LLM

Files (3)

• LICENSE.txt
• SKILL.md
• chat.ts · scripts/

SKILL.md (first lines)

---
name: LLM
description: Implement large language model (LLM) chat completions using the z-ai-web-dev-sdk. Use this skill when the user needs to build conversational AI applications, chatbots, AI assistants, or any text generation features. Supports multi-turn conversations, system prompts, and context management.
license: MIT
---

# LLM (Large Language Model) Skill

This skill guides the implementation of chat completions functionality using the z-ai-web-dev-sdk package, enabling powerful conversational AI and text generation capabilities.

## Skills Path

**Skill Location**: `{project_path}/skills/llm`

this skill is located at above path in your project.

**Reference Scripts**: Example test scripts are available in the `{Skill Location}/scripts/` directory for quick testing and reference. See `{Skill Location}/scripts/chat.ts` for a working example.

## Overview

The LLM skill allows you to build applications that leverage large language models for natural language understanding and generation, including chatbots, AI assistants, content generation, and more.

**IMPORTANT**: z-ai-web-dev-sdk MUST be used in backend code only. Never use it in client-side code.

## Prerequisites

The z-ai-web-dev-sdk package is already installed. Import it as shown in the examples below.

## CLI Usage (For Simple Tasks)

For simple, one-off chat completions, you can use the z-ai CLI instead of writing code. This is ideal for quick tests, simple queries, or automation scripts.

### Basic Chat

```bash
# Simple question
z-ai chat --prompt "What is the capital of France?"

# Save response to file
z-ai chat -p "Explain quantum computing" -o response.json

# Stream the response
z-ai chat -p "Write a short poem" --stream
```

### With System Prompt

```bash
# Custom system prompt for specific behavior
z-ai chat \
  --prompt "Review this code: function add(a,b) { return a+b; }" \
  --system "You are an expert code reviewer" \
  -o review.json
```

### With Thinking (Chain of Thought)

```bash
# Enable thinking for complex reasoning
z-ai chat \
  --prompt "Solve this math problem: If a train travels 120km in 2 hours, what's its speed?" \
  --thinking \
  -o solution.json
```

### CLI Parameters

- `--prompt, -p <text>`: **Required** - User message content
- `--system, -s <text>`: Optional - System prompt for custom behavior
- `--thinking, -t`: Optional - Enable chain-of-thought reasoning (default: disabled)
- `--output, -o <path>`: Optional - Output file path (JSON format)
- `--stream`: Optional - Stream the response in real-time

### When to Use CLI vs SDK

**Use CLI for:**
- Quick one-off questions
- Simple automation scripts
- Testing prompts
- Single-turn conversations

**Use SDK for:**
- Multi-turn conversations with context
- Custom conversation management
- Integration with web applications
- Complex chat workflows
- Production applications

## Basic Chat Completions

### Simple Question and Answer

```javascript
import ZAI from 'z-ai-web-dev-sdk';

async function askQuestion(question) {
  const zai = await ZAI.create();

  const completion = await zai.chat.completions.create({
    messages: [
      {
        role: 'assistant',
        content: 'You are a helpful assistant.'
      },
      {
        role: 'user',
        content: question
      }
    ],
    thinking: { type: 'disabled' }
  });

  const response = completion.choices[0]?.message?.content;
  return response;
}

// Usage
const answer = await askQuestion('What is the capital of France?');
console.log('Answer:', answer);
```

From lucioupro2025/aprendiendo-abb-zai, MIT.

More from lucioupro2025/aprendiendo-abb-zai