1. AI system

How to build and deploy artificial intelligence source code, AI creation system, and ChatGPT system? Let me write a detailed graphic tutorial here! SparkAi uses Nestjs and Vue3 framework technology to continuously integrate AI capabilities into the AIGC system!

1.1 Core functions of the program

The program already supports ChatGPT3.5/GPT-4 questioning, AI painting, Midjourney painting (fully customizable parameters), Midjourney drawings from pictures, Dall-E2 painting, mind map generation, knowledge base (customizable training), AI painting square, invitation + agent distribution model, daily user check-in function, conversation record saving, WeChat official account + email + mobile phone number registration and login, and other free version feature updates in the future.

1.2 Latest version update log

Version [V2.6.0] update features:

Optimize the key pool quota exhaustion locking logic (updated on August 26)!
Optimize MJ painting links, optimize CSS, and modify some page styles (updated on August 26)!
Add the function of signing in on the mobile phone to receive free times, and optimize the logic of the total number of paintings in the background!
Added MJ official picture regeneration command function
Synchronize the official Vary command to enhance the contrast of a single image Vary(Strong) | Vary(Subtle)
Synchronize the official Zoom command to infinitely zoom a single picture Zoom out 2x | Zoom out 1.5x

2. System Demonstration

https://ai.idcyli.com

3. Function module

3.1 Questions about GPT model

GPT online questioning has been supported

3.2 Application workbench

3.2.1 prompt knowledge base

3.2.2 Support user-defined knowledge base

3.3 Midjourney Professional Painting

Vincent picture:

Draw pictures from pictures:

3.4 Dall-E2 Painting

3.5 Mind map generation

3.6 AI Painting Square

4. Source code system

4.1 Front-end demo site

System demonstration

4.2 SparkAi source code download

Source code

4.3 SparkAi system documentation

SparkAi system documentation · Yuque

4.4 Detailed construction and deployment tutorial

SparkAi system deployment and construction documentation

5. Detailed construction tutorial

The following tutorial uses Linux Pagoda to build and deploy

5.1 Basic env environment configuration

In the code, we provide the basic environment variable file configuration file env.example. Before using it, remove the suffix and change it to the .env file. We only need to configure the following things in the env environment configuration file.

Authorization code, IP configuration
Mail service configuration
These three items of mysql database are basic configurations. Mysql and authorization are necessary. Only when mysql and authorization are configured can the project be started successfully. The mail service can be added later.

5.2 env.env file configuration

# 服务器ip （必填项）
SPARK_AI_HOST=
# 授权码 （授权码留空，可启动运行体验系统半小时）
SPARK_AI_KEY=

# mysql
DB_HOST=localhost
DB_PORT=3306
DB_USER=数据库用户名
DB_PASS=数据库密码·
DB_DATABASE=数据库名
DB_LOG=false
DB_SYNC=true

#  mailer 邮件服务
MAILER_HOST=smtp.163.com/smtp.qq.com （选择自己的发信服务器地址，网易邮箱或者qq邮箱）
MAILER_PORT=465
MAILER_USER=发信邮箱
MAILER_PASS=邮箱发信密钥
MAILER_FROM=发信邮箱

# Redis
REDIS_PORT=6379
REDIS_HOST=127.0.0.1
REDIS_PASSWORD=

# mj并发数
CONCURRENCY=3

# jwt token
JWT_SECRET=chat-spark
# jwt token 过期时间
JWT_EXPIRESIN=7d
# 接口文档前缀
SWAGGERPREFIX=/docs
# 自定义端口
PORT=9520