Recently, some netizens asked how Pagoda builds and deploys AI to create ChatGPT. Let me write a detailed graphic tutorial here.
Use Nestjs and Vue3 framework technology to continuously integrate AI capabilities into the AIGC system!
- Add the sign-in function on the mobile terminal, optimize the logic of the total number of paintings in the background!
- Added MJ official picture regeneration command function
- Synchronize the official Vary command Single image contrast enhancement Vary(Strong) | Vary(Subtle)
- Synchronize the official Zoom command Single picture unlimited zoom Zoom out 2x | Zoom out 1.5x
- Added GPT network questioning function, mobile phone number registration and login, sign-in function, management background function update, etc.
- Optimize MJ's first painting without superior ID display problem, optimize built-in MJ agent, and other optimizations
1. System functions
Support GPT3 model, GPT4 model, GPT networking function
Midjourney professional painting (full custom parameter adjustment), Midjourney generates pictures with pictures, Dall-E2 painting
Mind mind map generation
application workbench (Prompt knowledge base), Ai painting square
System Client Page
1.1 GPT model question
Support GPT networking questions
1.2 Application Workbench
1.3 Midjourney professional painting
1.4 mind map
2. Source code system
2.1 Front Demo Site
2.2 SparkAi source code download
2.3 SparkAi system documentation
3. Detailed construction tutorial
The following tutorial uses Linux Pagoda to build
3.1 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 .env file. We only need to configure the following things in the env environment configuration file.
-
Authorization code, ip configuration
-
Mail service configuration
-
The three items of the mysql database are the basic configuration, mysql and authorization are necessary, the project can be started successfully only when the mysql and authorization are configured, and the mail service can be added later.
4. Environmental installation
-
Nginx >= 1.19.8
-
MySQL >= 5.7 or MySQL 8.0
-
PHP-7.4
-
PM2 Manager 5.5
-
Redis 7.0.11
- Node version: >=16.19.1
Detailed tutorial:
4.1 Node version
Use PM2 to switch Node version (required)
Switch Node version to: v16.19.1
4.2 Install pnpm module
4.3 Install Redis
5. Deploy and run
5.1 Create a new site
Pagoda - Website - Add Site
5.2 Configuring SSL
5.2.1 Use your own ssl certificate
5.2.2 Let's Encrypt certificate application
If you don't have a certificate, use Pagoda's free certificate to apply for Let's Encrypt
5.3 Upload source code
delete original file
Upload and unzip the program to the root directory of the website
5.3.1 Configure the .env file
Double-click the .env.example file to edit directly in the pagoda, or edit it in the terminal vim
After the configuration is complete, delete the file suffix and the file name is .env
5.4 Start the project
5.4.1 Installation dependencies
Enter the ssh terminal in the root directory of the website
Use pnpm i to install dependencies
5.4.2 Start the project
Start the project with pnpm start
5.4.3 View startup log
Enter pm2 log to view the detailed log, and see the picture below to indicate success!
5.4.4 Add port
Add port 9520. Pagoda security needs to open this port, otherwise it cannot be accessed
6. Test and use the system
Deployment complete! Now you can access the SparkAi system through the domain name!
6.1 Management background
The default foreground address is the domain name address, and the default background address is: domain name address/sparkai/admin
The default super administrator account is super spark123
At this point we are done installing!