Skip to main content

Answer AI

Overview​

This documentation guides managing the system prompt for Answer AI LLM. System Prompt guides the AI in generating responses to the user query.

Answer AI

Dynamic Tokens​

Dynamic tokens are placeholders within a prompt that are replaced with dynamic content when a prompt is processed. Here is a list of Dynamic tokens you can use:

  • {query}: Inserts the user's question.
  • {vector-query}: Inserts the user's question.
  • {history}: Inserts the conversation history.
  • {title}: Inserts the title of the page where the search is conducted.
  • {origin}: Inserts the URL of the page.
  • {language}: Inserts the language of the page.
  • {referrer}: Inserts the referring URL that directed the user to the current page.
  • {attributes}: Allows insertion of additional; javascript would add it to the search control.
  • {org_name}: Inserts the name of the organization for which the copilot is configured.
  • {purpose}: Inserts the stated purpose of the AI bot.
  • {org_url}: Inserts the domain URL of the organization the bot is configured for.
  • {context_data} : Used by Answer AI output from the vector db
  • {tz=America/New_York} : Timezone creates the text of what is the time and date for the LLM to use
  • {image_upload_description} : Image descriptions of images uploaded by the site visitor into the search box processed by vision AI

Models that ai12z support for RAG​

  • GPT-4o:
    A next-generation GPT variant focused on robust reasoning and versatile language understanding.
  • GPT-4o-mini: Defalult A scaled-down version of GPT-4o providing faster responses and reduced resource usage, while still maintaining good quality.
  • Llama 3.2 Instruct (1B):
    A small, instruction-tuned Llama model optimized for task-following on a modest scale.
    • Llama 3.2 Instruct (3B):
      A mid-sized instruct model that balances efficiency with improved fluency and accuracy.
  • Llama 3.2 Instruct (11B):
    A larger Llama instruct model providing more coherent, context-aware responses than smaller counterparts.
  • Llama 3.2 Instruct (90B):
    A highly capable, large-scale Llama instruct model designed for complex tasks and in-depth reasoning.
  • Claude 3.5 Sonnet:
    A creative variant of Claude 3.5 tuned for expressive, structured writing like poetry or stylized prose.
  • Claude 3 Opus:
    A versatile Claude 3 model offering enhanced context management and refined long-form content generation.
  • Claude 3 Haiku:
    A succinct Claude 3 variant focusing on generating short, elegant, and poetic responses.
  • Gemini-1.5-Flash:
    A fast, nimble generation model that emphasizes quick, responsive text outputs at version 1.5.
  • Gemini-1.5-Pro:
    An upgraded Gemini model with professional-level language capabilities for more demanding tasks.
  • Gemini-1.5-Flash-8B:
    A larger, high-parameter Flash variant of Gemini 1.5, combining rapid output with richer, more detailed responses.

Defining System and User Prompts​

Auto Generate

You can re-edit the project information and check the check box, "Recreate Prompts" AI will use the information you entered when creating the project to recreate the prompt and system prompt. You can always go back and re-edit those properties. It will populate the dialog withe Is Default checked

Editing Prompts​

When editing a prompt, consider the following guidelines:

  • Keep the instructions clear and concise so the AI can understand them.

Best Practices​

  • Test prompts to see how the AI interprets them with different types of user queries.
  • Update prompts regularly to align with project goals or organization strategies changes.
  • Monitor the AI's responses to ensure they meet the expected quality and adjust the prompts accordingly.

Saving Changes​

After making your changes:

  1. Review the prompt to ensure accuracy and completeness.
  2. Click the "Save" button to apply the changes.
  3. Test the updated prompt with a few queries to ensure it functions as expected.

Conclusion​

Managing prompts effectively is crucial for the optimal performance of your AI interface. By following the guidelines outlined in this document, you can ensure that your AI provides relevant, accurate responses and in line with your organization's objectives.