skills.rest
databrickslabs
databrickslabsOFFICIAL
Explore all skills by this author →
WebsiteGitHub

databricks-vector-search

Create and operate vector similarity search infrastructure on Databricks.

38|12|Updated Apr 24, 2026
Search Tags:#embeddings#rag#semantic-search#vector-search#databricks#similarity-search#delta-sync
One-click install
npx skills add https://github.com/databrickslabs/coding-agents-databricks-apps --skill databricks-vector-search-databrickslabs
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: databricks-vector-search
Source: https://github.com/databrickslabs/coding-agents-databricks-apps/tree/main/.claude/skills/databricks-vector-search
Command: npx skills add https://github.com/databrickslabs/coding-agents-databricks-apps --skill databricks-vector-search-databrickslabs

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill eliminates the complexity of manually building and maintaining vector similarity search infrastructure for retrieval-augmented generation and semantic search applications on Databricks, removing the need to handle embedding generation, vector index management, and Delta table synchronization from scratch.

Core Features & Use Cases

  • Managed Vector Infrastructure: Create and configure Standard or Storage-Optimized endpoints and Delta Sync or Direct Access vector indexes with pre-built patterns.
  • Flexible Embedding Support: Use Databricks-managed embedding models or bring your own pre-computed embeddings for custom use cases.
  • Advanced Query Capabilities: Run similarity, hybrid (semantic + keyword), and filtered queries against vector indexes to power RAG chatbots, product search, and document retrieval tools.
  • Use Case: For example, use this Skill to set up a vector index over your internal knowledge base Delta table, then build a RAG-powered employee support assistant that retrieves relevant policy documents based on natural language questions.

Quick Start

Use the databricks-vector-search skill to create a Storage-Optimized vector search endpoint, set up a Delta Sync index over your product documentation Delta table with managed embeddings, and run a filtered similarity query to retrieve the top 5 most relevant documents for a given user search term.

Frequently Asked Questions about databricks-vector-search

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

FAQPage Schema
How do I build a RAG application using Databricks Vector Search?▼

You can build RAG on Databricks by creating a Delta Sync vector index over your knowledge base table and running similarity queries to retrieve relevant context for your generative model.

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

Delta Sync vector indexes automatically synchronize with Delta tables for managed updates, whereas Direct Access indexes require you to manually ingest and manage pre-computed embeddings for vector search.

Can I use pre-computed embeddings for semantic search on Databricks?▼

Yes, you can bring your own pre-computed embeddings to a Direct Access vector index, or use Databricks-managed embedding models with Delta Sync indexes for automated semantic search generation.

How do I run filtered or hybrid similarity queries against a vector index?▼

You can run filtered similarity queries by applying metadata filters to your vector search, or execute hybrid queries that combine semantic similarity with keyword matching against your vector index.

Do I need Unity Catalog to manage vector search endpoints on Databricks?▼

Databricks Vector Search integrates with Unity Catalog to provide governed access to vector indexes and Delta tables, ensuring secure and compliant RAG application infrastructure.

When should I use Storage-Optimized endpoints for vector search?▼

Use Storage-Optimized endpoints for large-scale cost-effective vector storage, and Standard endpoints for low-latency semantic search performance on the Databricks platform.

Related Skills

Explore More Data & Analytics Skills→
datasciencemonkeydatasciencemonkey
27

databricks-vector-search

Create and query Databricks Vector Search endpoints and indexes.

Community
Advanced
gil00pitagil00pita

pinecone

Store and query high-dimensional embeddings with Pinecone for semantic similarity.

Community
Advanced
mirakuimirakui

databricks-vector-search

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

Community
Advanced
mkgs-databricks-demosmkgs-databricks-demos
1

databricks-vector-search

Manage Databricks vector search endpoints and indexes for semantic retrieval.

Official
Advanced