databricks-ai-functions

Invoke Databricks AI Functions for sentiment analysis, classification, and summarization in SQL and PySpark pipelines.

Updated Jun 11, 2026
One-click install
npx skills add https://github.com/Zack2626-ok/DATN_Website-Dat-Ban-Va-Quan-Ly-Nha-Hang --skill databricks-ai-functions-zack2626-ok
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: databricks-ai-functions
Source: https://github.com/Zack2626-ok/DATN_Website-Dat-Ban-Va-Quan-Ly-Nha-Hang/tree/main/.windsurf/skills/databricks-ai-functions
Command: npx skills add https://github.com/Zack2626-ok/DATN_Website-Dat-Ban-Va-Quan-Ly-Nha-Hang --skill databricks-ai-functions-zack2626-ok

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pyspark, databricks-sql, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill allows users to integrate AI functionalities into their data pipelines without managing model endpoints, enabling efficient and scalable AI-driven data processing.

Core Features & Use Cases

  • Task-specific AI Functions: Perform sentiment analysis, text classification, entity extraction, summarization, and more with built-in functions.
  • General-purpose AI Functions: Use ai_query for complex JSON processing and custom model endpoints.
  • Time Series Forecasting: Predict future values with ai_forecast.
  • Document Processing: Parse and extract information from PDFs and other documents.
  • Use Case: Automate the classification of support tickets into categories based on content, extract information from invoices, or generate summaries of long documents.

Quick Start

Use the ai_classify function to classify a text column in your database:

SELECT ticket_id, ticket_text, ai_classify(ticket_text, ARRAY('urgent', 'not urgent', 'spam')) AS priority;

Frequently Asked Questions about databricks-ai-functions

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I add AI capabilities to SQL data pipelines in Databricks?

To add AI capabilities to SQL pipelines, use Databricks AI Functions for tasks like sentiment analysis, classification, and extraction directly within your queries, avoiding the need to manage external model endpoints.

Can I perform text classification and summarization using PySpark in Databricks?

Yes, you can perform text classification and summarization using PySpark by invoking Databricks AI Functions, which process data efficiently at scale across your Spark pipelines.

How do I query custom model endpoints from a Databricks SQL warehouse?

You can query custom model endpoints from a Databricks SQL warehouse using the general-purpose `ai_query` function, enabling complex JSON processing and custom model integrations.

Does Databricks support time series forecasting and document processing in SQL?

Databricks supports time series forecasting and document processing in SQL through built-in functions like `ai_forecast` and specialized document processing capabilities.

What Databricks runtime and dependencies are required for AI Functions?

AI Functions require a Databricks SQL warehouse with DBR 15.1 or higher, along with specific dependencies like PySpark and databricks-sql for execution.

What is the best way to extract information from invoices using Databricks SQL?

The best way to extract information from invoices in Databricks SQL is by using task-specific AI Functions like `ai_extract`, which parse and pull structured data directly from document content.