Are you still troubled by the varying quality of AI in China and poor performance? Then let’s take a look at Dev Cat AI (3in1)! This is an integrated AI assistant that combines GPT-4, Claude3, and Gemini. It covers all models of the three AI tools. Including GPT-4o and Gemini flash Now you can use … Read more
Click 01 Muggle Society Follow our public account, never get lost in AI learning Have you ever considered running open-source LLM locally? Do you have to manually download large model files? Are you struggling to build an API for your local model? Have you tried managing multiple models locally? I guess you have thought about … Read more
Have you heard of the tool Cursor? It’s like a combination of AI and VsCode. By binding APIs from large models like ChatGPT and Claude, you can achieve conversational self-programming, allowing you to develop a software application with just a casual chat. However, Cursor is limited by foreign networks, making it inaccessible for users in … Read more
On Windows, after configuring the DeepSeek large model in VS Code with Cline, the automatic programming attempt started. After the prompt was completed, there was almost no intervention throughout the process, and the project ran successfully on its own: Prompt: ### **Project: MP4 Video Upload and Online Playback Web Application** ### Architecture Requirements: Based on … Read more
1. DeepSeek is a Python library Install the library First, ensure your Python environment is properly configured (you can do this in VSCode by creating a virtual environment, etc.). Use pip install deepseek – your – specific – version (if there are specific version requirements) to install the DeepSeek library. Import and use in your … Read more
Mistral AI Previously, we briefly introduced Mistral AI. For a detailed introduction, please refer to: Introduction to Mistral AI.Mistral AI supports free calls to the API and Codestral API, today we will try to integrate Mistral AI with Roo Cline. Current Version Roo Cline 2.2.42 Limitations Currently, Roo Cline does not support direct integration using … Read more
In the second part, we explored the principles of modular design. We discussed strategies for decomposing the Agent system by borrowing the bounded context concept from microservices to determine the scope of each sub-Agent. We also hinted that modularization introduces a need for a well-thought-out interaction model between agents and sub-Agents. Today, we will delve … Read more
In VSCode, “cline” might be a vague concept. If “cline” is a typo and you want to ask about the difference between “cline” (related to command line interface concepts) and “Continue” (to continue executing code), then: 1. If it is related to command line interface concepts (assuming it’s a command sequence scenario) cline (here assumed … Read more
In the first part of this series, we introduced the overall architectural pattern of Agent systems. We discussed the three logical layers of Agent systems: the Tool Layer, Action Layer, and Reasoning Layer. We also examined mechanisms such as function calls that allow large language models (LLMs) to interact with the external world through the … Read more
I previously wrote two articles on address processing, detailed below: Address Processing in Risk Control: Simple and Effective Regex Replacement Address Processing in Risk Control: Simple, Accurate, and Effective Multi-label Clustering Today we are writing the third article, using KNN to construct similar addresses. Although this article is about addresses, many scenarios can draw on … Read more