Using General Large Model to Quickly Build AI Application
This document describes how to quickly build AI dialogue and AI image generation applications using EdgeOne Makers. It covers the complete workflow from API Key application, template selection, one-click deployment to local debugging, and supports two technical approaches: native API calls (highly flexible, suitable for deep customization) and AI SDK encapsulated calls (simple development, suitable for rapid integration).
Prerequisite Preparation
To implement an AI application, first sign up and obtain an API Key. The API Key serves as an identity credential for accessing AI services, similar to an account password, used for authentication and permitted to call the appropriate AI model service. The following is the API Key obtain address for each main AI provider:
Note: Not all API Keys require application, you only need to apply for the API Key of the model used.
Quick Start
Template Introduction
EdgeOne Makers provides multiple AI application templates, supporting two access methods: native API calls and SDK encapsulated calls, which cover dialogue and image generation features. The details are as follows:
All template projects listed in "Quick Start" support one-click deployment. Simply go to the template's detail page, click the blue "Deploy" button on the left to enter the Edgeone Makers console for rapid deployment. Taking the ai-sdk-chatbot-starter template as an example, after deploy is clicked, the following project configuration page will appear.
Environment variable configuration essentially involves setting up the API Key. Different templates will display different configuration lists based on their supported models. Here, you just need to configure the API Key corresponding to the model to be used. However, at least one valid API Key must be entered.
Configure the corresponding environment variable (API Key) on the project deployment page, then click "start deployment" to initiate deployment. Upon completion, visit the preview address.
The process for one-click deployment is the same across different templates, but the environment variable list in the template configuration may vary.
Local Debugging
Continuing with the ai-sdk-chatbot-starter template as an example, after the project is deployed to Edgeone Makers, a new project (the template project) is added under the associated Github account. At this point, if you need to debug the project locally, you can download the code to your local machine from the Github account using the clone command. The following figure shows an example:
After downloading the project code locally, you also need to configure environment variables locally to run the project. EdgeOne Makers provides the scaffolding tool Edgeone CLI. With the CLI, you can generate configurations within the project and perform local debugging. Before using EdgeOne CLI, you need to install and log in for authentication. For specific details, refer to the documentation for EdgeOne CLI.
After logging in, you need to associate with the project deployed in the previous context. In the project's root directory, run the following command to link your local project with the Edgeone Makers project.
edgeone makers link
After running `edgeone makers link`, you will be prompted to enter the EdgeOne Makers project name, which is the name of the template project deployed in the previous context. After the project name is entered, the environment variables from the EdgeOne Makers console for that project will be synchronized to your local machine. This is achieved by creating a `.env` file locally to synchronize the environment variable content.
EdgeOne CLI also supports enabling DEV mode locally. The commands to enable DEV mode are as follows:
edgeone makers dev
After enabling DEV mode, you can access it at localhost:8088. Taking ai-sdk-chatbot-starter as an example, upon successful local startup, the project interface at localhost:8088 is as follows:
Next, perform custom development and debug the effect locally. This can be modified based on personal business requirements.
After modifying the project, if you need to publish your local changes to the EdgeOne Makers online environment, simply use the following command to update the code to Github. The command is as follows:
gitadd.
git commit -m " ...write something..."
git push origin main
EdgeOne Makers automatically monitors updates to the associated Github project and deploys the latest project content to the online environment. Go to the EdgeOne Makers console and enter the project details page. If you see a "Deploying" status prompt, it indicates that EdgeOne Makers has detected the latest commit on Github and has automatically started deploying the latest content. After the "Deploying" status ends, a deployment success prompt appears, as shown in the following figure:
At this point, you can access the public network address of the project to verify whether the local changes are active.
