AI Personal Learning
and practical guidance
CyberKnife Drawing Mirror
Total 908 articles

Tags: ai open source projects Page 23

Unigraph:构建本地运行的知识图谱和个人搜索引擎-首席AI分享圈

Unigraph: building locally running knowledge graphs and personal search engines

General Introduction Unigraph is a local-first universal knowledge graph and personal search engine designed to provide users with an integrated workspace to help manage and search for a wide variety of data in their personal lives. With Unigraph, users can integrate data from different sources into a unified knowledge graph...

Unsloth:高效微调和训练大语言模型的开源工具-首席AI分享圈

Unsloth: an open source tool for efficiently fine-tuning and training large language models

General Introduction Unsloth is an open source project designed to provide efficient tools for fine-tuning and training large language models (LLMs). The project supports a wide range of well-known models, including Llama, Mistral, Phi, and Gemma, etc. Unsloth's main features are the ability to significantly reduce memory usage and speed up training...

MaxKB:开箱即用的AI知识库问答系统,适合智能客服和企业内部知识库-首席AI分享圈

MaxKB: Out-of-the-box AI Knowledge Base Q&A System for Smart Customer Service and In-house Knowledge Base

Comprehensive Introduction MaxKB (Max Knowledge Base) is an open source knowledge base Q&A system based on large language modeling and RAG (Retrieval Augmented Generation). The system is widely used in intelligent customer service, enterprise internal knowledge base, academic research and education and other scenarios.MaxKB supports direct upload documents or automatically crawl in...

OmniThink:生成高质量长文的写作框架,搜索外部知识后反思并逐步构建知识树-首席AI分享圈

OmniThink: a writing framework for generating high-quality long articles, searching for external knowledge and then reflecting on it and building a knowledge tree step by step

Comprehensive Introduction OmniThink is an innovative machine writing framework designed to generate high-quality, long-form articles by mimicking the iterative expansion and reflection of human cognitive processes. The framework focuses on extending the boundaries of knowledge and generating information that is rich and deep.OmniThink generates articles by building outlines and...

OpenAI Realtime Agents:多智能体语音交互应用(OpenAI示例)-首席AI分享圈

OpenAI Realtime Agents: A Multi-Intelligent Body Speech Interaction Application (OpenAI Example)

General Introduction OpenAI Realtime Agents is an open source project that aims to show how OpenAI's real-time API can be utilized to build multi-intelligent body speech applications. It provides a high-level intelligent body model (borrowed from OpenAI Swarm) that allows developers to build complex multi-intelligent body speech systems in a short time...

MiniRAG:简化检索增强生成框架,实体图索引召回相关文本块-首席AI分享圈

MiniRAG: Simplified Retrieval Enhanced Generation Framework, Entity Graph Index Recall Relevant Text Blocks

Comprehensive Introduction MiniRAG is an extremely simple Retrieval Augmented Generation (RAG) framework that aims to enable good RAG performance even for small models through heterogeneous graph indexing and lightweight topology-enhanced retrieval. It is developed by the Hong Kong University Data Science Laboratory (HKUDS) and focuses on solving the Small Language Model (SLM...

Omni-RGPT:图像和视频区域级理解多模态大模型,提升视觉内容分析能力-首席AI分享圈

Omni-RGPT: A Multimodal Large Model for Image and Video Region-Level Understanding to Enhance Visual Content Analysis

Comprehensive Introduction Omni-RGPT is a multimodal large language model designed to enable region-level understanding of images and videos. By introducing the Token Mark technique, Omni-RGPT is able to highlight target regions in the visual feature space and embed these tokens directly through region cues (e.g., boxes or masks), while placing...

百聆 (Bailing):低延时的开源语音对话助手,轻松实现自然对话交流-首席AI分享圈

Bailing: a low-latency open source voice dialog assistant that easily realizes natural conversational exchanges

Comprehensive Introduction Bailing (Bailing) is an open source voice conversation assistant designed to engage in natural conversations with users through speech. The project combines speech recognition (ASR), voice activity detection (VAD), large language modeling (LLM) and speech synthesis (TTS) technologies to achieve a GPT-4o-like speech...

en_USEnglish