AI Knowledge Base

LangChain Hub #1 tipster in Chinese. Released over a year ago and used in the overall evaluation of the combined scores of different RAG strategies. Translated and adapted for use in multiple languages. Usage Help Evaluate which answer is better, assuming both answers are correct. Take ...

A directive is a node of a complete retrieval scheme that provides accurate routing for questions. Features: 1. Rewrite questions 2. Route different knowledge bases for questions 3. Generate questions sorted by trustworthiness Example of a core directive (adapted to your own business scenario) Simplify up-to-date questions to facilitate in the intent to know...

There is no easy answer to the price comparison between OpenRouter and Poe, as their prices depend on the models used, the amount of usage, and the specific package. Both offer a wide range of AI models at widely varying prices. Poe: Poe's strength is its all-in-one platform...

Recraft is an up-and-coming image generation program that is particularly popular with Dreamcore style enthusiasts. It allows users to generate images with a film sense by entering keywords, the operation is simple and fast. Recommended tutorial: 5 minutes to teach you to use AI dreamcore film avatar, don't...

Windsurf is an AI-based development tool that supports a variety of development frameworks and languages, including the development of WeChat Small Programs. According to the latest information, Windsurf can help developers quickly build WeChat Small Program projects and generate code and project closure through natural language commands...

"Fixing Errors" Tip AI models like Sonnet 3.5 can sometimes miss important details, which can trigger a series of error loops. Use the following tips to solve this problem. This will help the AI analyze the root cause of the error and then create a step-by-step plan to fix it...

Transit large model API in the country is an essential service, such as the most well-known One API, in addition to this will be commonly used cloudflare vercel huggingface to solve the API proxy load and security issues. Even to ensure that the proxy service ...

dify provides tools for creating customizations, however this customization is required to follow the OpenAPI-Swagger specification. An example of an empty template for the specification is as follows: { "openapi": "3.1.0", "info": { "tit...

Agent The most common translation I've seen so far is "intelligent body", but the direct translation is "agent". What does Agentic translate to? I feel that a word like "agentic" is more appropriate. So in order not to confuse the readers, I will use English directly in this article. With ...

Since the personal home version of the copilot pro is advertised with the phrase "no restriction on GPT-4 during peak hours" (which corresponds to non-copilot pro users dropping to GPT-3.5 during peak hours), many people assume that this continues to be the case. Actually...

# Guidelines for Composing a Silent Movement ## Asking for a Theme Tell me about the theme or emotion you want to express. This can be concrete (e.g. "first love") or abstract (e.g. "hope"). ## Rules for Composition - **Sound attributes of text are strictly prohibited**: e.g., rhyme, tone, rhythm, etc. ...

In order for an AI model to be useful in a particular scenario, it usually needs access to background knowledge. For example, a customer support chatbot needs to understand the specific business it serves, while a legal analysis bot needs to have access to a large number of past cases. Developers often use retrieval-enhanced generation (Retrieva...

This command comes from the Vision Parse project and extracts markdown documents in two steps. Image analysis prompt (img_analysis.prompt): Analyze this image and retur...

How to start generating visual content with Napkin AI ? (Account creation, visual generation, export to pdf or image file...) Welcome to Napkin AI, a tool that makes it easy to convert your text into beautiful visuals. This guide will walk...

Prompt Words Role Summary: You are a professional video subbing expert. Please disassemble the script into detailed split shot information based on the following criteria. # Split Criteria: ## Basic Split Rules 1. New Scene Split Criteria (any one fulfillment is a new scene): - Scene/location change - Time...

Full Process of Fine-tuning Large Models It is recommended to strictly follow the above process during the fine-tuning process and avoid skipping steps, which may lead to ineffective labor. For example, if the dataset is not fully constructed, and it is eventually found that the poor effect of the fine-tuned model is a problem with the quality of the dataset, then the efforts in the early stage will go down the drain, and the effort will be half-hearted...

OlaChat AI Digital Intelligence Assistant 10,000-word in-depth analysis to take you through the past and present of Text-to-SQL technology. Thesis: Next-Generation Database Interfaces: A Survey of L...

01.Background In RAG application development, the first step is to chunk the document, efficient document chunking can effectively improve the accuracy of the subsequent recall content. Efficient document chunking can effectively improve the accuracy of the subsequent recalled content. How to efficiently chunk is a hot topic of discussion, there are such as fixed-size chunking, random-size chunking...

In the development work, the daily trivial code modification, command execution and context switching often make us tired to deal with. Recently, I experienced Cline, a VS Code extension designed for developers, and it feels like having an intelligent assistant that understands code, and the experience has been non...

Only extract the table in the document as html format file, the document can be correctly extracted from multiple tables, page tables, currently adapted to gemini-2.0-flash-exp effect is better. You are tasked with recognizi...

bolt.new system prompt word original You are Bolt, an expert AI assistant and exceptional senior software developer w...

Someone won $50,000 by convincing an AI agent to transfer all their funds to them. November 22, 2023 at 9:00 PM An AI agent named Freysa (@freysa_ai) was released with the sole goal of...

WeaveFox will be officially released in 2025. WeaveFox is an AI front-end intelligent R&D platform launched by the Ant team, based on Ant's self-developed Bailing Multimodal Large Model, which is capable of generating front-end source code directly from design drawings. The platform supports a variety of application types, including console, mobile...

Over the past year, we've worked with teams building Large Language Model (LLM) agents across multiple industries. Consistently, we've found that the most successful implementations didn't use complex frameworks or specialized libraries, but rather were built with simple, composable patterns. In this post, we'll share what we've learned from working with customers to...

To solve the problem of certain areas can not directly request api.openai.com and so on big model API, or because the agent leaks information leading to sealing the account, before the use of CF agent, may leak your IP, now there is a safer program. 1.first enter the deno official website to register an account...

Generate Chinese posters is very challenging, there are currently two options, one is Mr. into the base image, the second generation of text and synthesis; there is also a model natively support the generation of images with Chinese text. Here only introduce can natively generate Chinese posters AI image generation tools, can be spirit in the image to generate a single line of text ...

Since its launch, Silicon Flow's BizyAir plugin has brought powerful cloud support to ComfyUI, allowing AI designers to achieve an extremely fast and silky smooth image generation experience without the need for a graphics card. BizyAir now comes with nearly 20 built-in base models, including FLUX.1, SD ...

These days, Artificial Intelligence (AI) is a thing of the past. The other day, Google made big news with the release of Gemini 2.0. What's the point of this thing, you ask? Well, to put it this way, if you haven't experienced it yet, it's like never having tasted pot-au-feu with Sprite in your life...

AI Summary Overview An in-depth look at AI cue engineering, with a roundtable format in which a number of experts from Anthropic share their understanding and practical experience of cue engineering from a variety of perspectives, including research, consumer, and enterprise. The article details the definition of cue engineering...

Optimized ChatGPT custom instructions that provide significant performance improvements. Performance Tests Invested approximately $200 to perform a full MMLU benchmark of these custom instructions.MMLU is a comprehensive test for evaluating the performance of language models in a variety of domains including mathematics, calendars...

One Stream: Moving Gemini 2.0 into Cursor 1️⃣ Poke ⚙️Settings → Models If equipped with Deepseek, tap "Reset" to reset the Base URL 2️⃣ Fill in the Google...

NeoCodeium is a plugin that provides AI code completion functionality for Neovim, developed based on Codeium technology. The plugin aims to solve the flickering problem of the official plugin during multi-line virtual text processing and provide a smoother user experience.NeoC...

System: You are Grok 2, a curious AI built by xAI. You are intended to answer almost any quest...

Background: A few days ago I was using Windsurf and was prompted to download an update. After the update, Windsur advanced features such as claude 3.5 sonnet need to be subscribed to continue to use, otherwise you can only use the cascade base. Here following ...

Use Help: Claude's dedicated SVG graphic generator cue words can generate schematics for any subject matter content. Of course you can also use ChatGPT to generate, but you can't preview the SVG directly in the canvas: The output format of the cue word constraints, with a basic remodeling, can be...

With Cline + Gemini 2.0 Cursor, the popular AI code editor, while powerful, has recently begun preventing free use by detecting machine code and other ways to make many developers feel limited. As a competitor to Cursor, w...

Scaling Test-Time Compute has been one of the hottest topics in AI circles since OpenAI released the o1 model. Simply put, instead of piling up computing power in the pre-training or post-training phases, it is better to...

Based on CrewAI's multi-intelligence collaboration and the Cohere Command-R7B Big Model, the system automates the entire process from research to writing, like having a 24-hour newsroom Core Functions: Research and analysis: by the first AI ...

For Windows 11 users, the copilot button will not appear in the country, even if hanging ladders, for many users this is a little less convenient. However, this article can be realized through a convenient way to show the copilot on the taskbar, the use of which can be square...

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...