DeepSeek

DeepSeek is an advanced AI model provider, offering high-performance code generation and natural language processing capabilities.

Supported Models

• deepseek-chat - General conversational model
• deepseek-coder - Code-specialized model
• deepseek-coder-instruct - Instruction-following code model

Configuration

Basic Configuration

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

models:
  - name: "deepseek-coder"
    provider: "deepseek"
    model: "deepseek-coder-instruct"
    apiKey: "${DEEPSEEK_API_KEY}"
    roles: ["chat", "edit"]
    defaultCompletionOptions:
      temperature: 0.2
      maxTokens: 4096

Multi-Model Configuration

models:
  - name: "deepseek-chat"
    provider: "deepseek"
    model: "deepseek-chat"
    apiKey: "${DEEPSEEK_API_KEY}"
    roles: ["chat"]
    defaultCompletionOptions:
      temperature: 0.7
      maxTokens: 2048

  - name: "deepseek-coder"
    provider: "deepseek"
    model: "deepseek-coder-instruct"
    apiKey: "${DEEPSEEK_API_KEY}"
    roles: ["edit", "apply"]
    defaultCompletionOptions:
      temperature: 0.1
      maxTokens: 4096

Configuration Fields

Required Fields

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

Optional Fields

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

Environment Variables

# ~/.bashrc or ~/.zshrc
export DEEPSEEK_API_KEY="your-deepseek-api-key"

Getting API Key

1. Visit DeepSeek 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

Code Generation

models:
  - name: "code-gen"
    provider: "deepseek"
    model: "deepseek-coder-instruct"
    apiKey: "${DEEPSEEK_API_KEY}"
    roles: ["chat", "edit"]
    defaultCompletionOptions:
      temperature: 0.2
      maxTokens: 4096

General Chat

models:
  - name: "general-chat"
    provider: "deepseek"
    model: "deepseek-chat"
    apiKey: "${DEEPSEEK_API_KEY}"
    roles: ["chat"]
    defaultCompletionOptions:
      temperature: 0.7
      maxTokens: 2048

Troubleshooting

Common Errors

1. 401 Unauthorized: Check if API key is correct
2. 429 Too Many Requests: Rate limit reached
3. Model Not Found: Verify model name

Debugging Steps

1. Verify API key format and validity
2. Check rate limits
3. Confirm model name is correct
4. View error logs

Best Practices

1. Security

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

2. Performance Optimization

• Use low temperature for code tasks (0.1-0.3)
• Set appropriate maxTokens limits
• Choose the right model for the task

3. Cost Control

• Monitor API usage
• Use appropriate models for different tasks
• Set reasonable token limits