skills.rest
JingyiWng
JingyiWngCOMMUNITY
Explore all skills by this author →
GitHub

databricks-vector-search

Create and manage Databricks vector search endpoints and indexes.

Updated Mar 25, 2026
Search Tags:#embeddings#rag#semantic-search#vector-search#databricks#endpoint-management#delta-sync
One-click install
npx skills add https://github.com/JingyiWng/databricks_ai_dev_kit_price_watcher --skill databricks-vector-search-jingyiwng
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: databricks-vector-search
Source: https://github.com/JingyiWng/databricks_ai_dev_kit_price_watcher/tree/main/.claude/skills/databricks-vector-search
Command: npx skills add https://github.com/JingyiWng/databricks_ai_dev_kit_price_watcher --skill databricks-vector-search-jingyiwng

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill streamlines the end-to-end creation, management, and querying of Databricks Vector Search endpoints and indexes so teams can build reliable semantic search and RAG pipelines without wrestling with low-level index operations and sync details.

Core Features & Use Cases

  • Endpoint Management: Create and manage Standard and Storage-Optimized endpoints for different latency and capacity needs.
  • Indexing Modes: Support for Delta Sync (managed or self-managed embeddings) and Direct Access indexes for both batch and real-time workflows.
  • Querying & Filtering: Run semantic, hybrid, or vector-based queries with JSON or SQL-like filters depending on endpoint type, and integrate results into agents or applications.
  • Use Case Example: Build a knowledge-base index from a Delta table, sync changes via TRIGGERED or CONTINUOUS pipelines, and power a retrieval-augmented agent that answers user questions with up-to-date documents.

Quick Start

Create a storage-optimized endpoint, add a Delta Sync index from your Delta table with managed embeddings, and run a semantic query to return the top 3 matching documents.

Frequently Asked Questions about databricks-vector-search

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

FAQPage Schema
How do I create a Databricks vector search index from a Delta table?▼

To create a Databricks vector search index, configure a Delta Sync index on a storage-optimized endpoint, enabling managed embeddings to automatically process and synchronize your Delta table data for semantic retrieval.

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

Delta Sync indexes automatically synchronize embeddings from source Delta tables using TRIGGERED or CONTINUOUS pipelines, while Direct Access indexes require self-managed embeddings for direct batch and real-time vector querying.

Can I use SQL-like filters for hybrid queries in Databricks vector search?▼

Yes, Databricks vector search supports hybrid queries combining semantic similarity with metadata filtering, allowing you to apply either SQL-like or JSON filter syntaxes depending on your specific endpoint type.

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

Use Standard endpoints for general-purpose semantic search latency needs, and choose Storage-Optimized endpoints when your vector search workloads require higher capacity and optimized retrieval performance for large-scale RAG pipelines.

How do I keep my RAG pipeline knowledge base updated with Databricks vector search?▼

Maintain an up-to-date RAG knowledge base by configuring Delta Sync indexes with CONTINUOUS pipelines, which automatically synchronize Delta table changes into the vector search index for real-time retrieval.

Related Skills

Explore More Data & Analytics Skills→
mirakuimirakui

databricks-vector-search

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

Community
Advanced
rizaldiemrizaldiem

qdrant

Integrate Qdrant vector database with Java and Spring Boot applications.

Community
Advanced
tomztomz

azure-databricks

Provision Azure Databricks workspaces with Unity Catalog governance via az CLI.

Community
Advanced
DbillionaerDbillionaer
1

vector-database-engineer

Engineer vector database solutions for semantic search and RAG applications.

Community
Advanced