---
id: databricks-openai
version: "0.17.0"
license: Apache-2.0
license_treatment: permissive
maintenance: active
---

# databricks-openai — Support for Databricks AI support with OpenAI

License: permissive · Maintenance: active · Downloads: 1.4M/mo

## What it is and what it does

databricks-openai bridges Databricks AI capabilities into OpenAI-based applications by providing tool definitions that work with OpenAI's function-calling API. The primary use case is retrieval-augmented generation (RAG): it wraps Databricks vector search indexes as callable tools that OpenAI models can invoke during chat completions to fetch relevant context before generating responses.

The package depends on eight runtime libraries including databricks-ai-bridge, mlflow, openai, pydantic, and several Databricks-specific modules. It requires Python 3.10 or later and installs as a pure-Python wheel with low friction. The integration follows OpenAI's standard tool-use pattern: define a VectorSearchRetrieverTool pointing to a Databricks index, pass it to the chat completions API, parse the model's tool calls, execute the retrieval, and feed results back to the model.

Use it for:

- Build RAG systems where OpenAI models query Databricks vector indexes to ground responses in proprietary data
- Create chatbots that retrieve context from Databricks documentation or knowledge bases before answering user questions
- Integrate Databricks AI Search with OpenAI agents for multi-step reasoning over indexed data
- Combine MLflow model tracking with OpenAI function calling for reproducible, retrieval-augmented workflows

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Integrates Databricks AI features, particularly vector search, into OpenAI applications through tool definitions and retrieval workflows.

Yes, if you are building OpenAI applications that need to retrieve context from Databricks vector indexes. The low install friction, active maintenance, permissive license, and no known vulnerabilities make it a safe choice. The package is narrowly scoped to a specific integration pattern, so install only if you have both Databricks infrastructure and OpenAI API access.

## Install

pip install databricks-openai
uv add databricks-openai
poetry add databricks-openai

## Installing databricks-openai

Before you install: Low friction install with a pure-Python wheel. Active maintenance status and recent releases. Requires Python 3.10 or later.

License in practice: Apache-2.0 permissive license allows commercial use, modification, and distribution with minimal restrictions.

Quickstart:

pip install databricks-openai

from databricks_openai import VectorSearchRetrieverTool
import json
from openai import OpenAI

client = OpenAI()
dbvs_tool = VectorSearchRetrieverTool(index_name="catalog.schema.my_index")
messages = [{"role": "user", "content": "Answer based on Databricks docs"}]
response = client.chat.completions.create(
    model="gpt-4o",
    messages=messages,
    tools=[dbvs_tool.tool]
)

Requires Python 3.10 or later; Databricks workspace with a configured vector search index; OpenAI API key.

Verify before relying:

- Whether VectorSearchRetrieverTool requires pre-existing Databricks vector indexes or can create them
- Support for embedding models other than OpenAI's default
- Performance characteristics with large vector indexes or high query volume

## Package facts

- License: Apache-2.0 (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 1.4M/month (top 5,000 on PyPI)
- Known vulnerabilities: none known

## Tags

databricks vector search openai, rag with databricks and openai, databricks ai retrieval tools, openai function calling databricks, vector search retrieval integration, databricks mlflow openai agents, rag, vector-search, databricks-integration

[View on SkillFed](https://skillfed.io/packages/databricks-openai) · [View on PyPI](https://pypi.org/project/databricks-openai/)