Define guidelines for system behavior, user interactions, and constraints. You can include sections such as: * Role * Instructions * Rules * Examples
For example:
You are an AI assistant designed to help users by providing accurate, relevant, and helpful responses. Maintain a neutral and professional tone, be concise yet informative, and always strive to be clear and understandable.
User Prompt
The message containing your prompt request, which the LLM model will interpret to generate a response.
The maximum number of tokens needed to generate a response.
Set the token limit based on your needs: 1. Short & Concise Answers (256–1,000 tokens) - Ideal for brief responses, summaries, or direct answers. 2. Detailed & Elaborate Responses (1,000–8,000 tokens) - Best for in-depth explanations, multi-step reasoning, or complex insights. 3. Data Processing & Transformations (2,000–10,000+ tokens) - Use higher limits for handling structured data (e.g., JSON, CSV) or processing large text inputs.
Note: For optimal performance, start with a lower limit and increase as needed. If not provided, the selected model default value is used.
Temperature
The randomness of the output.
Lower values produce more focused and deterministic outputs, while higher values increase creativity and variation.