databricks-ai-bridge

What it is and what it does

Databricks AI Bridge is an official Python library that provides a unified API for interacting with Databricks AI capabilities, primarily Vector Search and AI/BI Genie. It serves as the foundation layer for building agents and applications on Databricks, with dedicated integration packages available for LangChain/LangGraph and OpenAI SDK users. The library depends on databricks-sdk for workspace connectivity, mlflow-skinny for model tracking, pandas for data handling, pydantic for validation, and tiktoken for token counting.

The package is designed for developers already working within the Databricks ecosystem who need to programmatically access AI features. It is not a standalone AI framework but rather a bridge between your application code and Databricks-hosted services. Use of this library is restricted by its proprietary license to connections with Databricks Services only, meaning it cannot be used independently or with non-Databricks deployments.

Use it for:

• Building agents on Databricks Agent Framework that query vector databases and AI/BI Genie
• Integrating Databricks Vector Search into LangChain or LangGraph workflows via databricks-langchain
• Using Databricks AI features with OpenAI SDK through the databricks-openai integration package
• Programmatically accessing Databricks generative AI capabilities from Python applications
• Token counting and embedding workflows that depend on tiktoken and Databricks services

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Provides a shared Python API layer for building agents and applications that integrate with Databricks AI features like Vector Search and AI/BI Genie.

Yes, if you are building on Databricks and need to integrate Vector Search or AI/BI Genie into agents or applications. The library is actively maintained, has low install friction, and is the official integration point for Databricks AI features. No, if you are not using Databricks Services or need to use these capabilities outside a Databricks workspace—the proprietary license explicitly restricts use to Databricks Services only.

Install

databricks-ai-bridge on PyPI

pip install databricks-ai-bridge

uv add databricks-ai-bridge

poetry add databricks-ai-bridge

Installing databricks-ai-bridge

Before you install

Low friction install with a pure-Python wheel. Active maintenance with recent releases. Requires Python 3.10 or later and eight runtime dependencies including databricks-sdk, mlflow-skinny, and tiktoken.

License in practice

Licensed under a proprietary Databricks License that restricts use to the Databricks Services per your Master Cloud Services Agreement. Redistribution is permitted only under these same terms. Not suitable for standalone or non-Databricks deployments.

Quickstart

pip install databricks-ai-bridge

from databricks_ai_bridge import VectorSearch
# Requires Databricks workspace connection via databricks-sdk

Requires active Databricks workspace and credentials; use restricted to Databricks Services per license terms.

Verify before relying

• Specific API surface and supported Databricks AI features beyond Vector Search and AI/BI Genie
• Whether integration packages (databricks-langchain, databricks-openai) are included or must be installed separately
• Performance characteristics and rate limits when used with Vector Search at scale

Package facts

Evidence: databricks_ai_bridge-0.21.0-py3-none-any.whl

Tags

More Artificial Intelligence packages

Further reading