USearch Images demo in 200 lines of Python
Hey everyone! I am excited to share updates on four of my & my teams' open-source projects that take large-scale search systems to the next level: USearch, UForm, UCall, and StringZilla. These projects are designed to work seamlessly together, end-to-end—covering everything from indexing and AI to storage and networking. And yeah, they're optimized for x86 AVX2/512 and Arm NEON/SVE hardware. USearch [1]: Think of it as Meta FAISS on steroids. It's now quicker, supports clustering of any granularity, and offers multi-index lookups. Plus, it's got more native bindings than probably…
What it does
In the maker’s words, at launch
Hey everyone! I am excited to share updates on four of my & my teams' open-source projects that take large-scale search systems to the next level: USearch, UForm, UCall, and StringZilla. These projects are designed to work seamlessly together, end-to-end—covering everything from indexing and AI to storage and networking. And yeah, they're optimized for x86 AVX2/512 and Arm NEON/SVE hardware. USearch [1]: Think of it as Meta FAISS on steroids. It's now quicker, supports clustering of any granularity, and offers multi-index lookups. Plus, it's got more native bindings than probably all other vector search engines combined: C++, C, Python, Java, JavaScript, Rust, Obj-C, Swift, C#, GoLang, and even slightly outdated bindings for Wolfram. Need to refresh that last one! UForm v2 [2]: Imagine a much smaller OpenAI CLIP but more efficient and trained on balanced multilingual datasets, with equal exposure to languages from English, Chinese, and Hindi to Arabic, Hebrew, and Armenian. UForm now supports 21 languages, is so tiny that you can run it in the browser, and outputs small 256-dimensional embeddings. Perfect for rapid image and video searches. It's already available on Hugging-Face as "unum-cloud/uform-vl-multilingual-v2". UCall [3]: It started as a FastAPI alternative focusing on JSON-RPC (instead of REST protocols), offering 70x the bandwidth and 1/50th the latency. It was good but not enough, so we've added REST and TLS support, broadening its appeal. I've merged that code, and it is yet to be tested. Early benchmarks suggest that we still hit the same 150'000-250'000 requests/s on a single CPU core in Python by reusing HTTPS connections. StringZilla [4]: This project lets you sift through multi-gigabyte or terabyte strings with minimal use of RAM and maximal use of SIMD and SWAR techniques. All these projects are engineered for scalability and efficiency, even on tight budgets. Our demo, for instance, works on hundreds of gigabytes of images using just a few gigabytes of RAM and no GPUs for AI inference. That is a toy example with a small, noisy dataset, and I look forward to showing a much larger setup. Interestingly, even this tiny setup illustrates issues common to UForm and much larger OpenAI CLIP models - the quality of Multi-Modal alignment [5]. It also shows how different/accurate the search results are across different languages. Synthetic benchmarks suggest massive improvements for some low-resource languages (like Armenian and Hebrew) and more popular ones (like Hindi and Arabic) [6]. Still, when we look at visual demos like this, I can see a long road ahead for us and the broader industry, making LLMs Multi-Modal in 2024 :) All of the projects and the demo code are available under an Apache license, so feel free to use them in your commercial projects :) PS: The demo looks much nicer with just Unsplash dataset of 25'000 images, but it's less representative of modern AI datasets, too small, and may not be the best way to honestly show our current weaknesses. The second dataset - Conceptual Captions - is much noisier, and quite ugly. [1]: https://github.com/unum-cloud/usearch [2]: https://github.com/unum-cloud/uform [3]: https://github.com/unum-cloud/ucall [4]: https://github.com/ashvardanian/stringzilla [5]: https://ashvardanian.com/posts/searching-stable-marriages/#e... [6]: https://www.unum.cloud/blog/2023-08-17-uform-graphcore
Does the same job
all alternatives →- ISI started a repo for sharing algorithm implementations2013 · github.com · ▲52
Everything that would be here is in the README. I hope this gets big, it has tons of potential.
- OAOsmoar: A Bayesian Suggestion Engine2010 · osmoar.com · ▲6
A friend and I are launching an alpha first thing in 2011. We're trying to gain some momentum and whatnot, so we're opening early registration as of tonight. We're planning to develop a Bayesian network to derive suggestions. If you're interested in seeing our progress, check it out. Edit: Any and all suggestions, criticism, advice, etc is highly appreciated!
- MWmy weekend project, a "framework" for IRC apps/bots2011 · ▲24
This is a little project I've been working on for a while in order to better learn Python. Although IRC may not exactly be the most exciting medium, I still find it to be fun and useful, this interest lead me to writing a bot. In doing this I realized that what would actually be more interesting would be if I had a framework. There may already be such a thing, certainly there are IRC libraries, but I don't know if they're well-suited to deploying bots. At any rate if for no other reason than the fact that I am relatively new to programming and eager to learn I decided to build a framework.…
- IBI built a local Elixir/Python pipeline to curate 14,000 RAW photosApr 2026 · qwelian.com · ▲5
I had 14,000 photos sitting on a drive and wanted an excuse to play with local vision models and Elixir/Phoenix. I originally tried to get LLaVA to tell me if a photo was 'good' or matched my style, but quickly learned that LLMs have terrible taste. I ended up demoting the LLM to just extract metadata, and built a custom CLIP/Ridge Regression pipeline to actually learn my preferences based on how I rate things. The stack is Phoenix/Oban on the orchestrator side, and Python/FastAPI/Instructor for the AI workers. Happy to answer any questions about the architecture,…
- HMHoodmaps Meets 4chan2024 · mapchan.com · ▲8
I made this as a pair programming exercise with o1-preview. o1 did most of the heavy lifting, through high level prompts, but eventually I needed to diverge from it to get to completion. My initial prompt was: --- I'm making a web app: It's like 4chan, but each thread starts with a gps coordinate. People can only post text and images. I want to build it with flask and sqlalchemy. I want just the backend and data model that supports these threads, anonymous users, and users that can register a permanent username. Write as much of it as you can for me. --- This produced a fully scaffolded…
- FAFuge, an Erlang Port of GitHub's Scientist Library2016 · github.com · ▲6
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
