cjinghong
Follow
Stars
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
Download all the wallpapers in MKBHD's "Panels" app
Chonktxt is an SDK that makes it easy to do contextual chunking. Inspired by https://www.anthropic.com/news/contextual-retrieval
WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
SuperPrompt is an attempt to engineer prompts that might help us understand AI agents.
Scalable unofficial ChatGPT API for production.
Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of …
[EMNLP 2024: Demo Oral] RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation
A Bulletproof Way to Generate Structured JSON from Language Models
🛰️ An approximate nearest-neighbor search library for Python and Java with a focus on ease of use, simplicity, and deployability.
The best way to start a full-stack, typesafe Next.js app
Next-generation ORM for Node.js & TypeScript | PostgreSQL, MySQL, MariaDB, SQL Server, SQLite, MongoDB and CockroachDB
This repo includes ChatGPT prompt curation to use ChatGPT better.
Cohere Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.
Efficient Retrieval Augmentation and Generation Framework
Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.
DSPy: The framework for programming—not prompting—language models
Stable Diffusion web UI
Incredibly fast JavaScript runtime, bundler, test runner, and package manager – all in one
🥢 A minimalist-friendly ~2.1KB routing for React and Preact
🇨🇭 A React renderer for Three.js
🐬 A simplified implementation of TypeScript's type system written in TypeScript's type system
Simple, powerful online communities.