News

GitHub
github.com > alibaba > zvec

GitHub - alibaba/zvec: A lightweight, lightning-fast, in-process vector database

6+ hour, 38+ min ago  (87+ words) " Quickstart | " Home | " Docs | " Benchmarks | " Discord | " X (Twitter) Requirements: Python 3.10 - 3.12 If you prefer to build Zvec from source, please check the Building from Source guide. Zvec delivers exceptional speed and efficiency, making it ideal for demanding production workloads. Stay updated and…...

GitHub
github.com > google > langextract

GitHub - google/langextract: A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

1+ mon, 3+ week ago  (769+ words) LangExtract is a Python library that uses LLMs to extract structured information from unstructured text documents based on user-defined instructions. It processes materials such as clinical notes or reports, identifying and organizing key details while ensuring the extracted data corresponds…...

GitHub
github.com > sorukumar > Bitcoin-Data-Labs

GitHub - sorukumar/Bitcoin-Data-Labs: Bitcoin Data Labs is a non-profit focused on research and open-source projects for the Bitcoin and Lightning Network ecosystems. We provide data analytics, tools, and insights.

3+ mon, 4+ day ago  (109+ words) Bitcoin Data Labs is a non-profit focused on research and open-source projects for the Bitcoin and Lightning Network ecosystems. We provide data analytics, tools, and insights. - GitHub - sorukumar/Bitcoin-Data-Labs: Bitcoin Data Labs is a non-profit focused on research and open-source…...

GitHub
github.com > NVlabs > describe-anything

GitHub - NVlabs/describe-anything: [ICCV 2025] Implementation for Describe Anything: Detailed Localized Image and Video Captioning

3+ mon, 6+ day ago  (237+ words) NVIDIA, UC Berkeley, UCSF International Conference on Computer Vision (ICCV) 2025 Long Lian, Yifan Ding, Yunhao Ge, Sifei Liu, Hanzi Mao, Boyi Li, Marco Pavone, Ming-Yu Liu, Trevor Darrell, Adam Yala, Yin Cui TL;DR: Our Describe Anything Model (DAM) takes in…...

GitHub
github.com > thoughtbot > administrate > releases > tag > v1.0.0

Release 1.0.0 · thoughtbot/administrate

3+ mon, 2+ week ago  (159+ words) After a long time in the making, and contributions from many different people, we're pleased to release Administrate v1.0.0! Thank you to everyone who uses, contributes and opens issues on Administrate. It couldn't be done without you. Aside from lots of…...

GitHub
github.com > rdumasia303 > deepseek_ocr_app

GitHub - rdumasia303/deepseek_ocr_app: A quick vibe coded app for deepseek OCR

3+ mon, 2+ week ago  (269+ words) Modern OCR web application powered by DeepSeek-OCR with a stunning React frontend and FastAPI backend. Now with PDF processing and multi-format document conversion! We've added powerful PDF processing capabilities based on community feedback! Here's what you can do now: Export…...

GitHub
github.com > stackernews > stacker.news > pull > 2507

Add question about AI usage to PR template by ekzyis · Pull Request #2507 · stackernews/stacker.news

5+ mon, 3+ day ago  (81+ words) Comments There was an error while loading. Please reload this page. - Notifications You must be signed in to change notification settings Add question about AI usage to PR template #2507 I did not use AI for this Sorry, something went wrong....

GitHub
github.com > KurtisStirling > OCR-Bitcoin

GitHub - KurtisStirling/OCR-Bitcoin: MIT Licensed OCR-B font modified for use in Bitcoin Knots

5+ mon, 2+ week ago  (83+ words) This font is licensed under the MIT License. See LICENSE.txt for details. Warning: this font is not intended for Optical Character Recognition use. We needed a free and open source font for the Bitcoin Knots project, so made this…...

GitHub
github.com > geeknik > least-likely-token

GitHub - geeknik/least-likely-token: LEAST likely next token predictor.

11+ mon, 2+ week ago  (212+ words) This project implements a least likely next token predictor using reinforcement learning. It leverages a pre-trained language model (GPT-2) to estimate token probabilities and trains a second model to predict tokens with the lowest probabilities, making it the "apex predator…...