NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
PyPI
PyPI, #4103 most downloaded on PyPI
Official Python library for Databricks AI support
Latest stable
0.22.0
Last release 2 months ago
18 Sep 2026
Release timing varies
gaps range from 1 weeks to 3 months
Most releases are documented
notes for 20 of 29 stable releases
1 version withdrawn
withdrawn after publishing
2 years old
31 releases · first in 2024
Drag across the ruler to compare, or tap a release to open it.
Release databricks-ai-bridge 0.22.0
Release databricks-ai-bridge 0.22.0 (#628)
DatabricksSandbox Deep Agents sandbox backend, available via the deepagents extra (#765)DatabricksSandboxTool and DatabricksSandboxSession for running code in a Databricks sandbox directly from LangChain, available via the sandbox extra (#791)DatabricksSandboxClient sandbox backend for the OpenAI Agents SDK, available via the sandbox extra (#774)openai<3 and openai-agents<0.21, since OpenAI 3 moved to httpx2 and is incompatible with the httpx clients this package supplies (#488)Release databricks-ai-bridge 0.22.0.dev0
Release databricks-ai-bridge 0.22.0.dev0
Your coding agent can read these notes before it upgrades. Set up the MCP server →
Strip unsupported metadata from rich ToolMessage text blocks before sending them to the model, allowing agents to continue after MCP tool calls (#664)
ToolMessage text blocks before sending them to the model, allowing agents to continue after MCP tool calls (#664).ChatDatabricks, and handle usage metadata with missing token details (#681).databricks-ai-bridge: Durable, crash-resumable agent execution for MLflow ResponsesAgent handlers
kwargs to maintain compatibility with newer versions of openai-agents (#426, #429)databricks-ai-bridge / databricks-langchain / databricks-openai: Agent Memory SDKs now allow custom schemas for Lakebase-backed checkpointers, stores,
ChatDatabricks now uses DatabricksOpenAI under the hood (#418)databricks-ai-bridge Lakebase utilities and databricks-langchain checkpoint/store (#420)_parse_attachments to support Genie self-correction (#419)Nothing published for this version
Support Lakebase autoscaling in stateful agent SDKs
Nothing published for this version
databricks-openai: Patch release to fix bug in 0.11.0 where importing classes crashed unless optional dependencies were installed
databricks-ai-bridge: Added AsyncLakebaseSQLAlchemy class for SQLAlchemy async engine with automatic OAuth token rotation
AsyncLakebaseSQLAlchemy class for SQLAlchemy async engine with automatic OAuth token rotationAsyncDatabricksSession class supporting Session Protocol for stateful conversation managementsimilarity_search_by_vector_with_scoreChatDatabricksLakebase Permission Granting SDK
LangGraph DatabricksStore for long term memory on Databricks using Lakebase
Addresses a dependency import bug introduced with the 0.10.0 release
return_pandas to return query results in pandas DataFrame format to databricks_langchain.GenieAgentAdd support for LLM-generated filter parameters in VectorSearchRetrieverTool
Improve OBO user authz error message with guidance on WorkspaceClient instantiation
Nothing published for this version
Nothing published for this version
Nothing published for this version
Add option to include similarity score in VectorSearchRetrieverTool result
Deprecate python 3.9 as a supported environment
Allow backticked vector search index names
Allow backticked vector search index names
Fix Databricks Connect and Tabulate Dependencies
Support On Behalf Of User rights with genie and VectorSearch Tool
VectorSearchRetrieverTool by disabling unwanted noticesIntroducing model as an argument to be passed to ChatDatabricks in Langchain and deprecating notice endpoint to confer with the schema in Langchain.
VectorSearchRetrieverTool API in both langchain and openai by introducing automatic description and resources needed to log the modelNothing published for this version
Nothing published for this version
Nothing published for this version
This is a patch release that includes bugfixes.
This is a patch release that includes bugfixes.
Bug fixes:
Initial version of databricks-ai-bridge and databricks-langchain packages
Initial version of databricks-ai-bridge and databricks-langchain packages
Features:
databricks_langchain.GenieAgent API in databricks-langchainlangchain-databricks under databricks-langchain. Specifically, this
release introduces databricks_langchain.ChatDatabricks, databricks_langchain.DatabricksEmbeddings, and
databricks_langchain.DatabricksVectorSearch APIs.Nothing published for this version
One column per month.