OpenAI API Guide

The /openai-pc command enables you to access OpenAI’s powerful AI capabilities through PinkConnect Proxy. Perfect for:

• Text generation and chat completions
• Image analysis and generation
• Audio transcription and synthesis
• Text embeddings for semantic search
• Function calling and tool use

​

Basic Usage

Use the command to work with OpenAI:

/openai-pc generate a professional email about project status

/openai-pc analyze this image and describe what you see

/openai-pc create embeddings for similarity search

​

Key Features

​

Text Generation

• Chat completions with GPT models
• System prompts and context
• Temperature and creativity control
• JSON mode support
• Structured responses

​

Vision Capabilities

• Image understanding
• Visual question answering
• Scene description
• Object detection
• Multi-modal conversations

​

Audio Processing

• Speech-to-text transcription
• Text-to-speech synthesis
• Multiple voice options
• Audio format support
• Language detection

​

Advanced Features

• Function calling
• Tool integration
• Embedding generation
• Semantic search
• Custom model fine-tuning

​

Example Commands

​

Text Generation

/openai-pc write a summary of the quarterly sales report

​

Image Analysis

/openai-pc describe the contents of this product image

​

Audio Processing

/openai-pc transcribe this meeting recording

​

Function Calling

/openai-pc get weather information for Boston using function calls

​

Chat Completions

​

Basic Chat

{
  "model": "gpt-4o",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant that responds in JSON format."
    },
    {
      "role": "user",
      "content": "What are the benefits of renewable energy?"
    }
  ],
  "max_tokens": 1500,
  "temperature": 0.7
}

​

Chat Response

{
  "id": "chatcmpl-9AbCdEf12345",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "gpt-4o",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "{\"benefits\": [\"Reduces carbon emissions\", \"Sustainable energy source\", \"Lower long-term costs\"]}"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 45,
    "total_tokens": 70
  }
}

​

Vision Capabilities

​

Image Analysis

{
  "model": "gpt-4o",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "What's in this image?"
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://example.com/image.jpg"
          }
        }
      ]
    }
  ],
  "max_tokens": 300
}

​

Vision Response

{
  "id": "chatcmpl-9AbCdEf12345",
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": "This image shows a golden retriever sitting in a park with green grass and trees in the background."
      },
      "finish_reason": "stop"
    }
  ]
}

​

Function Calling

​

Function Definition

{
  "model": "gpt-4o",
  "messages": [
    {
      "role": "user",
      "content": "What's the weather like in Boston?"
    }
  ],
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_current_weather",
        "description": "Get the current weather in a given location",
        "parameters": {
          "type": "object",
          "properties": {
            "location": {
              "type": "string",
              "description": "The city and state, e.g. San Francisco, CA"
            },
            "unit": {
              "type": "string",
              "enum": ["celsius", "fahrenheit"]
            }
          },
          "required": ["location"]
        }
      }
    }
  ],
  "tool_choice": "auto"
}

​

Function Response

{
  "id": "chatcmpl-9AbCdEf12345",
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": null,
        "tool_calls": [
          {
            "id": "call_abc123",
            "type": "function",
            "function": {
              "name": "get_current_weather",
              "arguments": "{\"location\": \"Boston, MA\"}"
            }
          }
        ]
      },
      "finish_reason": "tool_calls"
    }
  ]
}

​

Embeddings

​

Generate Embeddings

{
  "input": "The quick brown fox jumps over the lazy dog",
  "model": "text-embedding-3-small"
}

​

Embeddings Response

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "embedding": [0.123, -0.456, 0.789, ...],
      "index": 0
    }
  ],
  "model": "text-embedding-3-small",
  "usage": {
    "prompt_tokens": 8,
    "total_tokens": 8
  }
}

​

Image Generation

​

DALL-E Generation

{
  "model": "dall-e-3",
  "prompt": "A futuristic city skyline at sunset with flying cars",
  "n": 1,
  "size": "1024x1024",
  "quality": "standard",
  "style": "vivid"
}

​

Image Response

{
  "created": 1677652288,
  "data": [
    {
      "url": "https://oaidalleapiprodscus.blob.core.windows.net/private/..."
    }
  ]
}

​

Audio Processing

​

Speech-to-Text

{
  "file": "[AUDIO_FILE]",
  "model": "whisper-1",
  "language": "en"
}

​

Transcription Response

{
  "text": "Hello, this is a test transcription of the audio file."
}

​

Text-to-Speech

{
  "model": "tts-1",
  "input": "Hello world! This is a test of the text to speech API.",
  "voice": "alloy",
  "response_format": "mp3",
  "speed": 1.0
}

​

Available Models

​

GPT Models

• gpt-4o: Most advanced multimodal model
• gpt-4o-mini: Faster and more cost-effective
• gpt-4-turbo: High-intelligence model for complex tasks
• gpt-3.5-turbo: Fast, inexpensive model for simple tasks

​

DALL-E Models

• dall-e-3: Latest image generation model
• dall-e-2: Previous generation image model

​

Embedding Models

• text-embedding-3-large: Most capable embedding model
• text-embedding-3-small: Highly efficient embedding model
• text-embedding-ada-002: Legacy embedding model

​

Audio Models

• whisper-1: Speech recognition model
• tts-1: Text-to-speech model (standard)
• tts-1-hd: Text-to-speech model (high quality)

​

Model Capabilities

​

Text Generation

• Creative writing and content creation
• Code generation and debugging
• Data analysis and summarization
• Question answering
• Language translation

​

Vision Understanding

• Image description and analysis
• Object detection and recognition
• Scene understanding
• Visual question answering
• Chart and document analysis

​

Audio Processing

• Speech transcription in multiple languages
• Audio content analysis
• Voice synthesis with different personas
• Audio format conversion
• Real-time processing

​

Best Practices

1. Prompt Engineering

   • Use clear, specific instructions
   • Provide context and examples
   • Structure prompts logically
   • Test different approaches

2. Model Selection

   • Choose appropriate model for task
   • Consider cost vs. performance
   • Use specialized models when available
   • Test model capabilities

3. Parameter Tuning

   • Adjust temperature for creativity
   • Set appropriate max_tokens
   • Use system prompts effectively
   • Control response format

4. Error Handling

   • Handle rate limits gracefully
   • Implement retry logic
   • Validate inputs before sending
   • Monitor usage and costs

​

Common Use Cases

​

Content Creation

/openai-pc write a blog post about AI trends in 2025

​

Data Analysis

/openai-pc analyze this CSV data and provide insights

​

Code Generation

/openai-pc create a Python function for data validation

​

Image Processing

/openai-pc analyze this screenshot and extract the text

​

Connection Requirements

​

PinkConnect Setup

• Uses PC_BASE_URL + v1/ endpoint
• Requires OpenAI connection ID
• SELECTED_SKILL_ID must be “openai”
• Standard API authentication

​

Authentication

• API key authentication
• Organization ID support
• Usage tracking
• Rate limit management

​

Performance Optimization

​

Efficient Usage

• Cache responses when appropriate
• Use streaming for long responses
• Batch requests when possible
• Monitor token usage

​

Cost Management

• Choose cost-effective models
• Optimize prompt length
• Use appropriate max_tokens
• Monitor usage patterns

​

Integration Tips

​

Workflow Automation

• Chain multiple API calls
• Combine with other services
• Implement error recovery
• Use function calling for tools

​

Response Processing

• Parse JSON responses carefully
• Handle different response formats
• Extract relevant information
• Validate response quality

​

Tips

• Always specify SELECTED_SKILL_ID as “openai” for PinkConnect
• Use system prompts to establish context and behavior
• Test different temperature values for optimal creativity
• Implement proper error handling for rate limits and failures
• Monitor token usage to manage costs effectively
• Use function calling for structured interactions with external tools