OpenAI

OpenAI is one of the main model providers supported by ByteBuddy, offering powerful GPT series models.

Supported Models

GPT-4 Series

• gpt-4o - Latest GPT-4 model with multimodal support
• gpt-4o-mini - Lightweight version with lower cost
• gpt-4-turbo - Faster GPT-4 version, 128K context
• gpt-4-turbo-preview - GPT-4 Turbo preview

GPT-3.5 Series

• gpt-3.5-turbo - High-performance conversation model
• gpt-3.5-turbo-16k - 16K context version

Embedding Models

• text-embedding-ada-002 - Text embedding model
• text-embedding-3-small - Small embedding model
• text-embedding-3-large - Large embedding model

Configuration Methods

Basic Configuration

models:
  - name: "gpt-4o"
    provider: "openai"
    model: "gpt-4o"
    apiKey: "${OPENAI_API_KEY}"
    roles: ["chat", "edit"]
    defaultCompletionOptions:
      temperature: 0.7
      maxTokens: 4000

Multi-role Configuration

models:
  - name: "chat-model"
    provider: "openai"
    model: "gpt-4o"
    apiKey: "${OPENAI_API_KEY}"
    roles: ["chat"]
    defaultCompletionOptions:
      temperature: 0.7
      maxTokens: 4000

  - name: "edit-model"
    provider: "openai"
    model: "gpt-4o"
    apiKey: "${OPENAI_API_KEY}"
    roles: ["edit"]
    defaultCompletionOptions:
      temperature: 0.3
      maxTokens: 2000

  - name: "autocomplete-model"
    provider: "openai"
    model: "gpt-3.5-turbo"
    apiKey: "${OPENAI_API_KEY}"
    roles: ["autocomplete"]
    defaultCompletionOptions:
      temperature: 0.1
      maxTokens: 500

Embedding Model Configuration

models:
  - name: "embedding-model"
    provider: "openai"
    model: "text-embedding-3-small"
    apiKey: "${OPENAI_API_KEY}"
    roles: ["embed"]

Tool Use Model Configuration

models:
  - name: "tool-model"
    provider: "openai"
    model: "gpt-4o"
    apiKey: "${OPENAI_API_KEY}"
    roles: ["chat", "edit"]
    capabilities: ["tool_use"]
    defaultCompletionOptions:
      temperature: 0.7
      maxTokens: 4000

Environment Variables

# Required: API key
export OPENAI_API_KEY="sk-..."

# Optional: Organization ID
export OPENAI_ORG_ID="org-..."

# Optional: Custom API endpoint
export OPENAI_API_BASE="https://api.openai.com/v1"

Request Options

models:
  - name: "gpt-4o"
    provider: "openai"
    model: "gpt-4o"
    apiKey: "${OPENAI_API_KEY}"
    roles: ["chat"]
    requestOptions:
      timeout: 60000
      verifySsl: true
      headers:
        "User-Agent": "ByteBuddy/1.0"

Advanced Configuration Options

Complete Configuration Example

models:
  - name: "gpt-4o-advanced"
    provider: "openai"
    model: "gpt-4o"
    apiKey: "${OPENAI_API_KEY}"
    roles: ["chat", "edit", "apply"]
    capabilities: ["tool_use", "image_input"]
    defaultCompletionOptions:
      temperature: 0.7
      maxTokens: 4000
      topP: 0.9
      frequencyPenalty: 0.1
      presencePenalty: 0.1
      stream: true
    requestOptions:
      timeout: 60000
      verifySsl: true
      headers:
        "User-Agent": "ByteBuddy/1.0"

Use Case Configurations

Code Development

models:
  - name: "code-assistant"
    provider: "openai"
    model: "gpt-4o"
    apiKey: "${OPENAI_API_KEY}"
    roles: ["chat", "edit"]
    defaultCompletionOptions:
      temperature: 0.1
      maxTokens: 2000
      topP: 0.8

Conversation Interaction

models:
  - name: "conversation"
    provider: "openai"
    model: "gpt-4o"
    apiKey: "${OPENAI_API_KEY}"
    roles: ["chat"]
    defaultCompletionOptions:
      temperature: 0.7
      maxTokens: 1000
      stream: true

Fast Autocomplete

models:
  - name: "fast-autocomplete"
    provider: "openai"
    model: "gpt-3.5-turbo"
    apiKey: "${OPENAI_API_KEY}"
    roles: ["autocomplete"]
    defaultCompletionOptions:
      temperature: 0.1
      maxTokens: 200
      topP: 0.9
    requestOptions:
      timeout: 10000

Getting API Keys

1. Visit platform.openai.com
2. Register account and complete verification
3. Create new key on API Keys page
4. Set usage limits and payment method

Common Issues

Q: Why am I getting rate limit errors?

A: OpenAI has limits on API calls, you can:

• Wait for reset (usually per minute)
• Upgrade to paid plan
• Adjust request intervals

Q: How to handle long text?

A:

• Use models with long context support (like gpt-4-turbo)
• Reduce maxTokens setting
• Process long text in segments

Q: Response time is too long?

A:

• Use faster models (like gpt-3.5-turbo)
• Enable streaming response (stream: true)
• Reduce maxTokens
• Optimize prompt length

Q: How to use image input?

A: Use models that support image input:

models:
  - name: "vision-model"
    provider: "openai"
    model: "gpt-4o"
    apiKey: "${OPENAI_API_KEY}"
    roles: ["chat"]
    capabilities: ["image_input"]

Best Practices

1. Key Security

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

2. Cost Control

• Choose appropriate models based on task complexity
• Set reasonable maxTokens limits
• Use gpt-3.5-turbo for simple tasks

3. Performance Optimization

• Enable streaming response for better user experience
• Adjust temperature parameters based on use case
• Set reasonable request timeout

4. Model Selection Guide

• Complex tasks: Use gpt-4o
• Code related: Use gpt-4o or gpt-4-turbo
• Simple conversation: Use gpt-3.5-turbo
• Autocomplete: Use gpt-3.5-turbo
• Image processing: Use gpt-4o