach out to you to onboard you. Please mention you came from HN and I’ll prioritize your request. How our full API product offering works: Through Lume’s API, users can specify their source data and target schema. Lume’s engine, which includes AI and rule-based models, creates the desired transformation under the hood by producing the necessary logic, and returns the transformed data in the response. We also support mapper deployment, which allows you to edit and save the AI generated mappers for important production use cases. This allows you to confidently reuse a static and deterministic mapper for your data pipelines. Our clients have three primary use cases - Ingest Client Data: Each client you work with handles data differently. They name, format, and handle their data in their own way, and it means you have to iteratively ingest each new client's data. - Normalize data from unique data systems. To provide your business value, your team needs to connect to various data providers or handle legacy data. Creating pipelines from each one is time consuming, and things as small as column name differences between systems makes it burdensome to get started. - Build and maintain data pipelines. Creating different pipelines to that map to your target schema, whether for BI tooling, downstream data processing, or other purposes, means you have to manually create and maintain these mappings between schemas. We're still trying to figure out pricing so we don't have that on our website yet - sorry, but we wanted to share this even though it's still at an early stage. We’d love your feedback, ideas & questions. Also, feel free to reach out to me directly at nicolas@lume.ai. Thank you. https://www.lume.ai/ December 6, 2023 at 11:07PM

Show HN: Llama 2 Uncensored 70B as API https://ift.tt/GczhCqQ

Show HN: Llama 2 Uncensored 70B as API https://woolapi.com December 7, 2023 at 12:39AM

Show HN: Frogtab – Private, peaceful task management https://ift.tt/z9DQve0

Show HN: Frogtab – Private, peaceful task management Hi HN! I'm excited to share the task manager that I've been building and relying on for the past 9 months I started developing Frogtab after a particularly busy period at work, where a large number of ad-hoc tasks would need my attention each day. What I Initially tried was a single (long!) checklist of outstanding tasks, but I found that too overwhelming to look at all day long. Then I tried scheduling tasks based on when I expected to complete them, but that also required too much cognitive load - I only had the capacity to bucket tasks into "today" and "not today" And so Frogtab was born. Originally as a Google doc, then later as a rudimentary web app with some simple automation. The automation was there to nudge me towards good habits, e.g., grouping all my outstanding tasks at the beginning of each day and requiring me to consciously choose which tasks to tackle that day. I subsequently refined the system a little, but the core mechanic has been serving me well ever since! More than the benefits I've gotten from using Frogtab at work, it's been really fun to develop Frogtab into a form that is usable - dare I say enjoyable - by other people too. Thanks to feedback from the awesome community at Bear (bearblog.dev) and also from sharing an early version here on HN, I've been able to make a whole host of improvements to Frogtab Highlights include: - Support for a weekly routine, aka recurring tasks - Data export and import, including auto-backup in supported browsers - Ability to receive tasks sent from any device - Dark theme - Keyboard shortcuts - Full docs at frogtab.com/help As I've been developing Frogtab, one of my primary concerns has been data privacy. Frogtab stores data in your bowser and doesn't require an account. Also, Frogtab does not use cookies, collect PII, serve ads, or track you in any way. It's entirely free to use and fully open source - the code is at github.com/dwilding/frogtab If you try Frogtab, I hope that you have a great experience! I would love to hear any feedback/suggestions, thank you :) https://frogtab.com/ December 6, 2023 at 04:27AM

Show HN: Solving NYT Connections with ChatGPT https://ift.tt/XIivM0V

Show HN: Solving NYT Connections with ChatGPT Just for fun I decided to see if I could use chatGPT to solve NYT Connections word puzzles. It uses a pretty straightforward BFS search in which the LLM is first prompted to generate several possible groupings of four related words, and then a different prompt is used to evaluate the soundness of each of those groupings. This approach seems to be able to produce the correct solution somewhat less than half the time. Some observations: * For whatever reason, chatGPT-4 seems to be a bit worse than 3.5 at generating Connections groupings. I haven’t tested systematically so maybe this is just some small sample size bias. But at the very least it isn’t obviously better * It really struggles with the “words that can fill in the blank” style groups. Often it will correctly come up with the right category (e.g. “words that can precede `cheese`”) but will only be able to identify 2 of 4 words in that grouping * It frequently generates very vague categories (“words that can be nouns”) despite nothing like that appearing in the proposal prompt. Also it will still sometimes score them highly, despite there being several explicitly examples in the value prompt disallowing these types of categories If you have any idea for how to improve this, please let me know (or send a PR)! https://ift.tt/5zVmJkc December 6, 2023 at 01:41AM

Show HN: Dropbase – Build internal web apps with just Python https://ift.tt/hLTXipR

Show HN: Dropbase – Build internal web apps with just Python Hey HN, I’m Jimmy, co-founder of Dropbase ( https://www.dropbase.io ). We are an internal tools builder for Python developers. All you have to do is import any Python scripts/libraries, declare UI components, and layer app permissions so you can share them with others. We’re a middle ground between Airplane and Retool—simpler UI creation than Airplane, more code-centered than Retool. UI building is declarative and you can bind Python scripts/functions to UI components. You can write Python scripts/functions using our App Studio with support from a Python Language Server Protocol (LSP) for linting. Since the self-hosted worker directly references .py or .sql files in the filesystem, you can even write them on VSCode directly or import any other Python script or library. Our app layout is highly opinionated to speed up app building. Instead of an open canvas for UI building, we just give you a main table view and a widget sidebar. This approach significantly reduces app-building time while still covering what most tools need: see some data and take actions based on it. It’s not flexible enough to do absolutely anything, but that’s the point—there’s a tradeoff between flexibility and speed. Dropbase gives you most of what you need, plus speed! A neat feature we are experimenting with to build admin panels fast is “Smart Tables”. We convert any SQL SELECT statement (even across multiple joins and filters) into an inline editable table, like spreadsheets, without any additional code. We have a hybrid hosting model that combines a self-hosted client and a worker server, with a backend API for app/component definitions hosted by us to simplify pushing feature updates. The worker server sits in your machines so your sensitive data doesn’t leave your infra. We’re Python-centric for now, but plan to add support for Rust, Go, and others later. We made a few demo videos building common tools: - Customer approval tool: https://youtu.be/A1MIIRNkv3Q - Data editing tool (with Smart Table): https://youtu.be/R1cHO9lMRXo To try Dropbase, create an account at https://app.dropbase.io and generate a token, then follow these instructions for local setup: https://ift.tt/A2mbSxE . We are very early so we're really excited to get your feedback, especially on our approach to tools building with Python! My co-founder Ayazhan and some of our teammates will be around to answer questions. https://ift.tt/luGqma7 December 5, 2023 at 11:55PM

Show HN: Darwinio: An Attempt at an Evolution Simulator https://ift.tt/wAU2lCb

Show HN: Darwinio: An Attempt at an Evolution Simulator We made this for our school project. I think we went a little too ambitious. https://ift.tt/gwp6Ajc December 4, 2023 at 07:28PM

Show HN: Caption – Generate social media posts from a given image using LLaVA https://ift.tt/RVJcq6C

Show HN: Caption – Generate social media posts from a given image using LLaVA https://ift.tt/Qmkevp9 December 4, 2023 at 10:37AM

Show HN: A Who is Hiring app with AI filters – December update https://ift.tt/ZFmUGqo

Show HN: A Who is Hiring app with AI filters – December update A cureated list of Who is Hiring with posts with smart filters generated with AI https://ift.tt/nB0Vlq6 December 4, 2023 at 06:51AM

Show HN: OSHW Embedded Ethernet Switch https://ift.tt/RQG8WuC

Show HN: OSHW Embedded Ethernet Switch https://ift.tt/sRmgpCW December 3, 2023 at 07:19PM

Show HN: Audio plugin for circuit-bent MP3 compression sounds https://ift.tt/WdPVRUm

Show HN: Audio plugin for circuit-bent MP3 compression sounds I made MAIM, an open-source audio plugin that uses real MP3 encoders to distort the sound. I've also added knobs that let you "circuit bend" the encoders, changing parameters that would normally be inaccessible to the user to get strange glitchy sounds. The plugin lets you switch between two MP3 encoders, since under the MP3 standard, the specifics of what to lose in MP3 lossy compression is left up to the encoder. The encoders are LAME, the gold standard for open-source MP3 encoders, and BladeEnc, an old open-source MP3 encoder that has a really bubbly sound and was fun to work with. I'd love any feedback, and I'll be around to answer questions! https://ift.tt/etsKiHW December 3, 2023 at 11:31PM

Show HN: Fluvio – Distributed stream processing system written in Rust and WASM https://ift.tt/GKqSQ7r

Show HN: Fluvio – Distributed stream processing system written in Rust and WASM https://ift.tt/iI6XxLu December 3, 2023 at 06:05AM

Show HN: ThreeFold – Decentralized Cloud Infrastructure https://ift.tt/WEYAmHx

Show HN: ThreeFold – Decentralized Cloud Infrastructure We built it from the ground up, minimal Linux based operating system (written in go and rust), messaging system written in rust and infrastructure as code support (terraform and pulumi) There is even a dashboard, and a playground UI to manage it (that you can even run yourself) . Beautifully decentralized, you have full control of everything, you can deploy on your own servers if the cost of the cloud is too much. You can even run the whole system yourself if you want to. Here is a link to documentation https://manual.grid.tf/ Also, we are honored if it piqued your interest, and would love to support your testing journey free of charge. https://threefold.io/ December 3, 2023 at 02:13AM