Jie Wang's repositories
ai-renamer
A Node.js CLI that uses Ollama models (Llama, Gemma, Llava etc.) to intelligently rename files and images in a specified directory
360LayoutAnalysis
360LayoutAnaylsis, a series Document Analysis Models and Datasets deleveped by 360 AI Research Institute
agentscope
Start building LLM-empowered multi-agent applications in an easier way.
ai-artifacts
Hackable open-source version of Anthropic's AI Artifacts chat
awesome-foundation-model-leaderboards
A curated list of awesome leaderboards for foundation models
awesome-multi-agent-papers
A compilation of the best multi-agent papers
bergen
Benchmarking library for RAG
chatty
ChattyUI - your private AI chat for running LLMs in the browser
ComfyUI-3D-Pack
An extensive node suite that enables ComfyUI to process 3D inputs (Mesh & UV Texture, etc) using cutting edge algorithms (3DGS, NeRF, etc.)
ControlFlow
🦾 Take control of your AI agents
CosyVoice
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
dataline
Chat with your data - AI data analysis and visualization on CSV, Postgres, MySQL, Snowflake, SQLite...
dify-sandbox
A lightweight, fast, and secure code execution environment that supports multiple programming languages
docmost
Docmost is an open source collaborative documentation and wiki software. It is an open-source alternative to the likes of Confluence and Notion.
dropbase
Dropbase helps developers build and prototype web apps faster with AI. Dropbase is local-first and self hosted.
eval-dev-quality
DevQualityEval: An evaluation benchmark 📈 and framework to compare and evolve the quality of code generation of LLMs.
gptpdf
Using GPT to parse PDF
korvus
Korvus is a search SDK that unifies the entire RAG pipeline in a single database query. Built on top of Postgres with bindings for Python, JavaScript, Rust and C.
LazyLLM
Easyest and lazyest way for building multi-agent LLMs applications.
LivePortrait
Bring portraits to life!
LLaVolta
Efficient Multi-modal Models via Stage-wise Visual Context Compression
MindSQL
MindSQL: A Python Text-to-SQL RAG Library simplifying database interactions. Seamlessly integrates with PostgreSQL, MySQL, SQLite, Snowflake, and BigQuery. Powered by GPT-4 and Llama 2, it enables natural language queries. Supports ChromaDB and Faiss for context-aware responses.
ollama-app
A modern and easy-to-use client for Ollama
omniparse
Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks
Open-Sora
Open-Sora: Democratizing Efficient Video Production for All
PDF-Extract-Kit
A Comprehensive Toolkit for High-Quality PDF Content Extraction
RealtimeSTT_LLM_TTS
实时STT，连接智谱AI（流式LLM）和GPT-SOVITS，通过网页的方式，进行跨网络的服务调用，实现实时对话的效果