ai-model-nodejs

Generate text and images from Node.js backends via Tencent CloudBase.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/mrpersimmon/xiao-han-studio --skill ai-model-nodejs-mrpersimmon
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ai-model-nodejs
Source: https://github.com/mrpersimmon/xiao-han-studio/tree/main/.agents/skills/cloudbase/references/ai-model-nodejs
Command: npx skills add https://github.com/mrpersimmon/xiao-han-studio --skill ai-model-nodejs-mrpersimmon

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

It enables reliable server-side AI calls from Node.js backends (including Cloud Functions and CloudRun) with proper model enablement and Token Credits readiness checks.

Core Features & Use Cases

  • Managed multi-vendor text generation: Calls LLMs via @cloudbase/node-sdk using the managed cloudbase model group, with model IDs placed in the model field of generateText/streamText.
  • Server-side orchestration and streaming: Supports non-streaming generateText and streaming streamText for long responses and agent workflows.
  • Hunyuan image generation from Node.js: Uses ai.createImageModel("hunyuan-image") with generateImage, including guidance for cloud-function timeouts.
  • Guardrails for production correctness: Provides a mandatory two-step preflight (Token Credits eligibility + model group readiness via DescribeAIModels and DescribeManagedAIModelList) before any SDK code.

Quick Start

Use the backend to generate text by calling ai.createModel("cloudbase") and then using generateText with a verified model id like deepseek-v4-flash after the two-step preflight passes.

Frequently Asked Questions about ai-model-nodejs

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate text from a Node.js cloud function using Tencent CloudBase?

To generate text from a Node.js cloud function, use the @cloudbase/node-sdk to call ai.createModel("cloudbase") and execute generateText with a verified model id after passing the mandatory preflight checks for Token Credits and model group readiness.

Why do my server-side AI calls fail despite having Token Credits?

Server-side AI calls fail if you skip the mandatory two-step preflight. You must verify Token Credits eligibility and model group readiness via DescribeAIModels and DescribeManagedAIModelList before executing any generateText, streamText, or generateImage operations in your Node.js backend.

Can I use streaming text generation for long responses in Express or NestJS serverless APIs?

Yes, you can use streaming text generation in Express or NestJS serverless APIs by implementing the streamText method from @cloudbase/node-sdk, which supports long responses and agent orchestration workflows while keeping secrets server-side.

What's the best way to generate images with Hunyuan from a Node.js backend?

The best way to generate images is using ai.createImageModel("hunyuan-image") followed by generateImage. You must complete the Token Credits and model group readiness preflight, and configure appropriate cloud-function timeouts to handle image processing.

Does this approach support running scheduled jobs and agent orchestration with server-side secrets?

Yes, this approach supports scheduled jobs and agent orchestration by executing server-side AI calls through Tencent CloudBase. It ensures secrets remain server-side by using the @cloudbase/node-sdk within Cloud Functions and CloudRun environments.