databricks-ai-bridge
Official Python library for Databricks AI support
Decision gist · record as of 2026-08-14
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.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires active Databricks workspace and credentials; use restricted to Databricks Services per license terms.
- Low friction install with a pure-Python wheel.
- Active maintenance with recent releases.
License · maintenance · safety
(unclear) — 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.
last release 2026-06-25 (50 days)
0 known vulnerabilities (OSV.dev, 2026-08-14) · 2,188,231 downloads/mo, #3,224 on PyPI
Alternatives
Verify before relying
pip install databricks-ai-bridge
from databricks_ai_bridge import VectorSearch
# Requires Databricks workspace connection via databricks-sdk- 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
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 on it.
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
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.
Requires active Databricks workspace and credentials; use restricted to Databricks Services per license terms.
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-sdkVerify 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
| License | Not declared unclear |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 8 packagesdatabricks-ai-searchdatabricks-sdkmlflow-skinnypandaspydantictabulatetiktokentyping-extensions |
| Maintenance | Actively maintained 50 days since the last release |
| First released | |
| Downloads | 2,188,231 / month, #3,224 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
Evidence: databricks_ai_bridge-0.21.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “databricks ai integration”
- databricks-ai-bridgeProvides a shared Python API layer for building agents and…
- databricks-langchainIntegrates Databricks AI services—LLMs, vector search, embeddings,…
- databricks-agentsMosaic AI Agent Framework SDK provides a Python library for building…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also databricks-langchain · databricks-openai · langchain-databricks · databricks-agents · databricks-ai-search · genie.libs.robot · unitycatalog-openai · databricks-vectorsearch · langchain-azure-ai · databricks-feature-engineering