skills.rest
mkgs-databricks-demos
mkgs-databricks-demosOFFICIAL
Explore all skills by this author →
GitHub

databricks-ai-search

Create and query managed vector similarity indexes with Delta Lake integration.

Updated Jul 4, 2026
Search Tags:#RAG#AI Search#Semantic Search#Vector Search#Indexing
One-click install
npx skills add https://github.com/mkgs-databricks-demos/aiSkillUpdater --skill databricks-ai-search
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: databricks-ai-search
Source: https://github.com/mkgs-databricks-demos/aiSkillUpdater/tree/main/databricks-vector-search
Command: npx skills add https://github.com/mkgs-databricks-demos/aiSkillUpdater --skill databricks-ai-search

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill provides a comprehensive solution for RAG (Retrieval-Augmented Generation) and semantic search applications, simplifying the process of creating, managing, and querying AI Search indexes.

Core Features & Use Cases

  • Index Creation: Supports Delta Sync and Direct Access index types for various use cases.
  • Endpoint Management: Offers Standard and Storage-Optimized endpoint types with different latency and capacity characteristics.
  • Querying: Enables semantic search, hybrid search, and full-text search with various filtering options.
  • Use Case: Build a RAG application to improve the search experience in a knowledge base or document repository.

Quick Start

Install the package: pip install databricks-ai-search

Frequently Asked Questions about databricks-ai-search

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

FAQPage Schema
How do I build a RAG application with Delta Lake integration?▼

Build a RAG application with Delta Lake integration by using this managed vector similarity search service to automatically generate embeddings and query data through semantic, hybrid, or full-text search modes.

What is the difference between Delta Sync and Direct Access vector indexes?▼

Delta Sync indexes automatically synchronize with Delta Lake tables, while Direct Access indexes allow direct querying of source data. Both support managed embedding generation for semantic search applications.

How do I perform semantic search on a document repository?▼

Perform semantic search on a document repository by creating a vector index, utilizing automatic embedding generation, and querying the managed similarity search service using available filtering options.

Does databricks-ai-search support hybrid search and full-text search?▼

Yes, the service supports hybrid search and full-text search alongside semantic search. These multiple search modes include various filtering options to improve knowledge base query experiences.

What are the endpoint options for managing a vector similarity search service?▼

The vector similarity search service offers Standard and Storage-Optimized endpoint types. Standard endpoints provide lower latency, while Storage-Optimized endpoints handle different capacity characteristics.

Related Skills

Explore More Software Engineering Skills→
mirakuimirakui

databricks-vector-search

Create Databricks Vector Search endpoints and Delta Sync indexes for RAG retrieval.

Community
Advanced
woody1234567woody1234567
1

langchain-rag

Construct and execute a RAG pipeline with document loading, splitting, embedding, and storage.

Community
Intermediate
DrLuggelsDrLuggels
3

rag-implementation

Develops RAG systems for LLM applications using vector databases and embedding models.

Community
Advanced
ionmidoriionmidori

performing-similarity-search

Implement similarity search with Pinecone and Google Generative AI embeddings.

Community
Advanced