databricks-vector-search
This skill enables agents to build and query vector search indexes on Databricks for RAG and semantic search applications.
Identity proven by GitHub's verified organisation badge (databricks)
- Agents
- Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode
- License
- LicenseRef-Databricks (restricted)
- Pin
- e3df77bpinned Oct 9, 2026
- Context cost
- about 2,900 tokenswhen the skill loads
- GitHub stars
- 345on databricks/databricks-agent-skills
- Scripts
- None found
What it does
“Databricks Vector Search endpoints and indexes for RAG and semantic search; covers index types, search modes, end-to-end RAG patterns”
Generated summary from the skill's own text
This skill enables agents to build and query vector search indexes on Databricks for RAG and semantic search applications. It covers creating endpoints, managing three index types (Delta Sync managed/self-managed and Direct Access), querying with text or embeddings, and filtering results. The skill includes patterns for hybrid search, cost optimization, and integration with Databricks' managed embedding models.
When to use it
- Building RAG applications that retrieve relevant documents from large datasets
- Implementing semantic search or similarity matching across text or embeddings
- Creating vector indexes from Delta tables with automatic or manual syncing
- Choosing between standard low-latency or storage-optimized cost-effective endpoints
When not to
- Needing real-time indexing without any latency tolerance, as sync operations take time
- Working with non-text data that cannot be vectorized into embeddings
- Implementing traditional keyword search alone, where BM25 is sufficient
Install
Restricted license: install from the publisher's repository and read its terms.
These commands install from the publisher's repository and need no account.
skills CLI
npx skills add databricks/databricks-agent-skills --skill databricks-vector-searchInstalls from the repository's default branch, which may have changed since the commit we checked.
GitHub CLI 2.90 or later
gh skill install databricks/databricks-agent-skills databricks-vector-search@e3df77b3f0eb5d70392eb35c6761ca0f2929a4f6Installs the commit we checked (e3df77b).
Copy by hand
Download the folder at e3df77b and put it in .claude/skills/databricks-vector-search for Claude Code and in .agents/skills/databricks-vector-search for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.
Claude Code plugin
/plugin install databricks@claude-plugins-officialThe publisher's plugin in Claude's official marketplace. It may hold more than this skill, and we have not pinned it.
Copy for your agent
A prompt for any coding agent. It installs this skill from GitHub at the pinned commit, copies the files as they are, and runs nothing unless you ask.
Prompt
Install the agent skill "databricks-vector-search" by Databricks. Source, pinned to commit e3df77b3f0eb5d70392eb35c6761ca0f2929a4f6: https://github.com/databricks/databricks-agent-skills/tree/e3df77b3f0eb5d70392eb35c6761ca0f2929a4f6/plugins/databricks/claude/skills/databricks-vector-search 1. Download that folder at exactly this commit. Do not use the default branch. 2. Copy every file unchanged, keeping the folder structure, into .claude/skills/databricks-vector-search/ for Claude Code and .agents/skills/databricks-vector-search/ for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode. Create the folders if they do not exist. 3. Do not edit the files, and do not run any script in the folder unless I ask you to. 4. When you are done, list the files you copied and where you put them. Its license is restricted or not stated. Show me the license terms from the repository before you copy anything. Listing and checks: https://www.agentnative.dev/skills/databricks/databricks-vector-search
SKILL.md at the pin
The license of this skill does not let us show its files here.
Files
- SKILL.md12 KB · 50b84ee87a43
- agents/
- openai.yaml452 B · abaf0640c887
- assets/
- databricks.png15 KB · 06873c31ebda
- databricks.svg582 B · 00e528e4d5e6
- references/
- end-to-end-rag.md7.2 KB · d6c5e4b7ba14
- index-types.md6.4 KB · 1ed91a8b37be
- search-modes.md6.1 KB · f6b0c3c981b1
- troubleshooting-and-operations.md8.4 KB · 80dd3859ce99
8 files, 56 KB in total. Each file has a sha256 in the pin's manifest; the first 12 characters are shown.
Skill folder on GitHub at e3df77bAlso in
The same SKILL.md content appears in these places too. We list it once and credit the oldest public source.
- databricks/databricks-agent-skills/plugins/databricks/codex/skills/databricks-vector-search
- databricks/databricks-agent-skills/plugins/databricks/copilot/skills/databricks-vector-search
- databricks/databricks-agent-skills/plugins/databricks/cursor/skills/databricks-vector-search
- databricks/databricks-agent-skills/skills/databricks-vector-search
More from Databricks
databricks-agent-bricks
This skill enables agents to create and manage Knowledge Assistants for document question-answering via RAG on Volumes, and Supervisor Agents that orchestrate…
Claude Code, Codex, Cursor +3 · about 1.7K tokens · pinned 6 days ago
databricks-ai-functions
This skill provides built-in Databricks AI Functions that add AI capabilities directly to SQL and PySpark pipelines, including classification, extraction…
Claude Code, Codex, Cursor +3 · about 3.8K tokens · pinned 6 days ago
databricks-ai-runtime
This skill enables agents to submit and manage GPU training workloads on Databricks serverless compute using the `databricks air` CLI.
Claude Code, Codex, Cursor +4 · about 2.9K tokens · pinned 6 days ago
databricks-aibi-dashboards
Creates Databricks AI/BI dashboards using JSON specifications with support for multiple visualization types.
Claude Code, Codex, Cursor +3 · about 9.5K tokens · pinned 6 days ago
databricks-app-design
This skill helps design the user experience of custom-code Databricks Apps built with AppKit and React that display data.
Claude Code, Codex, Cursor +3 · about 1.6K tokens · pinned 6 days ago
databricks-apps
Build custom interactive data apps on Databricks using AppKit (TypeScript/React framework) or other frameworks like Streamlit or FastAPI.
Claude Code, Codex, Cursor +3 · about 5.5K tokens · pinned 6 days ago
Related in Data and databases
airflow-state-store
Helps agents work with Airflow 3.3's task and asset state stores for persisting coordination state across task retries, implementing crash-safe external job…
by AstronomerOfficial publisher
Claude Code, Codex, Cursor +4 · about 5.9K tokens · pinned 6 days ago
databricks-core
This skill enables the agent to authenticate with Databricks, manage CLI profiles, explore data catalogs and tables, and route to specialized product skills…
by DatabricksOfficial publisher
Contains scripts
Claude Code, Codex, Cursor +3 · about 1.8K tokens · pinned 6 days ago
databricks-data-discovery
This skill routes data discovery requests to Databricks Genie, enabling the agent to find tables and schemas, answer questions about data, and generate SQL…
by DatabricksOfficial publisher
Claude Code, Codex, Cursor +3 · about 2K tokens · pinned 6 days ago
databricks-dbsql
This skill provides access to Databricks SQL advanced features including SQL scripting, stored procedures, materialized views, geospatial functions…
by DatabricksOfficial publisher
Claude Code, Codex, Cursor +3 · about 2.5K tokens · pinned 6 days ago
databricks-docs
This skill provides reference access to Databricks documentation via llms.txt index to supplement other skills.
by DatabricksOfficial publisher
Claude Code, Codex, Cursor +3 · about 630 tokens · pinned 6 days ago
databricks-execution-compute
Execute Python, Scala, SQL, or R code on Databricks through three modes: Databricks Connect for local Spark jobs, serverless jobs for heavy processing, or…
by DatabricksOfficial publisher
Claude Code, Codex, Cursor +3 · about 2.2K tokens · pinned 6 days ago
Open roles at Databricks
5 of 136 open roles on the jobs board
- Sr. Forward Deployed Engineer
Tokyo, Japan
- Senior Software Engineer - Backend
San Francisco, California, USA
- Software Engineer - Backend
Aarhus, Denmark
- Senior Production Engineer - Realtime Products
Mountain View, California, USA
- Sr. Forward Deployed Engineer (FDE) - Retail
Austin, Texas, USA