Tags: #multimodal

A unified, production-ready inference API for deploying and serving open-source language, speech, and multimodal AI models on various infrastructures.

An AI-driven platform that transforms research papers, text, or topics into editable scientific figures, technical diagrams, and presentation slides with universal file support.

FlagEmbedding (BGE) is a comprehensive toolkit offering state-of-the-art embedding models for efficient search, Retrieval-Augmented Generation (RAG), and various multimodal AI applications.

OSWorld is a benchmark and environment for evaluating multimodal AI agents on open-ended tasks within real computer operating systems.

A comprehensive, full-stack guide to Retrieval Augmented Generation (RAG) technology for large language model application development, covering theory, practice, and engineering best practices.

SimpleMem offers an efficient, lifelong, and multimodal memory solution for LLM agents, featuring semantic lossless compression for diverse data types.

A comprehensive, continuously updated collection of the best resources for Large Language Models (LLMs), covering various aspects from data processing to advanced applications.

A framework for efficient, fast, and cheap serving of omni-modality (text, image, video, audio) AI models.

A high-performance data engine for AI and multimodal workloads, processing diverse data types at scale with Python and Rust.

An open-source implementation for efficiently fine-tuning Alibaba Cloud's Qwen-VL series of multimodal large language models using HuggingFace and Liger-Kernel.

A comprehensive AI-native toolset for accurate document search and storage, designed to integrate complex context from visually rich and multimodal data into AI applications.

An open-source desktop application providing a native GUI Agent for human-like task completion through multimodal AI, enabling local and remote computer/browser automation.

A Python library for extracting clean markdown, multimodal media, and structured data from complex documents using vision-language models.

PySpur is a visual playground designed to accelerate the iteration, debugging, and deployment of AI agents, helping engineers overcome common challenges like prompt hell and workflow blindspots.

A meticulously curated collection of academic papers and resources focused on enhancing and understanding the reasoning abilities of Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs).

A pioneering open-source multimodal large language model family aiming to match or exceed commercial models like GPT-4o/GPT-5 in performance.

An open-source Python package that transforms multi-modal content into captivating multilingual audio conversations using GenAI, serving as a programmatic alternative to tools like NotebookLM.