Articles by Yang Fan

Recently, the Qwen team has released a series of Qwen2.5-VL Use Case Notebook examples that demonstrate the power of the native models and APIs. The purpose of these notebooks is to help developers and users gain a deeper understanding of Qwen2.5-VL's powerful visual comprehension capabilities, and to inspire more...

Comprehensive Introduction PraisonAI is an out-of-the-box multi-intelligentsia framework for production environments, designed to create AI intelligentsia to automate and solve problems ranging from simple tasks to complex challenges. The framework provides a low-code solution that simplifies the construction and management of multi-intelligent body LLM systems, emphasizing simplicity...

With the wave of digitization sweeping the world today, data has become the core asset of enterprises. How to quickly extract valuable information from massive business data and present it in an intuitive and easy-to-understand way is the key for enterprises to stand out in the fierce market competition. At the same time, an efficient information delivery mechanism is like the god of the enterprise...

General Introduction The Hacker News Chinese Podcast project is an innovative platform based on AI technology that aims to automatically crawl popular articles on Hacker News every day and generate Chinese summaries and podcast content via AI. Developed by ccbikai, the project leverages an advanced technology stack that includes Next.js, Cl...

Comprehensive Introduction LangGraph Supervisor is a Python library based on the LangGraph framework, designed for creating and managing multi-intelligent body systems. The library coordinates the work of multiple specialized agents through a central supervisory agent, ensuring efficient management of communication flows and task allocation.LangGraph Superviso...

In recent years, Large Language Modeling (LLM) technology has been developing at an unprecedented rate and gradually penetrating into various industries. At the same time, there is a growing demand for local deployment of LLMs.Ollama, a convenient local large model deployment tool, has been recognized for its ease of use and support for advanced models such as DeepSeek...

DeepSeek as AI big model session of the top stream, came out of nowhere, forcing the GPT-5 and Baidu Wenxin Yiyin have lowered their heads for free. There are more than 100 domestic platforms online DeepSeek, but not every one of them is easy to use. Many platforms have several fatal problems: the online version of DeepSee is not full-blooded...

The purpose of this tutorial is to allow you to use the DeepSeek-R1 model on your phone while ensuring offline privacy and portability, whether it works well or not is up to you. 10 days of hard work... Nope... ...10 minutes to bring you a tutorial on how to install DeepSeek-R1 locally on your cell phone. Cell phone using DeepSeek-R1 Three scenarios In the installation...

Comprehensive Introduction Deep Searcher is a powerful tool combining Large Language Models (LLMs) and vector databases designed to search, evaluate and reason based on private data, providing highly accurate answers and comprehensive reports. It is suitable for enterprise knowledge management, intelligent Q&A systems and...

General Introduction NVIDIA AI Blueprint: PDF to Podcast is an open source project developed by NVIDIA to convert PDF documents into engaging audio content. The project utilizes NVIDIA NIM (NVIDIA Inference Microservices) technology to be able to securely run on private networks...

General Introduction Deep Research is an AI-based research assistant designed to perform iterative deep research by combining search engines, web crawling, and large language models. The project is published by dzhng on GitHub, with the goal of providing an easy-to-use deep research agent that enables deep research on any topic...

Delivering more accurate, flexible, and multimodal knowledge agents for your private and public data, Activeloop's Deep Thinking technology is now fully available. As we look ahead to 2025, generative AI (GenAI) is poised for a critical year in terms of return on investment (ROI). And multimodal data-based knowledge...

Perplexity today (February 14) announced the launch of Deep Research, a feature designed to help users dramatically save time and perform in-depth research and analysis on their behalf. When a user makes a Deep Research query, Perplexity performs dozens of searches, reads hundreds of sources, and analyzes this...

Comprehensive introduction Kreuzberg is a library to simplify the text extraction of PDF files , designed to provide a simple , hassle-free text extraction solution . The library is especially suited for RAG (Retrieval-Augmented Generation) services that require text extraction.Kreuzberg supports local operation, easy control and...

General Introduction HunyuanVideoGP is a large-scale video generation model developed by DeepBeepMeep and designed for low-end GPU users. The model is an improved version of the original Hunyuan Video model, with significantly reduced memory and video memory requirements, allowing it to run smoothly on GPUs ranging from 12GB to 24GB.H...

At a time when AI technology is changing rapidly, the cooperation model between tech giants and traditional media is quietly undergoing changes. Recently, OpenAI and the UK's old media, The Guardian Media Group, announced a strategic partnership, a news that undoubtedly sparked widespread attention in both the AI technology field and the news and communication...

General Introduction InspireMusic is a PyTorch-based open source toolkit focused on music, song, and audio generation. It provides a unified framework for generating high-quality audio with controls for text cues, music structure, and music style.InspireMusic supports 24kHz and 48kHz ...

General Introduction Gemini Playground is an open source project designed to help users quickly deploy a multimodal dialog site . The project is developed by the technical crawler shrimp , support for the use of Gemini API Key in 10 seconds to complete the deployment . No matter where the user is , can be Deno or Cloudflare ...