Stars
A flexible distributed key-value datastore that is optimized for caching and other realtime workloads.
Official Svelte components built for Flowbite and Tailwind CSS
⏩ Continue is the leading open-source AI code assistant. You can connect any models and any context to build custom autocomplete and chat experiences inside VS Code and JetBrains
LAVIS - A One-stop Library for Language-Vision Intelligence
Build vector tilesets from large collections of GeoJSON features.
The OpenStreetMap editor driven by open data, AI, and supercharged features
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…
Make OpenStreetMap vector tiles without the stack
Blazing fast and lightweight PostGIS, MBtiles and PMtiles tile server, tile generation, and mbtiles tooling.
OpenStreetMap raster tile renderer written in Rust
Unified framework for building enterprise RAG pipelines with small, specialized models
Retrieval Augmented Generation (RAG) chatbot powered by Weaviate
🦜🔗 Build context-aware reasoning applications
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
Get up and running with Llama 3.3, Mistral, Gemma 2, and other large language models.
ZincSearch . A lightweight alternative to elasticsearch that requires minimal resources, written in Go.
Large Language Model Text Generation Inference
Open source codebase powering the HuggingChat app
pipreqs - Generate pip requirements.txt file based on imports of any project. Looking for maintainers to move this project forward.
Best (most accurate) trained LSTM models.
Official Pytorch Implementation of: "ImageNet-21K Pretraining for the Masses"(NeurIPS, 2021) paper
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.