MegaPairs: a new multimodal vector embedding model from BGE
Comprehensive Introduction MegaPairs is an open source project on GitHub by the VectorSpaceLab team to generate multimodal embedding models for image-text-to-image retrieval tasks through large-scale data synthesis techniques. The project is based on more than 26 million iso...
LitServe: Rapidly Deploying Enterprise-Grade General AI Model Reasoning Services
Comprehensive Introduction LitServe is an open source AI model service engine from Lightning AI, built on FastAPI, focused on rapidly deploying inference services for general-purpose AI models. It supports everything from large language models (LLMs), visual...
LaWGPT: Chinese legal knowledge modeling, supporting legal quizzes and judicial exam training
General Introduction LaWGPT is an open source project supported by the Machine Learning and Data Mining Research Group of Nanjing University, which is dedicated to building a large language model based on Chinese legal knowledge. It is based on generalized Chinese models (such as Chinese-LLaMA and ChatGLM)...
Ali Bailian provides QwQ-32B API for free, and 1 million tokens are free to use it every day!
Recently, AliCloud's Hundred Refinement Platform announced the opening of API interfaces for the QwQ-32B large language model and provided a free daily usage quota of 1 million tokens, which undoubtedly significantly reduces the threshold for users to experience cutting-edge AI technology. For those who wish to experience Qw...
autoMate: a native tool that combines AI and RPA to automate computer tasks
Comprehensive Introduction autoMate is a local automation tool open-sourced and developed by yuruotong1 on GitHub, featuring AI+RPA (Artificial Intelligence+Robotic Process Automation) as its core feature. It combines the intelligent understanding of large-scale language models with RPA...
r1-reasoning-rag: new ideas for RAG based on recursive reasoning from collected information
Recently found an open source project, it provides a good RAG ideas, it will DeepSeek-R1 reasoning ability combined with Agentic Workflow applied to RAG retrieval Project address https://github...
Nanobrowser: Multi-Intelligence Plugin for Task Automation in Browsers
General Introduction Nanobrowser is an open source Chrome extension designed to automate web tasks through an AI-driven multi-agent system. It is a free alternative to OpenAI Operator, where users simply provide their LLM...
OWL: An automated tool for multi-intelligence collaboration on realistic tasks
Comprehensive Introduction OWL (Optimized Workforce Learning) is an open source framework developed by the CAMEL-AI team focused on optimizing multi-intelligence collaboration for automating real-world tasks. Based on the CAMEL-AI framework ...
Reflection: super-intelligent autonomous programming system (not open)
General Introduction Reflection is a company focused on AI technology development, based in the US, founded by experts who have worked in top AI labs such as Google DeepMind, such as co-founder Ioannis Antonoglou (Alph...
BuffGPT: A Low-Code Development Platform for Enterprise-Grade Generative AI Applications
Comprehensive Introduction BuffGPT is an open source AI application development platform based on the Large Language Model (LLM), providing out-of-the-box features such as data processing, model invocation, RAG retrieval, and visual workflow orchestration to help users easily build and operate generative AI applications. The platform supports privatization...