databricks-vector-search

Creates and queries Databricks Vector Search endpoints and indexes for semantic retrieval.

Updated May 20, 2026

Search Tags:#rag #semantic-search #vector-search #unity-catalog #hybrid-search #delta-sync #embedding-indexes

Ready to run

npx skills add https://github.com/ice-droid-99/BI-Dashboard-Generation-Agent-in-Databricks- --skill databricks-vector-search-ice-droid-99

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: databricks-vector-search
Source: https://github.com/ice-droid-99/BI-Dashboard-Generation-Agent-in-Databricks-/tree/main/.gemini/skills/databricks-vector-search
Command: npx skills add https://github.com/ice-droid-99/BI-Dashboard-Generation-Agent-in-Databricks- --skill databricks-vector-search-ice-droid-99

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Databricks Vector Search solves the problem of finding semantically relevant information fast by converting text (or embeddings) into vector indexes that can be queried with meaning, filters, and hybrid ranking.

Core Features & Use Cases

Vector Search Index Lifecycle: Create and manage Standard or Storage-Optimized endpoints and indexes, including Delta Sync (managed or self-managed embeddings) and Direct Access (manual upsert/delete).
RAG and Semantic Retrieval: Retrieve top-k documents for RAG, semantic search, similarity matching, and knowledge assistant pipelines with managed embedding models or precomputed vectors.
Filtering and Hybrid Search: Apply attribute filters and use HYBRID mode (vector + keyword) to ensure exact terms (IDs, error codes, proper nouns) are not missed.

Quick Start

Create a storage-optimized vector search endpoint and a Delta Sync index from your Delta table, then query it for the top matching chunks for a natural-language question.

Frequently Asked Questions about databricks-vector-search

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

FAQPage Schema

How do I set up Databricks Vector Search for semantic retrieval?▼

To set up Databricks Vector Search, create a vector search endpoint and Delta Sync index. You must define index specs like primary key, embedding source, pipeline type, and columns to sync to enable semantic retrieval for RAG.

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

Delta Sync automatically syncs vector indexes from Delta tables using managed or self-managed embeddings. Direct Access requires manual upserts and deletes, offering different storage and freshness trade-offs for your vector search.

Can I use hybrid search and filtering with Databricks Vector Search?▼

Yes, Databricks Vector Search supports hybrid search. You can apply HYBRID mode combining vector and keyword ranking, and use attribute filters to ensure exact terms like IDs or error codes are matched alongside semantic results.

Do I need Unity Catalog to create a Databricks Vector Search index?▼

Yes, Unity Catalog is required. Databricks Vector Search relies on Unity Catalog to manage Delta tables and synchronize them into vector indexes, ensuring governed access for your semantic search endpoints.

How do I query a Databricks Vector Search index using query_text or query_vector?▼

You can query Databricks Vector Search using query_text for natural language, query_vector for precomputed embeddings, or hybrid ranking. Query parameters must match embedding dimensions and filter syntax to retrieve top-k results.

What are the limitations of storage-optimized vector search endpoints?▼

Storage-optimized vector search endpoints are designed for specific scale and cost profiles. When choosing between Standard and Storage-Optimized, consider your storage capacity and query latency requirements for your specific vector index lifecycle.