Karini AI Documentation
Go Back to Karini AI
  • Introduction
  • Installation
  • Getting Started
  • Organization
  • User Management
    • User Invitations
    • Role Management
  • Model Hub
    • Embeddings Models
    • Large Language Models (LLMs)
  • Prompt Management
    • Prompt Templates
    • Create Prompt
    • Test Prompt
      • Test & Compare
      • Prompt Observability
      • Prompt Runs
    • Agentic Prompts
      • Create Agent Prompt
      • Test Agent Prompt
    • Prompt Task Types
    • Prompt Versions
  • Datasets
  • Recipes
    • QnA Recipe
      • Data Storage Connectors
      • Connector Credential Setup
      • Vector Stores
      • Create Recipe
      • Run Recipe
      • Test Recipe
      • Evaluate Recipe
      • Export Recipe
      • Recipe Runs
      • Recipe Actions
    • Agent Recipe
      • Agent Recipe Configuration
      • Set up Agentic Recipe
      • Test Agentic Recipe
      • Agentic Evaluation
    • Databricks Recipe
  • Copilots
  • Observability
  • Dashboard Overview
    • Statistical Overview
    • Cost & Usage Summary
      • Spend by LLM Endpoint
      • Spend by Generative AI Application
    • Model Endpoints & Datasets Distribution
    • Dataset Dashboard
    • Copilot Dashboard
    • Model Endpoints Dashboard
  • Catalog Schemas
    • Connectors
    • Catalog Schema Import and Publication Process
  • Prompt Optimization Experiments
    • Set up and execute experiment
    • Optimization Insights
  • Generative AI Workshop
    • Agentic RAG
    • Intelligent Document Processing
    • Generative BI Agentic Assistant
  • Release Notes
Powered by GitBook
On this page
  1. Recipes
  2. QnA Recipe

Export Recipe

PreviousEvaluate RecipeNextRecipe Runs

Last updated 10 months ago

Once you have created, run, and tested a recipe, the subsequent action is to export it for deploying . You can access the export page for a recipe in two ways: either by selecting the Export option from the Actions menu associated with the recipe, or by clicking the Export button directly available within the recipe interface.

You can fill out all necessary fields to customize your Copilot, with detailed explanations provided for each field below.

  • Copilot Name: A name for your copilot.

  • Welcome Message: A welcome message to greet users upon interaction with the Copilot.

  • Description: Description outlining the Copilot's purpose and capabilities.

  • Logo URL: The URL of the logo to be displayed alongside the Copilot for branding purposes.

  • Seed Questions: A set of initial questions or prompts to kickstart interactions with users.

  • Error Message: A message to be displayed in case of errors or misunderstandings during interaction.

  • Widget Settings: Customize the appearance and behavior of the Copilot widget for seamless integration, including widget size.\

  • Enable Positive Feedback: Enable "thumbs up" or positive feedback for users on Copilot interactions.

  • Enable Negative Feedback: Enable "thumbs down" or negative feedback for users on Copilot interactions.

  • Custom Feedbacks: You have the option to enable capturing various types of feedback on the copilot. This includes:

    • 5-stars: Copilot users can rate the content with a 5-star rating.

    • option: You can configure options to capture feedback on Copilot interactions based your specific requirement. E.g. You may configure the options as "Inaccurate", "Vaguely accurate", "Accurate". These predefined options are made available to the copilot users to provide feedback on Copilot interactions.

    • text feedback: Copilot users can provide descriptive text feedback.

    • Correction: Enabling this option will allow the copilot users to provide corrections or improvements to the copilot response.

  • Unsafe User Input Message: A message to be displayed when Copilot detects unsafe user input.

  • Toxic User Input Message: A message to be shown when Copilot identifies toxic user input.

  • Toxic Output Message: A message to handle toxic output generated by Copilot.

  • Greeting Default Response: A default message to greet users when the user question is detected as a greeting.

  • Show traces: Enabling this option will display the traces icon on Copilot and users can view the traces for the LLM invocations.

  • Base Domain URL: The base domain URL for the Copilot's web interface or integration.

Upon providing the base domain URL, you can see the Snippet Code which can be integrated into a customized user application.

After you Save export details, you can use the Internal Copilot URL to access the Copilot.

Copilots