Skip to content
TheChatArchiveThe Chat Archive
o1-preview-2024-09-12· OpenAIAi2 WildChat-4.8M (AI2)

system message open ai models

  1. User

    system message open ai models

  2. Assistant

    System messages in OpenAI models are used to guide the assistant's behavior and set the context for the conversation. They are provided at the beginning of a dialogue to define the role, tone, or specific instructions the assistant should follow when interacting with the user.

    Purpose of System Messages:

    • Role Definition: You can specify what role the assistant should play. For example, "You are a knowledgeable historian specializing in ancient civilizations."

    • Tone and Style: You can instruct the assistant to adopt a certain tone or style, such as being formal, casual, empathetic, or humorous.

    • Instructions and Constraints: You can provide specific guidelines or limitations. For example, "Provide answers using simple language that a fifth-grader can understand," or "Do not mention any unverified information."

    How to Use System Messages:

    When using the OpenAI API or platform that supports chat-based models, you structure the conversation as a list of messages, starting with a system message. Here's an example:

    [
      {
        "role": "system",
        "content": "You are a helpful assistant that provides clear and concise explanations about science topics."
      },
      {
        "role": "user",
        "content": "Can you explain how photosynthesis works?"
      }
    ]
    

    In this example:

    • The system message sets the context, telling the assistant to provide clear and concise explanations about science topics.

    • The user message is the question posed by the user.

    Tips for Writing Effective System Messages:

    1. Be Clear and Specific: Clearly state the desired behavior or style. Vague instructions may not produce the intended results.

    2. Set the Appropriate Tone: Decide if the assistant should be formal, friendly, professional, etc., depending on your use case.

    3. Provide Necessary Context: If the conversation requires the assistant to have certain knowledge or context, include that in the system message.

    4. Avoid Overloading the Message: While it's important to provide guidance, overly long or complex instructions might confuse the model. Keep it concise and focused.

    Example Use Cases:

    • Educational Tutor: "You are a math tutor helping a student understand algebraic concepts."

    • Customer Support Agent: "You are a customer support agent for an e-commerce company, helping customers with their orders and inquiries."

    • Language Translator: "You are an assistant that translates English text into French."

    Need Further Assistance?

    If you have specific requirements or need help crafting a system message for a particular application, feel free to share more details, and I'd be happy to help!