AskSage

AskSage focuses on educational and learning scenarios, providing professional support for academic research and teaching.

Supported Models

• asksage-v1 - Main AskSage model
• asksage-v1-tutor - Specialized tutoring model
• asksage-v1-research - Academic research model
• asksage-v1-math - Math-specific model

Configuration

Basic Configuration

Configure in config.yaml or ~/.bytebuddy/config.yaml:

models:
  - name: "asksage-general"
    provider: "asksage"
    model: "asksage-v1"
    apiKey: "${ASKSAGE_API_KEY}"
    roles: ["chat"]
    defaultCompletionOptions:
      temperature: 0.7
      maxTokens: 4096

Tutoring Configuration

models:
  - name: "asksage-tutor"
    provider: "asksage"
    model: "asksage-v1-tutor"
    apiKey: "${ASKSAGE_API_KEY}"
    roles: ["chat"]
    defaultCompletionOptions:
      temperature: 0.5
      maxTokens: 2048

Multi-Model Configuration

models:
  - name: "asksage-general"
    provider: "asksage"
    model: "asksage-v1"
    apiKey: "${ASKSAGE_API_KEY}"
    roles: ["chat"]
    defaultCompletionOptions:
      temperature: 0.7
      maxTokens: 4096

  - name: "asksage-math"
    provider: "asksage"
    model: "asksage-v1-math"
    apiKey: "${ASKSAGE_API_KEY}"
    roles: ["chat"]
    defaultCompletionOptions:
      temperature: 0.3
      maxTokens: 2048

Configuration Fields

Required Fields

• name: Unique identifier for the model configuration
• provider: Set to "asksage"
• model: Model name
• apiKey: AskSage API key

Optional Fields

• roles: Model roles [chat, edit, apply]
• defaultCompletionOptions:
  • temperature: Control randomness (0-1)
  • maxTokens: Maximum tokens
  • topP: Nucleus sampling parameter
  • frequencyPenalty: Frequency penalty
  • presencePenalty: Presence penalty

Environment Variables

# ~/.bashrc or ~/.zshrc
export ASKSAGE_API_KEY="your-asksage-api-key"

Getting API Key

1. Visit AskSage Website
2. Register and log in to account
3. Navigate to API keys page
4. Generate new API key
5. Save the key to environment variable

Use Case Configurations

Educational Tutoring

models:
  - name: "tutor"
    provider: "asksage"
    model: "asksage-v1-tutor"
    apiKey: "${ASKSAGE_API_KEY}"
    roles: ["chat"]
    defaultCompletionOptions:
      temperature: 0.5
      maxTokens: 2048

Academic Research

models:
  - name: "research"
    provider: "asksage"
    model: "asksage-v1-research"
    apiKey: "${ASKSAGE_API_KEY}"
    roles: ["chat"]
    defaultCompletionOptions:
      temperature: 0.3
      maxTokens: 4096

Math Tutoring

models:
  - name: "math-tutor"
    provider: "asksage"
    model: "asksage-v1-math"
    apiKey: "${ASKSAGE_API_KEY}"
    roles: ["chat"]
    defaultCompletionOptions:
      temperature: 0.2
      maxTokens: 2048

Troubleshooting

Common Errors

1. 401 Unauthorized: Check if API key is correct
2. 429 Too Many Requests: Rate limit reached, wait and retry
3. Model Not Available: Confirm subscription plan supports the model

Debugging Steps

1. Verify API key format and validity
2. Check rate limits and quotas
3. Confirm model name spelling
4. View error logs for details

Best Practices

1. Security

• Use environment variables to store API keys
• Rotate keys regularly
• Monitor unusual usage

2. Performance Optimization

• Choose appropriate model for the task
• Use lower temperature for educational scenarios
• Set reasonable maxTokens limits

3. Cost Control

• Monitor API usage
• Select models based on task complexity
• Set quota alerts