Graph RAG: Merging Knowledge Graphs with Large Models

Training Materials September 2024 Issue This video is a community sharing report from the AI-themed discussion meeting of the Yunhan Community held on August 3, 2024. Speaker: Chen Xiaoyang (Member of the Yunhan Community Committee, General Manager of Fucheng Company) Report Title: “Graph RAG – When Knowledge Graphs Meet Large Models“ AI Video Summary: This … Read more

Building RAG AI Assistants with PhiData: A Comprehensive Guide

Building RAG AI Assistants with PhiData: A Comprehensive Guide

Introduction In the field of artificial intelligence, building an intelligent assistant that can understand and respond to user needs is a challenging task. PhiData, as an open-source framework, provides developers with the possibility to create AI assistants with long-term memory, rich knowledge, and powerful tools. This article will introduce the core advantages of PhiData, application … Read more

Open Source End-to-End RAG Solution RAGFlow

Open Source End-to-End RAG Solution RAGFlow

Introduction RAG has developed to become a consensus for LLM’s service to B-end, however, questions regarding it have never ceased to exist. Simply put: for many Q&A systems represented by individuals and small to medium enterprises, there is indeed no need to use RAG. However, these long-context LLMs have either already addressed or are in … Read more

Understanding the Differences Between DeepSeek V3, R1, and Janus-Pro

Understanding the Differences Between DeepSeek V3, R1, and Janus-Pro

Recently, I have been unwell with a gastrointestinal flu for several days, but I am feeling better today and can update on the recent hot topics related to DeepSeek. I won’t go into much detail about the specific news regarding DeepSeek, but on New Year’s Eve, they launched Janus-Pro, and various media outlets have been … Read more

DeepSeek Launches Janus-Pro: A Breakthrough in Multimodal AI

DeepSeek Launches Janus-Pro: A Breakthrough in Multimodal AI

While Wall Street’s tech stocks experienced a dramatic plunge on January 28, a new star in China’s AI sector was illuminating the entire industry with its disruptive brilliance—the DeepSeek team’s officially open-sourced Janus-Pro series model not only redefined the performance boundaries of multimodal large models but also showcased China’s hardcore strength in AI to the … Read more

Open Source Search Engine MiniPerplx: An AI Search Engine Powered by Agent Brain

Open Source Search Engine MiniPerplx: An AI Search Engine Powered by Agent Brain

1. Overview of MiniPerplx2. Features2.1 Intelligent Search Planning and Accurate Result Presentation2.2 Rich Search Types2.3 Powerful Integration Features2.4 Diversified Information Acquisition3. Technical Support and Model Applications4. Differences from Other Search Engines5. Conclusion 1. Overview of MiniPerplx MiniPerplx is a minimalist artificial intelligence search engine supported by the Vercel AI SDK, designed to help users find … Read more

MiniPerplx: Open Source AI Search Engine Based on Grok 2.0

MiniPerplx: Open Source AI Search Engine Based on Grok 2.0

🚀 Quick Read Feature-Rich: Supports various functions such as web search, academic paper search, YouTube video search, etc. Advanced Technology: Built on the Grok 2.0 model, combined with technologies like Next.js and Vercel AI SDK. Open Source and Free: Provides a free alternative, allowing users to deploy and view the source code themselves. Main Content … Read more

Overview of Qwen Series Technology 1 – The Evolution of Qwen

Overview of Qwen Series Technology 1 - The Evolution of Qwen

Introduction The moon of ancient times is unseen by people today, yet this month once shone upon the ancients. Hello everyone, I am the little girl selling hot dry noodles. I am very glad to share cutting-edge technologies and thoughts in the field of artificial intelligence with my friends. With the rapid development of Large … Read more

Qwen2.5-1M: Open Source Model Supporting 1 Million Tokens Context

Qwen2.5-1M: Open Source Model Supporting 1 Million Tokens Context

01 Introduction Two months ago, the Qwen team upgraded Qwen2.5-Turbo to support a context length of up to one million tokens. Today, Qwen officially launched the open-source Qwen2.5-1M model along with its corresponding inference framework support. Here are the highlights of this release: Open Source Models: This release includes two new open-source models, namely Qwen2.5-7B-Instruct-1M … Read more

Qwen-Agent Framework: Exploring Open Source Qwen Model Capabilities

Qwen-Agent Framework: Exploring Open Source Qwen Model Capabilities

  Qwen-Agent is a code framework designed to explore the tool usage, planning, and memory capabilities of the open-source Qwen model. Based on Qwen-Agent, we developed a Chrome browser extension called BrowserQwen, which has the following main features: Discuss the content of the current webpage or PDF document with Qwen. With your authorization, BrowserQwen will record … Read more