Karini AI Documentation
  • Introduction
  • 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
      • Evaluation
    • Prompt Task Types
    • Prompt Versions
  • Datasets
  • Recipes
    • QnA Recipe
      • Data Storage Connectors
      • Vector Stores
      • Create Recipe
      • Run Recipe
      • Test Recipe
      • Evaluate Recipe
      • Export Recipe
      • Recipe Runs
    • Agent Recipe
    • Batch Recipe
    • 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
    • Retrieval Augmented Generation(RAG)
    • Agentic RAG
    • Generative Business Intelligence
    • Intelligent Automation
    • GraphRAG Agent
Powered by GitBook
On this page
  1. Catalog Schemas

Catalog Schema Import and Publication Process

PreviousConnectorsNextPrompt Optimization Experiments

Last updated 22 days ago

Follow the steps outlined below to import the catalog schema and publish it.

1. Browse schema

  • Users can expand the database (e.g., "dev") to view its available schemas and tables by clicking the “Browse schema” button.

  • When a table is selected, an overview and a sample dataset containing five records will be presented.

2. Selecting and Importing Schemas

  • The Import Selected Schemas button becomes enabled once a table(s) is selected.

  • Upon initiation, the system retrieves metadata from the selected tables(s).

  • The status will update to reflect the progress of the import (e.g., "Importing").

Once the process is complete, the imported table will be displayed under the Catalog Explorer, allowing users to view its structure, including tables and columns.

3. Metadata Generation Requirement

To proceed with publishing the catalog, metadata must be generated for each table.

  • Metadata generation requires the Natural Language Assistant model to be configured at the Organization level within the system settings

  • Once this configuration is in place, you can generate metadata for each table.

  • After metadata generation is complete, descriptions for the table and its rows will be displayed.

  1. Publishing the Catalog Schema

To publish table metadata, the Global Embeddings Model must be configured at the Organization level.

  • After completing the metadata generation, you can publish the catalog schema.

  • Once published, the status will be updated to Published.

  1. Synchronizing Database Modifications

  • When changes occur in the database tables, a Sync button is available within the catalog.

  • This feature allows users to synchronize and reflect the latest updates within the catalog.

The published catalog schemas can be utilized as tools within Agent prompts.