unitycatalog-openai
Support for Unity Catalog functions as OpenAI tools
What it is and what it does
This package bridges Unity Catalog functions and OpenAI's function-calling API, allowing you to register UC functions as tools that OpenAI models can invoke during agent conversations. It wraps the unitycatalog-ai client and pydantic for schema validation, handling the translation between UC function definitions and OpenAI's tool format.
You define or reference UC functions (either in a self-hosted Unity Catalog server or Databricks-managed UC), wrap them in a UCFunctionToolkit, and pass the resulting tool definitions to OpenAI's chat completion API. When the model decides to call a tool, you execute it against your UC client and feed the result back into the conversation loop. The package includes utilities for handling tool responses and managing different client configurations.
Use it for:
- Build AI agents that query or transform data stored in Databricks Unity Catalog by having OpenAI models invoke UC functions.
- Enable customer support chatbots to execute business logic functions (e.g., data lookups, calculations) stored in UC without hardcoding integrations.
- Create agentic workflows where OpenAI decides which UC functions to call based on user input, then chains results across multiple function calls.
- Integrate Databricks-managed UC functions into OpenAI-powered applications without writing custom API layers.
- Prototype multi-step data pipelines where an LLM orchestrates UC function calls to process and analyze data.
Worth the install?
AI-flagged interpretation of the facts on this page — verify before relying
Exposes Unity Catalog functions as tools for OpenAI models, enabling agents to call UC functions through OpenAI's function-calling interface.
Yes, if you are building OpenAI agents that need to invoke Unity Catalog functions. The package is actively maintained, has low install friction, and cleanly abstracts the function-calling protocol. Install it only if you have access to a Unity Catalog instance (self-hosted or Databricks) and are already using OpenAI's API.
Install
unitycatalog-openai on PyPI
pip
pip install unitycatalog-openaiuv
uv add unitycatalog-openaipoetry
poetry add unitycatalog-openaiInstalling unitycatalog-openai
Before you install
Low install friction with three straightforward runtime dependencies. Actively maintained as of the latest release.
License in practice
Apache-2.0 permissive license allows commercial use, modification, and distribution with minimal restrictions.
Quickstart
pip install unitycatalog-openai
from unitycatalog.ai.openai.toolkit import UCFunctionToolkit
toolkit = UCFunctionToolkit(function_names=["catalog.schema.function_name"])
tools = toolkit.tools
# Pass tools to OpenAI API
import openai
response = openai.chat.completions.create(
model="gpt-4o-mini",
messages=[{"role": "user", "content": "query"}],
tools=tools
)
Requires Python >=3.10 and an active Unity Catalog server or Databricks workspace with appropriate authentication.
Verify before relying
- Whether the package supports async function execution or only synchronous calls
- Performance characteristics when working with large numbers of UC functions
- Compatibility with OpenAI models beyond gpt-4o-mini
Package facts
| License | Apache-2.0 (permissive) |
| Python support | supports the current Python release (>=3.10) |
| Install friction | low — pure-Python wheel |
| Runtime dependencies | 3 — openai, pydantic, unitycatalog-ai |
| Maintenance | actively maintained — 112 days since the last release |
| First released | |
| Downloads | 1,479,713/month — #3,852 on PyPI (30-day window, as of 2026-08-14) |
| Known vulnerabilities | none known (OSV.dev, checked 2026-08-14) |
Evidence: unitycatalog_openai-0.4.0-py3-none-any.whl
Tags
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to…
permissive · top 100 on PyPI
huggingface-hubClient library and CLI tool for downloading,…
permissive · top 100 on PyPI
langchainLangChain provides a framework for building…
permissive · top 1,000 on PyPI
hf-xethf-xet provides chunk-based deduplication and…
permissive · top 1,000 on PyPI
tokenizersTokenizers converts raw text into token…
permissive · top 1,000 on PyPI
transformersTransformers provides a unified framework for…
permissive · top 1,000 on PyPI
unitycatalog-aiProvides Python APIs to create, retrieve, and…
permissive · top 5,000 on PyPI
unitycatalog-langchainExposes Unity Catalog functions as LangChain…
permissive · top 5,000 on PyPI
unitycatalog-clientProvides async Python bindings to the Unity…
permissive · top 5,000 on PyPI
databricks-openaiIntegrates Databricks AI features, particularly…
permissive · top 5,000 on PyPI
UnityPyUnityPy extracts and edits Unity asset files…
permissive · top 15,000 on PyPI
databricks-ai-bridgeProvides a shared Python API layer for building…
unclear · top 5,000 on PyPI
databricks-feature-engineeringDatabricks Feature Engineering client for…
unclear · top 5,000 on PyPI
dbt-databricksdbt-databricks is a dbt adapter that enables…
permissive · top 5,000 on PyPI
composio-openai-agentsBridges Composio's tool catalog to OpenAI's…
permissive · top 15,000 on PyPI
agent-framework-openaiProvides OpenAI and Azure OpenAI integration…
permissive · top 5,000 on PyPI