🏆Project Introduction

SparkAi system is a one-stop AI system based on OpenAi/ChatGPT and large AI model capabilities; it supports "🤖AI Chat", "🎨Professional AI Painting", "🧠AI Agents", "🎬AI Video Generation", etc., and supports independent private deployment!

It provides comprehensive solutions for individual users (ToC), developers (ToD), and enterprises (ToB).

As of June 2025, the system has been continuously developed and iterated for nearly two years...

🔒System Copyright

The SparkAi system has obtained software copyright and is protected by the National Copyright Administration. The source code includes a private protocol, and retransmission, secondary development, and malicious dissemination are not supported without authorization. We reserve all rights to pursue infringement. Users of pirated or cracked programs are fully responsible for any security data risks. For those who use pirated versions and distribute them for profit, we will reserve all legal rights to pursue them!

🎉Official Website Users

The SparkAi system has also launched an official website to provide users with richer and more convenient services.

• Rich model support: The official website supports 80+ mainstream AI models from home and abroad, covering multiple fields such as text, images, audio, and video.
• High cost-performance: We offer highly competitive prices, allowing users to enjoy high-quality AI services at a lower cost.
• Convenient user experience: A user-friendly interface design allows you to get started easily and quickly use various AI functions.
• Continuous updates: We are constantly introducing new models and features to ensure that users can always use the most advanced AI technology.
• Visit our official website to experience more exciting features: SparkAi Official Site

🚀Free Deployment Version for Public Welfare

SparkAi Public Welfare Free Edition (SparkAI-ChatGPT-AiWeb): Can be used for personal study and internal use by enterprises. (Not for commercial operation!)

• Supports user registration and login: WeChat QR code registration and login, email registration and login, mobile phone number registration and login.
• Card secret system: Supports batch production of card secrets for users to redeem, and the user end can redeem card secrets or purchase them from third-party card networks, supporting a complete card secret redemption code system, and supporting functions such as custom points.
• AI large model support: Supports docking with OpenAI GPT3.5/GPT4.0 models, and docking with some domestic AI models (Baidu Wenxin Yiyan, Microsoft Azure, Alibaba Cloud Tongyi Qianwen model, Tsinghua ChatGLM, iFlytek Spark large model).
• Supports DallE painting: DallE2, DallE3 painting.
• Supports AI painting: MJ text-to-image, image-to-image, local editing and redrawing.
• Supports AI agents: Prompt custom preset applications, supports custom AI agent applications.
• Other core functions.....

🛍️Authorized Commercial Deployment Version

The commercial version is suitable for professional and team users who need more advanced features, more comprehensive AI functions, more powerful performance, and more comprehensive support. It provides a comprehensive AI service management solution that can meet the complex needs of commercialization.

• The commercial version is a closed-source authorization model, and the source code is not open. If you have open-source code requirements, please contact the author on WeChat.
• The commercial version contains the user end | management end | back-end three-end encrypted source code (closed source code) and an authorization code to start the service.
• The commercial version supports modifying some content and replacing static resource files.

🌟System Core Functions (Authorized Commercial Deployment Version)

System Features

• 🚀 Server-side rendering technology: Using Node.js + NestJs server-side rendering technology, supports high concurrency (tens of thousands or even tens of millions of users requesting at the same time); provides higher availability and stability.
• 📲 System platform support: Supports PC + H5 + WeChat official account integration (supports H5 packaging for other platforms).
• 📡 Multi-terminal support: Adaptive layout, adapting to PC, mobile, tablet and other devices. Supports Web / PWA / App / Mini Program (subsequent development), UI mobile adaptation, supports light and dark theme switching, supports Windows / MacOS / Linux / Android / iOS App.
• 🖥️ Deployment and operation: Supports regular deployment with Pagoda and one-click deployment with Docker. All docking configurations can be completed in the background interface.
• 🤖 Multi-mode scenarios: Public welfare learning / commercial operation / student tools / enterprise internal / internal institutions and other multi-mode scenarios; supports flexible billing and various plan modes, and other core functions.
• 🎉 One-stop AIGC system: The system integrates AI large model Q&A, AI painting, professional-grade AI video generation, document upload and analysis, multi-modal model image understanding, AI agents, TTS & voice recognition dialogue, text-to-image, image-to-image, reference image generation, image mixing (mixing images to generate images), AI face swapping, local editing and redrawing, and other powerful functions.
• 🔥 Full model support: Supports OpenAI official API + all chat format transfer system custom model docking (that is, supports all OpenAI models, third-party large models, and all domestic models); supports OpenAI / DeepSeek large models / gpt-4.5 large models / Azure OpenAI / Anthropic Claude / Google Gemini / Midjourney / Doubao / iFlytek Spark / Baichuan AI / Moonshot / ChatGLM / Tongyi Qianwen / Lark large models / Tencent Hunyuan / 360 Zhi Nao and other models, adapts to LocalAI / Ollama and other models (LLaMa / RWKV / SDXL), etc.
• 💭 Supports streaming output of AI large models, supports displaying the deep thinking process of inference and thinking large models, and supports deep search display.
• 🛍️ Payment system: Supports official WeChat payment, EasyPay, CodePay, HupiJiao Pay and other payment methods, supports synchronous checking of order status, and supports order search and management.
• 🛒 Supports WeChat official native payment: When official WeChat payment is enabled, we will call native payment on the PC (directly generate a payment QR code), and in the mobile WeChat environment, we will call Jsapi payment (directly call the mobile WeChat wallet for payment)!
• 🆕 Latest model support: Supports DeepSeek large model deepseek-r1-671B full-blooded version, the latest gpt-4.5 large model released by openai, claude-3-7 large model docking, and the latest 4o advanced drawing function model (supports Chinese character drawing large models).
• ✏️ Supports GPT-4o large model editing and drawing; supports uploading multiple pictures for editing and drawing.
• 📍Deeply adapts to the image format in the API return, and automatically supports the image preview function.
• 🤔 01/03 inference and thinking large model support: Supports the latest OpenAI o1, o3 inference large models (o3-mini, o3-mini-all, o3-mini-high, o3-mini-high-all, o1-mini, o1-mini-all, o1-preview, o1-preview-all), etc.
• 🎈 Fully custom model docking: All models follow OpenAI's input format. When OpenAI releases a new language model, it can be added in the background as soon as possible, without the need for system development and docking every time to use it! Similarly, it supports docking with transfer systems of other third-party models. That is, the latest released models of OpenAI's full models, third-party large models, and domestic large models can be used quickly. Dialogue models can be custom classified, custom named, custom sorted, and some functions can be customized.
• 🏄‍♂️Open multi-platform API knowledge base + workflow application docking (for example, coze workflow agent (needs to be converted to chat format by yourself), FastGPT knowledge base application (can be directly docked with the official API), FastGPT workflow application (can be directly docked with the official API)): The request dialogue interface is compatible with the chat interface, and supports docking with knowledge bases or workflow applications of the OpenAPI dialogue interface. Other platform APIs can be converted to the chat standard format through one api and other transfer systems, and then docked with the API. They can be displayed as models or bound to agents for use, so that knowledge bases or workflow applications of other platform APIs can be docked with this system!
• 🧠 AI agent system: GPTs application + Prompt custom preset application; supports access to all GPTs applications in the official OpenAI store. GPTS-supports custom addition of GPTS in the background, and can also be searched throughout the site = official search.
• 🎬 Independent AI video generation function: Supports text-to-video / image-to-video (PIka AI video).
• 📽️ SoraAI video generation will be supported soon: (waiting for the official API to be opened).
• ✨ Self-developed channel load balancing and distribution algorithm: Supports multi-channel high-concurrency call management, supports multi-API Key polling! (priority/weight/status management).
• 💻Complete management background: Complete user background management and data statistics.
• 🤯 User data synchronization: Dialogue session isolation, cloud storage, supports multi-device data sharing.
• 🏳️‍🌈 Multi-modal model support: Supports analysis of files, videos, images, etc., supports real-time networking, and supports custom dialogue models to enable multi-modal support.
• 🛜 Supports independent networking mode: The model can be extended to search and summarize real-time content on the current network.
• 🗣️ TTS voice recognition: Supports OpenAI / Azure and other voice recognition & TTS models, supports Whisper & TTS format transfer; supports TTS dialogue input and reply mode.
• 🎨 Midjourney painting full function: Supports many functions such as Imagine / Upscale / Vary / Zoom Out, supports Seed acquisition. Supports transfer API / supports local redrawing (Vary Region), etc.
• 📚 Professional painting system: Text-to-image, image-to-image, matting and mixing, character-consistent reference image, style-consistent reference image generation, etc., AI face swapping, mixing images to generate images.
• 🖼️ AI gallery plaza: The system recommends an open system; supports classified display of painting works.
• 📝 Creator center: Display of creator information of painting works (subsequent development and improvement of various related functions).
• 🔍 Carousel display: Supports advertising space, activities, and tutorial document display functions.
• 🪄 DallE2, DallE3 painting support: Supports all parameters and has a separate module.
• Ⓜ️ Powerful Markdown syntax support: (supports code highlighting / LaTeX formulas / Mermaid mind maps / chart drawing), supports integrated dialogue drawing models (DALL-E / Stable Diffusion / Midjourney, etc.).
• 🔢 Math formula supports KaTeX's inline math mode and KaTeX's independent math mode.
• 🌏 Out-of-the-box document parsing service: Supports parsing of file types such as Pdf / Docx / Xlsx / audio / images.
• 🗂️ Storage system: Supports local, Alibaba Cloud OSS, Tencent Cloud COS, Chevereto image hosting and other types.
• 🧑‍🤝‍🧑 Membership system: Provides three currency types: ordinary model points, advanced ordinary model points, and painting points. It supports custom deduction modes and quotas for various commodities. It supports custom model deduction fee types and multiple billing methods: time-limited, unlimited, and custom combination package settings (free / points (times) deduction billing).
• 🛍️ Mall system: Custom commodity packages, can be customized to generate permanent packages, limited-time packages.
• 🔶 Sign-in system: Supports configuring daily sign-in to give different amounts of rewards.
• 👋 Visitor system: Supports using some content without logging in, and can experience the functions of the site in guest mode.
• 📣 Invitation system: Promotion invitation rewards, supports setting custom point rewards for inviting and invited users.
• ⏏️ Distribution system: Supports A + B distribution mode, the background can customize the distribution commission, and can be set separately for individual users. Supports setting withdrawal threshold options, and supports users to choose multiple withdrawal methods (Alipay, WeChat, bank card, etc.).
• 💳 Card secret system: Supports batch production of card secrets for users to redeem, and the user end can redeem card secrets or purchase them from third-party card networks, supporting a complete card secret redemption code system, and supporting custom points, batch generation, and card secret redemption code management, and supports viewing the receiving user / creation time / receiving time and other information of the card secret redemption code; deleting the card secret redemption code and other functions.
• 🚣 Login system: Supports different login and registration methods such as email | mobile phone SMS | WeChat QR code for selection.
• 🧩 Plugin system: Various plugins are supported internally and more plugins will be continuously developed.
• ✔️ Professional site management system: Supports custom configuration of website LOGO / site name / footer / Baidu statistics / AI name / copyright information / contact information / site announcement / welcome message and other content; supports setting user initial points, separate user group configuration, etc.
• 📊 Data statistics: Rich and beautiful dashboard statistics, supports daily new user number statistics / total and daily dialogue number / total and daily new painting number / total and daily order number statistics / and other information statistics chart trend display.
• 🚥 Risk control system: Multiple restrictions on sensitive words, supports custom sensitive words / Baidu content review and other security checks, which can be enabled together. Supports query and statistics of sensitive word check records!
• 🧩 Dynamic menu system: Custom sections are embedded in the website page, and section icons can be set to make the site richer and more diverse. Supports embedded web pages, external link jumps, internal path jumps, custom switch menus, adding menus, custom ICONs, custom menu types, can use third-party sites for embedding, and supports separate settings for mobile and PC.
• Permission system: The management end supports super administrator and ordinary demo accounts for the distribution system, and ordinary accounts only have read-only permissions.
• Automatic reply mechanism: The management end supports configuring keyword replies, and can customize keywords and reply content, which can be linked with WeChat official accounts.
• 🏅 Continuous updates: More AI capabilities are continuously being developed and updated...

✨System Technical Architecture

System Architecture

• Front-end: Vite + vue3 + ts + NaiveUI + Tailwindcss
• Management end: Vite4 + Vue3 + Element-Plus
• Back-end: Node.js + NestJs
• Data support: Mysql5.7(+) + Redis
• Operating environment: Linux, Windows, MacOs (Linux is recommended)
• Data storage: local storage | object storage Alibaba Cloud OSS | object storage Tencent Cloud COS | chevereto image hosting

🛠️Operating Environment

Operating Environment

• Linux (recommended)
• Windows
• MacOS Server
• Docker
• Kubernetes
• Supports ARM64 & X86 (32/64) architecture

🎯Server Configuration Requirements

Minimum server configuration requirements are 1C1G (actual memory usage < 500M), and 2C4G or above is recommended for high concurrency.