Features

• Multiple AI model management (OpenAI, Google Gemini)
• Support for OpenAI-compatible APIs
• Support for Google Gemini AI (API and Vertex AI)
• Interactive Q&A with streaming responses
• Continuous chat sessions for multi-turn conversations
• Support for thinking mode (for compatible models)
• Expert mode with domain-specific knowledge
• Configurable API endpoints
• Default model configuration
• Simple and intuitive CLI interface
• Persistent configuration storage

Installation

Install globally via npm:

npm install -g viho

Requirements

• Node.js >= 18.0.0

Quick Start

1. Add your first AI model:

viho model add

2. Set it as default:

viho model default

3. Start asking questions:

viho ask

Commands

Model Management

viho model add

Add a new AI model configuration interactively.

First, you'll select the platform:

• openai - For OpenAI official API
• gemini api - For Google Gemini AI Studio
• gemini vertex - For Google Gemini Vertex AI
• deepseek - For DeepSeek (OpenAI-compatible)
• kimi - For Kimi/Moonshot (OpenAI-compatible)

Then you'll be prompted to enter the required information based on the platform:

For OpenAI-compatible platforms (openai, deepseek, kimi):

• Model name (a custom identifier)
• API key
• Base URL (e.g., https://api.openai.com/v1)
• Model ID (e.g., gpt-4, gpt-4o)
• Thinking mode (enabled/disabled)

For Gemini API:

• Model name (a custom identifier)
• API key (from Google AI Studio)
• Model ID (e.g., gemini-pro, gemini-1.5-flash, gemini-1.5-pro)

For Gemini Vertex:

• Model name (a custom identifier)
• Project ID (your GCP project)
• Location (e.g., us-east1, us-central1)
• Model ID (e.g., gemini-1.5-flash-002, gemini-1.5-pro-002)

viho model add

After adding a model, it will be available for use with viho ask, viho chat, and viho expert commands.

viho model list

List all configured models with detailed information.

viho model list

This command displays:

• Model name with a (default) tag for the default model
• Platform (openai, deepseek, kimi, gemini api, or gemini vertex)
• Platform-specific configuration details

Example output:

Configured models:

  • gpt4 (default)
    Platform: openai
    Model ID: gpt-4o
    Base URL: https://api.openai.com/v1
    Thinking: enabled

  • deepseek
    Platform: deepseek
    Model ID: deepseek-chat
    Base URL: https://api.deepseek.com/v1
    Thinking: enabled

  • gemini
    Platform: gemini api
    Model ID: gemini-1.5-flash
    API Key: ***

  • gemini-pro
    Platform: gemini vertex
    Model ID: gemini-1.5-pro-002
    Project ID: my-project-123
    Location: us-east1

viho model remove

Remove a model configuration:

viho model remove

You'll be presented with a list of your configured models to choose from. If the removed model was set as default, you'll need to set a new default model.

viho model default

Set a default model for chat and ask sessions:

viho model default

You'll be presented with a list of your configured models to choose from. The default model will be used when you run viho ask, viho chat, or viho expert commands without specifying a model name.

Ask

viho ask [modelName]

Ask a question to an AI model.

If no model name is provided, uses the default model:

viho ask

Or specify a model explicitly:

viho ask mymodel

The interface includes:

• Editor-based question input
• Streaming responses
• Visual thinking process (when enabled)
• Colored output for better readability

Chat

viho chat [modelName]

Start a continuous chat session with an AI model for multi-turn conversations.

If no model name is provided, uses the default model:

viho chat

Or specify a model explicitly:

viho chat mymodel

The chat session runs in a loop, allowing you to ask multiple questions continuously without restarting the command. Each question uses the same model configuration but starts a fresh conversation context.

Note: The main difference between viho ask and viho chat:

• viho ask - Single question, exits after receiving the answer
• viho chat - Continuous loop, keeps asking for new questions until manually stopped (Ctrl+C)

Expert Mode

Expert mode allows you to chat with an AI model that has access to domain-specific documentation, making it more knowledgeable about particular libraries or frameworks.

viho expert list

List all available expert resources:

viho expert list

This displays available experts like:

• antd - Ant Design documentation
• daisyui - DaisyUI documentation

viho expert <name> [modelName]

Start an expert chat session with domain-specific knowledge:

viho expert antd

Or specify a model explicitly:

viho expert daisyui mymodel

The expert mode works similarly to viho chat but includes the relevant documentation as context, making the AI more accurate when answering questions about that specific library or framework.

Example:

# Get help with Ant Design
viho expert antd

# Ask: "How do I create a responsive table with sorting?"
# The AI will use Ant Design documentation to provide accurate answers

Configuration

Configuration is stored in ~/viho.json. You can manage all settings through the CLI commands.

Example Configuration Structure

{
  "models": [
    {
      "modelName": "mymodel",
      "apiKey": "your-api-key",
      "baseURL": "https://api.openai.com/v1",
      "modelID": "gpt-4",
      "modelThinking": "auto"
    }
  ],
  "default": "mymodel"
}

Supported Providers

viho supports multiple AI providers and platforms:

OpenAI-Compatible APIs

• OpenAI - Official OpenAI API (GPT-4, GPT-4o, GPT-3.5, etc.)
• DeepSeek - DeepSeek AI with reasoning capabilities
• Kimi - Moonshot AI (Kimi)
• Any other OpenAI-compatible API endpoints

Google Gemini

• Gemini API (via Google AI Studio)

  • Ideal for personal development and prototyping
  • Get API key from Google AI Studio

• Gemini Vertex AI (via Google Cloud)

  • Enterprise-grade with advanced features
  • Requires Google Cloud project with Vertex AI enabled
  • Supports context caching for cost optimization

Examples

Adding an OpenAI Model

viho model add
# Select platform: openai
# Enter model name: gpt4
# Enter API key: sk-...
# Enter base URL: https://api.openai.com/v1
# Enter model ID: gpt-4o
# Thinking mode: disabled

Adding a DeepSeek Model

viho model add
# Select platform: deepseek
# Enter model name: deepseek
# Enter API key: sk-...
# Enter base URL: https://api.deepseek.com/v1
# Enter model ID: deepseek-chat
# Thinking mode: enabled

Adding a Kimi Model

viho model add
# Select platform: kimi
# Enter model name: kimi
# Enter API key: sk-...
# Enter base URL: https://api.moonshot.cn/v1
# Enter model ID: moonshot-v1-8k
# Thinking mode: disabled

Adding a Gemini API Model

viho model add
# Select platform: gemini api
# Enter model name: gemini
# Enter API key: your-google-ai-api-key
# Enter model ID: gemini-1.5-flash

Adding a Gemini Vertex AI Model

viho model add
# Select platform: gemini vertex
# Enter model name: gemini-pro
# Enter projectId: my-gcp-project
# Enter location: us-east1
# Enter model ID: gemini-1.5-pro-002

Setting Up for First Use

# Add a model
viho model add

# Set it as default
viho model default

# Start asking questions
viho ask

Dependencies

• qiao-cli - CLI utilities
• qiao-config - Configuration management
• qiao-file - File utilities
• viho-llm - Multi-provider LLM integration (OpenAI, Gemini)

License

MIT

Author

uikoo9 [email protected]

Issues

Report issues at: https://github.com/uikoo9/viho/issues

Homepage

https://github.com/uikoo9/viho