AI Knowledge Base

Anyone who has worked on Dify should know that although Dify is a great AI app, the API it provides is incompatible with Open AI, which makes it impossible for some apps to dock to Dify. What can be done to solve this problem?

A very simple, yet hot Prompt on the Snackprompt site, close to 16k views, centers on using the rule of two or eight to locate key parts of learning. The Pareto principle (Pareto) suggests focusing on the concept of 20%, which will...

The Windows cloud desktop from Microsoft is configured with 6 cores, 12G RAM, and unlimited times. The experience is very silky smooth, almost a little delay. First of all, enter the website: https://learn.microsoft.com/zh-cn/tra...

Looking back to 2024, the big models are changing day by day, and hundreds of intelligent bodies are competing. As an important part of AI applications, RAG is also a "group of heroes and lords". At the beginning of the year, ModularRAG continues to heat up, GraphRAG shines, and in the middle of the year, open source tools are in full swing, and knowledge graphs are...

In recent years, with the rapid development of Generative AI (GAI) and Large Language Modeling (LLM), the issues of their security and reliability have attracted much attention. A recent study has discovered a method called Best-of-N jailbreak (BoN for short)...

AI programming tools have been very hot lately, from Cursor, V0, Bolt.new to the recent Windsurf. In this post, we'll start with the open-source solution - Bolt.new, which has a revenue of $4 million in four weeks since the product was launched. The site is helplessly state...

Long Text Vector Modeling The ability to encode ten pages of text into a single vector sounds powerful, but is it really practical? Many people think... Not necessarily. Is it okay to use it directly? Should it be chunked? How to divide the most efficient? In this article, we will take you to an in-depth discussion of different chunking strategies for long text vector models, analyze the li...

The last update was about ChatGPT's new Canvas features. However, it only briefly describes the various functions of Canvas, but does not elaborate the academic applications of Canvas. Therefore, the author will slowly give a detailed description of the academic applications of Canvas...

A UCI physics PhD tested o1 and found that the code for his PhD thesis, which took him 1 year to complete, was implemented by AI in less than an hour. o1 models are already strong enough to straighten out PhD thesis code! This also means revolutionizing the writing of academic papers. By carefully constructing prompt words...

Writing a dissertation can be a difficult challenge, especially when faced with the overwhelming amount of information, nitty-gritty details, and endless rewrites that are often overwhelming. In this post, I will show you the entire process of how to utilize ChatGPT to complete the first draft of an academic paper - from selecting a topic, to literature review, to the entire paper...

In academic writing, clear, concise and persuasive expression is essential to communicate research findings. However, many non-native English-speaking researchers face language barriers when writing and embellishing academic papers. To address this problem, Stanford University has shared a series of efficient paper touch-ups through an open source project to mention...

I. The Root Cause of Testing Prompts: LLM is highly sensitive to prompts, and subtle changes in wording can lead to significantly different outputs Untested prompts can produce: Factually incorrect information Irrelevant replies Unnecessary wasted API costs II. Systematizing the Prompts...

Take the Halo AI video as an example, and write the cue word: 00:00 Cat's eyes, zoom in 00:02 Gray tabby cat, zoom out 00:04 A gray tabby cat sprawled on the grass under a big tree in the forest Because the video is 6 seconds long at the most, leave 2 seconds for the last shot...

;; ━━━━━━━━━━━━━━ ;; Author: Li Jigang ;; Version: 0.1 ;; Model: Claude Sonnet ;; Purpose: Convert heartfelt words into weekly reports ;; ━━━━━━━━━━━━━━ ;; Set ...

In order to better use Conch AI (MiniMax) video generation for the image domain, we maintain a ComfyUI node. ComfyUI MiniMax Video is a powerful extension that integrates MiniMax AI's...

Wrote a lot of models and tools that can AI fitting, either need to recharge, or need to use magic on the extranet to use, or have to be deployed locally, the simplest and most foolproof to use or can be Ling has just launched the AI fitting function. After the announcement of the new upgrade of its 1.5 model by the Kerin AI platform under Racer, it has released a...

Implementing a Full-Featured AI Agent App in Less Than 50 Lines of Python Code (Step-by-Step Guide) AI tools are changing the way entrepreneurs identify trends and make decisions, but building a scalable solution to analyze startup opportunities often requires integrating multiple data sources and processing them quickly. However...

In our last post, we discussed Devin, an Agentic AI that enables fully automated programming.Compared to other Agentic AI tools, such as Cursor and Windsurf, it is better at process planning, self-evolution...

Natural Language Interactive Database Reading and Writing Toward the end of the year, ushering in the bidding season, the preparation of large documents such as bidding documents is often a headache. Not only do you need to ensure that the content is accurate and professional, but also highlight the advantages of the enterprise, both test professional knowledge, but also requires copywriting skills. Even with both, it still takes time...

This article uses Dify v0.12.1 version, mainly introduces through the HTTP node in the Dify workflow, to call siliconflow's tencent/HunyuanVideo interface, through the text to generate the specific implementation of the video. Among them, Di...

Video face-swapping technology popularization: common software recommendations and application analysis What is video face-swapping technology? Video face-swapping technology is an image processing technology based on artificial intelligence and deep learning, capable of replacing one face with another and maintaining the natural consistency of dynamic expressions and head movements. In recent years, this ...

I tried to use Windsurf to write code for interface automation testing, and actually felt its convenience and efficiency.Windsurf does not require high code ability of users, and at the same time, the accuracy of the generated code is high. Windsurf does not require high coding skills from the user, and the accuracy of the generated code is high. What's more, the scenario coverage of the generated test cases is...

In modern life, video conferencing, online learning and live streaming have become an important part of daily activities. However, many computers come with poor quality webcams that cannot fulfill the need for clarity. At this time, cell phone cameras, as an underrated resource, can be easily transformed into high-quality computer cameras. Pick up ...

🚀 Prompt Engineering Prompt Engineering, a key skill in the era of generative AI, is the art and science of designing effective instructions to guide language models in generating desired output. According to DataCamp, this emerging discipline involves...

Don't believe the news on the Internet about "a man who doesn't know how to program and made a million dollars a month with Windsurf", he may not really know how to program, but his father did. If you don't know a little bit of programming or even English, it's really hard to write a complete program. The internet is full of people who know how to program and teach you how to use Windsurf in the real world....

Overview This guide will walk you through creating a simple Retrieval Augmentation Generation (RAG) system using pure Python. We will use an embedding model and a large language model (LLM) to retrieve relevant documents and generate responses based on user queries. https...

1, System Prompt statement that articulates the underlying guidelines and provides a description of the available tools. (See Prompt1 and Prompt2.) 2. User goals are presented to the Big Model. 3, The big model elaborates on the expected modification behavior of the user goal and specifies the execution plan. 4, The engine proposes...

Introduction Retrieval-enhanced generation (RAG) is a powerful technique that combines the benefits of large language models with the ability to retrieve relevant information from a knowledge base. This approach improves the quality and accuracy of generated responses by basing them on specific retrieved information.a This note...

INTRODUCTION BM25 Retrieval Augmented Generation (BM25 RAG) is an advanced technique that combines the BM25 (Best Matching 25) algorithm for information retrieval with a large language model for text generation. By using a validated probabilistic retrieval model, this method...

Cursor reset machine code to achieve permanent free use At present, the new version of Cursor led to the reset machine code tool is invalid, can be used temporarily: Cursor Reset: Reset Cursor 0.45.x above the version of the device identification of the script Previously released ...

Both ChatGPT and Claude have introduced special modes to facilitate the writing of longer articles. This time, we will unbox these two new services, learn how they are used and their features, and try to figure out the most appropriate way to apply them. Imagine a scenario where you are writing a longer article using AI...

I. Introduction Although most LLMs can now support the output of tens of thousands of Token. However, when we are in the actual business landing, we still often encounter the situation that LLM does not output according to the format we specified. In particular, we need to output results with structured, convenient for us to follow...

# The Role You are a master narrator with 10 years of experience. ## Skills Very good at understanding content to explain AI related technical articles in a narrated interactive manner. Automatically summarizes content into a dialogue format with good transitions between dialogues. ## Tasks You will be required to follow user...

INTRODUCTION Data chunking is a key step in Retrieval Augmented Generation (RAG) systems. It breaks large documents into smaller, manageable pieces for efficient indexing, retrieval, and processing. This README provides an overview of the various chunking methods available in the RAG pipeline. https...

One of the biggest breakthroughs in the field of AI this year should be in the field of programming, with AI programming tools like Cursor and v0 dev not only drastically lowering the threshold of programming for the average person, but also allowing professional programmers to dramatically increase their development efficiency. But the news we've been hearing is not...

Currently, it is not possible. According to the official description, there is a possibility to open up local large model configuration for individual free plans in the future.

When faced with complex text structures, or mixed-text content, it is good to utilize the visual model OCR capability to extract the content. Multi-modal macromodels or specialized visual models can understand the content of the image and receive instructions to perform the recognition task, we will use this ability to make the output content meet our requirements. O...

General Introduction LangChain Academy is an online learning platform focused on teaching the basics of the LangChain ecosystem. The platform provides rich course content covering basic concepts and advanced topics of the LangGraph framework. l...

Introduction Evaluation is a key component in the development and optimization of Retrieval Augmentation Generation (RAG) systems. Evaluation involves measuring the performance, accuracy, and quality of all aspects of the RAG process, from retrieval effectiveness to the relevance and authenticity of generated responses. Importance of RAG Evaluation For RAG...

GPUStack is an open source Big Model-as-a-Service platform that efficiently integrates and leverages a variety of heterogeneous GPU/NPU resources such as Nvidia, Apple Metal, Huawei Rise, and Moore Threads, to provide local, privately deployed Big Model solutions. GPU...

Tongyi Thousand Questions released a code pattern that makes it easy to generate web pages, and we utilized this ability to generate planetary trajectory run charts for kinetic effects. Sort of a flat replacement tool for Artifacts. Code mode is mainly used to generate code, but depends on the library is difficult to much can not be loaded, and can not understand the LISP semantics...

It's been a long time since I've experienced Dream AI, but this time I found that it has changed a lot. The most surprising thing is to find a "Picture 2.1" image generation model, which states "Stable structure and strong film texture support the generation of Chinese and English fonts." I don't know whether the model's native ability to generate Chinese, or in the image generation...

How to use: Settings - Rules for Al and put it in. Original responses will be in Chinese by default. Claude is able to think...

You are a parenting expert, master the following parenting knowledge: ## I. Basic Theory ### # 1. Original Mind Theory - Everyone's original mind is good, including parents and children - Behind the so-called "bad behaviors" there is a good child hidden - To link the behaviors (what is done) with the original mind ...

Welcome to this notebook where we will explore how to set up and observe the Retrieval Augmented Generation (RAG) pipeline using Llama Index. https://github.com/adithya-s-k/AI-Engineeri...

Attempts to unlock paid news by utilizing large model crawls on it. We tried this with pi.ai. The risk here is that the big model does not capture newer information or that the big model itself places security restrictions on capturing paid news. The prompt is as follows: # I am a governme...

This article was co-authored by LangChain's Harrison Chase, Erick Friis, and Linda Ye. Generative AI is set to revolutionize the user experience in the coming years. A key step in this process is the introduction of technologies that can intelligently...

Abstract The field of role-playing research for generating human-like responses has attracted increasing attention as Large Language Models (LLMs) have demonstrated a high degree of human-like capabilities. This has facilitated the exploration of role-playing agents in a variety of applications, such as chatbots that can engage in natural conversations with users, and those that can provide personal ...

These two days by the film style of the superb infj dream core Kitty brush circle, derived from avatars, face change, animation, take pictures of their own pets and a series of applications. And you see the 90% pictures are from this new photogenic AI graphic software, jianghu known as the small panda: Recraft ...

A comprehensive guide to everything you need to know about Bolt 🧵 Initial options may seem obvious, but they're still easy to overlook. You can start directly with your favorite front-end framework. Prepare your cue words ahead of time in gpt/claude. Save tons of Tok...

The reordering model will improve the results of semantic ranking by reordering the list of candidate documents based on their semantic match to the user's question. Commonly used bge-reranker-v2-m3 or cohere

Education has long been considered one of the industries that will be changed the most by LLM. education makes up a large portion of ChatGPT's usage scenarios, and its usage often fluctuates with the start of the school year and the regularity of vacations. Andrej Karpathy has chosen education as the direction for his venture. People are expect...

Sentence Window-Based Retrieval RAG Approach Introduction The Sentence Window-Based Retrieval RAG (Retrieval-Augmented Generation) approach is a high-level implementation of the RAG framework designed to enhance the context in which AI generates replies...

Using the ChatGPT 4o-mini test, let's start with two examples: Playing the silent stone Playing the stone Expectations of "validity" Playing the "silent stone", what do you expect to be the correct feedback from the big model? If you expect the big model to be silent, you can't do it, you have to add...

Domestic has not been able to connect directly to the OPENAI API, the recent xai api does not support direct access to the domestic, but you can continue to use it through the vercel proxy, the code is as follows: First create a warehouse (it is recommended to create a new private warehouse), a new filename ...

Build your own private search engine SearXNG Preparation: Make sure you have Docker and Docker Compose installed on your machine. Step 1: Create an instance directory First, create a directory to hold SearXNG's configurations...

# Chekhov Lacks Money and Goes Crazy Literature Generator - Author: 云中江树 - Language: 中文 - Model: Claude 3.5 Sonnet ## Style Chekhov Lacks Money and Goes Crazy Text Features: - Strong Emotional Contrast - Humorous Dramatic Contrast ...

Introduction The Sentence Window-based Retrieval-Augmented Generation (RAG) method is a high-level implementation of the RAG framework that aims to enhance the context-awareness and coherence of AI-generated responses. The method ...

⚙️PearAI Core Features CMD+I - Inline code editing: PearAI will make changes to your current file and show the differences. CMD+L - New Chat (if you select a code, it will also be added to the chat). CMD+SHIFT...

No-code tool "Seconda", a software to realize any idea without writing code, covering the features of no-code programming, multi-intelligence body collaboration and multi-tools invocation, just talk, you can build a variety of applications. It can help more people and more enterprises to build millions of "super useful" applications...

Introduction: Say goodbye to cumbersome manual updatesToday Dify updated version 0.12.1, but the traditional way of updating is daunting to old gold me - backing up data, downloading updates, overriding the installation, each step may take a lot of time and energy. In the face of these troubles, the emergence of Windsurf...

Introduction The Automated Merge Retriever is a high-level implementation of the Enhanced Retrieval Generation (RAG) framework. It aims to enhance the context-awareness and coherence of AI-generated responses by merging potentially fragmented and smaller contexts into larger and more comprehensive ones. https://g...

I've found that a lot of people are confused about understanding the differences between AI IDE tools like Bolt, v0, and Cursor. Since I've been using them for a few months now (and subscribed to the services), I'll summarize their key points here. The full content is as follows: 🧵 B...

A systematic guide to AI prompt words with 8 practical tips, from basic role-playing to advanced assessment methods, each with a standardized template and instructions for use, to help users get better AI conversations Basic Tips (first 5) Role-playing Prompt Template: "Are you the {leader...

In 2022 OpenAI released ChatGPT, which became the fastest APP in the world to break through the hundreds of millions of users, and at that time people thought that we were closer to true artificial intelligence. But people soon realized that ChatGPT could have conversations and even write poems and essays...

TOML is a clean and simple configuration file format 📄 designed to be more human readable and writable ✨. ✅ Easier to write: Configurations are represented as key-value pairs without complex indentation and syntax rules, reducing the error rate. ✅ Clearer: Supports grouping [group] and nesting structure, layer...

Introduction The Query Transformations User Manual demonstrates a variety of techniques for transforming and disambiguating user queries before they are executed in a Retrieval-Augmented Generation (RAG) query engine, intelligences, or other processes. These transformations can improve the quality and relevance of responses in AI applications. https://gith...

You're on your side, and since yesterday's release of Anthropic's open source Model Context Protocol: Model Context Protocol (MCP), according to Anthropic, Block, and Apollo, among others...

It's like being a smart kid who doesn't understand coding best practices. You need to tell the AI exactly what you want: is it a web application? What functionality is needed? What is the structure? And so on. Here's how to make AI your full-stack developer: Context to...

[bilibili]https://www.bilibili.com/video/BV1dSzGYvEUQ/?share_source=copy_web&vd_source=b66a94312...

Introduction Thomas joined Vespa in April 2024 as a Senior Software Engineer. In one of his last previous assignments as an AI consultant, he actually built a RAG application based on Vespa's massive PDF collection...

It's an open standard we've developed at Anthropic to address the core challenge of Large Language Model (LLM) applications - connecting them to your data. There's no need to build custom integrations for each data source.MCP provides one protocol to connect all data sources: ...

Today, we open-sourced Model Context Protocol (MCP), a new standard for connecting AI assistants to systems that store data, including content repositories, business tools, and development environments. Its goal is to help cutting-edge models generate better...

Introduction Self-Query RAG (SQRAG) is a state-of-the-art Retrieval Augmented Generation (RAG) approach that enhances the traditional RAG process by introducing metadata extraction in the ingestion phase and intelligent query parsing in the retrieval phase. https...

What is Windsurf? Windsurf is an AI-powered coding assistant that offers a range of features to streamline the coding process for developers. Similar to GitHub Copilot, it utilizes machine learning models to understand code context and provide intelligent...

Windsurf is Codeium's latest big move, an AI IDE that's "both smart and knowledgable", using the same approach as Cursor, which directly forked VSCode in order to deeply integrate AI capabilities into...

One of the risks of using big model is outputting sensitive content, although the big model itself has made security restrictions in terms of security. However, in the domestic development of large model-related projects, especially content output applications, generally use specialized keyword filtering services, there are many providers here is not recommended. Note: If your service ...

Microsoft 365 Agents are designed to enhance personal effectiveness and transform business processes through seamless human-computer collaboration, AI collaboration, and automated business processes. A wide range of Agents, including SharePoint Agents...

Introduction RAG-Fusion is an advanced information retrieval and text generation methodology built on Retrieval Augmented Generation (RAG). This project implements RAG-Fusion to provide more accurate, contextually relevant and comprehensive responses to user queries. htt...

First of all, the conclusion: copilot for powerbi works normally on domestic networks without any scientific means. A lot of guys see the copilot button, click on it but it shows unavailable, often mistakenly think that it is unavailable because of their own domestic network: There are also some guys...

The conditions for the use of copilot for powerbi were mentioned earlier: To use Copilot for Power BI, you must have access to advanced Power BI capacity (P1 and above) or paid fabric capacity...

To purchase a Windsurf membership, Chinese users can follow the steps below: Visit the official website: First, go to Windsurf's official website, where there are usually detailed information about membership registration and purchase. Choose the type of membership: According to individual needs, choose the appropriate...

v0.dev system prompt has been upgraded again, and compared to the previous version, it takes up twice as many tokens! And will this bigger system prompt lead to better optimization features? Let's take a look back at the last iteration of v0.dev system prompt...

Math formulas are used as commands to make Claude generate magical animations that I'm sure you'll be very surprised to see. Simply enter the following math formula into Claude: a=(x,y,d=mag(k=x/8-12,e=y/8-9)**2/50)=&g...

Windsurf allows you to generate new code or edit existing code directly in the editor window through natural language input. To invoke a command, press ⌘+I on a Mac or Ctrl+I on Windows/Linux.From here, you can enter self...

Introduction RAPTOR (Recursive Abstract Processing for Tree-Structured Retrieval Enhanced Generation) is an advanced Retrieval Enhanced Generation (RAG) method. It enhances the traditional RAG process by introducing hierarchical document structuring and summarization techniques. https://github.com...

Glif This tool we have introduced many times before, built-in rich image creative workflow, a lot of small red book pop-up creative images are derived from this tool. Using Glif you do not need to carry out complex configuration, because the author has encapsulated the entire process, you only need to fill in the input box text or image...

ColBERT (Contextualized Post-Cultural Interaction based on BERT) is different from the traditional dense embedding model. Here is a brief description of how ColBERT works: Token level embedding: Unlike directly creating individual vectors for an entire document or query, ColBER...

Embedding and reordering are important nodes needed to handle the knowledge base process, good embedding models allow better understanding of the semantics, and reordering models are necessary for ordering knowledge fragments. Local installation of embedding and reordering models is inconvenient to use, it has to be started every time, and connecting to remote services often has various exceptions. Moreover, the small size of ...

codeium is available in China, especially in Windsurf, you can write code for any model you choose, because it doesn't call the original interface of the model directly. The reason of unavailability usually appears in the registration and login stage, please choose to enter the email password to log in...

Windsurf Many people are not adapted to the use of the English interface, in fact, he and VS to switch to the same principle of the Chinese interface, only need a Chinese extension. Here to teach you quickly set Windsurf for the Chinese interface. First open Windsurf, click on the right side of the extension, and then enter the Chinese ...

Introduction GraphRAG (Graph Structure Based Retrieval Enhanced Generation) is an advanced retrieval and generation method. It combines the advantages of graph data structures with the capabilities of Large Language Models (LLMs) to overcome some of the limitations of traditional RAG systems. https://githu...

INTRODUCTION Intelligent body based approach to enhance retrieval augmented generation. Multi-Document Agentic RAG (Retrieval Augmented Generation) is an advanced ...

I. Login Website: https://m365.cloud.microsoft/chat?auth=2 After inputting the account password, if the following interface appears, click "Fixed" and then display this, it means that there is no problem with the account login. Two...

Copilot Agents, the second wave of the Copilot update released in September, has recently made its official debut: Today, we're ready for Copilot Agents to introduce themselves. Select "writing coa...

Notes: https://colab.research.google.com/github/run-llama/llama_index/blob/main/docs/docs/examples/multi...

📚 Repository Structure Models/Catalogs Description and Content Axolotl A framework for fine-tuning language models Gemma Google's latest implementation of a large language model - finetune-gemma.ipynb - gemma-sft.p...

Welcome to the AI Agents section of the AI Engineering Academy! This module explores the fascinating world of AI agents, from basic patterns to practical applications. Learn how to create, orchestrate, and deploy intelligent agents that can perform complex tasks and reason about their environment. 📚 Repository structure Classes...